Commits · 987506bca63d95d9ff4ebb3a37e3f2447fa0757c · OpenDAS / vllm_cscc

"vscode:/vscode.git/clone" did not exist on "81c57f60a2c77d169dbec021bb58a467edf580f6"

23 Feb, 2026 3 commits
- [Refactor] Simplify dummy data generation (#35025) · 987506bc
  Cyrus Leung authored Feb 23, 2026
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  987506bc
- [Model Runner V2] Remove propose_draft method (#35070) · c645e9a2
  Woosuk Kwon authored Feb 22, 2026
```
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
```
  c645e9a2
- [Model Runner V2][Minor] Remove redundant `do_spec_decode` field (#35039) · 944ffb59
  Nick Hill authored Feb 22, 2026
```
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: Woosuk Kwon <woosuk@inferact.ai>
```
  944ffb59
22 Feb, 2026 11 commits
- [Spec Decode] Reduce TP communication for speculative decoding draft token generation (#34049) · 2bcf71b9
  qizixi authored Feb 22, 2026
```
Signed-off-by: qizixi <qizixi@meta.com>
Co-authored-by: Lu Fang <30275821+houseroad@users.noreply.github.com>
```
  2bcf71b9
- [Model] Add NVFP4 quantization support for Step3.5-Flash (#34478) · b7892a3b
  tacos8me authored Feb 22, 2026
```
Signed-off-by: tacos8me <ian@cloudhabit.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
```
  b7892a3b
- [Bug] Refactor max_num_batched_tokens to account for drafting (#34898) · 682566b1
  Benjamin Chislett authored Feb 22, 2026
```
Signed-off-by: Benjamin Chislett <bchislett@nvidia.com>
```
  682566b1
- [Spec Decode] Defer clearing KV connector metadata for EAGLE3 speculative... · b9c2a565
  qizixi authored Feb 22, 2026
```
[Spec Decode] Defer clearing KV connector metadata for EAGLE3 speculative decode + prefill / decode disagg setup (#34529)
Signed-off-by: qizixi <qizixi@meta.com>
Co-authored-by: Lu Fang <30275821+houseroad@users.noreply.github.com>
```
  b9c2a565
- [Bugfix] Fix Qwen3/Qwen3.5 Reasoning Parser (#34779) · 40f88d83
  Roger Wang authored Feb 21, 2026
```
Signed-off-by: Roger Wang <hey@rogerw.io>
```
  40f88d83
- [Model Runner V2] Enable CUDA graph for Eagle3 (#35040) · 2cbf9656
  Woosuk Kwon authored Feb 21, 2026
```
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
```
  2cbf9656
- Fix apply_top_k_top_p_triton called by non-cuda logits Tensor (#35030) · 30132cd1
  Xiao Li authored Feb 21, 2026
```
Signed-off-by: Xiao Li <ilx@meta.com>
```
  30132cd1
- [Benchmark] Use `sns.relplot` for plotting (#35027) · cbd95a2d
  Cyrus Leung authored Feb 22, 2026
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  cbd95a2d
- [New Model] Add ColModernVBERT (#34558) · 970861ac
  Athrael Soju authored Feb 22, 2026
```
Signed-off-by: Athrael Soju <athrael.soju@gmail.com>
Signed-off-by: athrael-soju <athrael-soju@users.noreply.github.com>
```
  970861ac
- [Model Runner V2] Support attention group (#35036) · b71fbd06
  Woosuk Kwon authored Feb 21, 2026
```
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
```
  b71fbd06
- [Model Bash][DSR1] Add selective dynamic shape marking for CustomOp (#34900) · 74d90b1c
  Vadim Gimpelson authored Feb 22, 2026
```
Signed-off-by: Vadim Gimpelson <vadim.gimpelson@gmail.com>
```
  74d90b1c
21 Feb, 2026 19 commits

[Model Runner V2] Support Eagle3 (no CUDA graph) (#35029) · a4047d4e
Woosuk Kwon authored Feb 21, 2026
```
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
```
a4047d4e

[Frontend] Add automatic language detection for Whisper transcription (#34342) · 98b0205c

Roman authored Feb 21, 2026


Signed-off-by: space_check <roman.vuskov@rwth-aachen.de>
Signed-off-by: Roman <45857014+spacecheck@users.noreply.github.com>
Co-authored-by: Nicolò Lucchesi <nicolo.lucchesi@gmail.com>
Co-authored-by: Nicolò Lucchesi <nlucches@redhat.com>

98b0205c

[Benchmark] Improve benchmarks (#35012) · f74f1572
Cyrus Leung authored Feb 21, 2026
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
f74f1572
[Core] Minor structured-output related scheduler optimization (#34765) · 820d7815
Nick Hill authored Feb 21, 2026
```
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
```
820d7815
[PD] Change kv_load_failure_policy Default from "recompute" to "fail" (#34896) · ab6f3487
Nicolò Lucchesi authored Feb 21, 2026
```
Signed-off-by: NickLucche <nlucches@redhat.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
```
ab6f3487
[ROCm] Enable bitsandbytes quantization support on ROCm (#34688) · 8dc8a99b
BADAOUI Abdennacer authored Feb 21, 2026
```
Signed-off-by: badaoui <abdennacerbadaoui0@gmail.com>
```
8dc8a99b
[ROCM] Optimize ROCM_AITER_FA spec decode eagle performance (#34541) · 2aab2bb5
jennyyyyzhen authored Feb 20, 2026
```
Signed-off-by: jennyyyyzhen <yzhen@hmc.edu>
```
2aab2bb5
[ROCm][AITER] Fix aiter paged_attention_v1 decode for sliding window and head_size < 64 (#34570) · cf93c1a1
Andreas Karatzas authored Feb 20, 2026
```
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
```
cf93c1a1

[feat] Add per-block extra_keys to KV events (#33304) · a0fe7ea2

zhongdaor-nv authored Feb 20, 2026


Signed-off-by: zhongdaor-nv <zhongdaor@nvidia.com>
Co-authored-by: Nicolò Lucchesi <nlucches@redhat.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>

a0fe7ea2

[CI][MCP][Harmony] Heavy refactoring Harmony & MCP response tests and... · 991d6bff

Andreas Karatzas authored Feb 20, 2026


[CI][MCP][Harmony] Heavy refactoring Harmony & MCP response tests and stabilizing with deterministic test infrastructure (#33949)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>

991d6bff

[Frontend] Support multimodal inputs for late-interaction scoring (ColQwen3) +... · 5719a4e4

Kata Coder authored Feb 21, 2026


[Frontend] Support multimodal inputs for late-interaction scoring (ColQwen3) + NewModel: nvidia/nemotron-colembed (#34574)
Signed-off-by: craftsangjae <craftsangjae@gmail.com>

5719a4e4

[Realtime] Add Qwen3-ASR realtime streaming support (#34613) · 11be2c74

pougetat authored Feb 20, 2026


Signed-off-by: Thomas Pouget-Abadie <thomaspou@microsoft.com>
Co-authored-by: Thomas Pouget-Abadie <thomaspou@microsoft.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: Nicolò Lucchesi <nlucches@redhat.com>

11be2c74

[Kernel] Optimize sample_recovered_tokens_kernel (#34974) · 7a5adad4
Xin Yang authored Feb 20, 2026
```
Signed-off-by: Xin Yang <xyangx@amazon.com>
```
7a5adad4
Support prompt_embeds for pooling requests in output processor (#34904) · 59c62332
Li authored Feb 20, 2026
```
Signed-off-by: Li Zhang <lzhanga@amazon.com>
Co-authored-by: Li Zhang <lzhanga@amazon.com>
```
59c62332
[Misc] Fix mypy errors in vllm/profiler and remove from exclude list (#34959) · d38cd3dd
Taneem Ibrahim authored Feb 20, 2026
```
Signed-off-by: Taneem Ibrahim <taneem.ibrahim@gmail.com>
```
d38cd3dd

[ROCm][Bugfix]: Only save unpadded sizes for shared_experts in MoERunner to... · ded333fb

Rohan Potdar authored Feb 20, 2026


[ROCm][Bugfix]: Only save unpadded sizes for shared_experts in MoERunner to fix rmsnorm pad fusion (#34636)
Signed-off-by: Rohan138 <rohanpotdar138@gmail.com>

ded333fb

[Kernel] [Helion] [9/N] Canonicalize GPU variant names to base model names (#34928) · 9d7577b2
Yanan Cao authored Feb 20, 2026
```
Signed-off-by: Yanan Cao <gmagogsfm@gmail.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
```
9d7577b2

[LoRA] Support Quantized Adapters (#30286) · a55caf6a

yugong333 authored Feb 20, 2026


Signed-off-by: Yu Gong <yu3.gong@gmail.com>
Signed-off-by: wz1qqx <ziqi.wang@novita.ai>
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: wz1qqx <55830058+wz1qqx@users.noreply.github.com>
Co-authored-by: wz1qqx <ziqi.wang@novita.ai>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>

a55caf6a

Revert "[Llama4,Quantization] Simplify and generalize logic for Q/K... · 0e22cd61
Lucas Wilkinson authored Feb 20, 2026
```
Revert "[Llama4,Quantization] Simplify and generalize logic for Q/K permutations in quantized self-attn layers " (#34997)
```
0e22cd61

20 Feb, 2026 7 commits
- Bump Flashinfer Version and Re-enable DeepSeek NVFP4 AR+Norm Fusion (#34899) · ea5f903f
  Wei Zhao authored Feb 20, 2026
```
Signed-off-by: wzhao18 <wzhao18.sz@gmail.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
```
  ea5f903f
- [CI] Revert PRs 34818 and 33600 (#34979) · aaefc58e
  Lucas Wilkinson authored Feb 20, 2026
  
  aaefc58e
- [compile] Fix torch.compile time discrepancy in logging. (#34912) · f8639940
  Zhengxu Chen authored Feb 20, 2026
```
Signed-off-by: zhxchen17 <zhxchen17@fb.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
```
  f8639940
- [compile] Move torch_aot_compile directory under torch_compile_cache (#34831) · e4a5d8c6
  Zhengxu Chen authored Feb 20, 2026
```
Signed-off-by: zhxchen17 <zhxchen17@fb.com>
```
  e4a5d8c6
- [Kernel] [Helion] [6/N] Add num_tokens dimension to silu_mul autotuning and dispatching (#34185) · a6d0299c
  Yanan Cao authored Feb 20, 2026
```
Signed-off-by: Yanan Cao <gmagogsfm@gmail.com>
```
  a6d0299c
- [perf] Avoid dtype promotion sync in mamba_get_block_table_tensor (#34870) · 1fe46216
  Huamin Li authored Feb 20, 2026
```
Signed-off-by: Huamin Li <3ericli@gmail.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
```
  1fe46216
- [Refactor] Extract Harmony streaming SSE event builders into streaming_events.py (#34909) · ed31a020
  Flora Feng authored Feb 20, 2026
```
Signed-off-by: sfeng33 <4florafeng@gmail.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
```
  ed31a020