Commits · 88faa466d788e25082c02dc9688931d7976361f9 · OpenDAS / vllm_cscc

01 Aug, 2025 3 commits
- [CI] Initial tests for SM100 Blackwell runner (#21877) · 88faa466
  Michael Goin authored Aug 01, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  88faa466
- [Refactor] Remove Duplicate `per_block_cast_to_fp8`, Remove Dependencies of DeepGEMM (#21787) · 37006420
  Wentao Ye authored Jul 31, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  37006420
- Add DeepGEMM to Dockerfile in vllm-base image (#21533) · e360316a
  Matthew Bonanni authored Jul 31, 2025
```
Signed-off-by: Matthew Bonanni <mbonanni001@gmail.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
```
  e360316a
30 Jul, 2025 1 commit
- [Test] Add Benchmark and Unit Test for `per_token_group_quant` (#21860) · 0271c2ff
  Wentao Ye authored Jul 30, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  0271c2ff
29 Jul, 2025 1 commit
- [Bugfix] Fix workspace buffer None issue for Flashinfer TRTLLM Backend (#21525) · 58b11b24
  elvischenv authored Jul 29, 2025
```
Signed-off-by: elvischenv <219235043+elvischenv@users.noreply.github.com>
```
  58b11b24
28 Jul, 2025 1 commit
- [Kernel] SM90 CUTLASS FP8 GEMM: add support for swap AB + kernel tuning (#20396) · c6c9122d
  lyrisz authored Jul 28, 2025
```
Signed-off-by: Faqin Zhong <faqin.zhong@gmail.com>
Co-authored-by: Duncan Moss <djm.moss@gmail.com>
```
  c6c9122d
27 Jul, 2025 1 commit
- Fix CUDA permute/unpermute for use with DeepGemm Moe (#17934) · 57c22e57
  Caleb_Du authored Jul 27, 2025
```
Signed-off-by: Caleb_Du <Caleb_Du@zju.edu.cn>
```
  57c22e57
25 Jul, 2025 1 commit

[ROCm][AITER] Enable fp8 kv cache on rocm aiter backend. (#20295) · b3caeb82

who who who authored Jul 25, 2025


Signed-off-by: fsx950223 <fsx950223@outlook.com>
Signed-off-by: amd-ruitang3 <Rui.Tang2@amd.com>
Co-authored-by: amd-ruitang3 <Rui.Tang2@amd.com>

b3caeb82

24 Jul, 2025 1 commit
- [Bugfix] Fix CUDA arch flags for MoE permute (#21426) · 2ded067f
  Ming Yang authored Jul 24, 2025
```
Signed-off-by: Ming Yang <minos.future@gmail.com>
```
  2ded067f
23 Jul, 2025 2 commits
- [Misc] fixed nvfp4_moe test failures due to invalid kwargs (#21246) · 6929f8b4
  Yang Chen authored Jul 23, 2025
```
Signed-off-by: Yang Chen <yangche@fb.com>
```
  6929f8b4
- Mamba V2 Test not Asserting Failures. (#21379) · 32ec9e2f
  Yu Chin Fabian Lim authored Jul 23, 2025
```
Signed-off-by: Yu Chin Fabian Lim <flim@sg.ibm.com>
```
  32ec9e2f
22 Jul, 2025 3 commits
- [Perf] Cuda Kernel for Per Token Group Quant (#21083) · 774d0c01
  Wentao Ye authored Jul 22, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  774d0c01
- [perf] Add fused MLA QKV + strided layernorm (#21116) · 4fb56914
  Mickaël Seznec authored Jul 22, 2025
```
Signed-off-by: Mickael Seznec <mickael@mistral.ai>
Co-authored-by: mgoin <mgoin64@gmail.com>
```
  4fb56914
- Revert "[Performance] Performance improvements in non-blockwise fp8 CUTLASS MoE (#20762) (#21334) · e7b20426
  Ming Yang authored Jul 21, 2025
```
Signed-off-by: Ming Yang <minos.future@gmail.com>
```
  e7b20426
21 Jul, 2025 1 commit
- [Misc] Add sliding window to flashinfer test (#21282) · 6dda13c8
  Woosuk Kwon authored Jul 21, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  6dda13c8
19 Jul, 2025 2 commits
- [V0 Deprecation] Deprecate BlockSparse Attention & Phi3-Small (#21217) · 752c6ade
  Woosuk Kwon authored Jul 19, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  752c6ade
- Add torch golden impl for moe_align_block_size kernel test (#20653) · 7d945771
  shixianc authored Jul 19, 2025
```
Signed-off-by: Shixian Cui <shixian@amazon.com>
Co-authored-by: Shixian Cui <shixian@amazon.com>
```
  7d945771
18 Jul, 2025 1 commit
- [Perf] Add swap_ab to SM90 FP8 non-block CUTLASS moe grouped gemm (#20911) · 5780121c
  shixianc authored Jul 17, 2025
```
Signed-off-by: Shixian Cui <shixian@amazon.com>
Co-authored-by: Shixian Cui <shixian@amazon.com>
```
  5780121c
17 Jul, 2025 2 commits
- [Performance] Performance improvements in non-blockwise fp8 CUTLASS MoE (#20762) · 9fb2d220
  ElizaWszola authored Jul 17, 2025
```
Signed-off-by: ElizaWszola <ewszola@redhat.com>
```
  9fb2d220
- [Kernel] DeepGemm MoE : Integrate triton permute / unpermute kernels (#20903) · 11dfdf21
  Varun Sundar Rabindranath authored Jul 17, 2025
```
Signed-off-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
Co-authored-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
```
  11dfdf21
16 Jul, 2025 1 commit
- [CI] update typos config for CI pre-commit and fix some spells (#20919) · 1eb2b9c1
  Peter Pan authored Jul 16, 2025
```
Signed-off-by: Peter Pan <Peter.Pan@daocloud.io>
```
  1eb2b9c1
13 Jul, 2025 2 commits
- [Refactor] Change the way of import triton (#20774) · c1acd6d7
  Wentao Ye authored Jul 12, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  c1acd6d7
- [Perf] Use Triton instead of Torch for DeepGEMM Per Token Group Quant (#20841) · 42d440c2
  Wentao Ye authored Jul 12, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  42d440c2
11 Jul, 2025 3 commits
- [Misc] Add unit tests for MoE ModularKernel combinations + Profiling utility (#20449) · 53fa4573
  Varun Sundar Rabindranath authored Jul 11, 2025
```
Signed-off-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
Co-authored-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
```
  53fa4573
- [Core] Add Flashinfer TRTLLM Backend for Flashinfer decode path (SM100). (#19825) · 7bd4c37a
  Pavani Majety authored Jul 11, 2025
```
Signed-off-by: Pavani Majety <pmajety@nvidia.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: shuw <shuw@nvidia.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
```
  7bd4c37a
- [Feature] Integrate SM100 DeepGEMM support (#20087) · e2de455c
  Wentao Ye authored Jul 10, 2025
  
  e2de455c
10 Jul, 2025 2 commits

[Misc] MoE ModularKernel : Introduce TopKWeightAndReduce (#20648) · f0c98cae

Varun Sundar Rabindranath authored Jul 10, 2025


Signed-off-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
Co-authored-by: Varun Sundar Rabindranath <vsundarr@redhat.com>

f0c98cae

[Bugfix] Fused MoE Modular Kernel chunking loop (#20392) · fdadb6f4

Varun Sundar Rabindranath authored Jul 10, 2025


Signed-off-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
Co-authored-by: Varun Sundar Rabindranath <vsundarr@redhat.com>

fdadb6f4

09 Jul, 2025 2 commits

[Feature][Quantization] MXFP4 support for MOE models (#17888) · 332d4cb1

fxmarty-amd authored Jul 09, 2025


Signed-off-by: Felix Marty <felmarty@amd.com>
Signed-off-by: Bowen Bao <bowenbao@amd.com>
Signed-off-by: Felix Marty <Felix.Marty@amd.com>
Co-authored-by: Bowen Bao <bowenbao@amd.com>

332d4cb1

[Kernel] Triton implementation of causal-conv1d for Mamba-based models (#18218) · 47043eb6

Tuan, Hoang-Trong authored Jul 09, 2025


Signed-off-by: Tuan M. Hoang-Trong <tmhoangt@us.ibm.com>
Co-authored-by: Tuan M. Hoang-Trong <tmhoangt@us.ibm.com>
Co-authored-by: Tyler Michael Smith <tysmith@redhat.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>

47043eb6

08 Jul, 2025 1 commit
- [Bugfix] Fix Maverick correctness by filling zero to cache space in cutlass_moe (#20167) · afb7cff1
  Ming Yang authored Jul 07, 2025
```
Signed-off-by: Ming Yang <yming@meta.com>
```
  afb7cff1
06 Jul, 2025 4 commits
- [V1] Support any head size for FlexAttention backend (#20467) · 9fb52e52
  Cyrus Leung authored Jul 07, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  9fb52e52
- [V0 deprecation] Remove V0 CPU/XPU/TPU backends (#20412) · e202dd27
  Woosuk Kwon authored Jul 06, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
Signed-off-by: jiang1.li <jiang1.li@intel.com>
Co-authored-by: Li, Jiang <jiang1.li@intel.com>
```
  e202dd27
- [BUG] Fix #20484. Support empty sequence in cuda penalty kernel (#20491) · f73d02aa
  Vadim Gimpelson authored Jul 06, 2025
```
Signed-off-by: Vadim Gimpelson <vadim.gimpelson@centml.ai>
```
  f73d02aa
- test_attention compat with coming xformers change (#20487) · c5ebe040
  Jeremy Reizenstein authored Jul 06, 2025
```
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
```
  c5ebe040
05 Jul, 2025 1 commit
- [v1] Re-add fp32 support to v1 engine through FlexAttention (#19754) · 32c9be22
  Isotr0py authored Jul 05, 2025
```
Signed-off-by: Isotr0py <2037008807@qq.com>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  32c9be22
04 Jul, 2025 3 commits
- [CI Bugfix] Fix pre-commit failures on main (#20502) · c108781c
  Michael Goin authored Jul 05, 2025
  
  c108781c
- [feat]: CUTLASS block scaled group gemm for SM100 (#19757) · 3d184b95
  Duncan Moss authored Jul 04, 2025
```
Signed-off-by: Duncan Moss <djm.moss@gmail.com>
Co-authored-by: Duncan Moss <dmoss@nvidia.com>
```
  3d184b95
- [Misc] Add SPDX-FileCopyrightText (#20428) · 1caca5a5
  Jee Jee Li authored Jul 04, 2025
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  1caca5a5
03 Jul, 2025 1 commit
- [Kernel] Enable fp8 support for pplx and BatchedTritonExperts. (#18864) · 78fe7753
  bnellnm authored Jul 03, 2025
```
Signed-off-by: Bill Nell <bnell@redhat.com>
```
  78fe7753