Commits · 071d863e208b40fa1bb986ad230e322b2bbbbcf5 · OpenDAS / vllm_cscc · GitLab

13 Feb, 2026 27 commits
- Extend ColBERT support to non-standard BERT backbones (#34170) · 071d863e
  Ilya Boytsov authored Feb 13, 2026
```
Signed-off-by: Ilya Boytsov <ilya.boytsov@aleph-alpha.com>
```
  071d863e
- [GDN] Use CPU tensors to build GDN metadata (#34498) · 0916e796
  Woosuk Kwon authored Feb 13, 2026
```
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
```
  0916e796
- [Feature] Pipeline Parallel Async send/recv, 2.9% E2E throughput improvement (#33368) · 3d2a026f
  Wentao Ye authored Feb 13, 2026
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Signed-off-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
Co-authored-by: Nick Hill <nhill@redhat.com>
```
  3d2a026f
- [Core] Move pause and resume functions into engine (#34125) · dddbff46
  Aaron Hao authored Feb 13, 2026
```
Signed-off-by: ahao-anyscale <ahao@anyscale.com>
Signed-off-by: Aaron Hao <ahao@anyscale.com>
Signed-off-by: hao-aaron <ahao@anyscale.com>
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
```
  dddbff46
- [KVConnector] Clean up redundant code in KV connectors (#34147) · 47e9b63e
  Martin Hickey authored Feb 13, 2026
```
Signed-off-by: Martin Hickey <martin.hickey@ie.ibm.com>
```
  47e9b63e
- [Perf] fused_moe: add int4_w4a16 benchmark support and tuning config (#34130) · 934acdde
  Matthias Gehre authored Feb 13, 2026
```
Signed-off-by: Matthias Gehre <matthias.gehre@amd.com>
Co-authored-by: TJian <tunjian.tan@embeddedllm.com>
```
  934acdde
- [Bug Fix] Fix MambaManager.cache_blocks() crash on null blocks in align mode (#34418) · 4137c5df
  haosdent authored Feb 13, 2026
```
Signed-off-by: haosdent <haosdent@gmail.com>
```
  4137c5df
- [BugFix] Fix and optimize max_num_blocks_per_req calculation for MambaSpec (#34440) · 7a8a46dd
  Harry Huang authored Feb 13, 2026
```
Signed-off-by: huanghaoyan.hhy <huanghaoyan.hhy@alibaba-inc.com>
```
  7a8a46dd
- [New Model] support new model ovis2.6 (#34426) · bcf0731a
  myselvess authored Feb 13, 2026
```
Signed-off-by: myselvess <23743269+myselvess@users.noreply.github.com>
```
  bcf0731a
- [Refactor] Call renderer for online IO processor request (#34490) · ec090c24
  Cyrus Leung authored Feb 13, 2026
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Signed-off-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
```
  ec090c24
- [Bugfix] Fix mamba state dtype setting for Qwen3-Next and Qwen3.5 (#34489) · eea3024f
  Roger Wang authored Feb 12, 2026
```
Signed-off-by: Roger Wang <hey@rogerw.io>
```
  eea3024f
- [Refactor] Pass full VllmConfig to Renderer (#34485) · 2f308214
  Cyrus Leung authored Feb 13, 2026
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  2f308214
- [Bugfix] Fix encoder cache underestimation for GLM-4V/GLM-OCR single image (#34483) · dcf6ee85
  haosdent authored Feb 13, 2026
```
Signed-off-by: haosdent <haosdent@gmail.com>
```
  dcf6ee85
- [Bugfix] Standardize getting number of image patches/tokens (#34358) · 372b2e76
  Cyrus Leung authored Feb 13, 2026
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  372b2e76
- [Hybrid] Fix and optimize block-aligned splitting in mamba cache align mode (#33706) · bf37812c
  Harry Huang authored Feb 13, 2026
```
Signed-off-by: huanghaoyan.hhy <huanghaoyan.hhy@alibaba-inc.com>
```
  bf37812c
- [Bugfix] Fix Random Dataset Prefix Length Inaccuracy (#33907) · b86bf441
  Frank Wang authored Feb 12, 2026
```
Signed-off-by: frankwang28 <frank.wbb@hotmail.com>
Co-authored-by: Roger Wang <hey@rogerw.io>
```
  b86bf441
- [Kernel] [Helion] [5/N] Add Helion Autotuning infrastructure (#34025) · de13dd78
  Yanan Cao authored Feb 12, 2026
```
Signed-off-by: Yanan Cao <gmagogsfm@gmail.com>
```
  de13dd78
- [Bugfix] Delete unused redundant code in Kimi-K2.5 (#34427) · 62788f99
  LoganJane authored Feb 13, 2026
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  62788f99
- [Refactor] Simplify BOS/EOS token handling (#34435) · ea5ff3a1
  Cyrus Leung authored Feb 13, 2026
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  ea5ff3a1
- [Bugfix] Remove assert that's no longer valid (#34443) · 04ea31ba
  bnellnm authored Feb 12, 2026
```
Signed-off-by: Bill Nell <bnell@redhat.com>
```
  04ea31ba
- [BugFix] Add block_size validation for mamba cache align mode (#34445) · 6f019e6e
  Harry Huang authored Feb 13, 2026
```
Signed-off-by: huanghaoyan.hhy <huanghaoyan.hhy@alibaba-inc.com>
```
  6f019e6e
- Fix num_logprobs parameter description in sampler.py (#34451) · d707678d
  Zhuohan Li authored Feb 12, 2026
```
Signed-off-by: Zhuohan Li <zhuohan123@gmail.com>
```
  d707678d
- [Kernel] [Helion] [4/N] Add silu_mul_fp8 Helion kernel (#33373) · 96161fe9
  Yanan Cao authored Feb 12, 2026
```
Signed-off-by: Yanan Cao <gmagogsfm@gmail.com>
```
  96161fe9
- [Core] Profiler improvements and lazy initialization (#33198) · 4453ba8d
  Jaewon authored Feb 12, 2026
```
Signed-off-by: Jaewon Lee <jaewon@meta.com>
Co-authored-by: Lu Fang <30275821+houseroad@users.noreply.github.com>
```
  4453ba8d
- [Core] Add sleep level 0 mode with enqueue/wait pattern (#33195) · aa181c92
  Jaewon authored Feb 12, 2026
```
Signed-off-by: Jaewon Lee <jaewon@meta.com>
Co-authored-by: Lu Fang <30275821+houseroad@users.noreply.github.com>
```
  aa181c92
- [Frontend] Enable generic structured_outputs for responses API (#33709) · be7370da
  Alec S authored Feb 12, 2026
```
Signed-off-by: Alec Solder <alecs@fb.com>
Co-authored-by: Alec Solder <alecs@fb.com>
```
  be7370da
- Use paged_attention_v1 for sliding window decode in rocm_aiter_fa (#34378) · 9ea1f598
  Mengtao (Martin) Yuan authored Feb 12, 2026
```
Signed-off-by: Martin Yuan <myuan@meta.com>
Co-authored-by: Martin Yuan <myuan@meta.com>
```
  9ea1f598
12 Feb, 2026 13 commits
- [Kernel] Support Flashinfer trtllm fused MoE non gated FP8 & NVFP4 (#33506) · f120bd42
  amitz-nv authored Feb 12, 2026
```
Signed-off-by: amitz-nv <203509407+amitz-nv@users.noreply.github.com>
```
  f120bd42
- [Bugfix] Enforce DeepGEMM when using sparse_attn_indexer on CUDA (#34374) · 6d4e27ce
  Michael Goin authored Feb 12, 2026
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  6d4e27ce
- [Voxtral Realtime] Refactor & Improve buffering logic (#34428) · 6c0baee6
  Patrick von Platen authored Feb 12, 2026
```
Signed-off-by: Patrick von Platen <patrick.v.platen@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
```
  6c0baee6
- [Voxstral Realtime] Enable tests (#33803) · 1100a976
  Patrick von Platen authored Feb 12, 2026
```
Signed-off-by: Patrick von Platen <patrick.v.platen@gmail.com>
```
  1100a976
- [ROCm][quantization] improve OCP weight quant parser robust (#34431) · 766e1678
  xuebwang-amd authored Feb 13, 2026
```
Signed-off-by: xuebwang-amd <xuebwang@amd.com>
Co-authored-by: TJian <tunjian.tan@embeddedllm.com>
```
  766e1678
- [Bugfix] Remove broken raw url GGUF model loading support (#34433) · becbe248
  Isotr0py authored Feb 13, 2026
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  becbe248
- Fix MoE for the Transformers modelling backend (#34436) · 679ca5d8
  Harry Mellor authored Feb 12, 2026
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  679ca5d8
- [Attention] Add FlashInfer Sparse MLA backend (#33451) · f2c47886
  Matthew Bonanni authored Feb 12, 2026
```
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
```
  f2c47886
- [BUG] Reset running requests when clearing cache for pause/resume (#34382) · 7b5a8b4a
  Aaron Hao authored Feb 12, 2026
```
Signed-off-by: hao-aaron <ahao@anyscale.com>
```
  7b5a8b4a
- Add config file for fused MoE for Nemotron (TP4, B200) (#34411) · dea63512
  danisereb authored Feb 12, 2026
```
Signed-off-by: Daniel Serebrenik <daserebrenik@nvidia.com>
```
  dea63512
- [ROCm] Enable MXFP4 MoE weight pre-shuffling on gfx950 and update aiter (#34192) · 8a798be9
  Douglas Lehr authored Feb 12, 2026
```
Signed-off-by: Doug Lehr <douglehr@amd.com>
Co-authored-by: Doug Lehr <douglehr@amd.com>
Co-authored-by: Gregory Shtrasberg <156009573+gshtras@users.noreply.github.com>
Co-authored-by: tjtanaavllm <tunjian.tan@amd.com>
```
  8a798be9
- [V0 Deprecation] Remove code related to per-request logits processors (#34400) · fb455ed5
  Cyrus Leung authored Feb 12, 2026
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  fb455ed5
- Fix Mistral config remap to accept compressed-tensors quantization #34028 (#34104) · f5897613
  baonudesifeizhai authored Feb 12, 2026
```
Signed-off-by: baonudesifeizhai <baonudesifeizhai@gmail.com>
```
  f5897613