Commits · 38d8096760cd8f42fb65fc0ba2b9fb11f98d8ac3 · OpenDAS / vllm_cscc

11 Sep, 2025 4 commits

[Perf] Use upstream CUTLASS for SM90 Block FP8 kernel (#23280) · c3aea10d

Michael Goin authored Sep 11, 2025


Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>

c3aea10d

[Kernel][B200] `mxfp4` fused cutlass moe (#23696) · 074854b2

Duncan Moss authored Sep 11, 2025


Signed-off-by: Duncan Moss <djm.moss@gmail.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>

074854b2

fix some typos (#24616) · e26fef83
co63oc authored Sep 12, 2025
```
Signed-off-by: co63oc <co63oc@users.noreply.github.com>
```
e26fef83

[Model] New model support for Motif-1-Tiny (#23414) · 9bd831f5

TaehyunKim authored Sep 11, 2025


Signed-off-by: ca1207 <ca1207zzz@gmail.com>
Signed-off-by: TaehyunKim <73943231+ca1207@users.noreply.github.com>
Co-authored-by: WyldeCat <skan1543@gmail.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>

9bd831f5

10 Sep, 2025 4 commits
- [Kernel] Flashinfer MLA (trtllm-gen) decode kernel integration (#21078) · dcb28a33
  Hanjie Qiu authored Sep 10, 2025
```
Signed-off-by: hjjq <hanjieq@nvidia.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
```
  dcb28a33
- Feature/vit attention unification# 23880 (#23978) · 6cbd4190
  baonudesifeizhai authored Sep 10, 2025
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  6cbd4190
- [gpt-oss] Cache permute indices for faster MXFP4 MoE layer loading (#24154) · 0efdb5c3
  Wei authored Sep 09, 2025
```
Signed-off-by: Wei Wei <wwei6@meta.com>
```
  0efdb5c3
- [CI] Retry flaky fp8 cutlass mla tests (#24536) · 7e7db043
  Nick Hill authored Sep 09, 2025
```
Signed-off-by: Nick Hill <nhill@redhat.com>
```
  7e7db043
09 Sep, 2025 2 commits
- [Doc]: fixing typos to improve docs (#24480) · 46876dff
  Didier Durand authored Sep 09, 2025
```
Signed-off-by: Didier Durand <durand.didier@gmail.com>
```
  46876dff
- [Flashinfer] Support Flashinfer TRTLLM FP8-qkv BF16/FP16-out Attention Kernel (#23647) · bba1042c
  elvischenv authored Sep 09, 2025
```
Signed-off-by: elvischenv <219235043+elvischenv@users.noreply.github.com>
```
  bba1042c
08 Sep, 2025 2 commits

[Bugfix] Fix mamba2 prefill chunking (#23279) · e0413141

tomeras91 authored Sep 08, 2025

Signed-off-by: Tomer Asida <57313761+tomeras91@users.noreply.github.com>
Signed-off-by: tomeras91 <57313761+tomeras91@users.noreply.github.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

e0413141

[Kernel] Support decode context parallelism on Blackwell with CUTLASS MLA (#24385) · 86173ad5

Ming Yang authored Sep 07, 2025


Signed-off-by: Ming Yang <minos.future@gmail.com>
Signed-off-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>

86173ad5

06 Sep, 2025 2 commits
- [Bugfix] Fix unstable silu_mul+nvfp4 quant fusion test (#24370) · e68dc2f0
  elvischenv authored Sep 07, 2025
```
Signed-off-by: elvischenv <219235043+elvischenv@users.noreply.github.com>
```
  e68dc2f0
- [Bugfix] Fix test_mixtral_moe (#24371) · 7555d6b3
  Jee Jee Li authored Sep 07, 2025
  
  7555d6b3
04 Sep, 2025 3 commits

[Bugfix][Misc] Fix silu_and_mul_nvfp4_quant issue and extract common utils for... · adc3ddb4

elvischenv authored Sep 05, 2025


[Bugfix][Misc] Fix silu_and_mul_nvfp4_quant issue and extract common utils for nvfp4 kernel source files (#23727)
Signed-off-by: elvischenv <219235043+elvischenv@users.noreply.github.com>
Signed-off-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>

adc3ddb4

[Attention] FlashAttn MLA (#14258) · 402759d4

Lucas Wilkinson authored Sep 04, 2025


Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: Matthew Bonanni <mbonanni001@gmail.com>
Co-authored-by: Matthew Bonanni <mbonanni001@gmail.com>
Co-authored-by: Matthew Bonanni <mbonanni@redhat.com>

402759d4

[CPU] Refactor CPU unquantized linear (#24150) · 57b1ce94
Li, Jiang authored Sep 04, 2025
```
Signed-off-by: jiang1.li <jiang1.li@intel.com>
```
57b1ce94

03 Sep, 2025 4 commits
- [Attention] Blackwell FP8 MLA support with CUTLASS_MLA backend (#23289) · a7423220
  Matthew Bonanni authored Sep 03, 2025
```
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
```
  a7423220
- [Kernels] Overlap shared experts with send/recv (#23273) · e9b92dcd
  bnellnm authored Sep 03, 2025
```
Signed-off-by: Bill Nell <bnell@redhat.com>
```
  e9b92dcd
- [Doc]: fix typos in Python comments (#24093) · d7e1e599
  Didier Durand authored Sep 03, 2025
```
Signed-off-by: Didier Durand <durand.didier@gmail.com>
```
  d7e1e599
- fix some typos (#24071) · 1bd007f2
  co63oc authored Sep 03, 2025
```
Signed-off-by: co63oc <co63oc@users.noreply.github.com>
```
  1bd007f2
02 Sep, 2025 2 commits
- [CI Failure] Skip failing nvfp4 silu test (#23959) · e66ed3e6
  Michael Goin authored Sep 02, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
```
  e66ed3e6
- [Doc]: fix typos in Python comments (#24077) · fad73be1
  Didier Durand authored Sep 02, 2025
```
Signed-off-by: Didier Durand <durand.didier@gmail.com>
```
  fad73be1
28 Aug, 2025 2 commits

[NVIDIA] Support SiluMul + NVFP4 quant fusion (#23671) · 16a45b3a

elvischenv authored Aug 29, 2025


Signed-off-by: jindih <jindih@nvidia.com>
Signed-off-by: elvischenv <219235043+elvischenv@users.noreply.github.com>
Co-authored-by: jindih <jindih@nvidia.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Luka Govedic <lgovedic@redhat.com>

16a45b3a

[Kernel] cuda kernels for upcoming decode context parallel feature (#23791) · 186aced5
yzds authored Aug 28, 2025
```
Co-authored-by: hongchao <hongchao@msh.team>
```
186aced5

27 Aug, 2025 1 commit

[Feature] Add Hopper DeepGEMM E8M0 for DeepSeekV3.1 scale_fmt (#23666) · 3af47c3c

Wentao Ye authored Aug 27, 2025


Signed-off-by: yewentao256 <zhyanwentao@126.com>
Signed-off-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>

3af47c3c

26 Aug, 2025 3 commits
- [Misc] Fix comments in `tests/kernels/quantization` (#23675) · c37c0af9
  Jiangyun Zhu authored Aug 27, 2025
```
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
```
  c37c0af9
- [Kernel] Added flashinfer fp8 per-tensor gemms (#22895) · f66673a3
  nvjullin authored Aug 26, 2025
```
Signed-off-by: Julien Lin <jullin@nvidia.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
```
  f66673a3
- [CI Fix] Pin deepep and pplx tags in tools/ep_kernels/, gate multigpu tests (#23568) · 906e461e
  Michael Goin authored Aug 25, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  906e461e
25 Aug, 2025 2 commits
- [Kernel] Add fused grouped_topk kernel for MoE (#23274) · 8a3cd90a
  Xin Yang authored Aug 25, 2025
```
Signed-off-by: Xin Yang <xyangx@amazon.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
```
  8a3cd90a
- Updates to Flex + VLLm integration (#21416) · e0329ed4
  Driss Guessous authored Aug 25, 2025
```
Signed-off-by: drisspg <drisspguessous@gmail.com>
```
  e0329ed4
24 Aug, 2025 1 commit
- [kernel] Support W4A8 on Hopper (#23198) · e76e2335
  czhu-cohere authored Aug 24, 2025
```
Signed-off-by: czhu-cohere <conway.zhu@cohere.com>
```
  e76e2335
22 Aug, 2025 3 commits

[NVIDIA][torch.compile] Support Flashinfer TRTLLM FP8-q/kv NVFP4-out Attention Kernel (#22703) · 24d0c9e6

elvischenv authored Aug 23, 2025


Signed-off-by: elvischenv <219235043+elvischenv@users.noreply.github.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>

24d0c9e6

fix(tests): Ensure reliable CUDA cache clearing in MoE test (#23416) · 341923b9

Aziz authored Aug 22, 2025

Signed-off-by: AzizCode92 <azizbenothman76@gmail.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

341923b9

[Kernel] Add FP8 support with FlashMLA backend (#22668) · 19fe1a05
Matthew Bonanni authored Aug 21, 2025
```
Signed-off-by: Matthew Bonanni <mbonanni001@gmail.com>
```
19fe1a05

21 Aug, 2025 4 commits
- [Perf] Small optimizations for silu_mul_fp8_quant_deep_gemm (#23265) · 3bbe11cc
  Michael Goin authored Aug 21, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  3bbe11cc
- [Core] Always use tensor cores for Flashinfer Decode Wrapper (#23214) · 1d353b63
  Pavani Majety authored Aug 21, 2025
```
Signed-off-by: Pavani Majety <pmajety@nvidia.com>
```
  1d353b63
- add tg-mxfp4-moe-test (#22540) · f8ce0229
  Lain authored Aug 21, 2025
```
Signed-off-by: siyuanf <siyuanf@nvidia.com>
Signed-off-by: Siyuan Fu <siyuanf@nvidia.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
```
  f8ce0229
- [CPU] Refactor CPU W8A8 scaled_mm (#23071) · 7be5d113
  Li, Jiang authored Aug 21, 2025
```
Signed-off-by: jiang1.li <jiang1.li@intel.com>
```
  7be5d113
20 Aug, 2025 1 commit
- [Kernel/Quant] Remove the original marlin format and qqq (#23204) · 0cdbf5e6
  Michael Goin authored Aug 20, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  0cdbf5e6