Commits · 2e6bc4682181b2124beb71fc532cc12187cbceea · OpenDAS / vllm_cscc

11 Sep, 2025 9 commits
- [CI/Build] Add bc-linter to vLLM CI (#21234) · 7d465199
  Zhewen Li authored Sep 11, 2025
```
Signed-off-by: zhewenli <zhewenli@meta.com>
```
  7d465199
- [flashinfer] [kernel] support for fp8 kv cache for trtllm prefill attention (#24197) · e42af78b
  Xiaozhu Meng authored Sep 11, 2025
```
Signed-off-by: Xiaozhu <mxz297@gmail.com>
```
  e42af78b
- Update Spec Decode metrics to include drafted and accepted token throughput (#24127) · 79ac59f3
  Andrew Xia authored Sep 11, 2025
```
Signed-off-by: Andrew Xia <axia@meta.com>
```
  79ac59f3
- fix some typos (#24616) · e26fef83
  co63oc authored Sep 12, 2025
```
Signed-off-by: co63oc <co63oc@users.noreply.github.com>
```
  e26fef83
- Allow users to specify kv cache memory size (#21489) · 94e6b2d5
  Boyuan Feng authored Sep 11, 2025
```
Signed-off-by: Boyuan Feng <boyuan@meta.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  94e6b2d5
- Move `LoRAConfig` from `config/__init__.py` to `config/lora.py` (#24644) · 5f5271f1
  Harry Mellor authored Sep 11, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  5f5271f1
- Add the support for the qwen3 next model (a hybrid attention model). (#24526) · e93f4cc9
  Tao He authored Sep 11, 2025
```
Signed-off-by: Tao He <linzhu.ht@alibaba-inc.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
```
  e93f4cc9
- [Doc]: fixing doc typos (#24635) · e2b1f863
  Didier Durand authored Sep 11, 2025
```
Signed-off-by: Didier Durand <durand.didier@gmail.com>
```
  e2b1f863
- [BugFix] Fix pipeline parallel (#24621) · e2d8c27f
  Nick Hill authored Sep 10, 2025
```
Signed-off-by: Nick Hill <nhill@redhat.com>
```
  e2d8c27f
10 Sep, 2025 14 commits
- [Kernel] Flashinfer MLA (trtllm-gen) decode kernel integration (#21078) · dcb28a33
  Hanjie Qiu authored Sep 10, 2025
```
Signed-off-by: hjjq <hanjieq@nvidia.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
```
  dcb28a33
- [Perf] Warmup FlashInfer attention during startup (#23439) · fba78565
  Michael Goin authored Sep 10, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Signed-off-by: Luka Govedič <lgovedic@redhat.com>
Co-authored-by: Luka Govedič <lgovedic@redhat.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Co-authored-by: Matthew Bonanni <mbonanni001@gmail.com>
```
  fba78565
- [gpt-oss] raise error for flashinfer backend without trtllm (#24482) · b5e383cd
  Chen Zhang authored Sep 10, 2025
```
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
```
  b5e383cd
- [torch.compile][ROCm][V1] Enable attention output FP8 fusion for V1 attention backends (#19767) · 9a161307
  Gregory Shtrasberg authored Sep 10, 2025
```
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
Signed-off-by: Luka Govedič <lgovedic@redhat.com>
Co-authored-by: Luka Govedič <lgovedic@redhat.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
```
  9a161307
- [v1] Add Whisper model support (encoder-decoder) (#21088) · 37e8182b
  Russell Bryant authored Sep 10, 2025
```
Signed-off-by: Russell Bryant <rbryant@redhat.com>
Co-authored-by: NickLucche <nlucches@redhat.com>
```
  37e8182b
- [Bugfix] Enable FP8 KV cache for FlashInfer and Triton backend on non-sm100 GPUs (#24577) · a0933c3b
  Thien Tran authored Sep 11, 2025
```
Signed-off-by: Thien Tran <gau.nernst@yahoo.com.sg>
```
  a0933c3b
- fix some typos (#24167) · 3144d902
  co63oc authored Sep 10, 2025
```
Signed-off-by: co63oc <co63oc@users.noreply.github.com>
Co-authored-by: Russell Bryant <rbryant@redhat.com>
```
  3144d902
- [BugFix] Ensure integrity of reused CPU tensors during async scheduling (#24527) · f4f1a8df
  Nick Hill authored Sep 10, 2025
```
Signed-off-by: Nick Hill <nhill@redhat.com>
Co-authored-by: guoze.lin <guozelin@tencent.com>
```
  f4f1a8df
- [Attention] add DCP support for FLASH_ATTN_MLA backend (#24453) · 0ae43dbf
  Lucas Wilkinson authored Sep 10, 2025
```
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: Matthew Bonanni <mbonanni@redhat.com>
```
  0ae43dbf
- [Bugfix] Guard `_may_reorder_batch` for encoder-only models on CPU (#24319) (#24348) · feaf202e
  Remy authored Sep 10, 2025
```
Signed-off-by: Remy <eunhwan.shin@dtonic.io>
Co-authored-by: Li, Jiang <jiang1.li@intel.com>
```
  feaf202e
- [Core] Simplify and unify mm uuid handling & auto-generated mm hash overrides processing. (#24271) · 009d689b
  Chenheli Hua authored Sep 09, 2025
```
Signed-off-by: Chenheli Hua <huachenheli@outlook.com>
```
  009d689b
- [KV Connector] More async support for `get_num_new_matched_tokens` (#23620) · b4a01aaf
  Yihua Cheng authored Sep 09, 2025
```
Signed-off-by: ApostaC <yihua98@uchicago.edu>
```
  b4a01aaf
- [BugFix] Fix async core engine client finalizer (#24540) · f88e8401
  Nick Hill authored Sep 09, 2025
```
Signed-off-by: Nick Hill <nhill@redhat.com>
```
  f88e8401
- [Perf] Convert np array to torch tensor to index into block table for attn chunking (#24474) · dc625ea6
  Yong Hoon Shin authored Sep 09, 2025
```
Signed-off-by: Yong Hoon Shin <yhshin@meta.com>
```
  dc625ea6
09 Sep, 2025 7 commits
- [Feature] Disallow FlashMLA on Blackwell (#24521) · 15de5ff9
  Wentao Ye authored Sep 09, 2025
```
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>
```
  15de5ff9
- [TPU] Fix tpu structured decoding in mixed batches (#24458) · c3f9773b
  Chenyaaang authored Sep 09, 2025
```
Signed-off-by: Chenyaaang <chenyangli@google.com>
```
  c3f9773b
- [Core] Run garbage collector after CUDA graph capture to fix throughput regression (#24128) · 1c63a16b
  Micah Williamson authored Sep 09, 2025
```
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
Co-authored-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
```
  1c63a16b
- [Bugfix] Handle the edge case in detokenizer where processed tokens contain... · 922d3b40
  d.transposed authored Sep 09, 2025
```
[Bugfix] Handle the edge case in detokenizer where processed tokens contain both `stop` str and `eos` token (#23938)
Signed-off-by: dtransposed <damian.bogunowicz@gmail.com>
```
  922d3b40
- [Misc] Improve Worker process title and logging prefix (#22205) · 0cdd2136
  22quinn authored Sep 08, 2025
```
Signed-off-by: 22quinn <33176974+22quinn@users.noreply.github.com>
```
  0cdd2136
- [Core] Use sha256 bytes instead of BlockHash to reduce GC overhead (#23673) · 82dfb12e
  Zebing Lin authored Sep 09, 2025
```
Signed-off-by: linzebing <linzebing1995@gmail.com>
```
  82dfb12e
- [Flashinfer] Support Flashinfer TRTLLM FP8-qkv BF16/FP16-out Attention Kernel (#23647) · bba1042c
  elvischenv authored Sep 09, 2025
```
Signed-off-by: elvischenv <219235043+elvischenv@users.noreply.github.com>
```
  bba1042c
08 Sep, 2025 7 commits

[Bugfix] Disable the statslogger if the api_server_count is greater than 1 (#22227) · e680723e
Chauncey authored Sep 09, 2025
```
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
Co-authored-by: Nick Hill <nhill@redhat.com>
```
e680723e

[Attention] FlashAttention MLA cudagraph support (#23958) · 620db1fc

Matthew Bonanni authored Sep 08, 2025


Signed-off-by: Matthew Bonanni <mbonanni001@gmail.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>

620db1fc

[Bugfix] Fix mamba2 prefill chunking (#23279) · e0413141

tomeras91 authored Sep 08, 2025

Signed-off-by: Tomer Asida <57313761+tomeras91@users.noreply.github.com>
Signed-off-by: tomeras91 <57313761+tomeras91@users.noreply.github.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

e0413141

[Doc]: fix typos in Python comments (#24417) · f4962a6d
Didier Durand authored Sep 08, 2025
```
Signed-off-by: Didier Durand <durand.didier@gmail.com>
```
f4962a6d
[P/D] Add a shutdown method to the Connector API (#22699) · 61aa4b29
Chauncey authored Sep 08, 2025
```
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
```
61aa4b29

[Sampler] Support returning all prompt logprobs (#23868) · b3d7e3c8

Xingyu Liu authored Sep 07, 2025


Signed-off-by: Xingyu Liu <charlotteliu12x@gmail.com>
Co-authored-by: 22quinn <33176974+22quinn@users.noreply.github.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>

b3d7e3c8

[Kernel] Support decode context parallelism on Blackwell with CUTLASS MLA (#24385) · 86173ad5

Ming Yang authored Sep 07, 2025


Signed-off-by: Ming Yang <minos.future@gmail.com>
Signed-off-by: youkaichao <youkaichao@gmail.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>

86173ad5

07 Sep, 2025 3 commits
- Skip MM Encoder for non-first PP ranks (#24387) · 2e5d2137
  Woosuk Kwon authored Sep 07, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  2e5d2137
- [TPU] Remove TopKTopPSampler dependency for TPU sampler (#24391) · 105d3d62
  Woosuk Kwon authored Sep 07, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  105d3d62
- [attention][DCP] use AttentionImpl.need_to_return_lse_for_decode (#24372) · 558f0907
  youkaichao authored Sep 07, 2025
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
  558f0907