Skip to content

Pull requests: vllm-project/vllm

New pull request New
399 Open 3,181 Closed
399 Open 3,181 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

[Misc] Remove SqueezeLLM ready ONLY add when PR is ready to merge/full CI is needed
#8220 opened Sep 6, 2024 by dsikka Loading…
3
[Misc] Fused MoE Marlin support for GPTQ
#8217 opened Sep 5, 2024 by dsikka • Draft
1
[BugFix] Fix Granite model configuration ready ONLY add when PR is ready to merge/full CI is needed
#8216 opened Sep 5, 2024 by njhill Loading…
Add VLLM_LOGGING_INTERVAL_SEC envvar to control logging rate
#8213 opened Sep 5, 2024 by mgoin • Draft
1
1
[Misc] Upgrade vllm-flash-attn to v2.6.2 ready ONLY add when PR is ready to merge/full CI is needed
#8211 opened Sep 5, 2024 by WoosukKwon Loading…
1
Fix shutdown problem
#8209 opened Sep 5, 2024 by Bye-legumes Loading…
1
2
[Model] Adding Granite MoE.
#8206 opened Sep 5, 2024 by shawntan Loading…
7
[CI/Build] Increasing timeout for multiproc worker tests ready ONLY add when PR is ready to merge/full CI is needed
#8203 opened Sep 5, 2024 by alexeykondrat Loading…
6
[Model][VLM] Support multi-images inputs for InternVL2 models
#8201 opened Sep 5, 2024 by Isotr0py • Draft
1 of 2 tasks
2
Reshape cache to be XQA kernel compatible
#8200 opened Sep 5, 2024 by wenscarl Loading…
1
[Core] *Prompt* logprobs support in Multi-step
#8199 opened Sep 5, 2024 by afeldman-nm • Draft
1
6
[OpenVINO] Enable GPU support for OpenVINO vLLM backend Intel GPU
#8192 opened Sep 5, 2024 by sshlyapn Loading…
1
[Frontend] Add --logprobs argument to benchmark_serving.py ready ONLY add when PR is ready to merge/full CI is needed
#8191 opened Sep 5, 2024 by afeldman-nm Loading…
1
10
[Benchmark] Add block_size option to benchmark_throughput.py
#8175 opened Sep 5, 2024 by liangfu Loading…
5
[Core/Bugfix] pass VLLM_ATTENTION_BACKEND to ray workers ready ONLY add when PR is ready to merge/full CI is needed
#8172 opened Sep 4, 2024 by SolitaryThinker Loading…
2
[Model] Allow loading from original Mistral format ready ONLY add when PR is ready to merge/full CI is needed
#8168 opened Sep 4, 2024 by patrickvonplaten Loading…
31
[Misc] remove peft as dependency for prompt models ready ONLY add when PR is ready to merge/full CI is needed
#8162 opened Sep 4, 2024 by prashantgupta24 Loading…
7
[Core][Bugfix][Perf] Introduce MPLLMEngine to avoid Avoid AsyncLLMEngine overheads
#8157 opened Sep 4, 2024 by alexm-neuralmagic Loading…
1
8
[Bugfix] Fix missing post_layernorm in CLIP and sharded weight loading in SigLIP
#8155 opened Sep 4, 2024 by DarkLight1337 Loading…
3
[Bugfix]disable cuda graph when max_decode_seq_len is close to max_seq_len_to_capture
#8145 opened Sep 4, 2024 by Ximingwang-09 Loading…
3
[Misc] add iteration_tokens metric ready ONLY add when PR is ready to merge/full CI is needed
#8140 opened Sep 4, 2024 by LucasWilkinson Loading…
2
[Misc] GPTQ Activation Ordering
#8135 opened Sep 3, 2024 by kylesayrs • Draft
16
[CI/Build] Use python 3.12 in cuda image ready ONLY add when PR is ready to merge/full CI is needed
#8133 opened Sep 3, 2024 by joerunde Loading…
8
Adding Cascade Infer to FlashInfer
#8132 opened Sep 3, 2024 by raywanb • Draft
@comaniac
1
[CI/Build] Enabling kernels tests for AMD, ignoring some of then that fail ready ONLY add when PR is ready to merge/full CI is needed rocm
#8130 opened Sep 3, 2024 by alexeykondrat Loading…
1
ProTip! Adding no:label will show everything without a label.