Commits · 50632adc583fe1af8e2ee112b48c61c14153574f · OpenDAS / vllm_cscc · GitLab

14 Jan, 2026 3 commits
- Consolidate Intel Quantization Toolkit Integration in vLLM (#31716) · 50632adc
  Yi Liu authored Jan 14, 2026
```
Signed-off-by: yiliu30 <yi4.liu@intel.com>
```
  50632adc
- [ROCm][CI] Disable Async Scheduling For Qwen3-Next-80B-A3B-Instruct MTP Async... · 6fa6e7ef
  Micah Williamson authored Jan 13, 2026
```
[ROCm][CI] Disable Async Scheduling For Qwen3-Next-80B-A3B-Instruct MTP Async EPLB Accuracy Test (#32275)
Signed-off-by: Micah Williamson <micah.williamson@amd.com>
```
  6fa6e7ef
- [Model Runner V2] Refactor Sampler (#32245) · 90c08369
  Woosuk Kwon authored Jan 13, 2026
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  90c08369
13 Jan, 2026 36 commits
- [Kernel][Performance] Enable smaller Scaling Factor tiling for NVFP4 small-batch decoding (#30885) · 8ef50d9a
  Roberto L. Castro authored Jan 14, 2026
```
Signed-off-by: LopezCastroRoberto <roberto.lopez.castro@udc.es>
Signed-off-by: Roberto L. Castro <38211239+LopezCastroRoberto@users.noreply.github.com>
Signed-off-by: LopezCastroRoberto <rocastro@redhat.com>
```
  8ef50d9a
- [Improvement] Persist CUDA compat libraries paths to prevent reset on `apt-get` (#30784) · 2a60ac91
  emricksini-h authored Jan 13, 2026
```
Signed-off-by: emricksini-h <emrick.birivoutin@hcompany.ai>
```
  2a60ac91
- Add mergify label job for "bug" in PR titles (#31980) · 9e65bb4e
  Michael Goin authored Jan 13, 2026
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  9e65bb4e
- [Build] Add scripts for cherry-picking and trigger build (#32282) · 0db574b1
  Simon Mo authored Jan 13, 2026
```
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
```
  0db574b1
- [Misc] Add In-Container restart capability through supervisord for sagemaker entrypoint (#28502) · 2f4a71da
  HappyAmazonian authored Jan 13, 2026
```
Signed-off-by: Shen Teng <sheteng@amazon.com>
Signed-off-by: HappyAmazonian <91216626+HappyAmazonian@users.noreply.github.com>
```
  2f4a71da
- fix(rocm): Use refresh_env_variables() for rocm_aiter_ops in test_moe (#31711) · 69f8a0ea
  Rabi Mishra authored Jan 14, 2026
```
Signed-off-by: rabi <ramishra@redhat.com>
```
  69f8a0ea
- [Perf] Optimize grouped topk kernel, 1.2%~2% E2E Throughput improvement (#32058) · f28125d8
  Wentao Ye authored Jan 13, 2026
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  f28125d8
- Fix CUDA 13 wheel installation doc (#32276) · 46f8c6b7
  Dmitry Tokarev authored Jan 13, 2026
```
Signed-off-by: Dmitry Tokarev <dtokarev@nvidia.com>
```
  46f8c6b7
- [responseAPI] support partial message generation (#32100) · af54d2e2
  Andrew Xia authored Jan 13, 2026
```
Signed-off-by: Andrew Xia <axia@fb.com>
Signed-off-by: Andrew Xia <mitandrewxia@gmail.com>
Signed-off-by: Lu Fang <30275821+houseroad@users.noreply.github.com>
Co-authored-by: Andrew Xia <axia@fb.com>
Co-authored-by: Lu Fang <30275821+houseroad@users.noreply.github.com>
```
  af54d2e2
- [EPLB][Cleanup] Remove `is_async_enabled` from `EplbModelState` (#32050) · 6beef12b
  Sage Moore authored Jan 13, 2026
```
Signed-off-by: Sage Moore <sage@neuralmagic.com>
```
  6beef12b
- [Trivial] Remove duplicate enable_mfu_metrics (#32246) · ab74b2a2
  Mark McLoughlin authored Jan 13, 2026
```
Signed-off-by: Mark McLoughlin <markmc@redhat.com>
```
  ab74b2a2
- [4/N][Attention] Move MLA common to model_executor (#32060) · 2263d44b
  Matthew Bonanni authored Jan 13, 2026
```
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
```
  2263d44b
- nixl_connector: export UCX_MEM_MMAP_HOOK_MODE=none to avoid a UCX memory leak (#32181) · 4f3676e7
  Mathis Felardos authored Jan 13, 2026
```
Signed-off-by: Mathis Felardos <mathis@mistral.ai>
```
  4f3676e7
- [BugFix] [KVConnector] Fix KV events for LMCache connector (#32169) · 51026547
  Martin Hickey authored Jan 13, 2026
```
Signed-off-by: Martin Hickey <martin.hickey@ie.ibm.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
```
  51026547
- [Refactor] [7/N] to simplify the vLLM lora serving architecture (#32251) · 4f02cb2e
  Chauncey authored Jan 13, 2026
```
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
```
  4f02cb2e
- [Refactor] Remove `MultiModalProfiler` (#32254) · 252c0110
  Cyrus Leung authored Jan 13, 2026
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  252c0110
- [6/N][Attention] Move utils to more appropriate locations (#32215) · 98f60e5a
  Matthew Bonanni authored Jan 13, 2026
```
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
```
  98f60e5a
- [Refactor] [6/N] to simplify the vLLM openai chat_completion serving architecture (#32240) · fefce498
  Chauncey authored Jan 13, 2026
```
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
```
  fefce498
- [Quantization] fix: overflow with static per-tensor scaling (#29867) · a5bbbd2f
  Mickaël Seznec authored Jan 13, 2026
```
Signed-off-by: Mickael Seznec <mickael@mistral.ai>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
```
  a5bbbd2f
- [Docs] Nixl Usage recommend `fail` kv_load_failure_policy (#32198) · 8c8653b6
  Nicolò Lucchesi authored Jan 13, 2026
```
Signed-off-by: NickLucche <nlucches@redhat.com>
```
  8c8653b6
- [Bugfix] Replace `PoolingParams.normalize` with `use_activation` (#32243) · 232214b2
  Cyrus Leung authored Jan 13, 2026
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  232214b2
- [Refactor] Remove `get_encoder_dummy_data` (#32241) · eb28e806
  Cyrus Leung authored Jan 13, 2026
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  eb28e806
- [Model] Use mm_position to compute mrope positions for Qwen2-VL/2.5-VL (#32126) · 542a4059
  YunzhuLu authored Jan 13, 2026
```
Signed-off-by: YunzhuLu <lucia.yunzhu@gmail.com>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  542a4059
- [ROCm][CI] Fix engine core client tests for ROCm spawn multiprocessing (#32061) · df7e1271
  Andreas Karatzas authored Jan 13, 2026
```
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
```
  df7e1271
- [Doc] Update installation from source command (#32239) · 44c34f22
  Roy Wang authored Jan 13, 2026
```
Signed-off-by: esmeetu <jasonailu87@gmail.com>
```
  44c34f22
- [BugFix]Fix eagle draft_model_config and add tests (#31753) · 80221e18
  Xingyu Liu authored Jan 12, 2026
```
Signed-off-by: Xingyu Liu <charlotteliu12x@gmail.com>
```
  80221e18
- [ROCm][CI] Fix HuggingFace flash_attention_2 accuracy issue in Isaac vision encoder (#32233) · 5e714f7f
  Andreas Karatzas authored Jan 13, 2026
```
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
```
  5e714f7f
- [ROCm][Bugfix] Fix Mamba batched decode producing incorrect output (#32099) · 11b6af52
  Andreas Karatzas authored Jan 12, 2026
```
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
```
  11b6af52
- [Perf] Optimize requests abort (#32211) · 2a719e08
  Wentao Ye authored Jan 12, 2026
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  2a719e08
- Fix various typos found in `docs` (#32212) · f243abc9
  Andrew Bennett authored Jan 12, 2026
```
Signed-off-by: Andrew Bennett <potatosaladx@meta.com>
```
  f243abc9
- [Frontend] Add `reasoning_effort` to `OpenAIServing._preprocess_chat()` (#31956) · 60b77e14
  Sanghoon Yoon authored Jan 13, 2026
```
Signed-off-by: Sanghoon Yoon <seanyoon@kakao.com>
```
  60b77e14
- [Misc] improve warning/assert messages (#32226) · 15b33ff0
  cjackal authored Jan 13, 2026
```
Signed-off-by: cjackal <44624812+cjackal@users.noreply.github.com>
```
  15b33ff0
- [BugFix] Fix engine crash caused by chat tools + response_format (#32127) · c6bb5b56
  Nick Hill authored Jan 12, 2026
```
Signed-off-by: Nick Hill <nickhill123@gmail.com>
```
  c6bb5b56
- [Misc] Allow enabling NCCL for DP sync when async scheduling (#32197) · 9273a427
  Nick Hill authored Jan 12, 2026
```
Signed-off-by: Nick Hill <nickhill123@gmail.com>
```
  9273a427
- [Model] Handle `trust_remote_code` for transformers backend (#32194) · 78d13ea9
  Cyrus Leung authored Jan 13, 2026
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  78d13ea9
- [responsesAPI] add unit test for optional function tool call id (#32036) · a307ac07
  Andrew Xia authored Jan 12, 2026
```
Signed-off-by: Andrew Xia <axia@fb.com>
Co-authored-by: Andrew Xia <axia@fb.com>
```
  a307ac07
12 Jan, 2026 1 commit
- [ROCm][CI] Handle pytest status code 5 when a shard isn't allocated any tests (#32040) · a28d9f44
  Divakar Verma authored Jan 12, 2026
```
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
```
  a28d9f44