Commits · 8e75d885544c9d7602344e9db2c7e3cff9b73c11 · OpenDAS / vllm_cscc

28 Feb, 2026 7 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

[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
[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
[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

27 Feb, 2026 10 commits
- [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
- [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
- [Model Runner V2] Warmup kernels (#35172) · b1d9f537
  Nick Hill authored Feb 27, 2026
```
Signed-off-by: Nick Hill <nickhill123@gmail.com>
```
  b1d9f537
- [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
- [Core] Fix `gpu_worker.py` pre-commit errors (#35312) · 876312f0
  Nick Hill authored Feb 27, 2026
```
Signed-off-by: Nick Hill <nickhill123@gmail.com>
```
  876312f0
- [Bugfix] Fix DCP + FA3 crash due to missing num_splits in _forward_with_dcp (#35082) · 6d4f9d3a
  haosdent authored Feb 27, 2026
```
Signed-off-by: haosdent <haosdent@gmail.com>
```
  6d4f9d3a
- Flashinfer cuDNN backend for Qwen3 VL ViT attention (#34580) · 9c3fe993
  Max Hu authored Feb 27, 2026
```
Signed-off-by: Max Hu <maxhu@nvidia.com>
Signed-off-by: Max Hu <hyoung2991@gmail.com>
Co-authored-by: Max Hu <maxhu@nvidia.com>
Co-authored-by: Shang Wang <shangw@nvidia.com>
```
  9c3fe993
- [Misc] Move `GPUModelRunner.prepare_kernel_block_sizes` to utils (#35400) · cabdaa76
  Nicolò Lucchesi authored Feb 27, 2026
```
Signed-off-by: NickLucche <nlucches@redhat.com>
```
  cabdaa76
- [Core]Extract is_last_rank in Ray for tpu to override (#33012) · 06be5356
  Chenyaaang authored Feb 26, 2026
```
Signed-off-by: Chenyaaang <chenyangli@google.com>
```
  06be5356
- [Update] Use FlashInfer fast_decode_plan directly instead of replication (#34687) · 56a63717
  Andrii Skliar authored Feb 27, 2026
```
Signed-off-by: Andrii <askliar@nvidia.com>
Co-authored-by: Andrii <askliar@nvidia.com>
```
  56a63717
26 Feb, 2026 12 commits
- [Bugfix] Fix MessageQueue connect_ip for cross-node data parallelism (#35429) · 0f2f24c8
  Lucia Fang authored Feb 26, 2026
```
Signed-off-by: Lu Fang <fanglu@fb.com>
Co-authored-by: Lu Fang <30275821+houseroad@users.noreply.github.com>
```
  0f2f24c8
- [Performance] Extract KV cache update op from flashinfer forward (#35422) · 98217b09
  ElizaWszola authored Feb 26, 2026
```
Signed-off-by: ElizaWszola <ewszola@redhat.com>
```
  98217b09
- [Model Runner V2] Prepare attn metadata in ModelState [2/N] (#35383) · 3d66502e
  Woosuk Kwon authored Feb 26, 2026
```
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
```
  3d66502e
- [Model Runner V2] Add model states [1/N] (#35350) · c66aa48e
  Woosuk Kwon authored Feb 26, 2026
```
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
```
  c66aa48e
- [Model Runner V2] Fix error-handling (#35063) · b6d5a172
  Nick Hill authored Feb 26, 2026
```
Signed-off-by: Nick Hill <nickhill123@gmail.com>
```
  b6d5a172
- [Core] Support `min_tokens` with speculative decoding (#32642) · d9406076
  Yiliu Dong authored Feb 27, 2026
```
Signed-off-by: qianlihuang <yiliu.dong@qq.com>
Co-authored-by: qianlihuang <yiliu.dong@qq.com>
```
  d9406076
- [BugFix][kv_offload]: Fix kernel block size detection (#35125) · f2ad952f
  Or Ozeri authored Feb 26, 2026
```
Signed-off-by: Or Ozeri <oro@il.ibm.com>
```
  f2ad952f
- [Refactor] Remove dead or duplicate func utils or variables (#35318) · 05972ea7
  Wentao Ye authored Feb 26, 2026
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  05972ea7
- Remove `bc-lint` (#35274) · 01914445
  Harry Mellor authored Feb 26, 2026
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  01914445
- [Model Runner V2] Add coding style guide (#35325) · 13025e71
  Woosuk Kwon authored Feb 25, 2026
```
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
```
  13025e71
- [Bugfix] Fix AttributeError in SMControlContextManager (#35338) · 9511a3f8
  Lucas Wilkinson authored Feb 25, 2026
```
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
```
  9511a3f8
- [offloader] v2: Hide weight onloading latency via prefetching (#29941) · 6831650c
  Ming Yang authored Feb 25, 2026
```
Signed-off-by: Ming Yang <minos.future@gmail.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
```
  6831650c
25 Feb, 2026 5 commits
- [XPU]Support CUDAGraph on XPU Platform (#34482) · 35d44b45
  Xinyu Chen authored Feb 25, 2026
```
Signed-off-by: Xinyu Chen <xinyu1.chen@intel.com>
Co-authored-by: chzhang <chaojun.zhang@intel.com>
Co-authored-by: zhenwei-intel <zhenwei.liu@intel.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
```
  35d44b45
- [Platform] Add current_platform.num_compute_units interface (#35042) · 8ad54a99
  Kunshang Ji authored Feb 25, 2026
```
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
Signed-off-by: Kunshang Ji <jikunshang95@gmail.com>
```
  8ad54a99
- remove cuda check in `top_k_top_p_triton` kernel (#35011) · 92510edc
  Kunshang Ji authored Feb 25, 2026
```
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
```
  92510edc
- [Linear Attention] fix bug for linear attention + prefix caching + reset_prefix_cache (#35157) · 8fae54fa
  Chen Zhang authored Feb 24, 2026
```
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
```
  8fae54fa
- [Core] Cleanup engine pause/sleep logic (#34528) · dbf0da81
  Nick Hill authored Feb 24, 2026
```
Signed-off-by: Nick Hill <nickhill123@gmail.com>
```
  dbf0da81
24 Feb, 2026 6 commits

[Bug][DSV3.2] Always prepare metadata for DeepGEMM Sparse Attention (#35075) · 9fa5b25a
Benjamin Chislett authored Feb 24, 2026
```
Signed-off-by: Benjamin Chislett <bchislett@nvidia.com>
```
9fa5b25a

[Model][Spec Decode] Nemotron-H MTP and Mamba Speculative Decoding Support (#33726) · f5972a87

Benjamin Chislett authored Feb 24, 2026


Signed-off-by: Shahar Mor <smor@nvidia.com>
Signed-off-by: Benjamin Chislett <bchislett@nvidia.com>
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Shahar Mor <smor@nvidia.com>
Co-authored-by: Roi Koren <roik@nvidia.com>
Co-authored-by: Lucas Wilkinson <lwilkins@redhat.com>

f5972a87

[Perf] Optimize Python Slice for Structured Output using `islice` instead of [:] (#33593) · 9ce8fad2

Wentao Ye authored Feb 24, 2026

Signed-off-by: yewentao256 <zhyanwentao@126.com>
Signed-off-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

9ce8fad2

[CPU][Perf] Accelerate Attention head for s390x using vector intrinsics (#34434) · 34ce0ffd
R3hankhan authored Feb 24, 2026
```
Signed-off-by: Rehan Khan <Rehan.Khan7@ibm.com>
Co-authored-by: Li, Jiang <jiang1.li@intel.com>
```
34ce0ffd

[Attn,KV-cache] Use per-head scales in the attention selector (#34281) · a87cc508

Eldar Kurtić authored Feb 24, 2026


Signed-off-by: Your Name <you@example.com>
Signed-off-by: Eldar Kurtic <research@neuralmagic.com>
Co-authored-by: Eldar Kurtic <research@neuralmagic.com>
Co-authored-by: Your Name <you@example.com>

a87cc508

[Frontend] Always pass `supported_tasks` to validation (#35186) · 761e63e5
Cyrus Leung authored Feb 24, 2026
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
761e63e5