6fa718a460
[Misc] Modularize CLI Argument Parsing in Benchmark Scripts ( #19593 )
...
Signed-off-by: reidliu41 <reid201711@gmail.com>
Co-authored-by: reidliu41 <reid201711@gmail.com>
2025-06-14 16:54:52 +08:00
02f0c7b220
[Misc] Add SPDX-FileCopyrightText ( #19100 )
...
Signed-off-by: simon-mo <simon.mo@hey.com>
2025-06-03 11:20:17 -07:00
774c5fde30
[V1] fix torch profiling for V1 offline scenarios ( #18445 )
...
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
2025-05-28 04:16:30 +00:00
aaa4ac1c95
Disable prefix cache by default for benchmark ( #18639 )
...
Signed-off-by: cascade812 <cascade812@outlook.com>
2025-05-27 20:06:34 +08:00
009d9e7590
Convert `benchmarks` to `ruff format` ( #18068 )
...
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2025-05-13 13:43:29 +00:00
58abe35455
[Benchmarks] Make detokenization optional in benchmark scripts ( #11697 )
...
Signed-off-by: Jeremy Arnold <Jeremy.Arnold@amd.com>
2025-03-07 08:09:00 -08:00
cf069aa8aa
Update deprecated Python 3.8 typing ( #13971 )
2025-03-02 17:34:51 -08:00
e7ef74e26e
Fix some issues with benchmark data output ( #13641 )
...
Signed-off-by: Huy Do <huydhn@gmail.com>
2025-02-24 10:23:18 +08:00
7f6bae561c
[CI/Build] Fix pre-commit errors ( #13696 )
2025-02-22 00:31:26 -08:00
8aca27fa11
[Bugfix] Fix benchmark script bug: inaccurate stats for vllm backend when max_model_len < input_len + output_len ( #13691 )
...
Signed-off-by: WangErXiao <863579016@qq.com>
2025-02-22 14:10:38 +08:00
45186834a0
Run v1 benchmark and integrate with PyTorch OSS benchmark database ( #13068 )
...
Signed-off-by: Huy Do <huydhn@gmail.com>
2025-02-17 08:16:32 +00:00
e489ad7a21
[Misc] Add SPDX-License-Identifier headers to python source files ( #12628 )
...
- **Add SPDX license headers to python source files**
- **Check for SPDX headers using pre-commit**
commit 9d7ef44c3cfb72ca4c32e1c677d99259d10d4745
Author: Russell Bryant <rbryant@redhat.com>
Date: Fri Jan 31 14:18:24 2025 -0500
Add SPDX license headers to python source files
This commit adds SPDX license headers to python source files as
recommended to
the project by the Linux Foundation. These headers provide a concise way
that is
both human and machine readable for communicating license information
for each
source file. It helps avoid any ambiguity about the license of the code
and can
also be easily used by tools to help manage license compliance.
The Linux Foundation runs license scans against the codebase to help
ensure
we are in compliance with the licenses of the code we use, including
dependencies. Having these headers in place helps that tool do its job.
More information can be found on the SPDX site:
- https://spdx.dev/learn/handling-license-info/
Signed-off-by: Russell Bryant <rbryant@redhat.com>
commit 5a1cf1cb3b80759131c73f6a9dddebccac039dea
Author: Russell Bryant <rbryant@redhat.com>
Date: Fri Jan 31 14:36:32 2025 -0500
Check for SPDX headers using pre-commit
Signed-off-by: Russell Bryant <rbryant@redhat.com>
---------
Signed-off-by: Russell Bryant <rbryant@redhat.com>
2025-02-02 11:58:18 -08:00
1d967acb45
[Bugfix] fix beam search input errors and latency benchmark script ( #11875 )
...
Signed-off-by: Ye Qi <yeq@meta.com>
Co-authored-by: yeq <yeq@devgpu004.lla3.facebook.com>
2025-01-09 17:36:39 +08:00
4d29e91be8
[Misc] sort torch profiler table by kernel timing ( #11813 )
2025-01-08 10:57:04 +08:00
cb6fdaa0a0
[Misc] Make benchmarks use EngineArgs ( #9529 )
2024-10-22 15:40:38 -07:00
81ede99ca4
[Core] Deprecating block manager v1 and make block manager v2 default ( #8704 )
...
Removing the block manager v1. This is the initial piece of prefix-caching-centric design. In order to achieve prefix-caching-centric design, we need to simplify the code path so that we only use v2 block manager (which has much higher performance on prefix caching).
2024-10-17 11:38:15 -05:00
f3a507f1d3
[Core] Add an environment variable which needs to be set explicitly to allow BlockSpaceManagerV1 ( #9149 )
2024-10-10 14:17:17 +08:00
18b296fdb2
[core] remove beam search from the core ( #9105 )
2024-10-07 05:47:04 +00:00
3b00b9c26c
[Core] rename`PromptInputs` and `inputs` ( #8876 )
2024-09-26 20:35:15 -07:00
4f1ba0844b
Revert "rename PromptInputs and inputs with backward compatibility ( #8760 ) ( #8810 )
2024-09-25 10:36:26 -07:00
28e1299e60
rename PromptInputs and inputs with backward compatibility ( #8760 )
2024-09-25 09:36:47 -07:00
3185fb0cca
Revert "[Core] Rename `PromptInputs` to `PromptType`, and `inputs` to `prompt`" ( #8750 )
2024-09-24 05:45:20 +00:00
0057894ef7
[Core] Rename `PromptInputs` and `inputs`( #8673 )
2024-09-20 19:00:54 -07:00
8baa454937
[Misc] Move device options to a single place ( #8322 )
2024-09-11 13:25:58 -07:00
739b61a348
[Frontend] Refactor prompt processing ( #4028 )
...
Co-authored-by: Roger Wang <ywang@roblox.com>
2024-07-22 10:13:53 -07:00
3476ed0809
[Core] Optimize block_manager_v2 vs block_manager_v1 (to make V2 default) ( #5602 )
2024-07-01 20:10:37 -07:00
57f09a419c
[Hardware][Intel] OpenVINO vLLM backend ( #5379 )
2024-06-28 13:50:16 +00:00
2ce5d6688b
[Speculative Decoding] Support draft model on different tensor-parallel size than target model ( #5414 )
2024-06-25 09:56:06 +00:00
8065a7e220
[Frontend] Add FlexibleArgumentParser to support both underscore and dash in names ( #5718 )
2024-06-20 17:00:13 -06:00
d8714530d1
[Misc]Add param max-model-len in benchmark_latency.py ( #5629 )
2024-06-19 18:19:08 +08:00
7879f24dcc
[Misc] Add OpenTelemetry support ( #4687 )
...
This PR adds basic support for OpenTelemetry distributed tracing.
It includes changes to enable tracing functionality and improve monitoring capabilities.
I've also added a markdown with print-screens to guide users how to use this feature. You can find it here
2024-06-19 01:17:03 +09:00
9e4e6fe207
[CI] the readability of benchmarking and prepare for dashboard ( #5571 )
...
[CI] Improve the readability of performance benchmarking results and prepare for upcoming performance dashboard (#5571 )
2024-06-17 11:41:08 -07:00
728c4c8a06
[Hardware][Intel GPU] Add Intel GPU(XPU) inference backend ( #3814 )
...
Co-authored-by: Jiang Li <jiang1.li@intel.com>
Co-authored-by: Abhilash Majumder <abhilash.majumder@intel.com>
Co-authored-by: Abhilash Majumder <30946547+abhilash1910@users.noreply.github.com>
2024-06-17 11:01:25 -07:00
319ad7f1d3
[CI/Build][Misc] Add CI that benchmarks vllm performance on those PRs with `perf-benchmarks` label ( #5073 )
...
Co-authored-by: simon-mo <simon.mo@hey.com>
2024-06-13 22:36:20 -07:00
1a8bfd92d5
[Hardware] Initial TPU integration ( #5292 )
2024-06-12 11:53:03 -07:00
b3376e5c76
[Misc] Add args for selecting distributed executor to benchmarks ( #5335 )
2024-06-08 09:20:16 +08:00
616e600e0b
[Misc] add gpu_memory_utilization arg ( #5079 )
...
Signed-off-by: pandyamarut <pandyamarut@gmail.com>
2024-05-28 17:16:18 -07:00
5ae5ed1e60
[Core] Consolidate prompt arguments to LLM engines ( #4328 )
...
Co-authored-by: Roger Wang <ywang@roblox.com>
2024-05-28 13:29:31 -07:00
a3a73ab069
[Misc] Load FP8 kv-cache scaling factors from checkpoints ( #4893 )
...
The 2nd PR for #4532 .
This PR supports loading FP8 kv-cache scaling factors from a FP8 checkpoint (with .kv_scale parameter).
2024-05-22 13:28:20 -07:00
f09edd8a25
Add JSON output support for benchmark_latency and benchmark_throughput ( #4848 )
2024-05-16 10:02:56 -07:00
973617ae02
[Speculative decoding][Re-take] Enable TP>1 speculative decoding ( #4840 )
...
Co-authored-by: Cade Daniel <edacih@gmail.com>
Co-authored-by: Cade Daniel <cade@anyscale.com>
2024-05-16 00:53:51 -07:00
53b018edcb
[Bugfix] Get available quantization methods from quantization registry ( #4098 )
2024-04-18 00:21:55 -07:00
67b4221a61
[Core][5/N] Fully working chunked prefill e2e ( #3884 )
2024-04-10 17:56:48 -07:00
c013d32c75
[Benchmark] Add cpu options to bench scripts ( #3915 )
2024-04-09 21:30:03 -07:00
e4be7d70bb
[CI/Benchmark] add more iteration and use median for robust latency benchmark ( #3889 )
2024-04-06 21:32:30 +00:00
2ff767b513
Enable scaled FP8 (e4m3fn) KV cache on ROCm (AMD GPU) ( #3290 )
...
Co-authored-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
Co-authored-by: HaiShaw <hixiao@gmail.com>
Co-authored-by: AdrianAbeyta <Adrian.Abeyta@amd.com>
Co-authored-by: Matthew Wong <Matthew.Wong2@amd.com>
Co-authored-by: root <root@gt-pla-u18-08.pla.dcgpu>
Co-authored-by: mawong-amd <156021403+mawong-amd@users.noreply.github.com>
Co-authored-by: ttbachyinsda <ttbachyinsda@outlook.com>
Co-authored-by: guofangze <guofangze@kuaishou.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: jacobthebanana <50071502+jacobthebanana@users.noreply.github.com>
Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
2024-04-03 14:15:55 -07:00
b51c1cc9d2
[2/N] Chunked prefill data update ( #3538 )
2024-03-28 10:06:01 -07:00
1956931436
[Misc] add the "download-dir" option to the latency/throughput benchmarks ( #3621 )
2024-03-27 13:39:05 -07:00
17c3103c56
Make it easy to profile workers with nsight ( #3162 )
...
Co-authored-by: Roger Wang <136131678+ywang96@users.noreply.github.com>
2024-03-03 16:19:13 -08:00
72d3a30c63
[Minor] Fix benchmark_latency script ( #2765 )
2024-02-05 12:45:37 -08:00
Reid
Simon Mo
Divakar Verma
cascade
Harry Mellor
Jeremy Arnold
Huy Do
Cyrus Leung
Robin
Russell Bryant
Ye (Charlotte) Qi
Kuntai Du
sroy745
youkaichao
Aarni Koskela
Alexander Matveev
Ilya Lavrenov
Woo-Yeon Lee
Michael Goin
DearPlanet
Ronen Schaffer
Kunshang Ji
Woosuk Kwon
Benjamin Kitor
Marut Pandya
Cody Yu
SangBin Cho
Zedong Peng
Adrian Abeyta
AmadeusChan
Philipp Moritz