Commits · 2e693f48e7bd6fa621c8ce2c753ae76360793a04 · OpenDAS / vllm_cscc

12 Mar, 2026 4 commits

[Perf] Add TRTLLM FP8 MoE Modular Kernel (#36307) · 2e693f48

Wei Zhao authored Mar 12, 2026


Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>

2e693f48

[Perf] add packed recurrent fast path for decode (#36596) · 9e19f833
caozuoba authored Mar 12, 2026
```
Signed-off-by: hdj <1293066020@qq.com>
Co-authored-by: Roger Wang <hey@rogerw.io>
```
9e19f833

[MM][OOT] Support CPU `seq_lens` for OOT MMEncoderAttention kernels (#36605) · f0d3658c

Shanshan Shen authored Mar 12, 2026


Signed-off-by: shen-shanshan <467638484@qq.com>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>

f0d3658c

[Kernel][Helion][13/N] Force static_shapes=False in helion register (#36677) · 584a3f56
Yanan Cao authored Mar 11, 2026
```
Signed-off-by: Yanan Cao <gmagogsfm@gmail.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
```
584a3f56

11 Mar, 2026 4 commits

[Kernel] [Helion] [15/N] Split config files into per-platform files (#36698) · cf632499
Yanan Cao authored Mar 11, 2026
```
Signed-off-by: Yanan Cao <gmagogsfm@gmail.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
```
cf632499

[torch.compile] Add support for non-contiguous fused RMSNorm + group quant (#36551) · 9556af87

Luka Govedič authored Mar 11, 2026

Signed-off-by: Luka Govedič <lgovedic@redhat.com>
Signed-off-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Co-authored-by: Copilot <198982749+Copilot@users.noreply.github.com>
Co-authored-by: ProExpertProg <11367180+ProExpertProg@users.noreply.github.com>

9556af87

Add 320 dimension size support to MLA (#36161) · a5d06dc5
Julien Denize authored Mar 11, 2026
```
Signed-off-by: Julien Denize <julien.denize@mistral.ai>
```
a5d06dc5
Add XPU MLA Sparse backend for DeepSeek v3.2 (#33230) · e584dce5
Wuxun Zhang authored Mar 11, 2026
```
Signed-off-by: Zhang, Wuxun <wuxun.zhang@intel.com>
```
e584dce5

10 Mar, 2026 1 commit
- Improvements to wvSplitKrc skinny GEMM solution (#34304) · 721ae79f
  Hashem Hashemi authored Mar 10, 2026
```
Signed-off-by: Hashem Hashemi <hashem.hashemi@amd.com>
```
  721ae79f
09 Mar, 2026 5 commits
- [Attention][Perf][Kernel] Replace torch.cat with vectorized CUDA kernel MLA... · 580864d8
  Roberto L. Castro authored Mar 09, 2026
```
[Attention][Perf][Kernel] Replace torch.cat with vectorized CUDA kernel MLA query concat - DeepSeek-V3.2 (#34917)
Signed-off-by: LopezCastroRoberto <rocastro@redhat.com>
Signed-off-by: Roberto L. Castro <38211239+LopezCastroRoberto@users.noreply.github.com>
```
  580864d8
- [Attention][Perf] Optimize cp_gather_and_upconvert_fp8_kv_cache - DeepSeek-v3.2 (#35290) · 2b28b9b2
  Roberto L. Castro authored Mar 09, 2026
```
Signed-off-by: LopezCastroRoberto <rocastro@redhat.com>
Co-authored-by: Claude <noreply@anthropic.com>
```
  2b28b9b2
- Reapply [Attention] Refactor `check_and_update_config` (#35122) · 77a73458
  Matthew Bonanni authored Mar 09, 2026
```
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
```
  77a73458
- [MM Encoder] Default to use TORCH_SDPA backend for ViT on Volta/Turing GPU (#36472) · b0906d8b
  Isotr0py authored Mar 09, 2026
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  b0906d8b
- [Kernel] Add fused_sigmoid_gating_delta_rule_update kernel for Qwen3 Next (#35777) · dc6b5784
  Xin Yang authored Mar 08, 2026
```
Signed-off-by: Xin Yang <xyangx@amazon.com>
```
  dc6b5784
08 Mar, 2026 1 commit
- Add support for ModelOpt MXFP8 MoE models (#35986) · 0a6a3a12
  danisereb authored Mar 08, 2026
```
Signed-off-by: Daniel Serebrenik <daserebrenik@nvidia.com>
```
  0a6a3a12
06 Mar, 2026 2 commits

Enabling some B200-specific tests on MI355 (#35253) · 225d1090

Alexei-V-Ivanov-AMD authored Mar 06, 2026


Signed-off-by: Alexei V. Ivanov <alexei.ivanov@amd.com>
Signed-off-by: Alexei-V-Ivanov-AMD <156011006+Alexei-V-Ivanov-AMD@users.noreply.github.com>

225d1090

[CustomOp] CustomOp FusedRMSNormGated (#35877) · f3c6c9c9

eellison authored Mar 06, 2026


Signed-off-by: Elias Ellison <elias.ellison@gmail.com>
Signed-off-by: eellison <elias.ellison@gmail.com>

f3c6c9c9

05 Mar, 2026 3 commits
- [Bugfix][CI] fix typos (#34934) · 6a895197
  Jiayi Yan authored Mar 06, 2026
```
Signed-off-by: 1195343015 <1195343015@qq.com>
Signed-off-by: Jiayi Yan <66017932+1195343015@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  6a895197
- [ROCm] Refactor ROCm attention backend selection logic (#35246) · 8c760b6a
  Sage Moore authored Mar 05, 2026
```
Signed-off-by: Sage Moore <sage@neuralmagic.com>
```
  8c760b6a
- [Hardware] Replace `torch.cuda.synchronize()` api with `torch.accelerator.synchronize` (#36085) · 66a22096
  Kunshang Ji authored Mar 05, 2026
```
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
```
  66a22096
04 Mar, 2026 3 commits
- [CI] Bump `mypy` version (#34950) · 17dc9c7f
  Harry Mellor authored Mar 04, 2026
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  17dc9c7f
- [Misc] Add `--attention-backend auto` option (#35738) · 18e01a0a
  Nicolò Lucchesi authored Mar 04, 2026
```
Signed-off-by: NickLucche <nlucches@redhat.com>
```
  18e01a0a
- [Hardware] Replace `torch.cuda.empty_cache` with `torch.accelerator.empty_cache` (#30681) · 16d2ad1d
  Kunshang Ji authored Mar 04, 2026
```
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
Signed-off-by: Kunshang Ji <jikunshang95@gmail.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  16d2ad1d
03 Mar, 2026 2 commits

[MoE Refactor] Create MK for TRTLLM Kernels (#32564) · 97995f63

Robert Shaw authored Mar 03, 2026


Signed-off-by: Robert Shaw <robshaw@redhat.com>
Signed-off-by: Robert Shaw <rshaw@neuralmagic.com>
Signed-off-by: Robert Shaw <robertgshaw2@gmail.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: Robert Shaw <rshaw@neuralmagic.com>

97995f63

TRTLLM gen-full attn Test Coverage (#34986) · e05cb3b9

ojhaanshika authored Mar 03, 2026


Signed-off-by: Anshika Ojha <anshikao@nvidia.com>
Co-authored-by: Anshika Ojha <anshikao@gb-nvl-059-compute09.nvidia.com>

e05cb3b9

02 Mar, 2026 2 commits
- [Core] Move test utility to test file (#35672) · 4034c3d3
  Turner Jabbour authored Mar 02, 2026
```
Signed-off-by: Turner Jabbour <doubleujabbour@gmail.com>
```
  4034c3d3
- [Kernel] Integrate SM100 MXFP8 blockscaled grouped MM and quant kernels (#34448) · cb21972a
  EdalatiAli authored Mar 02, 2026
```
Signed-off-by: EdalatiAli <aliedalati@cohere.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
```
  cb21972a
01 Mar, 2026 2 commits
- [Bugfix] Fix dtype mismatch in RMSNormGated.forward_native() during torch.compile (#35256) · 62904708
  haosdent authored Mar 02, 2026
```
Signed-off-by: haosdent <haosdent@gmail.com>
```
  62904708
- [Mamba1] - Kernel Level Chunk Alignment for Prefix Caching (#34798) · bbf81f9a
  Asaf Gardin authored Mar 01, 2026
```
Signed-off-by: Josephasafg <ajgard7@gmail.com>
```
  bbf81f9a
28 Feb, 2026 2 commits

Add padding support to wvSplitK solution for skinny GEMMs (#33762) · 7600642e
Hashem Hashemi authored Feb 28, 2026
```
Signed-off-by: Hashem Hashemi <hashem.hashemi@amd.com>
```
7600642e

[1/N] Elastic EP Milestone 2 (#34861) · dea26833

Itay Alroy authored Feb 28, 2026


Signed-off-by: Yongji Wu <wuyongji317@gmail.com>
Signed-off-by: Itay Alroy <ialroy@nvidia.com>
Signed-off-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
Signed-off-by: Ron Tourgeman <rtourgeman@nvidia.com>
Co-authored-by: Yongji Wu <wuyongji317@gmail.com>
Co-authored-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
Co-authored-by: Ron Tourgeman <rtourgeman@nvidia.com>

dea26833

27 Feb, 2026 4 commits
- [Kernel] [Helion] [7/N] Use HOP to represent Helion Kernel call to enable fx... · 9098ce69
  Yanan Cao authored Feb 27, 2026
```
[Kernel] [Helion] [7/N] Use HOP to represent Helion Kernel call to enable fx tracing and pattern matching (#34390)
Signed-off-by: Yanan Cao <gmagogsfm@gmail.com>
```
  9098ce69
- Flashinfer cuDNN backend for Qwen3 VL ViT attention (#34580) · 9c3fe993
  Max Hu authored Feb 27, 2026
```
Signed-off-by: Max Hu <maxhu@nvidia.com>
Signed-off-by: Max Hu <hyoung2991@gmail.com>
Co-authored-by: Max Hu <maxhu@nvidia.com>
Co-authored-by: Shang Wang <shangw@nvidia.com>
```
  9c3fe993
- [CI] Actually run tests/kernels/quantization/test_block_fp8.py in CI (#34274) · 4fec53cf
  Michael Goin authored Feb 26, 2026
  
  4fec53cf
- [Update] Use FlashInfer fast_decode_plan directly instead of replication (#34687) · 56a63717
  Andrii Skliar authored Feb 27, 2026
```
Signed-off-by: Andrii <askliar@nvidia.com>
Co-authored-by: Andrii <askliar@nvidia.com>
```
  56a63717
26 Feb, 2026 1 commit

[WideEP] Remove pplx all2all backend (#33724) · eb19955c

Tyler Michael Smith authored Feb 26, 2026


Signed-off-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>

eb19955c

25 Feb, 2026 3 commits
- fix(mxfp4): Disable monolithic path for TRITON backend with EP (#34270) · c97234c0
  Elizabeth Thomas authored Feb 25, 2026
```
Signed-off-by: Elizabeth Thomas <email2eliza@gmail.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
```
  c97234c0
- [Platform] Add current_platform.num_compute_units interface (#35042) · 8ad54a99
  Kunshang Ji authored Feb 25, 2026
```
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
Signed-off-by: Kunshang Ji <jikunshang95@gmail.com>
```
  8ad54a99
- [Bugfix] Fix expert_ids padding values in moe_align_block_size kernel (#35161) · 3bbb2046
  Xin Yang authored Feb 24, 2026
```
Signed-off-by: Xin Yang <xyangx@amazon.com>
```
  3bbb2046
24 Feb, 2026 1 commit

[Attn,KV-cache] Use per-head scales in the attention selector (#34281) · a87cc508

Eldar Kurtić authored Feb 24, 2026


Signed-off-by: Your Name <you@example.com>
Signed-off-by: Eldar Kurtic <research@neuralmagic.com>
Co-authored-by: Eldar Kurtic <research@neuralmagic.com>
Co-authored-by: Your Name <you@example.com>

a87cc508