Commits · fcfc474d449af116f217d4aa2dbd9cea37fa3e55 · OpenDAS / vllm_cscc

06 Apr, 2025 1 commit
- [Model] Support Llama4 in vLLM (#16104) · c5752323
  Lu Fang authored Apr 05, 2025
  
  c5752323
04 Apr, 2025 1 commit

[Benchmark][Doc] Update throughput benchmark and README (#15998) · 95862f7b

Ziji Shi (Steven) authored Apr 04, 2025


Signed-off-by: StevenShi-23 <shi.ziji.sm@gmail.com>
Signed-off-by: Roger Wang <ywang@roblox.com>
Co-authored-by: Roger Wang <ywang@roblox.com>

95862f7b

03 Apr, 2025 1 commit

[Benchmark] Add AIMO Dataset to Benchmark (#15955) · 06f21ce7

Ziji Shi (Steven) authored Apr 02, 2025


Signed-off-by: Ziji Shi <shi.ziji.sm@gmail.com>
Signed-off-by: StevenShi-23 <shi.ziji.sm@gmail.com>

06f21ce7

02 Apr, 2025 2 commits
- [Bugfix][Benchmarks] Ensure `async_request_deepspeed_mii` uses the OpenAI choices key (#15926) · 25293780
  Brayden Zhong authored Apr 02, 2025
```
Signed-off-by: Brayden Zhong <b8zhong@uwaterloo.ca>
```
  25293780
- [Benchmark]Fix error message (#15866) · aa557e64
  Li Wang authored Apr 02, 2025
```
Signed-off-by: wangli <wangli858794774@gmail.com>
Co-authored-by: Roger Wang <136131678+ywang96@users.noreply.github.com>
```
  aa557e64
01 Apr, 2025 2 commits
- Add option to use DeepGemm contiguous grouped gemm kernel for fused MoE operations. (#13932) · e59ca942
  bnellnm authored Apr 01, 2025
```
Signed-off-by: Bill Nell <bnell@redhat.com>
```
  e59ca942
- 去掉自研专家并行代码 · 9beadbfb
  王敏 authored Apr 01, 2025
  
  9beadbfb
31 Mar, 2025 1 commit
- [Benchmark] Update Vision Arena Dataset and HuggingFaceDataset Setup (#15748) · effc5d24
  Jennifer Zhao authored Mar 31, 2025
```
Signed-off-by: Jennifer Zhao <ai.jenniferzhao@gmail.com>
```
  effc5d24
28 Mar, 2025 2 commits
- [Minor] Remove TGI launching script (#15646) · 70e13224
  Woosuk Kwon authored Mar 28, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  70e13224
- [Misc]add coding benchmark for speculative decoding (#15303) · e7f720ea
  Chen Xia authored Mar 27, 2025
```
Signed-off-by: CXIAAAAA <cxia0209@gmail.com>
```
  e7f720ea
27 Mar, 2025 1 commit

[Kernel] CUTLASS grouped gemm fp8 MoE kernel (#13972) · 9239bf71

ElizaWszola authored Mar 27, 2025


Signed-off-by: ElizaWszola <eliza@neuralmagic.com>
Signed-off-by: ElizaWszola <ewszola@redhat.com>
Co-authored-by: Lucas Wilkinson <wilkinson.lucas@gmail.com>

9239bf71

26 Mar, 2025 1 commit
- [Misc] Warn about v0 in benchmark_paged_attn.py (#15495) · 23114d33
  Tyler Michael Smith authored Mar 25, 2025
```
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
```
  23114d33
23 Mar, 2025 1 commit
- [Misc] Add tuned R1 w8a8 and MoE configs for NVIDIA L20 (#15322) · f90d34b4
  DefTruth authored Mar 23, 2025
```
Signed-off-by: DefTruth <qiustudent_r@163.com>
```
  f90d34b4
20 Mar, 2025 3 commits
- [Core][V0] Add guidance backend for structured output (#14589) · 1f16b7fe
  Russell Bryant authored Mar 20, 2025
```
Signed-off-by: Russell Bryant <rbryant@redhat.com>
Co-authored-by: Loc Huynh <lohuynh@microsoft.com>
Co-authored-by: Michal Moskal <michal@moskal.me>
Co-authored-by: Aaron Pham <contact@aarnphm.xyz>
```
  1f16b7fe
- [Benchmark] Allow oversample request in benchmark dataset (#15170) · b88be221
  Jennifer Zhao authored Mar 19, 2025
```
Signed-off-by: Jennifer Zhao <ai.jenniferzhao@gmail.com>
```
  b88be221
- fix "Total generated tokens:" is 0 if using --backend tgi and --endpo… (#14673) · 40828ce5
  Wang, Yi authored Mar 20, 2025
```
Signed-off-by: Wang, Yi A <yi.a.wang@intel.com>
```
  40828ce5
19 Mar, 2025 1 commit

[Misc][Benchmark] Add support for different `tokenizer_mode` (#15040) · 6c5a3195

Aaron Pham authored Mar 19, 2025


Signed-off-by: Aaron Pham <contact@aarnphm.xyz>
Signed-off-by: Russell Bryant <rbryant@redhat.com>
Co-authored-by: Russell Bryant <rbryant@redhat.com>

6c5a3195

18 Mar, 2025 2 commits
- [Kernels] LoRA - Retire SGMV and BGMV Kernels (#14685) · 400d483e
  Varun Sundar Rabindranath authored Mar 18, 2025
```
Signed-off-by: Varun Sundar Rabindranath <varun@neuralmagic.com>
Co-authored-by: Varun Sundar Rabindranath <varun@neuralmagic.com>
```
  400d483e
- update benchmarks · 10ce38cc
  zhuwenwen authored Mar 18, 2025
  
  10ce38cc
17 Mar, 2025 1 commit
- [Benchmark] Do not save detailed info to json by default (#14879) · 583a9778
  Simon Mo authored Mar 16, 2025
```
Signed-off-by: simon-mo <simon.mo@hey.com>
```
  583a9778
16 Mar, 2025 1 commit
- [Misc][Doc] Minor benchmark README update (#14874) · 3453b964
  Roger Wang authored Mar 15, 2025
```
Signed-off-by: Roger Wang <ywang@roblox.com>
```
  3453b964
14 Mar, 2025 2 commits

[BugFix]Fix performance serving benchmark when enable profiling (#14737) · 09269b31
Li Wang authored Mar 14, 2025
```
Signed-off-by: wangli <wangli858794774@gmail.com>
```
09269b31

[Feature] Add visionarena offline support for benchmark_throughput (#14654) · a6e0d096

Jennifer Zhao authored Mar 13, 2025

Signed-off-by: Jennifer Zhao <7443418+JenZhao@users.noreply.github.com>
Signed-off-by: Jennifer Zhao <ai.jenniferzhao@gmail.com>
Co-authored-by: Jennifer Zhao <7443418+JenZhao@users.noreply.github.com>
Co-authored-by: Jennifer Zhao <JenZhao@users.noreply.github.com>
Co-authored-by: Roger Wang <136131678+ywang96@users.noreply.github.com>

a6e0d096

13 Mar, 2025 1 commit
- [Bugfix] fix benchmark moe (#14653) · a73122de
  Jee Jee Li authored Mar 13, 2025
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  a73122de
12 Mar, 2025 1 commit

[Doc] Update benchmarks README (#14646) · 4a42b9f5

Jennifer Zhao authored Mar 11, 2025

Signed-off-by: Jennifer Zhao <7443418+JenZhao@users.noreply.github.com>
Co-authored-by: Jennifer Zhao <7443418+JenZhao@users.noreply.github.com>
Co-authored-by: Roger Wang <136131678+ywang96@users.noreply.github.com>

4a42b9f5

11 Mar, 2025 3 commits
- dynamic distpatch of fp8 kernels (#14245) · a1c8f379
  Jeff Daily authored Mar 11, 2025
```
Signed-off-by: Jeff Daily <jeff.daily@amd.com>
```
  a1c8f379
- benchmarks: simplify test jsonschema (#14567) · 08a1a112
  Russell Bryant authored Mar 11, 2025
```
Signed-off-by: Russell Bryant <rbryant@redhat.com>
```
  08a1a112
- [feat]优化fused_moe tuning，上传K100_AI的configs · e3a0d6bb
  zhuwenwen authored Mar 11, 2025
  
  e3a0d6bb
10 Mar, 2025 4 commits

Fix typo in benchmark_serving_structured_output.py (#14566) · 432d6dad
Russell Bryant authored Mar 10, 2025
```
Signed-off-by: Russell Bryant <rbryant@redhat.com>
```
432d6dad

[V1] LoRA - Add triton kernels for V1 (#13096) · 5ff0d325

Varun Sundar Rabindranath authored Mar 10, 2025


Signed-off-by: Varun Sundar Rabindranath <varun@neuralmagic.com>
Co-authored-by: Varun Sundar Rabindranath <varun@neuralmagic.com>

5ff0d325

Correct capitalisation: `VLLM` -> `vLLM` (#14562) · 3b352a2f
Harry Mellor authored Mar 10, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
3b352a2f

[Feature] Consolidate performance benchmark datasets (#14036) · 1253b157

Jennifer Zhao authored Mar 10, 2025


Signed-off-by: Jennifer Zhao <7443418+JenZhao@users.noreply.github.com>
Signed-off-by: Roger Wang <ywang@roblox.com>
Co-authored-by: Jennifer Zhao <7443418+JenZhao@users.noreply.github.com>
Co-authored-by: Roger Wang <ywang@roblox.com>

1253b157

08 Mar, 2025 1 commit
- [benchmarks] Add option to use unique jsonschema for each request (#14457) · 9085aabd
  Russell Bryant authored Mar 08, 2025
```
Signed-off-by: Russell Bryant <rbryant@redhat.com>
```
  9085aabd
07 Mar, 2025 5 commits

[Benchmarks] Make detokenization optional in benchmark scripts (#11697) · 58abe354
Jeremy Arnold authored Mar 07, 2025
```
Signed-off-by: Jeremy Arnold <Jeremy.Arnold@amd.com>
```
58abe354

[V1][Core] Support for Structured Outputs (#12388) · 80e9afb5

Aaron Pham authored Mar 07, 2025


Signed-off-by: Aaron Pham <contact@aarnphm.xyz>
Signed-off-by: Russell Bryant <rbryant@redhat.com>
Co-authored-by: Russell Bryant <rbryant@redhat.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Nick Hill <nhill@redhat.com>

80e9afb5

[BUGFIX] Skip tokenization support for throughput benchmark (#12712) · 0ca3b8e0

Aleksandr Malyshev authored Mar 07, 2025


Signed-off-by: root <root@banff-cyxtera-s73-5.ctr.dcgpu>
Signed-off-by: Aleksandr Malyshev <maleksan@amd.com>
Co-authored-by: root <root@banff-cyxtera-s73-5.ctr.dcgpu>
Co-authored-by: Aleksandr Malyshev <maleksan@amd.com>

0ca3b8e0

[Bugfix] Correctly call `cudaProfilerStop` in benchmarks script (#14183) · c34eeec5
Brayden Zhong authored Mar 06, 2025
```
Signed-off-by: Brayden Zhong <b8zhong@uwaterloo.ca>
```
c34eeec5
[Doc] Fix a typo (#14385) · ad60bbb2
Daniel Li authored Mar 06, 2025

ad60bbb2

06 Mar, 2025 1 commit
- Add benchmark for DeepGEMM and vLLM Block FP8 Dense GEMM (#13917) · ca100c90
  Michael Goin authored Mar 05, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  ca100c90
05 Mar, 2025 1 commit

Deprecate `best_of` Sampling Parameter in anticipation for vLLM V1 (#13997) · a4f1ee35

Vincent authored Mar 05, 2025

Signed-off-by: vincent-4 <vincentzhongy+githubvincent4@gmail.com>
Signed-off-by: Brayden Zhong <b8zhong@uwaterloo.ca>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Brayden Zhong <b8zhong@uwaterloo.ca>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>

a4f1ee35