Commits · 8e75d885544c9d7602344e9db2c7e3cff9b73c11 · OpenDAS / vllm_cscc

28 Feb, 2026 25 commits
- add io_process_plugin for sparse embedding (#34214) · 8e75d885
  Augusto Yao authored Feb 28, 2026
```
Signed-off-by: augusto.yjh <augusto.yjh@antgroup.com>
Signed-off-by: Augusto Yao <augusto.yjh@antgroup.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
```
  8e75d885
- [Feature]Supports Anthropic Thinking Block (#33671) · 0892d1ab
  Mario Hong authored Feb 28, 2026
```
Signed-off-by: mariohong <mariohong128@gmail.com>
Co-authored-by: zetaohong <i-hongzetao@stepfun.com>
Co-authored-by: Chauncey <chaunceyjiang@gmail.com>
```
  0892d1ab
- Add padding support to wvSplitK solution for skinny GEMMs (#33762) · 7600642e
  Hashem Hashemi authored Feb 28, 2026
```
Signed-off-by: Hashem Hashemi <hashem.hashemi@amd.com>
```
  7600642e
- [ROCm][CI] Parametrize vision score tests across attention backends with... · 1e69c048
  Andreas Karatzas authored Feb 28, 2026
```
[ROCm][CI] Parametrize vision score tests across attention backends with per-backend tolerances (#35571)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
```
  1e69c048
- [Benchmark] Improve UX of sweep scripts (#35600) · 4292e3b8
  Cyrus Leung authored Feb 28, 2026
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  4292e3b8
- [Benchmark] Rename SLA Finder to Workload Explorer (#35586) · 24d6ea8a
  Cyrus Leung authored Feb 28, 2026
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  24d6ea8a
- [Misc] Change logging level from info to debug for tool parser import (#35575) · 57c86c07
  Chauncey authored Feb 28, 2026
```
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
```
  57c86c07
- [CI] add trainer_send_weights for MockWeightTransferEngine (#35589) · 06254d4c
  Chauncey authored Feb 28, 2026
```
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
```
  06254d4c
- [ROCm][CI] Expose tests to AMD production CI and fix amdsmi heap corruption (#35071) · f5d1281c
  Andreas Karatzas authored Feb 27, 2026
```
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
```
  f5d1281c
- [ROCm] Derive device capability from GCN arch string without CUDA init (#35069) · 94029ffa
  Andreas Karatzas authored Feb 27, 2026
```
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
```
  94029ffa
- [ROCm][CI] Adding infiniband mappings for moriio tests (#35170) · 88e8525f
  Andreas Karatzas authored Feb 27, 2026
```
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
```
  88e8525f
- [EPLB] Enforce sync eplb for NCCL-based all2all backend (#35212) · b2d8b422
  Ilya Markov authored Feb 28, 2026
```
Signed-off-by: ilmarkov <markovilya197@gmail.com>
```
  b2d8b422
- [Bugfix] Move chat completion response_format validation to Pydantic model_validator (#35510) · 1d5ab5d6
  Umut Polat authored Feb 28, 2026
```
Signed-off-by: umut-polat <52835619+umut-polat@users.noreply.github.com>
```
  1d5ab5d6
- [Bugfix] Propagate compilation_time from workers to main process for TP>1 (#35503) · 7b346ba8
  Huy Do authored Feb 27, 2026
```
Signed-off-by: Huy Do <huydhn@gmail.com>
```
  7b346ba8
- [1/N] Elastic EP Milestone 2 (#34861) · dea26833
  Itay Alroy authored Feb 28, 2026
```
Signed-off-by: Yongji Wu <wuyongji317@gmail.com>
Signed-off-by: Itay Alroy <ialroy@nvidia.com>
Signed-off-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
Signed-off-by: Ron Tourgeman <rtourgeman@nvidia.com>
Co-authored-by: Yongji Wu <wuyongji317@gmail.com>
Co-authored-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
Co-authored-by: Ron Tourgeman <rtourgeman@nvidia.com>
```
  dea26833
- [CI/Build] CPU release supports both of AVX2 and AVX512 (#35466) · 90805ff4
  Ma Jian authored Feb 28, 2026
```
Signed-off-by: jiang1.li <jiang1.li@intel.com>
Co-authored-by: jiang1.li <jiang1.li@intel.com>
```
  90805ff4
- [MTP] Validate that MTP weights are actually loaded (#35548) · 2562e027
  Matthew Bonanni authored Feb 27, 2026
```
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
```
  2562e027
- [Bugfix] Fixes for SLA finder (#35537) · fd68cd13
  Cyrus Leung authored Feb 28, 2026
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  fd68cd13
- [ROCm] Add `stablelm` Head Size 80 To Supported Head Sizes For ROCM_ATTN (#35527) · 0edf101d
  Micah Williamson authored Feb 27, 2026
```
Signed-off-by: Micah Williamson <micah.williamson@amd.com>
```
  0edf101d
- [ROCm][Quantization] Add Composable Kernel (CK) backend support for M… (#34301) · d5b6f3ba
  Douglas Lehr authored Feb 27, 2026
```
Signed-off-by: Doug Lehr <douglehr@amd.com>
Signed-off-by: Douglas Lehr <91553416+dllehr-amd@users.noreply.github.com>
Signed-off-by: Douglas Lehr <Doug.Lehr@amd.com>
Co-authored-by: Doug Lehr <douglehr@amd.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Rohan Potdar <66227218+Rohan138@users.noreply.github.com>
```
  d5b6f3ba
- [Model Runner V2] Move MM encoder to Model States [3/N] (#35564) · 1a014a0a
  Woosuk Kwon authored Feb 27, 2026
```
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
```
  1a014a0a
- [Model Runner V2] Support pooling models (#35120) · 86ac7bcf
  Woosuk Kwon authored Feb 27, 2026
```
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
```
  86ac7bcf
- [Misc] Clean up ResponsesRequest model validators (#35531) · 405f28d3
  Umut Polat authored Feb 28, 2026
```
Signed-off-by: umut-polat <52835619+umut-polat@users.noreply.github.com>
```
  405f28d3
- [misc] cleanup one level of error stack when nixl fails to initialize (#35517) · 5323672b
  youkaichao authored Feb 28, 2026
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
  5323672b
- [Refactor][Kernel] Add global helper to deduplicate vectorized memory ops (#35105) · a201ad72
  Roberto L. Castro authored Feb 28, 2026
```
Signed-off-by: LopezCastroRoberto <rocastro@redhat.com>
Signed-off-by: LopezCastroRoberto <roberto.lopez.castro@udc.es>
Signed-off-by: Roberto L. Castro <38211239+LopezCastroRoberto@users.noreply.github.com>
```
  a201ad72
27 Feb, 2026 15 commits

[ROCm]: fix aiter rope functionalization (#35533) · e3691988
Rohan Potdar authored Feb 27, 2026
```
Signed-off-by: Rohan138 <rohanpotdar138@gmail.com>
```
e3691988
[ROCm] Enabling encoder and encoder-decoder on ROCm and AITER unified backends (#35334) · 9fa6c68f
Gregory Shtrasberg authored Feb 27, 2026
```
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
```
9fa6c68f

[Feat][RL][2/2] Native Weight Syncing API: IPC (#34171) · 2ce6f3cf

Aaron Hao authored Feb 27, 2026


Signed-off-by: hao-aaron <ahao@anyscale.com>
Signed-off-by: Aaron Hao <ahao@anyscale.com>
Signed-off-by: ahao-anyscale <ahao@anyscale.com>

2ce6f3cf

[Bugfix][Model] Fix gpt-oss batch invariance (#35404) · 1f3dbd95
Jakub Zakrzewski authored Feb 27, 2026
```
Signed-off-by: Jakub Zakrzewski <jzakrzewski@nvidia.com>
```
1f3dbd95
[DP] Only use DP padding when cudagraphs are actually used (#34102) · 1d532f9d
Lucas Wilkinson authored Feb 27, 2026
```
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
```
1d532f9d
[Bugfix] Add monkeypatch to prevent race condition from writing (#35420) · 234a65b7
Lucas Kabela authored Feb 27, 2026
```
Signed-off-by: Lucas Kabela <lucaskabela@meta.com>
```
234a65b7

[Transformers backend] Ignore MTP weights when num_nextn_predict_layers=0 (#34888) · 2decec98

SteadfastAsArt authored Feb 28, 2026

Signed-off-by: SteadfastAsArt <695488173@qq.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>

2decec98

[compile] Fix caching error over pytree slice node. (#35308) · 29b35477
Zhengxu Chen authored Feb 27, 2026
```
Signed-off-by: zhxchen17 <zhxchen17@fb.com>
```
29b35477
[Model Runner V2] Warmup kernels (#35172) · b1d9f537
Nick Hill authored Feb 27, 2026
```
Signed-off-by: Nick Hill <nickhill123@gmail.com>
```
b1d9f537

[BugFix] Fix 3D rope in transformers backend (#35097) · fd6de37f

Raushan Turganbay authored Feb 27, 2026


Signed-off-by: raushan <raushan@huggingface.co>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>

fd6de37f

Support parakeet as audio encoder for nemotron-nano-vl (#35100) · c8aca0c9

Netanel Haber authored Feb 27, 2026


Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>
Co-authored-by: Roger Wang <hey@rogerw.io>

c8aca0c9

[Doc] Fix link to Llama chat template for usability (#35525) · b602e4f2

Martin Hickey authored Feb 27, 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>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>

b602e4f2

[perf] Use pinned memory for async H2D transfer in do_mamba_copy_block (#35480) · 157722da
Huamin Li authored Feb 27, 2026
```
Signed-off-by: Huamin Li <3ericli@gmail.com>
```
157722da
[Misc] Fill in some v1 CODEOWNERS gaps (#35524) · 1d897ff0
Nick Hill authored Feb 27, 2026
```
Signed-off-by: Nick Hill <nickhill123@gmail.com>
```
1d897ff0

[Model] Add huggingface skt/A.X-K1 model (#32407) · 905d76b5

fort726 authored Feb 28, 2026

Signed-off-by: Sungwan(Alex) Kim <sw0726.kim@sktelecom.com>
Signed-off-by: fort726 <38447663+fort726@users.noreply.github.com>
Co-authored-by: Sungwan(Alex) Kim <sw0726.kim@sktelecom.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: TJian <tunjian.tan@embeddedllm.com>

905d76b5