Commits · 02f5903b84cfdf0b7cb31d46e995e3d4b9ad9e53 · OpenDAS / vllm_cscc · GitLab

19 Nov, 2025 37 commits
- Eagle: MM Cuda Graphs with MRope (#28896) · 02f5903b
  Izzy Putterman authored Nov 19, 2025
```
Signed-off-by: Izzy Putterman <iputterman@nvidia.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
```
  02f5903b
- Upstreaming aiter triton attention backend as a new backend (#28701) · ac10fd3c
  Aleksandr Malyshev authored Nov 19, 2025
```
Signed-off-by: Aleksandr Malyshev <maleksan@amd.com>
Co-authored-by: Aleksandr Malyshev <maleksan@amd.com>
```
  ac10fd3c
- [Bugfix] Fix precision corruption when shared_experts_stream=None (#28942) · 9d2d5612
  杰兮 authored Nov 20, 2025
```
Signed-off-by: zhyajie <yajizhan@amd.com>
Co-authored-by: zhyajie <yajizhan@amd.com>
```
  9d2d5612
- [Kernels] Improve H200 Fused MoE Config (#28992) · fe69f331
  Robert Shaw authored Nov 19, 2025
```
Signed-off-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
```
  fe69f331
- [Core] Reuse created spec tokens lists to mitigate GC cost (#28917) · 3319a493
  Jialin Ouyang authored Nov 19, 2025
```
Signed-off-by: Jialin Ouyang <Jialin.Ouyang@gmail.com>
```
  3319a493
- Re-enable FlashInfer for Llama4 on Blackwell in e2e fusion tests (#28966) · 61728cd1
  Copilot authored Nov 19, 2025
```
Signed-off-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: ProExpertProg <11367180+ProExpertProg@users.noreply.github.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
```
  61728cd1
- GLM-V video segmentation solution adjustment (#28941) · 0c80efd9
  Yuxuan Zhang authored Nov 20, 2025
```
Signed-off-by: zRzRzRzRzRzRzR <2448370773@qq.com>
```
  0c80efd9
- 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
- [Model][Mamba] Add selector for mamba attention backend and make it pluggable... · d44e9df7
  Shanshan Shen authored Nov 20, 2025
```
[Model][Mamba] Add selector for mamba attention backend and make it pluggable for other device (#26487)
Signed-off-by: shen-shanshan <467638484@qq.com>
```
  d44e9df7
- [BugFix] Fix async-scheduling + FlashAttn MLA (#28990) · 48fc8b1e
  Lucas Wilkinson authored Nov 19, 2025
```
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
```
  48fc8b1e
- [torch.compile] caching of config fields should be opt-out by default (#26468) · 1ffe934c
  vnadathur authored Nov 19, 2025
```
Signed-off-by: vnadathur <glvikramn@gmail.com>
Signed-off-by: WorldExplored <srreyansh.sethi@gmail.com>
Signed-off-by: Srreyansh Sethi <srreyansh.sethi@gmail.com>
Signed-off-by: Srreyansh Sethi <107075589+WorldExplored@users.noreply.github.com>
Co-authored-by: WorldExplored <srreyansh.sethi@gmail.com>
Co-authored-by: Srreyansh Sethi <107075589+worldexplored@users.noreply.github.com>
Co-authored-by: vnadathur <236933696+vnadathur@users.noreply.github.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
```
  1ffe934c
- [CI] Reorganize compile tests so new tests are automatically included in CI (#28625) · 2c8b9182
  Yanan Cao authored Nov 19, 2025
```
Signed-off-by: Yanan Cao <gmagogsfm@gmail.com>
```
  2c8b9182
- Relax Transformers modeling backend MoE experts check (#28952) · 4f5299f7
  Harry Mellor authored Nov 19, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  4f5299f7
- [Doc]: fix typos in various files (#29010) · 09540cd9
  Didier Durand authored Nov 19, 2025
```
Signed-off-by: Didier Durand <durand.didier@gmail.com>
```
  09540cd9
- [Feat][Perf] Enable deepep-low-latency with round-robin expert placement. (#28449) · da2f6800
  Chen Bruce authored Nov 19, 2025
```
Signed-off-by: bruceszchen <bruceszchen@tencent.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  da2f6800
- [config] Expose `get_total_num_hidden_layers()` in ModelConfig (#28961) · ba558c02
  Tova Movshovitz authored Nov 19, 2025
```
Signed-off-by: tovam <tovam@pliops.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
```
  ba558c02
- [Docs] Take env var definition out of folded admonition (#29005) · 97cfa99d
  Harry Mellor authored Nov 19, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  97cfa99d
- [CI/Build] Fix broken build on Apple M1 (#28999) · bbc6c2f1
  j20120307 authored Nov 19, 2025
```
Signed-off-by: Kan Zhu <j20120307@gmail.com>
```
  bbc6c2f1
- refactor(cpu_types_scalar.hpp): Unify scalar loop implementations using unroll_loop (#28847) · 81516095
  ihb2032 authored Nov 19, 2025
```
Signed-off-by: ihb2032 <1355790728@qq.com>
Co-authored-by: lyd1992 <liuyudong@iscas.ac.cn>
```
  81516095
- [Docs] Clean up moe_kernel_features.md (#28530) · fdf93486
  Michael Yao authored Nov 19, 2025
```
Signed-off-by: windsonsea <haifeng.yao@daocloud.io>
```
  fdf93486
- add support for --fully-sharded-loras in fused_moe (#28761) · d69062c6
  gnovack authored Nov 19, 2025
```
Signed-off-by: gnovack <gnovack@amazon.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
```
  d69062c6
- Add CPU support model (#28697) · ae4821a1
  Louie Tsai authored Nov 18, 2025
```
Signed-off-by: Tsai, Louie <louie.tsai@intel.com>
```
  ae4821a1
- [Doc]: fix typos in various files (#28945) · 7ed27f3c
  Didier Durand authored Nov 19, 2025
```
Signed-off-by: Didier Durand <durand.didier@gmail.com>
```
  7ed27f3c
- Speed up macOS smoke test (#28954) · a4511e38
  Michael Goin authored Nov 19, 2025
```
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  a4511e38
- [Misc] Update embedding/cross encoder tests to use `mteb` v2 (#27329) · 71d0ae1c
  Roman Solomatin authored Nov 19, 2025
```
Signed-off-by: Roman Solomatin <36135455+Samoed@users.noreply.github.com>
Signed-off-by: wang.yuqi <noooop@126.com>
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: wang.yuqi <noooop@126.com>
Co-authored-by: wang.yuqi <yuqi.wang@daocloud.io>
```
  71d0ae1c
- [Model][QwenVL] Simplify cos/sin rotary embedding indexing (#28962) · 3d4e7d34
  Lukas Geiger authored Nov 19, 2025
```
Signed-off-by: Lukas Geiger <lukas.geiger94@gmail.com>
```
  3d4e7d34
- [Docs] Update oneshot imports (#28188) · 6a25ea5f
  Uranus authored Nov 19, 2025
```
Signed-off-by: UranusSeven <109661872+UranusSeven@users.noreply.github.com>
```
  6a25ea5f
- [Bugfix] Fix typo in Qwen3 Next model executor (#28960) · 73ff872d
  Gleb Kurchanov authored Nov 19, 2025
```
Signed-off-by: Gleb Kurchanov <nepherpitou@gmail.com>
```
  73ff872d
- [Bugfix] Fix FusedMoEModularKernel for triton backend (#28913) · 468a8d72
  Xin Yang authored Nov 18, 2025
```
Signed-off-by: Xin Yang <xyangx@amazon.com>
```
  468a8d72
- [Attention] FlashAttention ViT support, make default backend (#28763) · 4c23690f
  Matthew Bonanni authored Nov 18, 2025
```
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
```
  4c23690f
- Enable bitsandbytes quantization on AMD GPUs that use warp size 32 (#27307) · 814843e0
  Strahinja Stamenkovic authored Nov 19, 2025
```
Signed-off-by: sstamenk <strahinja.stamenkovic@amd.com>
```
  814843e0
- [CPU] Refactor CPU WNA16 (#28826) · 20852c8f
  Li, Jiang authored Nov 19, 2025
```
Signed-off-by: jiang1.li <jiang1.li@intel.com>
```
  20852c8f
- [Core] Switch Flat logprob control from environment variable to SamplingParams (#28914) · 40b6b38f
  Jialin Ouyang authored Nov 18, 2025
```
Signed-off-by: Jialin Ouyang <Jialin.Ouyang@gmail.com>
Co-authored-by: 22quinn <33176974+22quinn@users.noreply.github.com>
```
  40b6b38f
- Move online quantization to `model.load_weights` (#26327) · da94c7c0
  Jerry Zhang authored Nov 18, 2025
```
Signed-off-by: Jerry Zhang <jerryzh168@gmail.com>
```
  da94c7c0
- [Hybrid][torch.compile] Refactor mamba2 forward to avoid obscuring linear... · 1395461f
  tomeras91 authored Nov 19, 2025
```
[Hybrid][torch.compile] Refactor mamba2 forward to avoid obscuring linear projections under custom op (#28587)
Signed-off-by: Tomer Asida <57313761+tomeras91@users.noreply.github.com>
```
  1395461f
- [Build] Add OpenAI triton_kernels (#28788) · 9912b8cc
  Varun Sundar Rabindranath authored Nov 18, 2025
```
Signed-off-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
Co-authored-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
```
  9912b8cc
- [NVIDIA] Guard SM100 CUTLASS MoE macro to SM100 builds v2 (#28938) · 49ef847a
  Johnny authored Nov 19, 2025
```
Signed-off-by: johnnynunez <johnnynuca14@gmail.com>
Signed-off-by: Johnny <johnnynuca14@gmail.com>
```
  49ef847a
18 Nov, 2025 3 commits
- Supress verbose logs from model_hosting_container_standards (#28949) · 67745d18
  Michael Goin authored Nov 18, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  67745d18
- 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
- [NIXL] fix cpu PD after physical <> logical block_size PR (#28904) · c3e29786
  Chendi.Xue authored Nov 18, 2025
```
Signed-off-by: Chendi Xue <chendi.xue@intel.com>
```
  c3e29786