Skip to content

Debug stats #4

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Draft
wants to merge 4 commits into
base: main
Choose a base branch
from
Draft

Debug stats #4

wants to merge 4 commits into from

Conversation

@22quinn
Copy link
Owner

@22quinn 22quinn commented Oct 4, 2025 •
edited by github-actions bot
Loading 

INFO 10-04 14:05:38 [llm.py:310] Supported_tasks: ['generate']
INFO 10-04 14:05:39 [llm_engine.py:277] len(outputs.outputs)=2
INFO 10-04 14:05:39 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=2, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=4.941321803586529e-05, prefix_cache_stats=PrefixCacheStats(reset=False, requests=2, queries=10, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f22582240>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:39 [llm_engine.py:277] len(outputs.outputs)=4
INFO 10-04 14:05:39 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=4, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=9.882643607161956e-05, prefix_cache_stats=PrefixCacheStats(reset=False, requests=2, queries=14, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f23a01d90>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:39 [llm_engine.py:277] len(outputs.outputs)=4
INFO 10-04 14:05:39 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=4, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=9.882643607161956e-05, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f22581910>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:39 [llm_engine.py:277] len(outputs.outputs)=4
INFO 10-04 14:05:39 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=4, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=9.882643607161956e-05, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f239721b0>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:39 [llm_engine.py:277] len(outputs.outputs)=4
INFO 10-04 14:05:39 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=4, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=9.882643607161956e-05, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f22582240>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:39 [llm_engine.py:277] len(outputs.outputs)=4
INFO 10-04 14:05:39 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=4, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=9.882643607161956e-05, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f23a01d90>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:39 [llm_engine.py:277] len(outputs.outputs)=4
INFO 10-04 14:05:39 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=4, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=9.882643607161956e-05, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f22581910>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:39 [llm_engine.py:277] len(outputs.outputs)=4
INFO 10-04 14:05:39 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=4, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=9.882643607161956e-05, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f239721b0>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:39 [llm_engine.py:277] len(outputs.outputs)=4
INFO 10-04 14:05:39 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=4, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=9.882643607161956e-05, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f22582240>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:39 [llm_engine.py:277] len(outputs.outputs)=4
INFO 10-04 14:05:39 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=4, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=9.882643607161956e-05, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f23a01d90>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:39 [llm_engine.py:277] len(outputs.outputs)=4
INFO 10-04 14:05:39 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=4, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=9.882643607161956e-05, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f22581910>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:39 [llm_engine.py:277] len(outputs.outputs)=4
INFO 10-04 14:05:39 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=4, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00014823965410748485, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f239721b0>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:39 [llm_engine.py:277] len(outputs.outputs)=4
INFO 10-04 14:05:39 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=4, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00019765287214335014, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f22582240>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:39 [llm_engine.py:277] len(outputs.outputs)=4
INFO 10-04 14:05:39 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=4, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00019765287214335014, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f23a01d90>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:39 [llm_engine.py:277] len(outputs.outputs)=4
INFO 10-04 14:05:39 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=4, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00019765287214335014, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f22581910>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:39 [llm_engine.py:277] len(outputs.outputs)=4
INFO 10-04 14:05:39 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=4, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00019765287214335014, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f239721b0>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:39 [llm_engine.py:277] len(outputs.outputs)=4
INFO 10-04 14:05:39 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=4, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00019765287214335014, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f22582240>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:39 [llm_engine.py:277] len(outputs.outputs)=4
INFO 10-04 14:05:39 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=4, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00019765287214335014, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f23a01d90>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:39 [llm_engine.py:277] len(outputs.outputs)=4
INFO 10-04 14:05:39 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=4, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00019765287214335014, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f22581910>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:39 [llm_engine.py:277] len(outputs.outputs)=4
INFO 10-04 14:05:39 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=4, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00019765287214335014, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f239721b0>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:39 [llm_engine.py:277] len(outputs.outputs)=4
INFO 10-04 14:05:39 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=4, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00019765287214335014, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f22582240>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:39 [llm_engine.py:277] len(outputs.outputs)=3
INFO 10-04 14:05:39 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=3, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00014823965410748485, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f23a01d90>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:39 [llm_engine.py:277] len(outputs.outputs)=3
INFO 10-04 14:05:39 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=3, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00014823965410748485, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f22581910>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:39 [llm_engine.py:277] len(outputs.outputs)=3
INFO 10-04 14:05:39 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=3, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00014823965410748485, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f239721b0>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:39 [llm_engine.py:277] len(outputs.outputs)=3
INFO 10-04 14:05:39 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=3, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00014823965410748485, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f22582240>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=3
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=3, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00014823965410748485, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f23a01d90>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=3
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=3, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00014823965410748485, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f22581910>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=3
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=3, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.000172946263125362, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f239721b0>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=3
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=3, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00022235948116122728, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f225819d0>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=3
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=3, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00022235948116122728, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f2255f350>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=3
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=3, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00022235948116122728, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f22581910>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=3
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=3, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00022235948116122728, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f239721b0>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=3
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=3, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00022235948116122728, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f225819d0>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=3
INFO 10-04 14:05:40 [output_processor.py:453] Request 0_1 metrics: RequestStateStats(num_generation_tokens=33, arrival_time=1759611939.7106962, queued_ts=3392014.154878037, scheduled_ts=3392014.154887912, first_token_ts=3392014.168248312, last_token_ts=3392014.490322987, first_token_latency=0.05086398124694824)
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=3, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00022235948116122728, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f2255f350>, processed_outputs.request_outputs=[RequestOutput(request_id=1, prompt='The president of the United States is', prompt_token_ids=[785, 4767, 315, 279, 3639, 4180, 374], encoder_prompt=None, encoder_prompt_token_ids=None, prompt_logprobs=None, outputs=[CompletionOutput(index=0, text=' a person who has to appoint only 1 person for each person in the state of Texas, but he does not need to appoint people for other states. He ', token_ids=[264, 1697, 879, 702, 311, 9540, 1172, 220, 16, 1697, 369, 1817, 1697, 304, 279, 1584, 315, 8257, 11, 714, 566, 1558, 537, 1184, 311, 9540, 1251, 369, 1008, 5302, 13, 1260, 374], cumulative_logprob=None, logprobs=None, finish_reason=stop, stop_reason=is), CompletionOutput(index=1, text=' the only person who has the power to create and enforce laws. Which of the following statements ', token_ids=[279, 1172, 1697, 879, 702, 279, 2355, 311, 1855, 323, 28162, 6872, 13, 15920, 315, 279, 2701, 12239, 374], cumulative_logprob=None, logprobs=None, finish_reason=stop, stop_reason=is)], finished=True, metrics=RequestStateStats(num_generation_tokens=33, arrival_time=1759611939.7106962, queued_ts=3392014.154878037, scheduled_ts=3392014.154887912, first_token_ts=3392014.168248312, last_token_ts=3392014.490322987, first_token_latency=0.05086398124694824), lora_request=None, num_cached_tokens=0, multi_modal_placeholders={})]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=3
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=3, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00022235948116122728, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f22581910>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=2
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=2, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00014823965410748485, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f239721b0>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=2
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=2, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00014823965410748485, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f225819d0>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=2
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=2, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00014823965410748485, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f2255f350>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=2
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=2, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00014823965410748485, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f22581910>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=2
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=2, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00014823965410748485, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f239721b0>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=2
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=2, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00014823965410748485, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f225819d0>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=2
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=2, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00014823965410748485, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f2255f350>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=2
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=2, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00014823965410748485, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f22581910>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=2
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=2, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00014823965410748485, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f239721b0>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=2
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=2, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00019765287214335014, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f225819d0>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=2
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=2, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00019765287214335014, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f2255f350>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=2
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=2, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00019765287214335014, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f22581910>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=2
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=2, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00019765287214335014, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f239721b0>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=2
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=2, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00019765287214335014, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f225819d0>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=2
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=2, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00019765287214335014, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f2255f350>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=2
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=2, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00019765287214335014, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f22581910>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=2
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=2, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00019765287214335014, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f239721b0>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=2
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=2, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00019765287214335014, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f225819d0>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=2
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=2, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00019765287214335014, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f2255f350>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=2
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=2, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00019765287214335014, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f22581910>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=2
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=2, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00019765287214335014, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f239721b0>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=2
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=2, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00019765287214335014, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f225819d0>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=2
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=2, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00019765287214335014, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f2255f350>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=2
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=2, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00019765287214335014, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f22581910>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=2
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=2, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00019765287214335014, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f239721b0>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=2
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=2, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.0002470660901791044, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f225819d0>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=2
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=2, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.0002470660901791044, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f2255f350>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=2
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=2, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.0002470660901791044, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f22581910>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=2
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=2, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.0002470660901791044, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f239721b0>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=2
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=2, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.0002470660901791044, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f225819d0>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=2
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=2, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.0002470660901791044, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f2255f350>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=2
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=2, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.0002470660901791044, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f22581910>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=2
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=2, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.0002470660901791044, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f239721b0>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=2
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=2, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.0002470660901791044, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f225819d0>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=2
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=2, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.0002470660901791044, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f2255f350>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=2
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=2, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.0002470660901791044, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f22581910>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=2
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=2, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.0002470660901791044, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f239721b0>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=2
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=2, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.0002470660901791044, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f225819d0>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=2
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=2, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.0002470660901791044, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f2255f350>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=2
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=2, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.0002470660901791044, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f22581910>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=2
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=2, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.0002470660901791044, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f239721b0>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=2
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=2, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.0002964793082149697, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f225819d0>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=2
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=2, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.0002964793082149697, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f2255f350>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=2
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=2, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.0002964793082149697, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f22581910>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=2
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=2, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.0002964793082149697, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f239721b0>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=2
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=2, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.0002964793082149697, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f225819d0>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=2
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=2, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.0002964793082149697, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f2255f350>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=2
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=2, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.0002964793082149697, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f22581910>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=2
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=2, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.0002964793082149697, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f239721b0>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=2
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=2, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.0002964793082149697, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f225819d0>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=2
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=2, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.0002964793082149697, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f2255f350>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=2
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=2, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.0002964793082149697, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f22581910>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00014823965410748485, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f239721b0>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00014823965410748485, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f225819d0>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00014823965410748485, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f239721b0>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00014823965410748485, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f2e8d0200>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00014823965410748485, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f239721b0>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.000172946263125362, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f2e8d0200>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.000172946263125362, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f25b66420>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.000172946263125362, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f2e8d0200>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.000172946263125362, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f25b66420>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.000172946263125362, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f239721b0>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.000172946263125362, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f25b66420>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.000172946263125362, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f239721b0>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.000172946263125362, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f2e8d0200>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.000172946263125362, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f239721b0>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.000172946263125362, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f2e8d0200>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.000172946263125362, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f25b66420>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.000172946263125362, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f2e8d0200>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.000172946263125362, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f25b66420>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.000172946263125362, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f239721b0>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.000172946263125362, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f25b66420>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.000172946263125362, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f239721b0>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00019765287214335014, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f2e8d0200>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00019765287214335014, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f239721b0>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00019765287214335014, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f2e8d0200>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00019765287214335014, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f25b66420>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00019765287214335014, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f2e8d0200>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00019765287214335014, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f25b66420>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00019765287214335014, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f239721b0>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00019765287214335014, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f25b66420>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00019765287214335014, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f239721b0>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00019765287214335014, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f2e8d0200>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00019765287214335014, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f239721b0>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00019765287214335014, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f2e8d0200>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00019765287214335014, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f25b66420>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00019765287214335014, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f2e8d0200>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00019765287214335014, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f25b66420>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00019765287214335014, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f239721b0>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00022235948116122728, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f25b66420>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00022235948116122728, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f239721b0>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00022235948116122728, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f2e8d0200>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:40 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:40 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00022235948116122728, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f239721b0>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:41 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:41 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00022235948116122728, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f2e8d0200>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:41 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:41 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00022235948116122728, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f25b66420>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:41 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:41 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00022235948116122728, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f2e8d0200>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:41 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:41 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00022235948116122728, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f25b66420>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:41 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:41 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00022235948116122728, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f239721b0>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:41 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:41 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00022235948116122728, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f25b66420>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:41 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:41 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00022235948116122728, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f239721b0>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:41 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:41 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00022235948116122728, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f2e8d0200>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:41 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:41 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00022235948116122728, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f239721b0>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:41 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:41 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00022235948116122728, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f2e8d0200>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:41 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:41 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00022235948116122728, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f25b66420>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:41 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:41 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00022235948116122728, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f2e8d0200>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:41 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:41 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.0002470660901791044, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f25b66420>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:41 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:41 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.0002470660901791044, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f239721b0>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:41 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:41 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.0002470660901791044, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f25b66420>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:41 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:41 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.0002470660901791044, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f239721b0>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:41 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:41 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.0002470660901791044, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f2e8d0200>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:41 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:41 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.0002470660901791044, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f239721b0>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:41 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:41 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.0002470660901791044, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f2e8d0200>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:41 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:41 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.0002470660901791044, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f25b66420>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:41 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:41 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.0002470660901791044, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f2e8d0200>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:41 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:41 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.0002470660901791044, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f25b66420>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:41 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:41 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.0002470660901791044, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f239721b0>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:41 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:41 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.0002470660901791044, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f25b66420>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:41 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:41 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.0002470660901791044, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f239721b0>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:41 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:41 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.0002470660901791044, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f2e8d0200>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:41 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:41 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.0002470660901791044, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f239721b0>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:41 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:41 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.0002470660901791044, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f2e8d0200>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:41 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:41 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00027177269919698155, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f25b66420>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:41 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:41 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00027177269919698155, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f2e8d0200>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:41 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:41 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00027177269919698155, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f25b66420>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:41 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:41 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00027177269919698155, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f239721b0>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:41 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:41 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00027177269919698155, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f25b66420>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:41 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:41 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00027177269919698155, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f239721b0>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:41 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:41 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00027177269919698155, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f2e8d0200>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:41 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:41 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00027177269919698155, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f239721b0>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:41 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:41 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00027177269919698155, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f2e8d0200>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:41 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:41 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00027177269919698155, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f25b66420>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:41 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:41 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00027177269919698155, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f2e8d0200>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:41 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:41 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00027177269919698155, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f25b66420>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:41 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:41 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00027177269919698155, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f239721b0>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:41 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:41 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00027177269919698155, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f25b66420>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:41 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:41 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00027177269919698155, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f239721b0>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:41 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:41 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.00027177269919698155, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f2e8d0200>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:41 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:41 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.0002964793082149697, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f239721b0>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:41 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:41 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.0002964793082149697, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f2e8d0200>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:41 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:41 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.0002964793082149697, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f25b66420>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:41 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:41 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.0002964793082149697, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f2e8d0200>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:41 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:41 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.0002964793082149697, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f25b66420>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:41 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:41 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.0002964793082149697, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f239721b0>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:41 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:41 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.0002964793082149697, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f25b66420>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:41 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:41 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.0002964793082149697, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f239721b0>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:41 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:41 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.0002964793082149697, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f2e8d0200>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:41 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:41 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.0002964793082149697, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f239721b0>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:41 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:41 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.0002964793082149697, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f2e8d0200>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:41 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:41 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.0002964793082149697, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f25b66420>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:41 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:41 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.0002964793082149697, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f2e8d0200>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:41 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:41 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.0002964793082149697, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f25b66420>, processed_outputs.request_outputs=[]
INFO 10-04 14:05:41 [llm_engine.py:277] len(outputs.outputs)=1
INFO 10-04 14:05:41 [output_processor.py:453] Request 0_0 metrics: RequestStateStats(num_generation_tokens=187, arrival_time=1759611939.6918318, queued_ts=3392014.118035717, scheduled_ts=3392014.118145124, first_token_ts=3392014.154796472, last_token_ts=3392015.930020975, first_token_latency=0.056993961334228516)
INFO 10-04 14:05:41 [llm_engine.py:298] EngineCore: outputs.scheduler_stats=SchedulerStats(num_running_reqs=1, num_waiting_reqs=0, step_counter=0, current_wave=0, kv_cache_usage=0.0002964793082149697, prefix_cache_stats=PrefixCacheStats(reset=False, requests=0, queries=0, hits=0, preempted_requests=0, preempted_queries=0, preempted_hits=0), spec_decoding_stats=None, kv_connector_stats=None, num_corrupted_reqs=0), iteration_stats=<vllm.v1.metrics.stats.IterationStats object at 0x7f7f239721b0>, processed_outputs.request_outputs=[RequestOutput(request_id=0, prompt='Hello, my name is', prompt_token_ids=[9707, 11, 847, 829, 374], encoder_prompt=None, encoder_prompt_token_ids=None, prompt_logprobs=None, outputs=[CompletionOutput(index=0, text=" Josh and I'm in the middle of a project to develop a hybrid mobile app. I'm looking for guidance on how to go about using modular frameworks. I want to use React and Vue. I need to decide on the framework to use. Can you help me choose the right framework and suggest some best practices for using them?\n\nAdditionally, I want to know what are the best practices for using a modular framework in the context of a web application? Also, what are the best practices for using a modular framework in the context of a mobile application? Also, what are the best practices for using a modular framework in the context of a hybrid app? Please explain each of these best practices. Also, what are the best practices for using a modular framework when integrating a third-party application with a third-party framework? Also, please explain each of these best practices in simple terms and explain each of these best practices in simple terms. Please l", token_ids=[18246, 323, 358, 2776, 304, 279, 6149, 315, 264, 2390, 311, 2225, 264, 24989, 6371, 906, 13, 358, 2776, 3330, 369, 18821, 389, 1246, 311, 728, 911, 1667, 43893, 48025, 13, 358, 1366, 311, 990, 3592, 323, 22256, 13, 358, 1184, 311, 10279, 389, 279, 12626, 311, 990, 13, 2980, 498, 1492, 752, 5157, 279, 1290, 12626, 323, 4190, 1045, 1850, 12378, 369, 1667, 1105, 1939, 49574, 11, 358, 1366, 311, 1414, 1128, 525, 279, 1850, 12378, 369, 1667, 264, 43893, 12626, 304, 279, 2266, 315, 264, 3482, 3766, 30, 7281, 11, 1128, 525, 279, 1850, 12378, 369, 1667, 264, 43893, 12626, 304, 279, 2266, 315, 264, 6371, 3766, 30, 7281, 11, 1128, 525, 279, 1850, 12378, 369, 1667, 264, 43893, 12626, 304, 279, 2266, 315, 264, 24989, 906, 30, 5209, 10339, 1817, 315, 1493, 1850, 12378, 13, 7281, 11, 1128, 525, 279, 1850, 12378, 369, 1667, 264, 43893, 12626, 979, 53852, 264, 4843, 24031, 3766, 448, 264, 4843, 24031, 12626, 30, 7281, 11, 4486, 10339, 1817, 315, 1493, 1850, 12378, 304, 4285, 3793, 323, 10339, 1817, 315, 1493, 1850, 12378, 304, 4285, 3793, 13, 5209, 1140], cumulative_logprob=None, logprobs=None, finish_reason=stop, stop_reason=is), CompletionOutput(index=1, text=" Tom. I'm from the UK and live in California. I'm a computer programmer and I love programming. I'm very enthusiastic about programming and I've never been shy. I'm currently working on a project that involves creating a game. Let me know if there's anything I can do to support you, Tom.\nOkay, I need to help Tom from the UK to the US. Let me think about how to approach th", token_ids=[8364, 13, 358, 2776, 504, 279, 6424, 323, 3887, 304, 7043, 13, 358, 2776, 264, 6366, 47788, 323, 358, 2948, 15473, 13, 358, 2776, 1602, 41602, 911, 15473, 323, 358, 3003, 2581, 1012, 32294, 13, 358, 2776, 5023, 3238, 389, 264, 2390, 429, 17601, 6825, 264, 1809, 13, 6771, 752, 1414, 421, 1052, 594, 4113, 358, 646, 653, 311, 1824, 498, 11, 8364, 624, 32313, 11, 358, 1184, 311, 1492, 8364, 504, 279, 6424, 311, 279, 2274, 13, 6771, 752, 1744, 911, 1246, 311, 5486, 419], cumulative_logprob=None, logprobs=None, finish_reason=stop, stop_reason=is)], finished=True, metrics=RequestStateStats(num_generation_tokens=187, arrival_time=1759611939.6918318, queued_ts=3392014.118035717, scheduled_ts=3392014.118145124, first_token_ts=3392014.154796472, last_token_ts=3392015.930020975, first_token_latency=0.056993961334228516), lora_request=None, num_cached_tokens=0, multi_modal_placeholders={})]
Prompt: [9707, 11, 847, 829, 374], Generated tokens: [18246, 323, 358, 2776, 304, 279, 6149, 315, 264, 2390, 311, 2225, 264, 24989, 6371, 906, 13, 358, 2776, 3330, 369, 18821, 389, 1246, 311, 728, 911, 1667, 43893, 48025, 13, 358, 1366, 311, 990, 3592, 323, 22256, 13, 358, 1184, 311, 10279, 389, 279, 12626, 311, 990, 13, 2980, 498, 1492, 752, 5157, 279, 1290, 12626, 323, 4190, 1045, 1850, 12378, 369, 1667, 1105, 1939, 49574, 11, 358, 1366, 311, 1414, 1128, 525, 279, 1850, 12378, 369, 1667, 264, 43893, 12626, 304, 279, 2266, 315, 264, 3482, 3766, 30, 7281, 11, 1128, 525, 279, 1850, 12378, 369, 1667, 264, 43893, 12626, 304, 279, 2266, 315, 264, 6371, 3766, 30, 7281, 11, 1128, 525, 279, 1850, 12378, 369, 1667, 264, 43893, 12626, 304, 279, 2266, 315, 264, 24989, 906, 30, 5209, 10339, 1817, 315, 1493, 1850, 12378, 13, 7281, 11, 1128, 525, 279, 1850, 12378, 369, 1667, 264, 43893, 12626, 979, 53852, 264, 4843, 24031, 3766, 448, 264, 4843, 24031, 12626, 30, 7281, 11, 4486, 10339, 1817, 315, 1493, 1850, 12378, 304, 4285, 3793, 323, 10339, 1817, 315, 1493, 1850, 12378, 304, 4285, 3793, 13, 5209, 1140]
Prompt: [785, 4767, 315, 279, 3639, 4180, 374], Generated tokens: [264, 1697, 879, 702, 311, 9540, 1172, 220, 16, 1697, 369, 1817, 1697, 304, 279, 1584, 315, 8257, 11, 714, 566, 1558, 537, 1184, 311, 9540, 1251, 369, 1008, 5302, 13, 1260, 374]
ERROR 10-04 14:05:41 [core_client.py:564] Engine core proc EngineCore_DP0 died unexpectedly, shutting down client.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

No reviews

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

2 participants

@22quinn