Commits · 62b1bbe470ea820b728cf2b6eee4f5f8b9655a57 · OpenDAS / vllm_cscc

"vllm/vscode:/vscode.git/clone" did not exist on "f34410715f9758a2ee2d45acd56179f9c1c06fc3"

23 Apr, 2026 3 commits

[Spec Decode] Move `SpecDecodeBaseProposer` out of `eagle.py` (#40732) · cde8d247
Matthew Bonanni authored Apr 23, 2026
```
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
```
cde8d247

[Bugfix] Fix workspace resize leaking reserved GPU memory (#39226) · 7ff65b19

czhu-cohere authored Apr 23, 2026


Signed-off-by: root <conway.zhu@cohere.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>

7ff65b19

[Bugfix] Make Attention Backend Auto-Selection Batch-Invariance-Aware (#40193) · b7a26050

Srreyansh Sethi authored Apr 23, 2026


Signed-off-by: Srreyansh Sethi <srreyansh.sethi@gmail.com>
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>

b7a26050

22 Apr, 2026 2 commits

[Refactor] Clean up log once `scope="local"` (#40540) · 8f87eb46

Wentao Ye authored Apr 22, 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>

8f87eb46

[Bugfix] LoRA for DeepSeek V3.2 (#35077) · a250f1bd

ℍ𝕠𝕝𝕝𝕠𝕨 𝕄𝕒𝕟 authored Apr 22, 2026


Signed-off-by: Hollow Man <hollowman@opensuse.org>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>

a250f1bd

21 Apr, 2026 5 commits

[Startup][UX] Enable CUDAGraph memory profiling by default (#38284) · 96a85c57
Matthew Bonanni authored Apr 21, 2026
```
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
```
96a85c57

[MRv2]fix: model accuracy regression caused by reusing the stale... · 9a6a66f3

Zijing Liu authored Apr 21, 2026


[MRv2]fix: model accuracy regression caused by reusing the stale last_sampled_tokens and draft_tokens (#39833)
Signed-off-by: Zijing Liu <liuzijing2014@gmail.com>

9a6a66f3

[Model Runner V2] Multiple prompt logprobs support (#39937) · 66cc3fa5

Wentao Ye authored Apr 21, 2026


Signed-off-by: yewentao256 <zhyanwentao@126.com>
Signed-off-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>

66cc3fa5

[UX] Bump version in CG memory profiling log message (#40465) · ab5666eb
Matthew Bonanni authored Apr 21, 2026
```
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
```
ab5666eb

[MM][CG] Optimize default `max_frames_per_batch` auto-infer for ViT CUDA graph... · 936e0b79

Shanshan Shen authored Apr 21, 2026


[MM][CG] Optimize default `max_frames_per_batch` auto-infer for ViT CUDA graph video inference (#40445)
Signed-off-by: shen-shanshan <467638484@qq.com>

936e0b79

20 Apr, 2026 4 commits
- [Misc][UX] Suppress confusing `num_gpu_blocks` log lines (#40402) · c075702e
  Matthew Bonanni authored Apr 20, 2026
```
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
```
  c075702e
- [Bug] Fix dcp error message (#40053) · b42e878e
  Wentao Ye authored Apr 20, 2026
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  b42e878e
- [EPLB] Add nixl-based eplb communicator (#36276) · 50dd4cb4
  Ilya Markov authored Apr 20, 2026
```
Signed-off-by: ilmarkov <markovilya197@gmail.com>
Signed-off-by: Markov Ilya <markovilya19@gmail.com>
```
  50dd4cb4
- [XPU] [torch.compile] Skipping CUDA graph memory estimation to avoid startup errors. (#39977) · 4f4713f9
  Chaojun Zhang authored Apr 20, 2026
```
Signed-off-by: chaojun-zhang <chaojun.zhang@intel.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
```
  4f4713f9
17 Apr, 2026 2 commits
- [Bugfix][Core] Fix stuck chunked pipeline parallelism with async scheduling (#38726) · 747256bb
  Jing Wang authored Apr 18, 2026
```
Signed-off-by: Jing Wang <jingwang96@qq.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
```
  747256bb
- [CPU] Refactor CPU affinity and memory management (#39781) · d02421a7
  Li, Jiang authored Apr 17, 2026
```
Signed-off-by: jiang1.li <jiang1.li@intel.com>
```
  d02421a7
16 Apr, 2026 2 commits
- Gate SSU dispatch setup (#40039) · b897f00c
  roikoren755 authored Apr 16, 2026
```
Signed-off-by: Roi Koren <roik@nvidia.com>
```
  b897f00c
- [Model Runner V2][BugFix] fix num_sampled dtype for probabilistic rej… (#39951) · 343f6523
  Giancarlo Delfin authored Apr 15, 2026
```
Signed-off-by: Giancarlo Delfin <gdelfin@inferact.ai>
```
  343f6523
15 Apr, 2026 2 commits
- [Attention Backend] TurboQuant: 2-bit KV cache compression with 4x capacity (#38479) · f4b42df0
  Vibhav Agarwal authored Apr 15, 2026
```
Signed-off-by: vibhavagarwal5 <vibhavagarwal5@gmail.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Xinyu Chen <xinyu1.chen@intel.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
```
  f4b42df0
- [Model Runner V2] Disable piecewise cudagraph mode fallback for eagle draft decodes (#39773) · 3bfe55a0
  Giancarlo Delfin authored Apr 14, 2026
```
Signed-off-by: Giancarlo Delfin <gdelfin@inferact.ai>
```
  3bfe55a0
14 Apr, 2026 4 commits
- [Hybrid] Simplify accepted token counting in spec decode for hybrid models (#38372) · 507df79a
  Francesco Fusco authored Apr 15, 2026
  
  507df79a
- [Mamba] Flashinfer selective_state_update (#36162) · ecf5ff7c
  roikoren755 authored Apr 14, 2026
```
Signed-off-by: Roi Koren <roik@nvidia.com>
```
  ecf5ff7c
- Measure encoder compile time seperate from llm backbone (#39240) · c08f3b2a
  Lucas Kabela authored Apr 14, 2026
```
Signed-off-by: Lucas Kabela <lucaskabela@meta.com>
```
  c08f3b2a
- [MM][Perf][CG] Support ViT full CUDA graph for Qwen3-VL video inference (#38061) · 80118853
  Shanshan Shen authored Apr 14, 2026
```
Signed-off-by: shen-shanshan <467638484@qq.com>
Signed-off-by: Shanshan Shen <87969357+shen-shanshan@users.noreply.github.com>
Co-authored-by: Roger Wang <hey@rogerw.io>
```
  80118853
13 Apr, 2026 1 commit
- [Model Runner V2] Add full cuda graph support for eagle prefill (#37588) · ccf90ba7
  Giancarlo Delfin authored Apr 13, 2026
```
Signed-off-by: Giancarlo Delfin <gdelfin@inferact.ai>
```
  ccf90ba7
10 Apr, 2026 6 commits
- [Model Runner V2] support auto resolve cudagraph mode/sizes based on attn backend (#32936) · 8f121f78
  zhrrr authored Apr 10, 2026
```
Signed-off-by: zhuhaoran <zhuhaoran.zhr@alibaba-inc.com>
```
  8f121f78
- [Model] Implement LoRA support for Qwen3ASRForConditionalGeneration (#37247) · 8d0f908b
  Peter Nguyen authored Apr 10, 2026
```
Signed-off-by: Peter Nguyen <petern0408@gmail.com>
```
  8d0f908b
- [Bugfix] Fix V1 dummy run writing NaN to KV cache null block (#39444) · ad720aef
  Elvir Crnčević authored Apr 10, 2026
```
Signed-off-by: Elvir Crncevic <elvircrn@gmail.com>
Co-authored-by: Claude Sonnet 4 <noreply@anthropic.com>
```
  ad720aef
- [Perf] Reduce H2D pageable memory copies (#38794) · 49d20346
  jackwang2120 authored Apr 10, 2026
```
Signed-off-by: jackcfwang <jackcfwang@tencent.com>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  49d20346
- [feat]: make DCP error msg clearer (#28443) · 3dd60971
  Srreyansh Sethi authored Apr 09, 2026
```
Signed-off-by: vnadathur <glvikramn@gmail.com>
Signed-off-by: WorldExplored <srreyansh.sethi@gmail.com>
Signed-off-by: Srreyansh Sethi <107075589+WorldExplored@users.noreply.github.com>
Co-authored-by: vnadathur <glvikramn@gmail.com>
Co-authored-by: vnadathur <236933696+vnadathur@users.noreply.github.com>
```
  3dd60971
- feat(cpu): add CPU support for draft model speculative decoding (#32662) · 445a2a4d
  Ganesh R authored Apr 10, 2026
```
Signed-off-by: R <Ganesh.R@amd.com>
```
  445a2a4d
09 Apr, 2026 4 commits
- [XPU] check is_xccl_available before oneccl warmup (#39302) · a8134aef
  Xinyu Chen authored Apr 10, 2026
```
Signed-off-by: Xinyu Chen <xinyu1.chen@intel.com>
```
  a8134aef
- [Perf] Optimize redundant sync for pooling model, 3.7% Throughput Improvement (#39113) · ed2f282b
  Wentao Ye authored Apr 09, 2026
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  ed2f282b
- [Bugfix] Fix cpu-offload-gb assertion with non-default block sizes (#36461) · 2f41d6c0
  Ajay Anubolu authored Apr 08, 2026
```
Signed-off-by: AjAnubolu <anuboluajay@gmail.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
```
  2f41d6c0
- [UX] Integrate DeepGEMM into vLLM wheel via CMake (#37980) · eb4205fe
  Michael Goin authored Apr 09, 2026
```
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>
```
  eb4205fe
08 Apr, 2026 3 commits
- [torch.compile] Allow usage of Opaque Objects in PyTorch 2.11 (#39286) · ba4a78eb
  Richard Zou authored Apr 09, 2026
```
Signed-off-by: Richard Zou <zou3519@gmail.com>
```
  ba4a78eb
- [Bugfix] Cuda Clean up scales Kvcache fp8/int8_per_token_head (#39224) · 140cbb11
  JartX authored Apr 08, 2026
```
Signed-off-by: JartX <sagformas@epdcenter.es>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
```
  140cbb11
- [Model Runner V2] Fuse probabilistic rejection sample kernels (#38496) · 5daf6227
  Giancarlo Delfin authored Apr 07, 2026
```
Signed-off-by: Giancarlo Delfin <gdelfin@inferact.ai>
```
  5daf6227
07 Apr, 2026 1 commit
- [BugFix][MRV2] Fix cuda event reuse race (#39115) · 62095e82
  Nick Hill authored Apr 06, 2026
```
Signed-off-by: Nick Hill <nickhill123@gmail.com>
```
  62095e82
06 Apr, 2026 1 commit
- [MRV2] Fix hanging issue with DeepSeek V3.2 by setting `skip_attn=False` (#39098) · f186cfe7
  Woosuk Kwon authored Apr 06, 2026
```
Signed-off-by: WoosukKwon <woosuk.kwon@berkeley.edu>
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
```
  f186cfe7