Commits · 85ee1d962b1339eb597bf9451a0bcf4b91c72f2a · OpenDAS / vllm_cscc · GitLab

06 Feb, 2026 22 commits
- [Bugfix] Fix models and tests for transformers v5 (#33977) · 85ee1d96
  Raushan Turganbay authored Feb 06, 2026
```
Signed-off-by: raushan <raushan@huggingface.co>
Signed-off-by: Raushan Turganbay <raushan.turganbay@alumni.nu.edu.kz>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  85ee1d96
- Update `WeightTransferConfig` to be more standard like the others (#33989) · 51a7bda6
  Harry Mellor authored Feb 06, 2026
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  51a7bda6
- [Docs] Improve documentation (#33799) · 6e7b1c4b
  SorenDreano authored Feb 06, 2026
```
Co-authored-by: Soren Dreano <soren@numind.ai>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
```
  6e7b1c4b
- [Bugfix][Model] Support LoRA on Qwen3 Output Embedding (#29816) · 2991dd3d
  Kurt Shuster authored Feb 06, 2026
```
Signed-off-by: kurt <kurt@thinkingmachines.ai>
```
  2991dd3d
- [torch.compile] Reorganize vllm/compilation and tests/compile (0/N for vLLM IR) (#33731) · ac32e66c
  Luka Govedič authored Feb 06, 2026
```
Signed-off-by: Luka Govedič <lgovedic@redhat.com>
Signed-off-by: ProExpertProg <luka.govedic@gmail.com>
Signed-off-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
```
  ac32e66c
- [CPU][BugFix] Fix loading of w8a8int models with bias (#33582) · f79d9dce
  Fadi Arafeh authored Feb 06, 2026
```
Signed-off-by: Fadi Arafeh <fadi.arafeh@arm.com>
```
  f79d9dce
- Bump HF Hub client to get bug fix (#33984) · ba5cbbf1
  Harry Mellor authored Feb 06, 2026
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  ba5cbbf1
- [PaddleOCR-VL] Add BC for transformers 5.0 config (#33976) · 233b26ab
  zhang-prog authored Feb 06, 2026
```
Signed-off-by: zhangyue66 <zhangyue66@baidu.com>
```
  233b26ab
- Consolidate and fix forbidden import `pre-commit` checks (#33982) · 791a94be
  Harry Mellor authored Feb 06, 2026
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  791a94be
- support view_from_cpu_tensor on XPU (#33868) · e969a169
  Xinyu Chen authored Feb 06, 2026
```
Signed-off-by: Xinyu Chen <xinyu1.chen@intel.com>
```
  e969a169
- Fix `main` pre-commit (#33975) · 6d8d34be
  Harry Mellor authored Feb 06, 2026
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  6d8d34be
- [cpu][performance] CPU Paged Attention NEON BFMMLA BF16 Implementation (#32263) · 1363e3d6
  Gassan Salama authored Feb 06, 2026
```
Signed-off-by: Gassan <gassan.salama@arm.com>
```
  1363e3d6
- Onboard voyage-4-nano (#33720) · 96552566
  chengchengpei authored Feb 05, 2026
```
Signed-off-by: Chengcheng Pei <chengchengpei@outlook.com>
Signed-off-by: chengchengpei <5881383+chengchengpei@users.noreply.github.com>
Co-authored-by: chengchengpei <5881383+chengchengpei@users.noreply.github.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
```
  96552566
- [XPU]Replace pip in docker.xpu with uv pip (#31112) · 6550815c
  sihao_li authored Feb 06, 2026
```
Signed-off-by: sihao.li <sihao.li@intel.com>
```
  6550815c
- [XPU][4/N] add mxfp4 moe model support (#33679) · 7439e4f4
  Kunshang Ji authored Feb 06, 2026
```
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
```
  7439e4f4
- [CPU] Add BF16 Kernel type for s390x (#33788) · ac04dd37
  R3hankhan authored Feb 06, 2026
```
Signed-off-by: Rehan Khan <Rehan.Khan7@ibm.com>
```
  ac04dd37
- [Misc] Update code for encoder-decoder models (#33900) · 035a6cb0
  Cyrus Leung authored Feb 06, 2026
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  035a6cb0
- feat(frontend): early-fail tokenization guard for user requests (#31366) · a32cb49b
  Mingliang Li authored Feb 06, 2026
```
Signed-off-by: limingliang <limingliang@stepfun.com>
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Co-authored-by: limingliang <limingliang@stepfun.com>
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  a32cb49b
- fix(ROCm): Make flash_attn import optional in MLA attention (#33511) · 20d7454c
  Rabi Mishra authored Feb 06, 2026
```
Signed-off-by: rabi <ramishra@redhat.com>
```
  20d7454c
- [Docs] Add reo analytics (#33957) · 5819ca89
  Simon Mo authored Feb 05, 2026
```
Signed-off-by: simon-mo <simon.mo@hey.com>
```
  5819ca89
- [Perf] Disable clean_logits in deepgemm fp8_mqa_logits kernel (#33568) · 79028d43
  Xin Yang authored Feb 05, 2026
  
  79028d43
- [Feature] OTEL tracing during loading (#31162) · 325ab6b0
  emricksini-h authored Feb 06, 2026
  
  325ab6b0
05 Feb, 2026 18 commits
- [Bugfix] Fix DeepSeek v3.2 tokenizer outputting None issue (#33832) · 91a07ff6
  Wei Zhao authored Feb 05, 2026
```
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
```
  91a07ff6
- Adds padding and perf improvements to wvSplitK_fp8 (#33527) · d5c48001
  Hashem Hashemi authored Feb 05, 2026
```
Signed-off-by: Hashem Hashemi <hashem.hashemi@amd.com>
```
  d5c48001
- [Minor] Sort safetensors files to ensure deterministic loading order (#33491) · 42d5d705
  Lumosis authored Feb 05, 2026
```
Signed-off-by: Lihao Ran <imlihao.ran@gmail.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
```
  42d5d705
- [Bugfix] Make MM batching more robust (#33817) · 116880a5
  Cyrus Leung authored Feb 06, 2026
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  116880a5
- [Bugfix] Fix DSV3.2 NVFP4 (#33932) · 4145e50d
  Matthew Bonanni authored Feb 05, 2026
```
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
```
  4145e50d
- [Misc] Rename `translations` to `speech_to_text` for OAI serving component (#33904) · 20f5d185
  Nicolò Lucchesi authored Feb 05, 2026
```
Signed-off-by: NickLucche <nlucches@redhat.com>
```
  20f5d185
- Fix tokenizer test for renamed attr on Transformers v5 (#33902) · 1887acca
  Harry Mellor authored Feb 05, 2026
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  1887acca
- [Bugfix] Suppress non-TTY color output on the process name part of the log (#29714) · 92e7562a
  Tsukasa OI authored Feb 06, 2026
```
Signed-off-by: Tsukasa OI <floss_llm@irq.a4lg.com>
```
  92e7562a
- [Models] Consolidate Deepseek-OCR2 processor (#33909) · 87d0d17a
  Isotr0py authored Feb 06, 2026
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  87d0d17a
- [Moe Refactor] Make Inplace Flag for FusedMoEModularKernel part of the constructor (#33375) · a57c8228
  bnellnm authored Feb 05, 2026
```
Signed-off-by: Bill Nell <bnell@redhat.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
```
  a57c8228
- [Bugfix] Fix swapped engine_ids in NIXL Llama 4 local attention path (#33795) · 1ee95841
  zackyoray authored Feb 05, 2026
```
Signed-off-by: Yoray Zack <yorayz@nvidia.com>
```
  1ee95841
- [Misc] Add debug logs (#33931) · 7d8c6804
  Nicolò Lucchesi authored Feb 05, 2026
```
Signed-off-by: NickLucche <nlucches@redhat.com>
```
  7d8c6804
- [Spec Decode] Unified Parallel Drafting (#32887) · af3162d3
  Benjamin Chislett authored Feb 05, 2026
```
Signed-off-by: Benjamin Chislett <bchislett@nvidia.com>
```
  af3162d3
- [BugFix] Fix LoRA Fp8 (#33879) · 5b2a9422
  danisereb authored Feb 05, 2026
```
Signed-off-by: Daniel Serebrenik <daserebrenik@nvidia.com>
```
  5b2a9422
- [Feat][RL][1/2] Native Weight Syncing API: NCCL (#31943) · c1858b7e
  Aaron Hao authored Feb 05, 2026
```
Signed-off-by: ahao-anyscale <ahao@anyscale.com>
Signed-off-by: Aaron Hao <ahao@anyscale.com>
Co-authored-by: SumanthRH <sumanthrh99@gmail.com>
```
  c1858b7e
- [Bugfix] Fix step3p5 parser when using mtp (#33690) · 82914d2a
  Mario Hong authored Feb 06, 2026
```
Signed-off-by: mariohong <mariohong128@gmail.com>
```
  82914d2a
- [Docs] Add bart-plugin to docs (#33905) · 81a90e52
  Nicolò Lucchesi authored Feb 05, 2026
```
Signed-off-by: NickLucche <nlucches@redhat.com>
```
  81a90e52
- [Bugfix] Fix corner case of sparse embedding (#33886) · 1c3a221d
  wang.yuqi authored Feb 05, 2026
```
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
```
  1c3a221d