Commits · b798e39f931ad42354e0223de3d49e24523b79af · OpenDAS / vllm_cscc

30 Oct, 2025 1 commit
- [XPU][bugfix] fix rope for llama4 and deepseek (#25145) · b798e39f
  Yan Ma authored Oct 30, 2025
```
Signed-off-by: Yan Ma <yan.ma@intel.com>
```
  b798e39f
29 Oct, 2025 36 commits
- [Temp fix] Disable torch.compile for Qwen2.5 VL's VisionBlock temporarily. (#27760) · 48eb8eba
  Chenheli Hua authored Oct 29, 2025
```
Signed-off-by: Chenheli Hua <huachenheli@outlook.com>
Signed-off-by: Roger Wang <hey@rogerw.io>
Co-authored-by: Roger Wang <hey@rogerw.io>
```
  48eb8eba
- [Bug] Fix DBO IMA issue for DeepEPHT (#27666) · b5d90f74
  Wentao Ye authored Oct 29, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  b5d90f74
- [BugFix] Fix handling of resumed reqs in `SharedStorageConnector` (#27719) · d4aa1443
  Nick Hill authored Oct 29, 2025
```
Signed-off-by: Nick Hill <nhill@redhat.com>
```
  d4aa1443
- [Bug] Fix DeepEP low latency `assert self.batched_router_logits.size(-1) ==... · fcb1d570
  Wentao Ye authored Oct 29, 2025
```
[Bug] Fix DeepEP low latency `assert self.batched_router_logits.size(-1) == full_router_logits.size(-1)` Bug (#27682)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  fcb1d570
- [KVConnector] Add metrics to Prometheus-Grafana dashboard (#26811) · accb8fab
  Nicolò Lucchesi authored Oct 29, 2025
```
Signed-off-by: NickLucche <nlucches@redhat.com>
Signed-off-by: Mark McLoughlin <markmc@redhat.com>
Co-authored-by: Mark McLoughlin <markmc@redhat.com>
```
  accb8fab
- [Bug] Raise error explicitly if using incompatible backend (#27424) · 5b044810
  Wentao Ye authored Oct 29, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  5b044810
- [CI/Build] Test torchrun with 8 cards (#27548) · f7a66828
  22quinn authored Oct 29, 2025
```
Signed-off-by: 22quinn <33176974+22quinn@users.noreply.github.com>
```
  f7a66828
- `use_aot_compile` should respect `VLLM_DISABLE_COMPILE_CACHE` (#27698) · a9fe0793
  Boyuan Feng authored Oct 29, 2025
```
Signed-off-by: Boyuan Feng <boyuan@meta.com>
```
  a9fe0793
- [FIXBUG] Qwen3VL hallucinations without Contiguous on Torch.SDPA (#27744) · 7568a282
  JartX authored Oct 29, 2025
```
Signed-off-by: JartX <sagformas@epdcenter.es>
Co-authored-by: Lukas Geiger <lukas.geiger94@gmail.com>
```
  7568a282
- [Core] Exposing engine sleep & wake_up state as prometheus metrics (#24176) · 1da3309a
  Braulio Dumba authored Oct 29, 2025
```
Signed-off-by: Braulio Dumba <Braulio.Dumba@ibm.com>
```
  1da3309a
- [Chore] Optimize P2PNCCLEngine `http_address` (#27488) · 5522fb27
  Wentao Ye authored Oct 29, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  5522fb27
- [CI] Fix flaky `test_two_responses_with_same_prev_id` test (#27745) · 0f95a1c3
  Nicolò Lucchesi authored Oct 29, 2025
```
Signed-off-by: NickLucche <nlucches@redhat.com>
```
  0f95a1c3
- [ROCm][Platform] Add MI308X device id in _ROCM_DEVICE_ID_NAME_MAP (#27623) · ded24e3e
  Xiake Sun authored Oct 29, 2025
```
Signed-off-by: Xiake Sun <xiake.sun@amd.com>
```
  ded24e3e
- Fix MiniMax-M2 rmsnorm precision and remove useless code (#27627) · d6704dd0
  Roger Young authored Oct 29, 2025
```
Signed-off-by: xuebi <xuebi@minimaxi.com>
Co-authored-by: xuebi <xuebi@minimaxi.com>
```
  d6704dd0
- [Frontend] Add `vllm bench sweep` to CLI (#27639) · ecca3fee
  Cyrus Leung authored Oct 29, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  ecca3fee
- [CI/Build] Skip cpu offloading test on AMD (#27690) · 9a0d2f0d
  Zhewen Li authored Oct 29, 2025
```
Signed-off-by: zhewenli <zhewenli@meta.com>
```
  9a0d2f0d
- [VLM] Add Qwen3-VL generation test (#25185) · ad3ec895
  Isotr0py authored Oct 29, 2025
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Signed-off-by: Roger Wang <hey@rogerw.io>
Co-authored-by: Roger Wang <hey@rogerw.io>
```
  ad3ec895
- [chore] Remove models weight on S3 logic (#27725) · 3481e407
  Kevin H. Luu authored Oct 29, 2025
```
Signed-off-by: kevin <kevin@anyscale.com>
```
  3481e407
- Feature/video support in random mm dataset (#25963) · 5e72216d
  Eugene Khvedchenya authored Oct 29, 2025
```
Signed-off-by: Eugene Khvedchenia <ekhvedchenia@nvidia.com>
Signed-off-by: Eugene Khvedchenya <ekhvedchenia@nvidia.com>
Co-authored-by: Roger Wang <hey@rogerw.io>
```
  5e72216d
- [Misc] Raise error for missing video metadata in `MultiModalDataParser` (#27664) · 1a33aacf
  Isotr0py authored Oct 29, 2025
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Signed-off-by: Isotr0py <2037008807@qq.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
```
  1a33aacf
- [Fix] import get_kv_cache_torch_dtype error in LMCacheConnector integration (#27670) · 7ba6aa8f
  Yue Zhang authored Oct 29, 2025
```
Signed-off-by: KevinCheung2259 <2651309292@qq.com>
```
  7ba6aa8f
- [Frontend] [gpt-oss] Mcp type bug (#27689) · ab2eb27b
  Alec S authored Oct 29, 2025
```
Signed-off-by: Jialin Ouyang <Jialin.Ouyang@gmail.com>
Signed-off-by: Alec Solder <alecs@fb.com>
Signed-off-by: Ye (Charlotte) Qi <yeq@meta.com>
Co-authored-by: Jialin Ouyang <Jialin.Ouyang@gmail.com>
Co-authored-by: Alec Solder <alecs@fb.com>
Co-authored-by: Ye (Charlotte) Qi <yeq@meta.com>
```
  ab2eb27b
- [Frontend] [gpt-oss] Tool json call parsing error retry (#27675) · 3c7fefde
  Alec S authored Oct 29, 2025
```
Signed-off-by: Jialin Ouyang <Jialin.Ouyang@gmail.com>
Signed-off-by: Alec Solder <alecs@fb.com>
Signed-off-by: Ye (Charlotte) Qi <yeq@meta.com>
Co-authored-by: Jialin Ouyang <Jialin.Ouyang@gmail.com>
Co-authored-by: Alec Solder <alecs@fb.com>
Co-authored-by: Ye (Charlotte) Qi <yeq@meta.com>
```
  3c7fefde
- [Bugfix] Fix modular kernel tests (#27707) · 1891cf60
  bnellnm authored Oct 29, 2025
```
Signed-off-by: Bill Nell <bnell@redhat.com>
```
  1891cf60
- [perf] Enable concurrent execution of "shared_experts" and "selected_experts"... · 8df98c21
  Jiangyun Zhu authored Oct 29, 2025
```
[perf] Enable concurrent execution of "shared_experts" and "selected_experts" in qwen3-next (#27578)
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
```
  8df98c21
- [CI/Build] Move pre-commit only scripts to `tools/pre_commit` (#27657) · 4fb8771c
  Cyrus Leung authored Oct 29, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  4fb8771c
- [Speculators] Move tests + fix integration (#27308) · 413ef7a3
  Dipika Sikka authored Oct 29, 2025
```
Signed-off-by: Dipika Sikka <dipikasikka1@gmail.com>
Signed-off-by: Rahul Tuli <rtuli@redhat.com>
Signed-off-by: rahul-tuli <rtuli@redhat.com>
Co-authored-by: Rahul Tuli <rtuli@redhat.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
```
  413ef7a3
- [Bugfix] Fix non-contiguous tensor error in `rocm_unquantized_gemm_impl` (#27605) · 8b624950
  Zhewen Li authored Oct 29, 2025
```
Signed-off-by: zhewenli <zhewenli@meta.com>
```
  8b624950
- [CI/Build][Bugfix]Fix Quantized Models Test on AMD (#27712) · 83fd49b1
  Zhewen Li authored Oct 28, 2025
```
Signed-off-by: zhewenli <zhewenli@meta.com>
```
  83fd49b1
- [KV Connector] Update lmcache connector with latest compatibility (#27681) · a4a4f0f6
  Shaoting authored Oct 28, 2025
```
Signed-off-by: Samuel Shen <slshen@uchicago.edu>
Co-authored-by: Samuel Shen <slshen@uchicago.edu>
```
  a4a4f0f6
- [Model] Fix Qwen3VL and Qwen3Omni after torch.compile changes (#27705) · 0d8161b0
  Lukas Geiger authored Oct 29, 2025
```
Signed-off-by: Lukas Geiger <lukas.geiger94@gmail.com>
Signed-off-by: Roger Wang <hey@rogerw.io>
Co-authored-by: Roger Wang <hey@rogerw.io>
```
  0d8161b0
- [NIXL][XPU] update name of nixl wheel (#27631) · d2c33c39
  liuzhenwei authored Oct 29, 2025
```
Signed-off-by: zhenwei-intel <zhenwei.liu@intel.com>
```
  d2c33c39
- [Build] Revert triton_kernels requirements (#27659) · f6d5f588
  Varun Sundar Rabindranath authored Oct 29, 2025
  
  f6d5f588
- Revert "Install pre-built xformers-0.0.32.post2 built with pt-2.9.0" (#27714) · 9007bf57
  Simon Mo authored Oct 28, 2025
  
  9007bf57
- Install pre-built xformers-0.0.32.post2 built with pt-2.9.0 (#27598) · f2575447
  Huy Do authored Oct 28, 2025
```
Signed-off-by: Huy Do <huydhn@gmail.com>
Co-authored-by: Roger Wang <hey@rogerw.io>
```
  f2575447
- [Core] Early return in SlidingWindowManager.remove_skipped_blocks (#27673) · 0b51c9bd
  Jialin Ouyang authored Oct 28, 2025
```
Signed-off-by: Jialin Ouyang <Jialin.Ouyang@gmail.com>
```
  0b51c9bd
28 Oct, 2025 3 commits

[Bug] Fix deepep low latency use nvlink by default (#27677) · d3ab240f
Wentao Ye authored Oct 28, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
d3ab240f

[Misc][qwen2_5_vl][torch.compile] Enable `supports_torch_compile` on generic... · 94666612

Lucas Kabela authored Oct 28, 2025


[Misc][qwen2_5_vl][torch.compile] Enable `supports_torch_compile` on generic nn.Module and demonstrate speedup on Qwen Vision model (#23207)
Signed-off-by: Lucas Kabela <lucaskabela@meta.com>
Signed-off-by: Lucas Kabela <lucasakabela@gmail.com>

94666612

[AsyncScheduling] Make async overlap work with logprobs (#27615) · 4fe58953
Nick Hill authored Oct 28, 2025
```
Signed-off-by: Nick Hill <nhill@redhat.com>
```
4fe58953