Commits · c4afdb69cc22a23d23886528147b956796c1000c · OpenDAS / vllm_cscc · GitLab

15 Sep, 2025 17 commits
- Move `MultiModalConfig` from `config/__init__.py` to `config/multimodal.py` (#24659) · c4afdb69
  Harry Mellor authored Sep 15, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
```
  c4afdb69
- [USAGE] Improve error handling for weight initialization in Unquantized… (#20321) · b834b4cb
  Rafael Marcelino Koike authored Sep 15, 2025
```
Signed-off-by: Rafael Marcelino Koike <rafael.koike@oracle.com>
Signed-off-by: Rafael Koike <koike.rafael@gmail.com>
```
  b834b4cb
- Reinstate existing torch script (#24729) · 740f0647
  Harry Mellor authored Sep 15, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  740f0647
- Fp8 paged attention update (#22222) · 01413e0c
  xiao-llm authored Sep 15, 2025
```
Signed-off-by: Xiao Yu <xiao.yu@amd.com>
Signed-off-by: xiao-llm <xiao.yu.dc@outlook.com>
Co-authored-by: Xiao Yu <xiao.yu@metamaterial.com>
Co-authored-by: Xiao Yu <xiao.yu@amd.com>
Co-authored-by: Bowen Bao <bowenbao@amd.com>
```
  01413e0c
- [Bugfix] Fix GLM4.1V multimodal processor with compatability for Transformers v4.56 (#24822) · 0e219cd5
  Isotr0py authored Sep 15, 2025
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  0e219cd5
- [Model]: support Ling2.0 (#24627) · 72c99f2a
  ant-yy authored Sep 15, 2025
```
Signed-off-by: vito.yy <vito.yy@antgroup.com>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  72c99f2a
- [Misc] Fix examples openai_pooling_client.py (#24853) · bf214ca2
  wang.yuqi authored Sep 15, 2025
```
Signed-off-by: wang.yuqi <noooop@126.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  bf214ca2
- [XPU] Set consistent default KV cache layout (#24745) · 2e41f5ab
  Nicolò Lucchesi authored Sep 15, 2025
```
Signed-off-by: NickLucche <nlucches@redhat.com>
```
  2e41f5ab
- [UT] enhance free kv cache block queue popleft_n (#24220) · bc0f6059
  Ning Xie authored Sep 15, 2025
```
Signed-off-by: Andy Xie <andy.xning@gmail.com>
```
  bc0f6059
- [P/D]`kv_output_aggregator` support P TP > D TP (#23917) · 8de261b0
  Chao Lei authored Sep 15, 2025
```
Signed-off-by: LCAIZJ <leichao139636@163.com>
Co-authored-by: leichao.lc <leichao.lc@antgroup.com>
```
  8de261b0
- [Misc] Own KVConnectors installation (#24867) · a0d8b973
  Nicolò Lucchesi authored Sep 15, 2025
```
Signed-off-by: NickLucche <nlucches@redhat.com>
```
  a0d8b973
- [Misc] rename interval to max_recent_requests (#24229) · 59e17dd4
  Ning Xie authored Sep 15, 2025
```
Signed-off-by: Andy Xie <andy.xning@gmail.com>
```
  59e17dd4
- [Doc]: fix typos in various files (#24821) · 4979eb79
  Didier Durand authored Sep 15, 2025
```
Signed-off-by: Didier Durand <durand.didier@gmail.com>
```
  4979eb79
- [Bugfix] MiDashengLM model contact error under concurrent testing (#24738) · a8c0f599
  bingchen-mi authored Sep 15, 2025
```
Signed-off-by: chenbing8 <chenbing8@xiaomi.com>
Signed-off-by: bingchen-mi <chenbing8@xiaomi.com>
```
  a8c0f599
- [Frontend] Skip `stop` in reasoning content (#14550) · f4a948f3
  Ce Gao authored Sep 15, 2025
```
Signed-off-by: Ce Gao <cegao@tensorchord.ai>
Co-authored-by: Chauncey <chaunceyjiang@gmail.com>
```
  f4a948f3
- [kv cache] update num_free_blocks in the end (#24228) · 3f331398
  Ning Xie authored Sep 15, 2025
```
Signed-off-by: Andy Xie <andy.xning@gmail.com>
```
  3f331398
- [Docs] Have a try to improve frameworks/streamlit.md (#24841) · 78818dd1
  Michael Yao authored Sep 15, 2025
```
Signed-off-by: windsonsea <haifeng.yao@daocloud.io>
```
  78818dd1
14 Sep, 2025 10 commits
- [Hybrid Allocator] Support Pipeline Parallel (#23974) · 8e5cdcda
  Chen Zhang authored Sep 14, 2025
```
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
```
  8e5cdcda
- [Spec Decoding]Support Spec Decoding Metrics in DP Mode (#24049) · 90f3f7d7
  wuhang authored Sep 15, 2025
```
Signed-off-by: wuhang <wuhang6@huawei.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
```
  90f3f7d7
- [Chore] Remove ipex_ops warning (#24835) · 6dc8da5d
  Robert Shaw authored Sep 14, 2025
```
Signed-off-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
```
  6dc8da5d
- Force use C++17 globally to avoid compilation error (#24823) · 79cbcab8
  FengjinChen authored Sep 15, 2025
```
Signed-off-by: chenfengjin <1871653365@qq.com>
```
  79cbcab8
- [Benchmarks] Throw usage error when using dataset-name random and dataset-path together (#24819) · ff680359
  Ye (Charlotte) Qi authored Sep 14, 2025
```
Signed-off-by: Ye (Charlotte) Qi <yeq@meta.com>
```
  ff680359
- fix type of sampling rate for encode_base64 (#24826) · 1177dd53
  co63oc authored Sep 15, 2025
```
Signed-off-by: co63oc <co63oc@users.noreply.github.com>
```
  1177dd53
- [Perf] Fix DeepGEMM Contiguous Layout Issue, 5.5% Throughput Improvement (#24783) · fc2dbcda
  Wentao Ye authored Sep 14, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
```
  fc2dbcda
- [Misc] Improve `s3_utils` type hints with `BaseClient` (#24825) · fec347de
  Hyogeun Oh (오효근) authored Sep 14, 2025
```
Signed-off-by: Zerohertz <ohg3417@gmail.com>
```
  fec347de
- [Multi Modal][Performance] Fused Q,K's apply_rope into one (#24511) · cc3173ae
  Wenlong Wang authored Sep 14, 2025
```
Signed-off-by: wwl2755 <wangwenlong2755@gmail.com>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  cc3173ae
- [Chore] Minor simplification for non-PP path (#24810) · 3e903b6c
  Woosuk Kwon authored Sep 13, 2025
```
Signed-off-by: Woosuk Kwon <woosuk@thinkingmachines.ai>
```
  3e903b6c
13 Sep, 2025 13 commits
- [Minor] Simplify duplicative device check for cuda (#24793) · 973c9d01
  Victor Ziliang Peng authored Sep 13, 2025
```
Signed-off-by: Ziliang Peng <ziliangdotme@gmail.com>
```
  973c9d01
- Remove redundant assignment in xfer_buffers, This is a little fix (#24732) · 15b8fef4
  TaoYu Chen authored Sep 13, 2025
```
Signed-off-by: ChenTaoyu-SJTU <ctynb@qq.com>
```
  15b8fef4
- [CI][Spec Decode] Adjust threshold for flaky ngram spec decoding test again (#24771) · cfa3234a
  Wenlong Wang authored Sep 13, 2025
```
Signed-off-by: wwl2755 <wangwenlong2755@gmail.com>
```
  cfa3234a
- [Doc]: fix typos in various files (#24798) · 41ae4a1e
  Didier Durand authored Sep 13, 2025
```
Signed-off-by: Didier Durand <durand.didier@gmail.com>
```
  41ae4a1e
- [Misc] Correct an outdated comment. (#24765) · 4dad72f0
  Russell Bryant authored Sep 13, 2025
```
Signed-off-by: Russell Bryant <rbryant@redhat.com>
```
  4dad72f0
- [CI Failure] Fix test_flashinfer_cutlass_mxfp4_mxfp8_fused_moe (#24750) · 59d7ffc1
  Michael Goin authored Sep 13, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  59d7ffc1
- [Core][Multimodal] Cache `supports_kw` (#24773) · 1da0f144
  Lukas Geiger authored Sep 13, 2025
```
Signed-off-by: Lukas Geiger <lukas.geiger94@gmail.com>
```
  1da0f144
- [Kernels][DP/EP] Optimize Silu Kernel for R1 (#24054) · 98229db2
  Elvir Crnčević authored Sep 13, 2025
```
Signed-off-by: elvircrn <elvircrn@gmail.com>
```
  98229db2
- [Perf] Use NVIDIA hardware-accelerated instruction for float to fp8_e4m3 quantization (#24757) · dbeee384
  elvischenv authored Sep 13, 2025
```
Signed-off-by: elvischenv <219235043+elvischenv@users.noreply.github.com>
```
  dbeee384
- [Doc]: Remove 404 hyperlinks (#24785) · 30498f2a
  Rakesh Asapanna authored Sep 13, 2025
```
Signed-off-by: Rakesh Asapanna  <45640029+rozeappletree@users.noreply.github.com>
```
  30498f2a
- [Docs] Remove Neuron install doc as backend no longer exists (#24396) · abc7989a
  Harry Mellor authored Sep 13, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  abc7989a
- [Docs] Fix warnings in mkdocs build (continued) (#24791) · 9a8966bc
  Hyogeun Oh (오효근) authored Sep 13, 2025
```
Signed-off-by: Zerohertz <ohg3417@gmail.com>
```
  9a8966bc
- [Chore] Remove unused batched RoPE op & kernel (#24789) · 5febdc87
  Woosuk Kwon authored Sep 13, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  5febdc87