Commits · ab4be40fc5bde2dbe76e3fb081dc3721219b5a2b · OpenDAS / vllm_cscc

"vscode:/vscode.git/clone" did not exist on "a69efbd168332c99c70c0d6ed139152ce2697019"

18 Oct, 2025 3 commits
- [Feature] Batch Invariant: Support DeepGEMM and Blackwell (#27127) · 245e4f2c
  Wentao Ye authored Oct 18, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  245e4f2c
- [Misc] Rev DeepEP (#27122) · 30a33b92
  Varun Sundar Rabindranath authored Oct 18, 2025
```
Signed-off-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
Co-authored-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
```
  30a33b92
- [Perf] Add H100 fused MoE config (#25398) · c981f0ea
  ZiTian Zhao authored Oct 18, 2025
```
Signed-off-by: zitian.zhao <zitian.zhao@tencentmusic.com>
```
  c981f0ea
17 Oct, 2025 12 commits
- [Minor] Remove unnecessary error message (#27115) · d29483b5
  Zhuohan Li authored Oct 17, 2025
```
Signed-off-by: Zhuohan Li <zhuohan123@gmail.com>
```
  d29483b5
- [Chore] Remove unused `PolyNorm` layer (#27110) · 3125d799
  Isotr0py authored Oct 18, 2025
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  3125d799
- [Bugfix] [AITER] [ROCm] Fix Quark MoE Quant Config and AITER Fused MoE quant type logic (#27029) · e33ee23e
  vllmellm authored Oct 18, 2025
```
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
```
  e33ee23e
- [ROCM] MoE fp4 CK kernel (#26545) · 0925b28a
  Aleksandr Malyshev authored Oct 17, 2025
```
Signed-off-by: Aleksandr Malyshev <maleksan@amd.com>
Co-authored-by: Aleksandr Malyshev <maleksan@amd.com>
```
  0925b28a
- [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
- [Harware][AMD][Model] Triton MoE tuning configs for GLM-4.5 for MI350 and MI355 (#25586) · c253745e
  Reima Karhila (AMD) authored Oct 17, 2025
```
Signed-off-by: Reima Karhila <reima.karhila@amd.com>
Signed-off-by: xaguilar <Xavier.AguilarFruto@amd.com>
Co-authored-by: xaguilar <Xavier.AguilarFruto@amd.com>
```
  c253745e
- [Docs] Replace `rst` style double-backtick with `md` single-backtick (#27091) · 6c9fdbf7
  Harry Mellor authored Oct 17, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  6c9fdbf7
- [VLM][Refactor] Remove useless func `get_input_positions` in `MRotaryEmbedding` (#27088) · e20eba75
  Mengqing Cao authored Oct 17, 2025
```
Signed-off-by: MengqingCao <cmq0113@163.com>
```
  e20eba75
- [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
- disable graph partition in custom op (#26952) · 08405609
  Boyuan Feng authored Oct 16, 2025
```
Signed-off-by: Boyuan Feng <boyuan@meta.com>
Signed-off-by: Boyuan Feng <fby.1994@gmail.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
```
  08405609
- Remove unused imports (#26972) · 4d055ef4
  Lukas Geiger authored Oct 17, 2025
```
Signed-off-by: Lukas Geiger <lukas.geiger94@gmail.com>
```
  4d055ef4
- [Chore] Separate out `vllm.utils.importlib` (#27022) · 4d4d6bad
  Cyrus Leung authored Oct 17, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  4d4d6bad
16 Oct, 2025 12 commits

[NVIDIA] [Perf] Update to leverage flashinfer trtllm FP4 MOE throughput kernel (#26714) · 41d30719
jiahanc authored Oct 16, 2025
```
Signed-off-by: jiahanc <173873397+jiahanc@users.noreply.github.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
```
41d30719
[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

[Feature] Migrate DeepGEMM API from `get_m_alignment_for_contiguous_layout` to... · b3dda72c

Wentao Ye authored Oct 16, 2025


[Feature] Migrate DeepGEMM API from `get_m_alignment_for_contiguous_layout` to `get_mk_alignment_for_contiguous_layout` (#26935)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Signed-off-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

b3dda72c

[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
[Compressed Tensors] Always clone output for compile robustness (#26849) · a5464dcf
Kyle Sayers authored Oct 16, 2025
```
Signed-off-by: Kyle Sayers <kylesayrs@gmail.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
```
a5464dcf

[MISC] fix import violations for re and triton modules (#26654) · 00417f4e

Sungjae Lee authored Oct 16, 2025


Signed-off-by: Sungjae Lee <33976427+llsj14@users.noreply.github.com>
Co-authored-by: Mengqing Cao <cmq0113@163.com>

00417f4e

[Chore] Separate out `vllm.utils.collections` (#26990) · d2740faf
Cyrus Leung authored Oct 16, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
d2740faf

Deepseek-v3 Batch Invariant on 8xH100 (#26609) · 7d8975de

Bram Wasti authored Oct 15, 2025


Signed-off-by: Bram Wasti <bwasti@meta.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>

7d8975de

[PERF] Qwen3-next MTP speedup (change bool mask indexing to index_select /... · 785d8b64

Vadim Gimpelson authored Oct 16, 2025


[PERF] Qwen3-next MTP speedup (change bool mask indexing to index_select / index_copy to reduce d2h) (#26437)
Signed-off-by: Vadim Gimpelson <vadim.gimpelson@gmail.com>

785d8b64

[Chore] Rename `utils` submodules (#26920) · f6cdc9a0
Cyrus Leung authored Oct 16, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
f6cdc9a0

[ROCm][FEAT] Fuse DeepSeek shared experts into AITER fused_moe ops (#24097) · 13170343

kliuae authored Oct 16, 2025


Signed-off-by: chenjun <junchen2@amd.com>
Signed-off-by: kliuae <kuanfu.liu@embeddedllm.com>
Co-authored-by: valarLip <103567126+valarLip@users.noreply.github.com>
Co-authored-by: TJian <tunjian.tan@embeddedllm.com>

13170343

[Qwen3-Next] Add tuned MoE config for Qwen3-Next FP8 on H100 tp2 (#26887) · f96bc364
felixzhu555 authored Oct 15, 2025
```
Signed-off-by: Felix Zhu <felixzhu555@gmail.com>
```
f96bc364

15 Oct, 2025 7 commits

support flashinfer_fp4 moe for 5090 gpu (#26669) · 0b99f5d3

XiaobingZhang authored Oct 16, 2025


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

0b99f5d3

[NVIDIA] Add support for cudnn fp4 gemm via flashinfer (#26107) · de92d916

Kaixi Hou authored Oct 15, 2025


Signed-off-by: kaixih <kaixih@nvidia.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: mgoin <mgoin64@gmail.com>

de92d916

[ModelOpt] Remove NVFP4 MoE K%16==0 constraint (#26891) · d7963752
XiaobingZhang authored Oct 16, 2025
```
Signed-off-by: XiaobingSuper <xiaobingzhangupc@gmail.com>
```
d7963752
[Chore] Separate out `vllm.utils.func` (#26904) · 136a17fe
Cyrus Leung authored Oct 15, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
136a17fe
[Misc] Remove `isort` and `yapf` ignores (#26888) · f93e3480
Cyrus Leung authored Oct 15, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
f93e3480
[Model][2/N] Improve all pooling task | Support multi-vector retrieval (#25370) · f54f8512
wang.yuqi authored Oct 15, 2025
```
Signed-off-by: wang.yuqi <noooop@126.com>
```
f54f8512

[Frontend][torch.compile] CompilationConfig Overhaul (#20283): name change ... · 96b9aa5a

Morrison Turnansky authored Oct 14, 2025


[Frontend][torch.compile] CompilationConfig Overhaul (#20283): name change  compilation level to compilation mode, deprecation compilation level (#26355)
Signed-off-by: morrison-turnansky <mturnans@redhat.com>
Signed-off-by: Morrison Turnansky <mturnans@redhat.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>

96b9aa5a

14 Oct, 2025 6 commits
- [CI Failure] Fix torchao dep failure for Quantization Test (#26824) · 7e0ef408
  Michael Goin authored Oct 14, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  7e0ef408
- Added MoE configs for llama 4, H200 device with tp=4/8 tuning (#26837) · 0e658189
  Dhruvil Bhatt authored Oct 14, 2025
```
Signed-off-by: Dhruvil Bhatt <bhattdbh@amazon.com>
```
  0e658189
- llama4_vision_rope: add HIP override to accept (q, k) and avoid (positions, q, k) mismatch (#26790) · 87efc681
  Huamin Li authored Oct 14, 2025
```
Signed-off-by: Huamin Li <3ericli@gmail.com>
```
  87efc681
- [Kernel][MoE] Add MoE tunings for GLM 4.6-FP8 and GLM 4.5 Air on NVidia B200 (#26818) · aba48f7d
  Ze'ev Klapow authored Oct 14, 2025
  
  aba48f7d
- [Feature][Quantization] auto_round format add support for regex (#24024) · 29350922
  Heng Guo authored Oct 14, 2025
```
Signed-off-by: n1ck-guo <heng.guo@intel.com>
Signed-off-by: Heng Guo <heng.guo@intel.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
```
  29350922
- [torch.compile] Unwrap fused_marlin_moe custom op (#26739) · 8ae16928
  Varun Sundar Rabindranath authored Oct 13, 2025
```
Signed-off-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
Co-authored-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
```
  8ae16928