Commits · 3aaa94ac99f4b295ba95f14b4968620b2127044f · OpenDAS / vllm_cscc

19 Nov, 2025 6 commits

[Performance] Reduce DeepGEMM N dim restriction from 128 to 64 multiplier (#28687) · 3aaa94ac

Alexander Matveev authored Nov 19, 2025


Signed-off-by: Alexander Matveev <amatveev@redhat.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: mgoin <mgoin64@gmail.com>

3aaa94ac

[MoE] Nvfp4 Masked Gemm: Add flashinfer grouped_gemm_nt_masked (#25990) · 613abb50

Shu Wang authored Nov 19, 2025


Signed-off-by: Shu Wang. <shuw@nvidia.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>

613abb50

[CI/Build] Fix test_prefix_prefill for AMD (#28905) · 68d72319
Ryan Rock authored Nov 19, 2025
```
Signed-off-by: Ryan Rock <ryan.rock@amd.com>
```
68d72319

[Feature] Prefill Context Parallel (PCP) basic support (#28718) · 2fd893b4

Qiu authored Nov 20, 2025


Signed-off-by: QiuChunshuo <qiuchunshuo@huawei.com>
Signed-off-by: FENP <yuanyongjie.yyj@antgroup.com>
Signed-off-by: LookAround <lixushi@huawei.com>
Signed-off-by: Jingchun Gao <gaojingchun1@huawei.com>
Signed-off-by: zhenwenqi2024 <zhenwenqi_2022@qq.com>
Co-authored-by: FENP <yuanyongjie.yyj@antgroup.com>
Co-authored-by: LookAround <lixushi@huawei.com>
Co-authored-by: Jingchun Gao <gaojingchun1@huawei.com>
Co-authored-by: zhenwenqi2024 <zhenwenqi_2022@qq.com>
Co-authored-by: Jingchun Gao <63247409+gjc0824@users.noreply.github.com>

2fd893b4

Update `rope_scaling` to `rope_parameters` in preparation for Transformers v5 (#28542) · a8b70304
Harry Mellor authored Nov 19, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
a8b70304
[Attention] FlashAttention ViT support, make default backend (#28763) · 4c23690f
Matthew Bonanni authored Nov 18, 2025
```
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
```
4c23690f

18 Nov, 2025 1 commit
- Replace `torch.cuda.Event` with `torch.Event` for better hardware compatibility (#26985) · 2a2d5d27
  Kunshang Ji authored Nov 19, 2025
```
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
```
  2a2d5d27
16 Nov, 2025 1 commit
- Feature: Support Relu2 in FusedMoE fp8 cutlass path (#27261) · 03ee4811
  amirkl94 authored Nov 16, 2025
  
  03ee4811
15 Nov, 2025 2 commits
- [Misc] Make `SchedulerConfig.max_model_len` init-only (#28733) · 638e4196
  Cyrus Leung authored Nov 15, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  638e4196
- [Performance][DeepGEMM] Estimate expected_m (#28694) · 6965ef43
  Varun Sundar Rabindranath authored Nov 15, 2025
```
Signed-off-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
Co-authored-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
```
  6965ef43
14 Nov, 2025 1 commit
- [BugFix] Fix FA3 IMA with FULL_AND_PIECEWISE and cascade attention (default) (#28702) · db56a599
  Lucas Wilkinson authored Nov 14, 2025
  
  db56a599
13 Nov, 2025 2 commits
- [Performance][B200] silu_mul_quant: pack scales in int32 (#28358) · fe1cd770
  Varun Sundar Rabindranath authored Nov 13, 2025
```
Signed-off-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
Co-authored-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
```
  fe1cd770
- [platform] Move get_cu_count to utils (#27005) · 2dacd573
  wangxiyuan authored Nov 13, 2025
```
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
```
  2dacd573
12 Nov, 2025 3 commits
- [ROCm] [Bugfix] Fix `fused_qknorm_rope_kernel` rocm compatibility (#28500) · edb59a94
  TJian authored Nov 12, 2025
```
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
```
  edb59a94
- `VLLM_USE_TRITON_FLASH_ATTN` V0 variable deprecation (#27611) · 9f0247cf
  Andreas Karatzas authored Nov 11, 2025
```
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
Signed-off-by: Andreas Karatzas <Andreas.Karatzas@amd.com>
```
  9f0247cf
- [CPU] Refactor CPU attention backend (#27954) · 7f829be7
  Li, Jiang authored Nov 12, 2025
```
Signed-off-by: jiang1.li <jiang1.li@intel.com>
```
  7f829be7
11 Nov, 2025 4 commits
- [CI/Build] Refactor Attention backend for test_prefix_prefill from xformers to SDPA (#28424) · e5534249
  Zhewen Li authored Nov 11, 2025
```
Signed-off-by: zhewenli <zhewenli@meta.com>
Signed-off-by: Roger Wang <hey@rogerw.io>
Co-authored-by: Roger Wang <hey@rogerw.io>
```
  e5534249
- [Kernel][Perf] fuse QK Norm and RoPE into one cuda kernel for Qwen Model (#27165) · 68c09efc
  zhrrr authored Nov 12, 2025
```
Signed-off-by: zhuhaoran <zhuhaoran.zhr@alibaba-inc.com>
```
  68c09efc
- [Kernels] Split up fused_moe/layer.py, isolate more modular kernel code (#28064) · a1448b4b
  bnellnm authored Nov 11, 2025
  
  a1448b4b
- [Attention] Refactor CUDA attention backend selection logic (#24794) · b30dfa03
  Matthew Bonanni authored Nov 11, 2025
```
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Signed-off-by: Matthew Bonanni <mbonanni001@gmail.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
```
  b30dfa03
10 Nov, 2025 4 commits

[Test] Remove old non-varlen FA2 test (#28420) · 0bf29fad
Matthew Bonanni authored Nov 10, 2025
```
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
```
0bf29fad

[Bugfix] Fix persistent_masked_m_silu_mul_quant tests (#28366) · b039bfda

Varun Sundar Rabindranath authored Nov 10, 2025


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

b039bfda

[RFC][ROCm][AITER] Keep all AITER kernels in `_aiter_ops` class like... · f080a835

vllmellm authored Nov 10, 2025


[RFC][ROCm][AITER] Keep all AITER kernels in `_aiter_ops` class like `_custom_ops` and `_ipex_ops` (#24490)
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>

f080a835

[V0 deprecation] Remove no longer used `get_metadata_cls` (#28370) · e8697faf
Lucas Wilkinson authored Nov 10, 2025
```
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
```
e8697faf

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

Update Flashinfer from `v0.4.1` to `v0.5.2` (#27952) · 811df41e
Harry Mellor authored Nov 07, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
811df41e

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
05 Nov, 2025 2 commits

[ROCm][MLA] Support block-size > 1 for AITER MLA backend (#27224) · 6cae1e53
Pleaplusone authored Nov 05, 2025
```
Signed-off-by: ganyi <ygan@amd.com>
Co-authored-by: wuhuikx <hattie.wu@amd.com>
```
6cae1e53

Bugfix: Cutlass FP8 FusedMoE bad scaling factors (#27255) · 6b7a8118

amirkl94 authored Nov 05, 2025


Signed-off-by: Amir Klein <203507526+amirkl94@users.noreply.github.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>

6b7a8118

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
30 Oct, 2025 1 commit

kernels/moe test pruning (#27053) · b8c48c5d

Fardin Hoque authored Oct 29, 2025


Signed-off-by: Fardin Hoque <kfhfar@amazon.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>

b8c48c5d

29 Oct, 2025 1 commit
- [Bugfix] Fix modular kernel tests (#27707) · 1891cf60
  bnellnm authored Oct 29, 2025
```
Signed-off-by: Bill Nell <bnell@redhat.com>
```
  1891cf60
26 Oct, 2025 1 commit

[Chore]:Extract math and argparse utilities to separate modules (#27188) · 71b1c8b6

Yeshwanth N authored Oct 26, 2025


Signed-off-by: Yeshwanth Surya <yeshsurya@gmail.com>
Signed-off-by: Yeshwanth N <yeshsurya@gmail.com>
Signed-off-by: yeshsurya <yeshsurya@gmail.com>

71b1c8b6

24 Oct, 2025 1 commit
- [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
23 Oct, 2025 2 commits
- [Chore] Separate out `vllm.utils.platform_utils.py` (#27374) · ca76486a
  Jonathan Chen authored Oct 23, 2025
```
Signed-off-by: Jonathan <chenleejonathan@gmail.com>
```
  ca76486a
- [Misc] Add triton_kernels dependency (#27370) · a9f55dc5
  Varun Sundar Rabindranath authored Oct 23, 2025
```
Signed-off-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
Co-authored-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
```
  a9f55dc5
22 Oct, 2025 2 commits

[Chore] Separate out system utilities from vllm.utils (#27201) · a0003b56
dongbo910220 authored Oct 23, 2025
```
Signed-off-by: dongbo910220 <1275604947@qq.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
```
a0003b56

[Chore] Separate out optional dependency checks from vllm.utils (#27207) · 3ae082c3

dongbo910220 authored Oct 22, 2025

Signed-off-by: dongbo910220 <1275604947@qq.com>
Signed-off-by: dongbo910220 <32610838+dongbo910220@users.noreply.github.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>

3ae082c3

21 Oct, 2025 2 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