Add more percentiles and latencies #7759

wschin · 2024-08-21T21:59:43Z

99-precentile can be far away from median, average, and sometimes even 95-percentile. This PR adds more latency percentiles and end-to-end latency for profiling throughput.

Example usage (see --percentile-metrics and --metric-percentiles):

model_name="meta-llama/Meta-Llama-3.1-70B-Instruct"
python3 benchmark_serving.py \
    --backend vllm \
    --dataset-name sharegpt \
    --dataset-path ShareGPT_V3_unfiltered_cleaned_split.json \
    --model $model_name \
    --num-prompts 20 \
    --endpoint /v1/completions \
    --tokenizer $model_name \
    --save-result \
    --percentile-metrics "ttft,tpot,itl,e2el" \
    --metric-percentiles "30,50,70,90" \
    --port 9487 \
    2>&1 | tee benchmark_serving.txt
bench_serving_exit_code=$?

produces

============ Serving Benchmark Result ============
Successful requests:                     20        
Benchmark duration (s):                  34.57     
Total input tokens:                      3590      
Total generated tokens:                  3927      
Request throughput (req/s):              0.58      
Input token throughput (tok/s):          103.86    
Output token throughput (tok/s):         113.61    
---------------Time to First Token----------------
Mean TTFT (ms):                          280.00    
Median TTFT (ms):                        184.59    
P30 TTFT (ms):                           183.32    
P50 TTFT (ms):                           184.59    
P70 TTFT (ms):                           429.35    
P90 TTFT (ms):                           518.89    
-----Time per Output Token (excl. 1st token)------
Mean TPOT (ms):                          48.98     
Median TPOT (ms):                        48.70     
P30 TPOT (ms):                           47.43     
P50 TPOT (ms):                           48.70     
P70 TPOT (ms):                           49.40     
P90 TPOT (ms):                           50.74     
---------------Inter-token Latency----------------
Mean ITL (ms):                           47.45     
Median ITL (ms):                         46.75     
P30 ITL (ms):                            46.32     
P50 ITL (ms):                            46.75     
P70 ITL (ms):                            47.46     
P90 ITL (ms):                            48.31     
----------------End-to-end Latency----------------
Mean E2EL (ms):                          5670.77   
Median E2EL (ms):                        9628.67   
P30 E2EL (ms):                           2497.91   
P50 E2EL (ms):                           5670.77   
P70 E2EL (ms):                           13700.87  
P90 E2EL (ms):                           20139.72  
==================================================

github-actions · 2024-08-21T21:59:53Z

👋 Hi! Thank you for contributing to the vLLM project.
Just a reminder: PRs would not trigger full CI run by default. Instead, it would only run fastcheck CI which consists a small and essential subset of CI tests to quickly catch errors. You can run other CI tests on top of default ones by unblocking the steps in your fast-check build on Buildkite UI.

Once the PR is approved and ready to go, please make sure to run full CI as it is required to merge (or just use auto-merge).

To run full CI, you can do one of these:

Comment /ready on the PR
Add ready label to the PR
Enable auto-merge.

🚀

Drop a line lint

wschin · 2024-08-22T00:14:43Z

/ready

ywang96 · 2024-08-22T04:15:51Z

Hey @wschin! Thank you for making this PR!

I personally don't really mind this change, but this could affect the parsing of our performance benchmark CI. Also, when I initially worked on benchmark_serving.py, one of the design principles I made was to make it easily customizable and portable so that users can adjust this script according to their needs very conveniently without having to make it part of the main branch.

@KuntaiDu What do you think of this change since you would need to rework the parsing in perf CI if we merge this? I'm personally okay with the current benchmark too since median is usually a robust metric itself already.

comaniac · 2024-08-22T04:23:34Z

Can we make this optional so that we can still report/parse median values in CI, but users could configure to report more numbers they want? For example we could support an option like --percentiles "25,50,95". Also since everyone may care about different percentiles (e.g. we care P90 more than P95), and this approach offers such flexibility.

ywang96 · 2024-08-22T04:33:46Z

Can we make this optional so that we can still report/parse median values in CI, but users could configure to report more numbers they want? For example we could support an option like --percentiles "25,50,95". Also since everyone may care about different percentiles (e.g. we care P90 more than P95), and this approach offers such flexibility.

That's a good idea too!

wschin · 2024-08-22T16:26:13Z

Sounds good. I will make it optional.

benchmarks/benchmark_serving.py

comaniac

Overall LGTM. Only comment is we could just call "e2e" or "end to end". Also could you post the example outputs with this PR for illustration? Thanks l

benchmarks/benchmark_serving.py

wschin · 2024-08-24T04:20:33Z

Overall LGTM. Only comment is we could just call "e2e" or "end to end". Also could you post the example outputs with this PR for illustration? Thanks l

Done. Thanks.

comaniac · 2024-08-24T04:23:02Z

cc @ywang96 @KuntaiDu

wschin · 2024-08-26T16:06:11Z

@ywang96, @KuntaiDu gentle ping for reviewing. Thanks.

ywang96 · 2024-08-26T16:11:27Z

@wschin Will take a look today - sorry for the delay!

ywang96

Thank you for this PR! @wschin

I left a small nit. From a glance this shouldn't affect our perf benchmark parsing given the default values, but I will let @KuntaiDu confirm!

ywang96 · 2024-08-26T16:52:23Z

benchmarks/benchmark_serving.py

+    def process_one_metric(
+        # E.g., "ttft"
+        metric_attribute_name: str,
+        # E.g., "TTFT"
+        metric_name: str,
+        # E.g., "Time to First Token"
+        metric_header: str,
+    ):
+        # This function print and add statistics of the specified
+        # metric.
+        if metric_attribute_name not in selected_percentile_metrics:
+            return
+        print("{s:{c}^{n}}".format(s=metric_header, n=50, c='-'))
+        print("{:<40} {:<10.2f}".format(
+            f"Mean {metric_name} (ms):",
+            getattr(metrics, f"mean_{metric_attribute_name}_ms")))
+        print("{:<40} {:<10.2f}".format(
+            f"Median {metric_name} (ms):",
+            getattr(metrics, f"median_{metric_attribute_name}_ms")))
+        result[f"mean_{metric_attribute_name}_ms"] = getattr(
+            metrics, f"mean_{metric_attribute_name}_ms")
+        result[f"median_{metric_attribute_name}_ms"] = getattr(
+            metrics, f"median_{metric_attribute_name}_ms")
+        result[f"std_{metric_attribute_name}_ms"] = getattr(
+            metrics, f"std_{metric_attribute_name}_ms")
+        for p, value in getattr(metrics,
+                                f"percentiles_{metric_attribute_name}_ms"):
+            p_word = str(int(p)) if int(p) == p else str(p)
+            print("{:<40} {:<10.2f}".format(f"P{p_word} {metric_name} (ms):",
+                                            value))
+            result[f"p{p_word}_{metric_attribute_name}_ms"] = value


Thanks for this refactoring!

ywang96 · 2024-08-26T16:55:00Z

benchmarks/benchmark_serving.py

@@ -765,6 +804,23 @@ def main(args: argparse.Namespace):
        "{backend}-{args.request_rate}qps-{base_model_id}-{current_dt}.json"
        " format.",
    )
+    parser.add_argument(
+        "--percentile-metrics",


nit: could we have this as simply --metrics? I think having --percentile-metrics and --metric-percentiles together might be confusing to users.

From the doc string, it's clear what they are. In fact, it's kind of confusing even if we rename it to metrics because there are metrics always computed.

wschin · 2024-08-29T23:39:51Z

I feel lazy about more changes to this PR. Can you please merge to avoid merge conflict?

ywang96

@wschin Let's merge this, thank you for making this contribution!

KuntaiDu · 2024-09-05T22:46:35Z

Sry for not being responsive enough during last week and this week, was working hard on performance benchmark. This PR looks good to me and I will need to make some accommodating changes in various benchmarks.

commit a1d8742 Author: Simon Mo <simon.mo@hey.com> Date: Mon Sep 9 23:21:00 2024 -0700 Add NVIDIA Meetup slides, announce AMD meetup, and add contact info (vllm-project#8319) commit 6cd5e5b Author: Dipika Sikka <dipikasikka1@gmail.com> Date: Mon Sep 9 23:02:52 2024 -0400 [Misc] Fused MoE Marlin support for GPTQ (vllm-project#8217) commit c7cb5c3 Author: Kyle Sayers <kylesayrs@gmail.com> Date: Mon Sep 9 16:27:26 2024 -0400 [Misc] GPTQ Activation Ordering (vllm-project#8135) commit f9b4a2d Author: Vladislav Kruglikov <vladislavkruglikov@outlook.com> Date: Mon Sep 9 21:20:46 2024 +0300 [Bugfix] Correct adapter usage for cohere and jamba (vllm-project#8292) commit 58fcc85 Author: Adam Lugowski <alugowski@gmail.com> Date: Mon Sep 9 11:16:37 2024 -0700 [Frontend] Add progress reporting to run_batch.py (vllm-project#8060) Co-authored-by: Adam Lugowski <adam.lugowski@parasail.io> commit 08287ef Author: Kyle Mistele <kyle@mistele.com> Date: Mon Sep 9 09:45:11 2024 -0500 [Bugfix] Streamed tool calls now more strictly follow OpenAI's format; ensures Vercel AI SDK compatibility (vllm-project#8272) commit 4ef41b8 Author: Alexander Matveev <59768536+alexm-neuralmagic@users.noreply.github.com> Date: Sun Sep 8 00:01:51 2024 -0400 [Bugfix] Fix async postprocessor in case of preemption (vllm-project#8267) commit cfe712b Author: Joe Runde <Joseph.Runde@ibm.com> Date: Sat Sep 7 14:03:16 2024 -0600 [CI/Build] Use python 3.12 in cuda image (vllm-project#8133) Signed-off-by: Joe Runde <Joseph.Runde@ibm.com> commit b962ee1 Author: sumitd2 <91451282+sumitd2@users.noreply.github.com> Date: Sat Sep 7 23:48:40 2024 +0530 ppc64le: Dockerfile fixed, and a script for buildkite (vllm-project#8026) commit 36bf815 Author: Isotr0py <2037008807@qq.com> Date: Sun Sep 8 01:45:44 2024 +0800 [Model][VLM] Decouple weight loading logic for `Paligemma` (vllm-project#8269) commit e807125 Author: Isotr0py <2037008807@qq.com> Date: Sat Sep 7 16:38:23 2024 +0800 [Model][VLM] Support multi-images inputs for InternVL2 models (vllm-project#8201) commit 9f68e00 Author: Cyrus Leung <tlleungac@connect.ust.hk> Date: Sat Sep 7 16:02:39 2024 +0800 [Bugfix] Fix broken OpenAI tensorizer test (vllm-project#8258) commit ce2702a Author: youkaichao <youkaichao@gmail.com> Date: Fri Sep 6 22:40:46 2024 -0700 [tpu][misc] fix typo (vllm-project#8260) commit 795b662 Author: Wei-Sheng Chin <wschin@outlook.com> Date: Fri Sep 6 20:18:16 2024 -0700 Enable Random Prefix Caching in Serving Profiling Tool (benchmark_serving.py) (vllm-project#8241) commit 2f707fc Author: Cyrus Leung <tlleungac@connect.ust.hk> Date: Sat Sep 7 10:57:24 2024 +0800 [Model] Multi-input support for LLaVA (vllm-project#8238) commit 41e95c5 Author: Kyle Mistele <kyle@mistele.com> Date: Fri Sep 6 21:49:01 2024 -0500 [Bugfix] Fix Hermes tool call chat template bug (vllm-project#8256) Co-authored-by: Kyle Mistele <kyle@constellate.ai> commit 12dd715 Author: William Lin <SolitaryThinker@users.noreply.github.com> Date: Fri Sep 6 17:48:48 2024 -0700 [misc] [doc] [frontend] LLM torch profiler support (vllm-project#7943) commit 29f49cd Author: Patrick von Platen <patrick.v.platen@gmail.com> Date: Sat Sep 7 01:02:05 2024 +0200 [Model] Allow loading from original Mistral format (vllm-project#8168) Co-authored-by: Michael Goin <michael@neuralmagic.com> commit 23f3222 Author: Dipika Sikka <dipikasikka1@gmail.com> Date: Fri Sep 6 18:29:03 2024 -0400 [Misc] Remove `SqueezeLLM` (vllm-project#8220) commit 9db52ea Author: rasmith <Randall.Smith@amd.com> Date: Fri Sep 6 17:26:09 2024 -0500 [Kernel] [Triton] Memory optimization for awq_gemm and awq_dequantize, 2x throughput (vllm-project#8248) commit 1447c97 Author: Alexey Kondratiev(AMD) <143633163+alexeykondrat@users.noreply.github.com> Date: Fri Sep 6 14:51:03 2024 -0400 [CI/Build] Increasing timeout for multiproc worker tests (vllm-project#8203) commit de80783 Author: Rui Qiao <161574667+ruisearch42@users.noreply.github.com> Date: Fri Sep 6 09:18:35 2024 -0700 [Misc] Use ray[adag] dependency instead of cuda (vllm-project#7938) commit e5cab71 Author: afeldman-nm <156691304+afeldman-nm@users.noreply.github.com> Date: Fri Sep 6 12:01:14 2024 -0400 [Frontend] Add --logprobs argument to `benchmark_serving.py` (vllm-project#8191) commit baa5467 Author: Nick Hill <nickhill@us.ibm.com> Date: Thu Sep 5 20:39:29 2024 -0700 [BugFix] Fix Granite model configuration (vllm-project#8216) commit db3bf7c Author: Jiaxin Shan <seedjeffwan@gmail.com> Date: Thu Sep 5 18:10:33 2024 -0700 [Core] Support load and unload LoRA in api server (vllm-project#6566) Co-authored-by: Jee Jee Li <pandaleefree@gmail.com> commit 2febcf2 Author: sroy745 <142070531+sroy745@users.noreply.github.com> Date: Thu Sep 5 13:25:29 2024 -0700 [Documentation][Spec Decode] Add documentation about lossless guarantees in Speculative Decoding in vLLM (vllm-project#7962) commit 2ee4528 Author: Michael Goin <michael@neuralmagic.com> Date: Thu Sep 5 11:09:46 2024 -0400 Move verify_marlin_supported to GPTQMarlinLinearMethod (vllm-project#8165) commit 9da25a8 Author: Alex Brooks <alex.brooks@ibm.com> Date: Thu Sep 5 06:48:10 2024 -0600 [MODEL] Qwen Multimodal Support (Qwen-VL / Qwen-VL-Chat) (vllm-project#8029) Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com> Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk> commit 8685ba1 Author: manikandan.tm@zucisystems.com <94887255+Manikandan-Thangaraj-ZS0321@users.noreply.github.com> Date: Thu Sep 5 17:03:37 2024 +0530 Inclusion of InternVLChatModel In PP_SUPPORTED_MODELS(Pipeline Parallelism) (vllm-project#7860) commit 288a938 Author: Cyrus Leung <tlleungac@connect.ust.hk> Date: Thu Sep 5 18:51:53 2024 +0800 [Doc] Indicate more information about supported modalities (vllm-project#8181) commit e39ebf5 Author: Elfie Guo <164945471+elfiegg@users.noreply.github.com> Date: Wed Sep 4 22:12:26 2024 -0700 [Core/Bugfix] Add query dtype as per FlashInfer API requirements. (vllm-project#8173) commit ba262c4 Author: Kevin H. Luu <kevin@anyscale.com> Date: Wed Sep 4 20:33:12 2024 -0700 [ci] Mark LoRA test as soft-fail (vllm-project#8160) Signed-off-by: kevin <kevin@anyscale.com> commit 4624d98 Author: Woosuk Kwon <woosuk.kwon@berkeley.edu> Date: Wed Sep 4 20:31:48 2024 -0700 [Misc] Clean up RoPE forward_native (vllm-project#8076) commit 1afc931 Author: William Lin <SolitaryThinker@users.noreply.github.com> Date: Wed Sep 4 17:35:36 2024 -0700 [bugfix] >1.43 constraint for openai (vllm-project#8169) Co-authored-by: Michael Goin <michael@neuralmagic.com> commit e01c2be Author: Maureen McElaney <mmcelaney@users.noreply.github.com> Date: Wed Sep 4 19:50:13 2024 -0400 [Doc] [Misc] Create CODE_OF_CONDUCT.md (vllm-project#8161) commit 32e7db2 Author: Simon Mo <simon.mo@hey.com> Date: Wed Sep 4 16:34:27 2024 -0700 Bump version to v0.6.0 (vllm-project#8166) commit 008cf88 Author: Harsha vardhan manoj Bikki <39381063+hbikki@users.noreply.github.com> Date: Wed Sep 4 16:33:43 2024 -0700 [Neuron] Adding support for adding/ overriding neuron configuration a… (vllm-project#8062) Co-authored-by: Harsha Bikki <harbikh@amazon.com> commit 77d9e51 Author: Cody Yu <hao.yu.cody@gmail.com> Date: Wed Sep 4 13:23:22 2024 -0700 [MISC] Replace input token throughput with total token throughput (vllm-project#8164) Co-authored-by: Michael Goin <michael@neuralmagic.com> commit e02ce49 Author: Kyle Mistele <kyle@mistele.com> Date: Wed Sep 4 15:18:13 2024 -0500 [Feature] OpenAI-Compatible Tools API + Streaming for Hermes & Mistral models (vllm-project#5649) Co-authored-by: constellate <constellate@1-ai-appserver-staging.codereach.com> Co-authored-by: Kyle Mistele <kyle@constellate.ai> commit 561d6f8 Author: Woosuk Kwon <woosuk.kwon@berkeley.edu> Date: Wed Sep 4 13:05:50 2024 -0700 [CI] Change test input in Gemma LoRA test (vllm-project#8163) commit d1dec64 Author: alexeykondrat <143633163+alexeykondrat@users.noreply.github.com> Date: Wed Sep 4 14:57:54 2024 -0400 [CI/Build][ROCm] Enabling LoRA tests on ROCm (vllm-project#7369) Co-authored-by: Simon Mo <simon.mo@hey.com> commit 2ad2e56 Author: Cody Yu <hao.yu.cody@gmail.com> Date: Wed Sep 4 11:53:25 2024 -0700 [MISC] Consolidate FP8 kv-cache tests (vllm-project#8131) commit d331156 Author: wnma <wnma3mz@gmail.com> Date: Wed Sep 4 18:55:37 2024 +0800 [Bugfix] remove post_layernorm in siglip (vllm-project#8106) commit ccd7207 Author: TimWang <7367474+haitwang-cloud@users.noreply.github.com> Date: Wed Sep 4 14:17:05 2024 +0800 chore: Update check-wheel-size.py to read MAX_SIZE_MB from env (vllm-project#8103) commit 855c262 Author: Cyrus Leung <tlleungac@connect.ust.hk> Date: Wed Sep 4 13:22:17 2024 +0800 [Frontend] Multimodal support in offline chat (vllm-project#8098) commit 2be8ec6 Author: Peter Salas <peter@fixie.ai> Date: Tue Sep 3 21:38:21 2024 -0700 [Model] Add Ultravox support for multiple audio chunks (vllm-project#7963) commit e16fa99 Author: Dipika Sikka <dipikasikka1@gmail.com> Date: Tue Sep 3 22:12:41 2024 -0400 [Misc] Update fbgemmfp8 to use `vLLMParameters` (vllm-project#7972) Co-authored-by: Michael Goin <michael@neuralmagic.com> commit 61f4a93 Author: Woosuk Kwon <woosuk.kwon@berkeley.edu> Date: Tue Sep 3 18:35:33 2024 -0700 [TPU][Bugfix] Use XLA rank for persistent cache path (vllm-project#8137) commit d4db9f5 Author: Nick Hill <nickhill@us.ibm.com> Date: Tue Sep 3 17:57:41 2024 -0700 [Benchmark] Add `--async-engine` option to benchmark_throughput.py (vllm-project#7964) commit 2188a60 Author: Dipika Sikka <dipikasikka1@gmail.com> Date: Tue Sep 3 17:21:44 2024 -0400 [Misc] Update `GPTQ` to use `vLLMParameters` (vllm-project#7976) commit dc0b606 Author: Simon Mo <simon.mo@hey.com> Date: Tue Sep 3 14:11:42 2024 -0700 [CI] Change PR remainder to avoid at-mentions (vllm-project#8134) commit 0af3abe Author: Woosuk Kwon <woosuk.kwon@berkeley.edu> Date: Tue Sep 3 13:29:24 2024 -0700 [TPU][Bugfix] Fix next_token_ids shape (vllm-project#8128) commit f1575dc Author: Kevin H. Luu <kevin@anyscale.com> Date: Tue Sep 3 13:25:09 2024 -0700 [ci] Fix GHA workflow (vllm-project#8129) Signed-off-by: kevin <kevin@anyscale.com> commit c02638e Author: tomeras91 <57313761+tomeras91@users.noreply.github.com> Date: Tue Sep 3 22:37:08 2024 +0300 [CI/Build] make pip install vllm work in macos (for import only) (vllm-project#8118) commit 652c83b Author: Antoni Baum <antoni.baum@protonmail.com> Date: Tue Sep 3 12:28:25 2024 -0700 [Misc] Raise a more informative exception in add/remove_logger (vllm-project#7750) commit 6d646d0 Author: Alexander Matveev <59768536+alexm-neuralmagic@users.noreply.github.com> Date: Tue Sep 3 14:50:29 2024 -0400 [Core] Optimize Async + Multi-step (vllm-project#8050) commit 95a178f Author: Kevin H. Luu <kevin@anyscale.com> Date: Tue Sep 3 11:32:27 2024 -0700 [CI] Only PR reviewers/committers can trigger CI on PR (vllm-project#8124) Signed-off-by: kevin <kevin@anyscale.com> commit bd852f2 Author: Cody Yu <hao.yu.cody@gmail.com> Date: Tue Sep 3 10:49:18 2024 -0700 [Performance] Enable chunked prefill and prefix caching together (vllm-project#8120) Co-authored-by: Tao He <sighingnow@gmail.com> Co-authored-by: Juelianqvq <Juelianqvq@noreply.github.com> commit ec26653 Author: Isotr0py <2037008807@qq.com> Date: Tue Sep 3 21:37:52 2024 +0800 [Bugfix][VLM] Add fallback to SDPA for ViT model running on CPU backend (vllm-project#8061) commit 0fbc669 Author: Woosuk Kwon <woosuk.kwon@berkeley.edu> Date: Mon Sep 2 20:35:42 2024 -0700 [Bugfix] Fix single output condition in output processor (vllm-project#7881) commit 6e36f4f Author: wang.yuqi <noooop@126.com> Date: Tue Sep 3 05:20:12 2024 +0800 improve chunked prefill performance [Bugfix] Fix vllm-project#7592 vllm 0.5.4 enable_chunked_prefill throughput is slightly lower than 0.5.3~0.5.0. (vllm-project#7874) commit dd2a6a8 Author: Isotr0py <2037008807@qq.com> Date: Mon Sep 2 23:48:56 2024 +0800 [Bugfix] Fix internlm2 tensor parallel inference (vllm-project#8055) commit 4ca65a9 Author: Isotr0py <2037008807@qq.com> Date: Mon Sep 2 20:43:26 2024 +0800 [Core][Bugfix] Accept GGUF model without .gguf extension (vllm-project#8056) commit e2b2aa5 Author: Woosuk Kwon <woosuk.kwon@berkeley.edu> Date: Sun Sep 1 23:09:46 2024 -0700 [TPU] Align worker index with node boundary (vllm-project#7932) commit e6a26ed Author: Lily Liu <lilyliupku@gmail.com> Date: Sun Sep 1 21:23:29 2024 -0700 [SpecDecode][Kernel] Flashinfer Rejection Sampling (vllm-project#7244) commit f8d6014 Author: Shawn Tan <shawn@wtf.sg> Date: Sun Sep 1 21:37:18 2024 -0400 [Model] Add Granite model (vllm-project#7436) Co-authored-by: Nick Hill <nickhill@us.ibm.com> commit 5b86b19 Author: Roger Wang <136131678+ywang96@users.noreply.github.com> Date: Sun Sep 1 14:46:57 2024 -0700 [Misc] Optional installation of audio related packages (vllm-project#8063) commit 5231f08 Author: Roger Wang <136131678+ywang96@users.noreply.github.com> Date: Sat Aug 31 16:35:53 2024 -0700 [Frontend][VLM] Add support for multiple multi-modal items (vllm-project#8049) commit 8423aef Author: Robert Shaw <114415538+robertgshaw2-neuralmagic@users.noreply.github.com> Date: Sat Aug 31 15:44:03 2024 -0400 [BugFix][Core] Multistep Fix Crash on Request Cancellation (vllm-project#8059) commit 4f5d844 Author: Nicolò Lucchesi <nicolo.lucchesi@gmail.com> Date: Sat Aug 31 09:27:58 2024 +0200 [Bugfix] Fix ModelScope models in v0.5.5 (vllm-project#8037) commit d05f0a9 Author: Cyrus Leung <tlleungac@connect.ust.hk> Date: Sat Aug 31 13:26:55 2024 +0800 [Bugfix] Fix import error in Phi-3.5-MoE (vllm-project#8052) commit 622f8ab Author: Pavani Majety <pmajety@nvidia.com> Date: Fri Aug 30 22:18:50 2024 -0700 [Bugfix] bugfix and add model test for flashinfer fp8 kv cache. (vllm-project#8013) commit 1248e85 Author: Wenxiang <8460860+wenxcs@users.noreply.github.com> Date: Sat Aug 31 03:42:57 2024 +0800 [Model] Adding support for MSFT Phi-3.5-MoE (vllm-project#7729) Co-authored-by: Your Name <you@example.com> Co-authored-by: Zeqi Lin <zelin@microsoft.com> Co-authored-by: Zeqi Lin <Zeqi.Lin@microsoft.com> commit 2684efc Author: Woosuk Kwon <woosuk.kwon@berkeley.edu> Date: Fri Aug 30 09:01:26 2024 -0700 [TPU][Bugfix] Fix tpu type api (vllm-project#8035) commit 058344f Author: Kaunil Dhruv <dhruv.kaunil@gmail.com> Date: Fri Aug 30 08:21:02 2024 -0700 [Frontend]-config-cli-args (vllm-project#7737) Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com> Co-authored-by: Kaunil Dhruv <kaunil_dhruv@intuit.com> commit 98cef6a Author: Cyrus Leung <tlleungac@connect.ust.hk> Date: Fri Aug 30 23:20:34 2024 +0800 [Core] Increase default `max_num_batched_tokens` for multimodal models (vllm-project#8028) commit f97be32 Author: Jungho Christopher Cho <wjdgh6655@gmail.com> Date: Sat Aug 31 00:19:27 2024 +0900 [VLM][Model] TP support for ViTs (vllm-project#7186) Co-authored-by: Roger Wang <136131678+ywang96@users.noreply.github.com> Co-authored-by: Roger Wang <ywang@roblox.com> commit afd39a4 Author: Cyrus Leung <tlleungac@connect.ust.hk> Date: Fri Aug 30 23:03:28 2024 +0800 [Bugfix] Fix import error in Exaone model (vllm-project#8034) commit 2148441 Author: Richard Liu <39319471+richardsliu@users.noreply.github.com> Date: Fri Aug 30 00:27:40 2024 -0700 [TPU] Support single and multi-host TPUs on GKE (vllm-project#7613) commit dc13e99 Author: Yohan Na <nayohan13@gmail.com> Date: Fri Aug 30 15:34:20 2024 +0900 [MODEL] add Exaone model support (vllm-project#7819) commit 34a0e96 Author: Avshalom Manevich <12231371+avshalomman@users.noreply.github.com> Date: Fri Aug 30 11:11:39 2024 +0700 [Kernel] changing fused moe kernel chunk size default to 32k (vllm-project#7995) commit 80c7b08 Author: Woosuk Kwon <woosuk.kwon@berkeley.edu> Date: Thu Aug 29 19:35:29 2024 -0700 [TPU] Async output processing for TPU (vllm-project#8011) commit 428dd14 Author: afeldman-nm <156691304+afeldman-nm@users.noreply.github.com> Date: Thu Aug 29 22:19:08 2024 -0400 [Core] Logprobs support in Multi-step (vllm-project#7652) commit 4abed65 Author: Cyrus Leung <tlleungac@connect.ust.hk> Date: Fri Aug 30 08:49:04 2024 +0800 [VLM] Disallow overflowing `max_model_len` for multimodal models (vllm-project#7998) commit 0c785d3 Author: Wei-Sheng Chin <wechi@microsoft.com> Date: Thu Aug 29 16:48:11 2024 -0700 Add more percentiles and latencies (vllm-project#7759) commit 4664cea Author: chenqianfzh <51831990+chenqianfzh@users.noreply.github.com> Date: Thu Aug 29 16:09:08 2024 -0700 support bitsandbytes 8-bit and FP4 quantized models (vllm-project#7445) commit 257afc3 Author: Harsha vardhan manoj Bikki <39381063+hbikki@users.noreply.github.com> Date: Thu Aug 29 13:58:14 2024 -0700 [Neuron] Adding support for context-lenght, token-gen buckets. (vllm-project#7885) Co-authored-by: Harsha Bikki <harbikh@amazon.com> commit 86a677d Author: Dipika Sikka <dipikasikka1@gmail.com> Date: Thu Aug 29 16:46:55 2024 -0400 [misc] update tpu int8 to use new vLLM Parameters (vllm-project#7973) commit d78789a Author: Isotr0py <2037008807@qq.com> Date: Fri Aug 30 03:54:49 2024 +0800 [Bugfix] Fix incorrect vocal embedding shards for GGUF model in tensor parallelism (vllm-project#7954) commit c334b18 Author: kushanam <42385577+kushanam@users.noreply.github.com> Date: Thu Aug 29 12:15:04 2024 -0700 extend cuda graph size for H200 (vllm-project#7894) Co-authored-by: youkaichao <youkaichao@126.com> commit 6b34215 Author: Pavani Majety <pavanimajety@gmail.com> Date: Thu Aug 29 11:53:11 2024 -0700 [Core][Kernels] Enable FP8 KV Cache with Flashinfer backend. + BugFix for kv_cache_dtype=auto (vllm-project#7985) Co-authored-by: Simon Mo <simon.mo@hey.com> Co-authored-by: Cody Yu <hao.yu.cody@gmail.com> commit 3f60f22 Author: Alexander Matveev <59768536+alexm-neuralmagic@users.noreply.github.com> Date: Thu Aug 29 14:18:26 2024 -0400 [Core] Combine async postprocessor and multi-step (vllm-project#7921) commit f205c09 Author: Jonas M. Kübler <44084297+jmkuebler@users.noreply.github.com> Date: Thu Aug 29 07:18:13 2024 +0200 [Bugfix] Unify rank computation across regular decoding and speculative decoding (vllm-project#7899) commit ef99a78 Author: youkaichao <youkaichao@gmail.com> Date: Wed Aug 28 21:27:06 2024 -0700 Revert "[Core][Kernels] Use FlashInfer backend for FP8 KV Cache when available." (vllm-project#7982) commit 74d5543 Author: Peter Salas <peter@fixie.ai> Date: Wed Aug 28 20:24:31 2024 -0700 [VLM][Core] Fix exceptions on ragged NestedTensors (vllm-project#7974) commit a7f65c2 Author: youkaichao <youkaichao@gmail.com> Date: Wed Aug 28 17:32:26 2024 -0700 [torch.compile] remove reset (vllm-project#7975) commit 4289cad Author: Nick Hill <nickhill@us.ibm.com> Date: Wed Aug 28 17:22:43 2024 -0700 [Frontend] Minor optimizations to zmq decoupled front-end (vllm-project#7957) Co-authored-by: Robert Shaw <rshaw@neuralmagic> commit af59df0 Author: Michael Goin <michael@neuralmagic.com> Date: Wed Aug 28 19:19:17 2024 -0400 Remove faulty Meta-Llama-3-8B-Instruct-FP8.yaml lm-eval test (vllm-project#7961) commit ce6bf3a Author: youkaichao <youkaichao@gmail.com> Date: Wed Aug 28 16:10:12 2024 -0700 [torch.compile] avoid Dynamo guard evaluation overhead (vllm-project#7898) Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu> commit 3cdfe1f Author: bnellnm <49004751+bnellnm@users.noreply.github.com> Date: Wed Aug 28 18:11:49 2024 -0400 [Bugfix] Make torch registration of punica ops optional (vllm-project#7970) commit fdd9daa Author: Mor Zusman <mor.zusmann@gmail.com> Date: Thu Aug 29 01:06:52 2024 +0300 [Kernel/Model] Migrate mamba_ssm and causal_conv1d kernels to vLLM (vllm-project#7651) commit 8c56e57 Author: Stas Bekman <stas00@users.noreply.github.com> Date: Wed Aug 28 13:54:23 2024 -0700 [Doc] fix 404 link (vllm-project#7966) commit eeffde1 Author: Woosuk Kwon <woosuk.kwon@berkeley.edu> Date: Wed Aug 28 13:10:21 2024 -0700 [TPU] Upgrade PyTorch XLA nightly (vllm-project#7967) commit e5697d1 Author: rasmith <Randall.Smith@amd.com> Date: Wed Aug 28 14:37:47 2024 -0500 [Kernel] [Triton] [AMD] Adding Triton implementations awq_dequantize and awq_gemm to support AWQ (vllm-project#7386) commit b98cc28 Author: Pavani Majety <pavanimajety@gmail.com> Date: Wed Aug 28 10:01:22 2024 -0700 [Core][Kernels] Use FlashInfer backend for FP8 KV Cache when available. (vllm-project#7798) Co-authored-by: Simon Mo <simon.mo@hey.com> commit ef9baee Author: Cyrus Leung <tlleungac@connect.ust.hk> Date: Wed Aug 28 23:11:18 2024 +0800 [Bugfix][VLM] Fix incompatibility between vllm-project#7902 and vllm-project#7230 (vllm-project#7948) commit 98c12cf Author: Stas Bekman <stas00@users.noreply.github.com> Date: Wed Aug 28 05:12:32 2024 -0700 [Doc] fix the autoAWQ example (vllm-project#7937) commit f52a43a Author: youkaichao <youkaichao@gmail.com> Date: Wed Aug 28 01:27:07 2024 -0700 [ci][test] fix pp test failure (vllm-project#7945) commit e358053 Author: Cody Yu <hao.yu.cody@gmail.com> Date: Wed Aug 28 00:36:31 2024 -0700 [Performance] Enable chunked prefill and prefix caching together (vllm-project#7753)

Signed-off-by: Alvant <alvasian@yandex.ru>

wschin force-pushed the measure branch from 55c44db to 76c7465 Compare August 21, 2024 23:04

Add more percentiles and latencies

1b4f73b

Drop a line lint

github-actions bot added the ready ONLY add when PR is ready to merge/full CI is needed label Aug 22, 2024

DarkLight1337 requested a review from ywang96 August 22, 2024 08:20

Flexiable way to select some metrics

e876a0d

wschin force-pushed the measure branch from 76c7465 to e876a0d Compare August 24, 2024 01:01

wschin commented Aug 24, 2024

View reviewed changes

benchmarks/benchmark_serving.py Show resolved Hide resolved

wschin commented Aug 24, 2024

View reviewed changes

benchmarks/benchmark_serving.py Show resolved Hide resolved

wschin commented Aug 24, 2024

View reviewed changes

benchmarks/benchmark_serving.py Outdated Show resolved Hide resolved

wschin added 3 commits August 24, 2024 01:06

format

6899f0c

put repeated lines to function

e3ca8f6

format

2e48973

comaniac reviewed Aug 24, 2024

View reviewed changes

benchmarks/benchmark_serving.py Outdated Show resolved Hide resolved

etel -> e2el

e494450

ywang96 reviewed Aug 26, 2024

View reviewed changes

ywang96 approved these changes Aug 29, 2024

View reviewed changes

ywang96 merged commit 0c785d3 into vllm-project:main Aug 29, 2024
30 checks passed

dsikka pushed a commit to neuralmagic/nm-vllm that referenced this pull request Aug 31, 2024

Add more percentiles and latencies (vllm-project#7759)

08afb93

triple-Mu pushed a commit to triple-Mu/vllm_official that referenced this pull request Sep 4, 2024

Add more percentiles and latencies (vllm-project#7759)

5e31573

dsikka pushed a commit to neuralmagic/vllm that referenced this pull request Sep 5, 2024

Add more percentiles and latencies (vllm-project#7759)

ae911ff

Jeffwan pushed a commit to aibrix/vllm that referenced this pull request Sep 19, 2024

Add more percentiles and latencies (vllm-project#7759)

5876a84

siddharth9820 pushed a commit to axonn-ai/vllm that referenced this pull request Sep 30, 2024

Add more percentiles and latencies (vllm-project#7759)

dcae38e

Alvant pushed a commit to compressa-ai/vllm that referenced this pull request Oct 26, 2024

Add more percentiles and latencies (vllm-project#7759)

db00796

Signed-off-by: Alvant <alvasian@yandex.ru>

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Add more percentiles and latencies #7759

Add more percentiles and latencies #7759

wschin commented Aug 21, 2024 •

edited

Loading

github-actions bot commented Aug 21, 2024

wschin commented Aug 22, 2024

ywang96 commented Aug 22, 2024 •

edited

Loading

comaniac commented Aug 22, 2024

ywang96 commented Aug 22, 2024

wschin commented Aug 22, 2024

comaniac left a comment

wschin commented Aug 24, 2024

comaniac commented Aug 24, 2024

wschin commented Aug 26, 2024

ywang96 commented Aug 26, 2024

ywang96 left a comment

ywang96 Aug 26, 2024

ywang96 Aug 26, 2024

wschin Aug 29, 2024

wschin commented Aug 29, 2024

ywang96 left a comment

KuntaiDu commented Sep 5, 2024

Add more percentiles and latencies #7759

Add more percentiles and latencies #7759

Conversation

wschin commented Aug 21, 2024 • edited Loading

github-actions bot commented Aug 21, 2024

wschin commented Aug 22, 2024

ywang96 commented Aug 22, 2024 • edited Loading

comaniac commented Aug 22, 2024

ywang96 commented Aug 22, 2024

wschin commented Aug 22, 2024

comaniac left a comment

Choose a reason for hiding this comment

wschin commented Aug 24, 2024

comaniac commented Aug 24, 2024

wschin commented Aug 26, 2024

ywang96 commented Aug 26, 2024

ywang96 left a comment

Choose a reason for hiding this comment

ywang96 Aug 26, 2024

Choose a reason for hiding this comment

ywang96 Aug 26, 2024

Choose a reason for hiding this comment

wschin Aug 29, 2024

Choose a reason for hiding this comment

wschin commented Aug 29, 2024

ywang96 left a comment

Choose a reason for hiding this comment

KuntaiDu commented Sep 5, 2024

wschin commented Aug 21, 2024 •

edited

Loading

ywang96 commented Aug 22, 2024 •

edited

Loading