Commits · 9db1db5949f7abd4b03cd0231450f81bfeeaba0f · OpenDAS / vllm_cscc · GitLab

17 Dec, 2025 12 commits
- [compile] Ignore VLLM_FORCE_AOT_LOAD from cache factors (#30809) · 9db1db59
  Zhengxu Chen authored Dec 17, 2025
```
Signed-off-by: zhxchen17 <zhxchen17@fb.com>
```
  9db1db59
- [compile] Disable aot when eager backend is used. (#30810) · 177c391d
  Zhengxu Chen authored Dec 17, 2025
```
Signed-off-by: zhxchen17 <zhxchen17@fb.com>
```
  177c391d
- [UX] Make `vllm bench serve` discover model by default and use --input-len (#30816) · 519ef9a9
  Michael Goin authored Dec 17, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  519ef9a9
- [Kernels][FI] Skip trtllm attention when num_kv_heads=1 (#30842) · a1001522
  Ye (Charlotte) Qi authored Dec 17, 2025
```
Signed-off-by: Ye (Charlotte) Qi <yeq@meta.com>
```
  a1001522
- [Doc][ResponsesAPI] add documentation (#30840) · 4c054d89
  Andrew Xia authored Dec 17, 2025
```
Signed-off-by: Andrew Xia <axia@fb.com>
Co-authored-by: Andrew Xia <axia@fb.com>
```
  4c054d89
- CustomOp: grouped topk (#29575) · 3b1d440e
  Xinyu Chen authored Dec 17, 2025
```
Signed-off-by: Xinyu Chen <xinyu1.chen@intel.com>
```
  3b1d440e
- [Mamba] Removed disable cascade attn in MambaModelConfig (#30712) · a9e15c21
  Asaf Joseph Gardin authored Dec 17, 2025
```
Signed-off-by: asafg <39553475+Josephasafg@users.noreply.github.com>
```
  a9e15c21
- [Bugfix][Frontend] Prevent IndexError in MiniMax M2 tool parser during... · 20fda431
  Robin authored Dec 17, 2025
```
[Bugfix][Frontend] Prevent IndexError in MiniMax M2 tool parser during streaming extraction (#30555)
Signed-off-by: WangErXiao <863579016@qq.com>
```
  20fda431
- [XPU] fix broken fp8 online quantization for XPU platform (#30831) · 4f735bab
  Yan Ma authored Dec 17, 2025
```
Signed-off-by: Yan Ma <yan.ma@intel.com>
```
  4f735bab
- [Bugfix][CPU] Fix CPU backend ROPE dispatch for VL models (#30829) · 0cd53536
  Li, Jiang authored Dec 17, 2025
```
Signed-off-by: jiang1.li <jiang1.li@intel.com>
Signed-off-by: Li, Jiang <bigpyj64@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
```
  0cd53536
- Update note comment for flashinfer attention warmup (#30711) · d4d27517
  Michael Goin authored Dec 17, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  d4d27517
- Fix nemotron_nas intermediate_size computation (#30795) · f5db6385
  Grzegorz K. Karch authored Dec 17, 2025
```
Signed-off-by: Grzegorz Karch <gkarch@nvidia.com>
```
  f5db6385
16 Dec, 2025 26 commits
- [MM] Pass FA version in ViT Attn (#30756) · e087fbc3
  Nicolò Lucchesi authored Dec 17, 2025
```
Signed-off-by: NickLucche <nlucches@redhat.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
```
  e087fbc3
- [ROCm] [Bugfix] Fix torch sdpa hallucination (#30789) · 2410132b
  TJian authored Dec 17, 2025
```
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
```
  2410132b
- [Kernel][Quantization][MoE] add marlin kernel support for turing (sm75) (#29901) · ce96857f
  Jinzhen Lin authored Dec 17, 2025
```
Signed-off-by: Jinzhen Lin <jinzhen.ljz@antgroup.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
```
  ce96857f
- [Core][MM] Optimize encoder cache manager by operating with embeddings only (#30475) · f5f51e59
  Roger Wang authored Dec 16, 2025
```
Signed-off-by: Roger Wang <hey@rogerw.io>
Co-authored-by: Sun Kim <sunytokki@gmail.com>
```
  f5f51e59
- [Attention] Cache attention metadata builds across hybrid KV-cache groups (#29627) · 9fec0e13
  Lucas Wilkinson authored Dec 16, 2025
```
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Stanislaw Wozniak <stw@zurich.ibm.com>
```
  9fec0e13
- [Perf] Do FP4 quant before All gather on flashinfer trtllmgen MOE (#30014) · 254a7f8f
  jiahanc authored Dec 16, 2025
```
Signed-off-by: jiahanc <173873397+jiahanc@users.noreply.github.com>
```
  254a7f8f
- [Frontend] Add `max-completion-token` option to transcription/translation endpoints (#30769) · ca702a14
  Nicolò Lucchesi authored Dec 16, 2025
```
Signed-off-by: NickLucche <nlucches@redhat.com>
```
  ca702a14
- [CI] Generalize gsm8k test args and add Qwen3-Next MTP B200 test (#30723) · 10ee1c64
  Michael Goin authored Dec 16, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  10ee1c64
- [Docs][API] Remove warning about LoRARequest being internal-only (#30774) · 66c3537e
  Mark McLoughlin authored Dec 16, 2025
```
Signed-off-by: Mark McLoughlin <markmc@redhat.com>
```
  66c3537e
- Update where `bytes_to_unicode` is imported from (#30771) · e1625498
  Harry Mellor authored Dec 16, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  e1625498
- Remove `head_mask` from Ultravox and Swin (#30764) · 0b0acc75
  Harry Mellor authored Dec 16, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  0b0acc75
- [TRTLLM] Remove the MoE GEMM weight name change (#30713) · ce12b407
  Ming Yang authored Dec 16, 2025
```
Signed-off-by: Ming Yang <minos.future@gmail.com>
```
  ce12b407
- [Feat] Enable eplb with default all2all backend (#30559) · 59bd5f6a
  Wentao Ye authored Dec 16, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  59bd5f6a
- [BugFix] Fix memory spike in workspace allocation (#30744) · 00a8d762
  Lucas Wilkinson authored Dec 16, 2025
```
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
```
  00a8d762
- [Bugfix] Whisper fix number of allocated CrossAttn blocks per-request (#30772) · 75eb302a
  Nicolò Lucchesi authored Dec 16, 2025
```
Signed-off-by: NickLucche <nlucches@redhat.com>
```
  75eb302a
- [ROCm][MTP] Support MTP for AITER MLA backend (#28624) · 9dbbc59b
  Pleaplusone authored Dec 16, 2025
```
Signed-off-by: ganyi <ygan@amd.com>
```
  9dbbc59b
- update piecewise cudagraph warning when splitting_ops=[] (#30728) · 104003dc
  Boyuan Feng authored Dec 16, 2025
```
Signed-off-by: Boyuan Feng <boyuan@meta.com>
```
  104003dc
- [ROCm] [AITER] [DOC] Add usage description about check functions in `_aiter_ops` (#30586) · d0fb5729
  TJian authored Dec 16, 2025
```
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
```
  d0fb5729
- Don'e assume `position_embedding_type` will be present for BERT and RoBERTa models (#30770) · 6f15ac5d
  Harry Mellor authored Dec 16, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  6f15ac5d
- [Bugfix] Fix prefix_repetition routing in bench throughput (#29663) · 676db55e
  Junru Shen authored Dec 16, 2025
```
Signed-off-by: Junru Shen <jrshen.sjr@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
```
  676db55e
- [Bugfix] Fix RequestOutput miss lora_request (#30636) · 0e391e75
  Jee Jee Li authored Dec 16, 2025
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  0e391e75
- [responsesAPI][8] input/output messages for ResponsesParser (#30158) · 0d0c929f
  Andrew Xia authored Dec 16, 2025
```
Signed-off-by: Andrew Xia <axia@fb.com>
Signed-off-by: Andrew Xia <axia@meta.com>
Co-authored-by: Andrew Xia <axia@fb.com>
Co-authored-by: Chauncey <chaunceyjiang@gmail.com>
```
  0d0c929f
- [Bugfix] Fix broken ViT attention selection for Blackwell device (#30731) · e94384bb
  Isotr0py authored Dec 16, 2025
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  e94384bb
- [feature] extend DBO to XBO (#30120) · b9ff4f2a
  jiangkuaixue123 authored Dec 16, 2025
```
Signed-off-by: jiangkuaixue123 <jiangxiaozhou111@163.com>
Co-authored-by: root <root@hk01dgx028.cm.cluster>
```
  b9ff4f2a
- [CustomOp] Extract ApplyRotaryEmb as CustomOp and unify the dispatch logic (#29873) · 3bd9c491
  Shanshan Shen authored Dec 16, 2025
```
Signed-off-by: shen-shanshan <467638484@qq.com>
Co-authored-by: gcanlin <canlinguosdu@gmail.com>
Co-authored-by: TJian <tunjian.tan@embeddedllm.com>
```
  3bd9c491
- [Bugfix] fix streaming final output for non harmony (#30237) · bbd850e5
  penfree authored Dec 16, 2025
```
Signed-off-by: penfree <qiupengfei@baidu.com>
Co-authored-by: penfree <qiupengfei@baidu.com>
```
  bbd850e5
15 Dec, 2025 2 commits
- [UX][Attention] Add `attention_config` argument to `LLM()` (#30710) · a182be43
  Matthew Bonanni authored Dec 15, 2025
```
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
```
  a182be43
- Update batch invariant to use attention config (#30704) · 60dbf7d8
  Matthew Bonanni authored Dec 15, 2025
```
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
```
  60dbf7d8