Commits · 9f2fc16a6903f8988515ce2560d3ef0850809c42 · OpenDAS / vllm_cscc · GitLab

12 Dec, 2025 5 commits
- [Bugfix][Model] Fix Afmoe rope_parameters issue (#30505) · 9f2fc16a
  Michael Goin authored Dec 11, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  9f2fc16a
- gptq marlin quantization support for fused moe with lora (#30254) · 6a6fc41c
  Bhanu Prakash Voutharoja authored Dec 12, 2025
```
Signed-off-by: Bhanu068 <voutharoja.bhanu06@gmail.com>
```
  6a6fc41c
- [CPU][FIX] Fix build failures on Arm CPUs with torch nightly (#30481) · f355ad54
  Fadi Arafeh authored Dec 12, 2025
```
Signed-off-by: Fadi Arafeh <fadi.arafeh@arm.com>
```
  f355ad54
- [Core] Refactor `_build_attention_metadata` (#29628) · 042da732
  Lucas Wilkinson authored Dec 11, 2025
```
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
```
  042da732
- [fix] fix SM check for Flashinfer TRTLLM MOE (#30314) · 0ab23c2b
  jiahanc authored Dec 11, 2025
```
Signed-off-by: jiahanc <173873397+jiahanc@users.noreply.github.com>
```
  0ab23c2b
11 Dec, 2025 30 commits
- [EPLB] Support EPLB w/ NVFP4 (#29804) · a00d8897
  Andrew Briand authored Dec 11, 2025
```
Signed-off-by: Andrew Briand <abriand@nvidia.com>
Co-authored-by: Andrew Briand <abriand@nvidia.com>
```
  a00d8897
- [Perf] Optimize deepgemm experts initialization, 3.9% TTFT improvement (#30494) · c817b141
  Wentao Ye authored Dec 11, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Co-authored-by: li-jinpeng <3332126450@qq.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>
```
  c817b141
- [Core] Whisper Enable Encoder Batching (#29421) · 0efd9f86
  Nicolò Lucchesi authored Dec 11, 2025
```
Signed-off-by: NickLucche <nlucches@redhat.com>
```
  0efd9f86
- [BugFix][MM]support VLLM_RANDOMIZE_DP_DUMMY_INPUTS (#30472) · 90d6cf92
  Xingyu Liu authored Dec 11, 2025
```
Signed-off-by: Xingyu Liu <charlotteliu12x@gmail.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
```
  90d6cf92
- Standardise `get_rope` to use `rope_parameters["partial_rotary_factor"]`, not `rotary_dim` (#30389) · cf3eacfe
  Harry Mellor authored Dec 11, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  cf3eacfe
- [compile] Stop one-off setting enable_aot_compile and use context manager instead. (#30503) · 92fea56f
  Zhengxu Chen authored Dec 11, 2025
```
Signed-off-by: zhxchen17 <zhxchen17@fb.com>
```
  92fea56f
- [ROCm][Bugfix] Add MLACommonMetadata to allowed attention types for speculative decoding (#30430) · 72aaac5b
  Andreas Karatzas authored Dec 11, 2025
```
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
```
  72aaac5b
- [Feature] AWQ marlin quantization support for fused moe with lora (#30442) · 0e71eaa6
  汪志鹏 authored Dec 12, 2025
```
Signed-off-by: princepride <wangzhipeng628@gmail.com>
```
  0e71eaa6
- Add Eagle and Eagle3 support to Transformers modeling backend (#30340) · 8781cd6b
  Harry Mellor authored Dec 11, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  8781cd6b
- [IMPROVEMENT] Change MistralReasoningParser behavior (#30391) · aa3c250c
  Julien Denize authored Dec 11, 2025
```
Signed-off-by: juliendenize <julien.denize@mistral.ai>
Signed-off-by: Julien Denize <40604584+juliendenize@users.noreply.github.com>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
```
  aa3c250c
- Give pooling examples better names (#30488) · 93db3256
  Harry Mellor authored Dec 11, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  93db3256
- Make the `httpx` logger less annoying when Transformers v5 is installed (#30480) · 97a042f3
  Harry Mellor authored Dec 11, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  97a042f3
- [Misc] Improve error message for `is_multimodal` (#30483) · 3a3b06ee
  Cyrus Leung authored Dec 11, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  3a3b06ee
- [KVConnector] Add KV events to KV Connectors (#28309) · f4417f84
  Martin Hickey authored Dec 11, 2025
```
Signed-off-by: Martin Hickey <martin.hickey@ie.ibm.com>
```
  f4417f84
- [Misc][PCP&DCP] relocate PCP feature check (#30050) · a11f4a81
  Qiu authored Dec 11, 2025
```
Signed-off-by: QiuChunshuo <qiuchunshuo@huawei.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
```
  a11f4a81
- Fix typo of endpoint name in CLI args docs (#30473) · 853611bb
  Kenichi Maehashi authored Dec 11, 2025
```
Signed-off-by: Kenichi Maehashi <maehashi@preferred.jp>
```
  853611bb
- [Deprecation] Deprecation `--convert reward`, use `--convert embed` instead. (#30463) · a5f9fb59
  wang.yuqi authored Dec 11, 2025
```
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
```
  a5f9fb59
- [Fix] Update lazing loading of video loader backend (#30444) · 4515eb1a
  jeremyteboul authored Dec 11, 2025
```
Signed-off-by: Jeremy Teboul <jeremyteboul@fb.com>
Co-authored-by: Jeremy Teboul <jeremyteboul@fb.com>
```
  4515eb1a
- [Deprecation] Remove missed fallback for `embed_input_ids` (#30469) · 13d63b65
  Cyrus Leung authored Dec 11, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  13d63b65
- [bugfix] fix MiniMaxM2ReasoningParser streaming output not separating reasoning_content. (#29882) · 6299628d
  Rei. authored Dec 11, 2025
```
Signed-off-by: Rei <1477174254@qq.com>
```
  6299628d
- [perf] Use direct copy (broadcast) instead of cat for k_nope/k_pe in MLA prefill (#29710) · fba89069
  Ming Yang authored Dec 11, 2025
```
Signed-off-by: Ming Yang <minos.future@gmail.com>
```
  fba89069
- fix: enhance human_readable_int function (#30337) · d02d1043
  Ning Xie authored Dec 11, 2025
```
Signed-off-by: Andy Xie <andy.xning@gmail.com>
```
  d02d1043
- [Deprecation] Remove fallbacks for `embed_input_ids` and `embed_multimodal` (#30458) · 979f50ef
  Cyrus Leung authored Dec 11, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  979f50ef
- Ensure minimum frames for GLM 4.6V compatibility (#30285) · 36c9ce25
  gh-wf authored Dec 11, 2025
```
Signed-off-by: Wayne Ferguson <wayneferguson@gmail.com>
```
  36c9ce25
- [Chore] Fix torch precision warning (#30428) · d6464f26
  Wentao Ye authored Dec 10, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  d6464f26
- [Deprecation] Remove deprecated task, seed and MM settings (#30397) · 7e24e5d4
  Cyrus Leung authored Dec 11, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  7e24e5d4
- [Deprecation] Remove deprecated plugin and compilation fields for v0.13 release (#30396) · 5a87d8b9
  Cyrus Leung authored Dec 11, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  5a87d8b9
- [Bugfix] Fix grouped_topk pytorch impl when num_experts can't be grouped properly (#29439) · d1e1fb43
  Divakar Verma authored Dec 10, 2025
```
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
Co-authored-by: Gregory Shtrasberg <156009573+gshtras@users.noreply.github.com>
Co-authored-by: TJian <tunjian.tan@embeddedllm.com>
```
  d1e1fb43
- [ROCm] Fix broken import in platform attention backend dispatching (#30432) · b51255f3
  Andreas Karatzas authored Dec 10, 2025
```
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
```
  b51255f3
- Revert "[CI] Add Async Eplb nightly CI tests (#29385)" (#30431) · b4054c8a
  Sage Moore authored Dec 10, 2025
  
  b4054c8a
10 Dec, 2025 5 commits
- [Bugfix] fix confusing OOM errors during v1 init (#28051) · 8580919a
  shivampr authored Dec 10, 2025
```
Signed-off-by: Shivam <shivamprasad91@gmail.com>
Signed-off-by: shivampr <shivampr.dev@gmail.com>
Co-authored-by: Chen Zhang <zhangch99@outlook.com>
```
  8580919a
- fix(shm): Add memory barriers for cross-process shared memory visibility (#30407) · 166ac3c9
  Christina Norman authored Dec 10, 2025
```
Signed-off-by: Christina Holland <hey@christinaholland.com>
Signed-off-by: Christina <truffle@gmail.com>
```
  166ac3c9
- [LMCache] Fix breakage due to new LMCache version (#30216) · 6ccb7bae
  Nick Hill authored Dec 10, 2025
```
Signed-off-by: Nick Hill <nhill@redhat.com>
```
  6ccb7bae
- [bug] Fix "Current vLLM config is not set." warnings when FlashInfer attention is used (#30241) · eea41804
  Po-Han Huang (NVIDIA) authored Dec 11, 2025
```
Signed-off-by: Po-Han Huang <pohanh@nvidia.com>
```
  eea41804
- [Perf] Enable environment cache in EngineCore to enable the feature for... · 9f042ba2
  Jialin Ouyang authored Dec 10, 2025
```
[Perf] Enable environment cache in EngineCore to enable the feature for UniProcExecutor as well (#29289)
Signed-off-by: Jialin Ouyang <Jialin.Ouyang@gmail.com>
```
  9f042ba2