Commits · bd2b52fc2dd09b401991835c8a2a6f2ef940b2e4 · OpenDAS / vllm_cscc

"vscode:/vscode.git/clone" did not exist on "f58675bfb36b67cdbca4d2356a2f580e7a706ec3"

19 Dec, 2025 13 commits
- [CPU][Bugfix] Fix ppc64le CPU build (#30871) · bd2b52fc
  Nishidha Panpaliya authored Dec 19, 2025
```
Signed-off-by: Nishidha Panpaliya <nishidha.panpaliya@partner.ibm.com>
```
  bd2b52fc
- Enable aarch64 CPU performance benchmarks (#26494) · 420ba2db
  Li, Jiang authored Dec 19, 2025
```
Signed-off-by: Ioana Ghiban <ioana.ghiban@arm.com>
Signed-off-by: Fadi Arafeh <fadi.arafeh@arm.com>
Co-authored-by: Ioana Ghiban <ioana.ghiban@arm.com>
Co-authored-by: Fadi Arafeh <fadi.arafeh@arm.com>
```
  420ba2db
- [Frontend][Bug] allow tool calls in analysis channel (#28139) · 45594967
  Marko Rosenmueller authored Dec 19, 2025
```
Signed-off-by: Marko Rosenmueller <5467316+dr75@users.noreply.github.com>
Co-authored-by: Chauncey <chaunceyjiang@gmail.com>
```
  45594967
- [Bugfix] Add validation for tool requests when tool_parser is unavailable (#30613) · 086b9633
  lif authored Dec 19, 2025
```
Signed-off-by: majiayu000 <1835304752@qq.com>
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
```
  086b9633
- [Quantization] enable compressed-tensors marlin support for turing (2) (#31008) · 9187de9f
  Jinzhen Lin authored Dec 19, 2025
```
Signed-off-by: Jinzhen Lin <jinzhen.ljz@antgroup.com>
```
  9187de9f
- [Bugfix] Fix incorrect tiles creation for mm prefix triton attention (#30974) · ac1c9342
  Isotr0py authored Dec 19, 2025
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  ac1c9342
- Add hidden dimension validation for multimodal embedding inputs (#30968) · 4924ac58
  Wenqi Glantz authored Dec 19, 2025
```
Signed-off-by: Wenqi Glantz <wglantz@nvidia.com>
```
  4924ac58
- [Doc][CPU] Fix index link for CPU regular release wheels (#31015) · 096b25c9
  Li, Jiang authored Dec 19, 2025
```
Signed-off-by: jiang1.li <jiang1.li@intel.com>
```
  096b25c9
- [Quantization] enable compressed-tensors marlin support for turing (#31000) · de08b8f6
  Jinzhen Lin authored Dec 19, 2025
```
Signed-off-by: Jinzhen Lin <jinzhen.ljz@antgroup.com>
```
  de08b8f6
- [BugFix] Fix logprobs with spec decode and modified logits (#30846) · 2ac85a45
  Nick Hill authored Dec 18, 2025
```
Signed-off-by: Nick Hill <nhill@redhat.com>
```
  2ac85a45
- [ROCm][CI][Bugfix] Multi-Modal Model Support Fixes and Attention Backend Improvements (#30270) · 7b43db21
  Andreas Karatzas authored Dec 18, 2025
```
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
```
  7b43db21
- [Bugfix] Fix tool_choice="none" being ignored by GPT-OSS/harmony models (#30867) · 6a09612b
  PlatinumGod authored Dec 19, 2025
```
Signed-off-by: yujiepu <pyjapple@gmail.com>
Signed-off-by: PlatinumGod <pyjapple@gmail.com>
Co-authored-by: Chauncey <chaunceyjiang@gmail.com>
```
  6a09612b
- [BugFix] Handle errors when preprocessing added requests (#30895) · 45c0526a
  Nick Hill authored Dec 18, 2025
```
Signed-off-by: Nick Hill <nhill@redhat.com>
```
  45c0526a
18 Dec, 2025 27 commits
- [Cleanup] Refactor FlashInferMetadataBuilder (#29128) · d6b3d39b
  Benjamin Chislett authored Dec 18, 2025
```
Signed-off-by: Benjamin Chislett <bchislett@nvidia.com>
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Lucas Wilkinson <lwilkins@redhat.com>
```
  d6b3d39b
- [NIXL][BUG FIX] Fix both failing issue and accuracy issue with nixl + host_buffer on CUDA (#30419) · 6ca74bc1
  Chendi.Xue authored Dec 18, 2025
```
Signed-off-by: Chendi Xue <chendi.xue@intel.com>
Signed-off-by: Chendi.Xue <chendi.xue@intel.com>
Co-authored-by: Nicolò Lucchesi <nlucches@redhat.com>
```
  6ca74bc1
- Check for truthy `rope_parameters` not the existence of it (#30983) · 19c58339
  Harry Mellor authored Dec 18, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  19c58339
- [BugFix] Fix spec decode + structured outputs + preemption edge case (#30916) · b0b77c46
  Nick Hill authored Dec 18, 2025
```
Signed-off-by: Nick Hill <nhill@redhat.com>
```
  b0b77c46
- Strengthen input validation and tests for 'parse_raw_prompts’. (#30652) · 634a14bd
  Kayvan Mivehnejad authored Dec 18, 2025
```
Signed-off-by: Kayvan Mivehnejad <K.Mivehnejad@gmail.com>
```
  634a14bd
- [BugFix] Spec decode with VLLM_ENABLE_V1_MULTIPROCESSING=0 (#30319) · 24b65eff
  Chen Zhang authored Dec 18, 2025
```
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
```
  24b65eff
- Remove all2all backend envvar (#30363) · 41b6f920
  Elizabeth Thomas authored Dec 18, 2025
```
Signed-off-by: Elizabeth Thomas <email2eliza@gmail.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  41b6f920
- [Bug] Fix compressed tensor not using deepgemm (#30820) · 97000a2b
  Wentao Ye authored Dec 18, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  97000a2b
- [Bugfix] Remove `tile_size=64` for mm_prefix triton attention (#30973) · d2dc5dfc
  Isotr0py authored Dec 19, 2025
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  d2dc5dfc
- tuned fused configs for B300 (#30629) · b8c477c1
  navmarri14 authored Dec 18, 2025
  
  b8c477c1
- [Perf] enable flashinfer rotary_embedding custom ops in DeepSeek rotary (#30729) · 53ad423f
  jiahanc authored Dec 18, 2025
```
Signed-off-by: jiahanc <173873397+jiahanc@users.noreply.github.com>
```
  53ad423f
- [BugFix]Reclaim resources to prevent memory leaks when use LMCacheMPConnector (#30745) · 889f8bb2
  wz1qqx authored Dec 19, 2025
```
Signed-off-by: wz1qqx <ziqi.wang@novita.ai>
Co-authored-by: wz1qqx <ziqi.wang@novita.ai>
```
  889f8bb2
- [XPU] allow custom workers (e.g. vllm-omni workers) to be used on XPU (#30935) · 058926d4
  Fanli Lin authored Dec 19, 2025
```
Signed-off-by: Fanli Lin <fanli.lin@intel.com>
```
  058926d4
- [MM Encoder]: Migrate legacy ViT `MultiHeadAttention` to new... · 700a5ad6
  Isotr0py authored Dec 19, 2025
```
[MM Encoder]: Migrate legacy ViT `MultiHeadAttention` to new `MMEncoderAttention` interface (#30684)
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  700a5ad6
- [BugFix] Add sleep to fix tight loop and release GIL (#29476) · 62be3670
  Alec authored Dec 18, 2025
```
Signed-off-by: alec-flowers <aflowers@nvidia.com>
Signed-off-by: Alec <35311602+alec-flowers@users.noreply.github.com>
Co-authored-by: Nick Hill <nhill@redhat.com>
```
  62be3670
- [Bugfix] fix DP-aware routing in OpenAI API requests (#29002) · 500f26e6
  inkcherry authored Dec 19, 2025
```
Signed-off-by: inkcherry <mingzhi.liu@amd.com>
```
  500f26e6
- [Cleanup] Remove unused ModelRunner V1 `InputBatch.num_tokens` field (#30218) · 686cbaac
  Nick Hill authored Dec 18, 2025
```
Signed-off-by: Nick Hill <nhill@redhat.com>
```
  686cbaac
- fix fp8 online quantization streaming with tp > 1 (#30900) · f4ee2c3d
  Vasiliy Kuznetsov authored Dec 18, 2025
```
Signed-off-by: vasiliy <vasiliy@fb.com>
```
  f4ee2c3d
- [LoRA] Set default MXFP4 LoRA backend to Marlin (#30598) · 9a5e9652
  Xin Yang authored Dec 18, 2025
```
Signed-off-by: Xin Yang <xyangx@amazon.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
```
  9a5e9652
- [Doc] Add Sophgo TPU Support (#30949) · 326e7c31
  wzyrrr authored Dec 19, 2025
```
Co-authored-by: zhaoyang.wang <zhaoyang.wang@sophgo.com>
```
  326e7c31
- [Bugfix][torch2.10] Fix test_qwen2_5_vl_compilation with 2.10 RC (#30822) · 0db5439d
  Lucas Kabela authored Dec 18, 2025
```
Signed-off-by: Lucas Kabela <lucaskabela@meta.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
```
  0db5439d
- adds jais 2 support (#30188) · 28d15ab5
  sarathc-cerebras authored Dec 18, 2025
```
Signed-off-by: sarathc-cerebras <sarath.chandran@cerebras.net>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
```
  28d15ab5
- [Bug] Fix batch invariant in torch 2.10 (#30907) · 66287582
  Wentao Ye authored Dec 18, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Signed-off-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
```
  66287582
- [Misc] support nsys profile for bench latency (#29776) · eee600c3
  zhrrr authored Dec 18, 2025
```
Signed-off-by: zhuhaoran <zhuhaoran.zhr@alibaba-inc.com>
```
  eee600c3
- Filter safetensors files to download if .safetensors.index.json exists (#30537) · 100f93d2
  Michael Goin authored Dec 18, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  100f93d2
- [ROCm] Serving Fails on Radeon Due to AITER Dtype Import (#30952) · 96bf50a2
  vllmellm authored Dec 18, 2025
```
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
```
  96bf50a2
- [Bugfix][CPU] Fix Mac CPU build (#30955) · f90d3636
  Li, Jiang authored Dec 18, 2025
```
Signed-off-by: jiang1.li <jiang1.li@intel.com>
```
  f90d3636