Commits · 171133f929f2e896af767ca6e6402990a5c2814e · OpenDAS / vllm_cscc

08 Nov, 2025 2 commits

[Bugfix] Fix test fused quant layernorm tests (#27865) · 171133f9

ElizaWszola authored Nov 08, 2025


Signed-off-by: ElizaWszola <ewszola@redhat.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Co-authored-by: yewentao256 <zhyanwentao@126.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>

171133f9

[Perf][DeepSeek] Add sigmoid+bias fusion to fused_grouped_topk from TRTLLM (#28124) · 08525276

Michael Goin authored Nov 08, 2025

Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>

08525276

07 Nov, 2025 1 commit
- [Bugfix] Use latency MOE backend as default for Flashinfer and other misc fixes (#27439) · 72b1c2ae
  Pavani Majety authored Nov 07, 2025
```
Signed-off-by: Pavani Majety <pmajety@nvidia.com>
```
  72b1c2ae
06 Nov, 2025 1 commit
- [Bugfix][Kernel] fix merge attn states when both prefix and suffix are empty (#28181) · 981cadb3
  courage17340 authored Nov 06, 2025
```
Signed-off-by: courage17340 <courage17340@163.com>
```
  981cadb3
04 Nov, 2025 2 commits

[Perf] SM100 - add swap AB optimization to CUTLASS FP8 GEMM (#27284) · 97e3dda8

lyrisz authored Nov 04, 2025


Signed-off-by: Faqin Zhong <faqin.zhong@gmail.com>
Co-authored-by: Faqin Zhong <zhofaqin@amazon.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>

97e3dda8

[CPU]Improve dynamic 4bit moe performance (#27240) · f32cbc9a
xiangze-arm authored Nov 04, 2025
```
Signed-off-by: Zhang Xiangze <Xiangze.Zhang@arm.com>
```
f32cbc9a

03 Nov, 2025 1 commit

Early exit for MoE LoRA kernels (#27131) · 294c805f

gnovack authored Nov 03, 2025


Signed-off-by: gnovack <gnovack@amazon.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>

294c805f

02 Nov, 2025 1 commit
- [V1] [Hybrid] Mamba1 Automatic Prefix Caching (#26377) · 00b31a36
  Asaf Joseph Gardin authored Nov 02, 2025
```
Signed-off-by: asafg <39553475+Josephasafg@users.noreply.github.com>
```
  00b31a36
24 Oct, 2025 2 commits
- [cpu][fix] Fix onednn_mm crash on consecutive matmuls with same M,K,N and different dtype (#27472) · 2080b050
  Fadi Arafeh authored Oct 24, 2025
```
Signed-off-by: Fadi Arafeh <fadi.arafeh@arm.com>
```
  2080b050
- [Kernel] Add GPTQv2 format support for low-bit or asymmetric quantization, by... · 5cc6bddb
  Xiangyu Li authored Oct 24, 2025
```
[Kernel] Add GPTQv2 format support for low-bit or asymmetric quantization, by adapting gptq_gemm (#26092)
```
  5cc6bddb
22 Oct, 2025 1 commit
- Bugfix - pass 'max_num_tokens_padded' into 'moe_lora_align_block_size' (#27311) · 8e4ca4d1
  gnovack authored Oct 22, 2025
```
Signed-off-by: gnovack <gnovack@amazon.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
```
  8e4ca4d1
21 Oct, 2025 3 commits

[Deepseek v3.2] Remove extra logics in indexer (#26465) · 09a7e6f6

Lain authored Oct 21, 2025


Signed-off-by: Siyuan Fu <siyuanf@nvidia.com>
Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com>
Signed-off-by: Lain <siyuanf@nvidia.com>
Co-authored-by: Daniel Campora <961215+dcampora@users.noreply.github.com>

09a7e6f6

[Deepseek v3.2] Optimize top_k_per_row (#26763) · 80e94529
Daniel Cámpora authored Oct 21, 2025
```
Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com>
```
80e94529

[Feature][Kernel]FusedMoE LoRA (#21229) · 5f6cbf60

Chen Wu authored Oct 21, 2025


Signed-off-by: wuchen <cntryroa@gmail.com>
Signed-off-by: banjuede <lmklhc@163.com>
Signed-off-by: Chen Wu <cntryroa@gmail.com>
Signed-off-by: Danielle Robinson <dmmaddix@amazon.com>
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
Signed-off-by: bk-201 <joy25810@foxmail.com>
Co-authored-by: wuchen <wuchen@zetyun.com>
Co-authored-by: Nathan Van Gheem <vangheem@gmail.com>
Co-authored-by: banjuede <lmklhc@163.com>
Co-authored-by: Danielle Robinson <dmmaddix@amazon.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
Co-authored-by: bk-201 <joy25810@foxmail.com>

5f6cbf60

17 Oct, 2025 4 commits

[Chore] Remove unused `PolyNorm` layer (#27110) · 3125d799
Isotr0py authored Oct 18, 2025
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
3125d799

[ROCm][Bugfix][Model] Fix illegal memory access when running qwen3_moe models... · b10c64c8

rasmith authored Oct 17, 2025


[ROCm][Bugfix][Model] Fix illegal memory access when running qwen3_moe models with  rms_norm (Qwen3-235B-A22B,  Qwen3-30B-A3B, etc.) (#26192)
Signed-off-by: Randall Smith <ransmith@amd.com>
Signed-off-by: Randall Smith <Randall.Smith@amd.com>
Signed-off-by: rasmith <Randall.Smith@amd.com>
Co-authored-by: Randall Smith <ransmith@amd.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>

b10c64c8

[torch.compile] Enable attention and allreduce fusion without custom ops enabled (#24604) · bd7157a0
Luka Govedič authored Oct 17, 2025
```
Signed-off-by: Luka Govedič <lgovedic@redhat.com>
Signed-off-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
```
bd7157a0
[Kernel][Performance] Fuse float cast and renormalize to topk softmax kernel (#26717) · 75c7ad99
zhrrr authored Oct 17, 2025
```
Signed-off-by: zhuhaoran <zhuhaoran.zhr@alibaba-inc.com>
Signed-off-by: izhuhaoran <izhuhaoran@qq.com>
```
75c7ad99

16 Oct, 2025 3 commits
- [small][batch invariance] Rename the env and internal flags to simplify usage (#26855) · b2f78cba
  Bram Wasti authored Oct 16, 2025
```
Signed-off-by: Bram Wasti <bwasti@meta.com>
```
  b2f78cba
- [GPTOSS][DP/EP][Marlin] Enable GPTOSS Batched DP/EP using Marlin kernels (#25997) · fb0571b0
  Varun Sundar Rabindranath authored Oct 16, 2025
```
Signed-off-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
Co-authored-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
```
  fb0571b0
- [Attention] Tune CUTLASS MLA num_splits (#26846) · 314fa8ab
  Matthew Bonanni authored Oct 16, 2025
```
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
```
  314fa8ab
15 Oct, 2025 1 commit

Vectorize RMS norm variance using vectorize_read_with_alignment (#26234) · 1f491aa0

Benji Beck authored Oct 15, 2025


Signed-off-by: Benji Beck <benjibeck@meta.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>

1f491aa0

13 Oct, 2025 2 commits

[Bugfix][Rocm] fix qr error when different inp shape (#25892) · 134f70b3

haoyangli-amd authored Oct 14, 2025


Signed-off-by: Haoyang Li <lihaoyang0109@gmail.com>
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
Co-authored-by: ilmarkov <markovilya197@gmail.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>

134f70b3

[unrevert] Add batch invariant kernel override for FlashInfer backend [2/n] (#26373) · 32637990
Bram Wasti authored Oct 13, 2025
```
Signed-off-by: Bram Wasti <bwasti@meta.com>
Signed-off-by: Bram Wasti <bwasti@fb.com>
```
32637990

12 Oct, 2025 1 commit
- Update `Optional[x]` -> `x | None` and `Union[x, y]` to `x | y` (#26633) · 8fcaaf6a
  Harry Mellor authored Oct 12, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  8fcaaf6a
10 Oct, 2025 2 commits

Cache the environment variable check for batch invariance (#26510) · e317414c
Bram Wasti authored Oct 10, 2025
```
Signed-off-by: Bram Wasti <bwasti@meta.com>
```
e317414c

Silu v2 (#25074) · 7b03584d

Elvir Crnčević authored Oct 10, 2025


Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: elvircrn <elvircrn@gmail.com>
Signed-off-by: Elvir Crnčević <elvircrn@gmail.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Varun Sundar Rabindranath <varunsundar08@gmail.com>

7b03584d

08 Oct, 2025 2 commits

[Refactor] Refactor FP8 & INT8 Quant Folder inside `w8a8` (#25293) · 241b4cfe

Wentao Ye authored Oct 08, 2025


Signed-off-by: nicole-lihui <nicole.li@daocloud.io>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Signed-off-by: courage17340 <courage17340@163.com>
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Signed-off-by: Jacob Kahn <jacobkahn1@gmail.com>
Signed-off-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
Signed-off-by: Fadi Arafeh <fadi.arafeh@arm.com>
Signed-off-by: Roger Wang <hey@rogerw.io>
Signed-off-by: Agata Dobrzyniewicz <adobrzyniewicz@habana.ai>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Signed-off-by: zxw <1020938856@qq.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Signed-off-by: wang.yuqi <noooop@126.com>
Signed-off-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
Signed-off-by: chenlang <chen.lang5@zte.com.cn>
Signed-off-by: youkaichao <youkaichao@gmail.com>
Signed-off-by: Jonas Kuebler <kuebj@amazon.com>
Signed-off-by: jiang1.li <jiang1...

241b4cfe

Add gather_indexer_k_quant_cache kernel (#25931) · 127c8b78

Barry Kang authored Oct 08, 2025


Signed-off-by: Barry Kang <43644113+Barry-Delaney@users.noreply.github.com>
Signed-off-by: Simon Mo <simon.mo@hey.com>
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
Co-authored-by: Simon Mo <simon.mo@hey.com>
Co-authored-by: Yongye Zhu <zyy1102000@gmail.com>
Co-authored-by: Chen Zhang <zhangch99@outlook.com>

127c8b78

07 Oct, 2025 1 commit

Add topk logits torch op for DS3.2. (#25945) · e1098ced

Daniel Cámpora authored Oct 07, 2025

Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com>
Signed-off-by: Daniel Cámpora <961215+dcampora@users.noreply.github.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>

e1098ced

06 Oct, 2025 1 commit
- Fix per file ruff ignores related to line length (#26262) · 6c046382
  Harry Mellor authored Oct 06, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  6c046382
05 Oct, 2025 2 commits
- Remove all references to `yapf` as it's no longer used (#26251) · 4e256cad
  Harry Mellor authored Oct 05, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  4e256cad
- Convert formatting to use `ruff` instead of `yapf` + `isort` (#26247) · d6953beb
  Harry Mellor authored Oct 05, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  d6953beb
04 Oct, 2025 1 commit

[cpu][perf] Accelerate unquantized-linear for AArch64 through oneDNN/ACL and... · 9705fba7

Fadi Arafeh authored Oct 04, 2025


[cpu][perf] Accelerate unquantized-linear for AArch64 through oneDNN/ACL and weight prepack (#25948)
Signed-off-by: Fadi Arafeh <fadi.arafeh@arm.com>
Co-authored-by: Li, Jiang <jiang1.li@intel.com>

9705fba7

03 Oct, 2025 5 commits
- Avoid division by zero in cache DS MLA kernel (#26174) · 300a59c4
  Matthew Bonanni authored Oct 03, 2025
```
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
```
  300a59c4
- Fix undefined symbol: cutlass_moe_mm_sm100 (#26098) · 4f8f47e8
  Jun Jiang authored Oct 03, 2025
```
Signed-off-by: Jun Jiang <jasl9187@hotmail.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
```
  4f8f47e8
- [Perf] Optimize `reshape_and_cache` CUDA Kernel (#25955) · eb0fa438
  Jiangyun Zhu authored Oct 03, 2025
```
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
Co-authored-by: Liu-congo <1502632128@qq.com>
```
  eb0fa438
- [DeepSeek] Improve performance of DS MLA cache kernel (#26132) · 47b93395
  Matthew Bonanni authored Oct 02, 2025
```
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
```
  47b93395
- [CI/Build] Conditionally register cutlass_fp4_group_mm to fix building on Hopper (#26138) · 5d5146ee
  Michael Goin authored Oct 02, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  5d5146ee
01 Oct, 2025 1 commit
- [ROCm][Build] Add support for AMD Ryzen AI MAX / AI 300 Series (#25908) · aac622e0
  Hosang authored Oct 01, 2025
```
Signed-off-by: Hosang Yoon <hosang.yoon@amd.com>
```
  aac622e0