Commits · eef921f45e7d3efb2ed2ccab80ee20ee2e4ebe38 · OpenDAS / vllm_cscc · GitLab

10 Oct, 2025 33 commits
- AOT Compilation for torch.compile (Bundled) (#24274) · eef921f4
  Zhengxu Chen authored Oct 10, 2025
```
Signed-off-by: zhxchen17 <zhxchen17@fb.com>
```
  eef921f4
- Cache the environment variable check for batch invariance (#26510) · e317414c
  Bram Wasti authored Oct 10, 2025
```
Signed-off-by: Bram Wasti <bwasti@meta.com>
```
  e317414c
- [BugFix] Fix async scheduling + request preemption (#26385) · 949cb017
  Nick Hill authored Oct 10, 2025
```
Signed-off-by: Nick Hill <nhill@redhat.com>
```
  949cb017
- [BUG] Qwen3-next MTP. Fix attn metadata build bug (#26564) · e94cfd51
  Vadim Gimpelson authored Oct 10, 2025
```
Signed-off-by: Vadim Gimpelson <vadim.gimpelson@gmail.com>
```
  e94cfd51
- Fix some typing issues found by `mypy==1.18.2` (#26596) · 7c12763b
  Harry Mellor authored Oct 10, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  7c12763b
- Update CUDA architecture list in build pipeline for 12.9.1 wheels (#26592) · 3b780a4b
  Will Eaton authored Oct 10, 2025
```
Signed-off-by: Will Eaton <wseaton@users.noreply.github.com>
```
  3b780a4b
- Update `pre-commit` hook versions (#26591) · 30f78af1
  Harry Mellor authored Oct 10, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  30f78af1
- Add Qwen3-Omni moe thinker (#25550) · 19a9b169
  Xiong Wang authored Oct 11, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Signed-off-by: Roger Wang <hey@rogerw.io>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Xiong Wang <feizi.wx@alibaba-inc.com>
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
Co-authored-by: Roger Wang <hey@rogerw.io>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  19a9b169
- [Transform] [Quantization] Add QuTLASS support to vLLM (#24440) · 96ad65b7
  Roberto L. Castro authored Oct 10, 2025
```
Signed-off-by: LopezCastroRoberto <roberto.lopez.castro@udc.es>
Signed-off-by: Roberto L. Castro <38211239+LopezCastroRoberto@users.noreply.github.com>
Signed-off-by: Andrei Panferov <andrei@panferov.org>
Co-authored-by: Andrei Panferov <andrei@panferov.org>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
```
  96ad65b7
- [Model] Add FlexOlmo model implementation (#24923) · 8d2b8c0f
  Shane A authored Oct 10, 2025
```
Signed-off-by: Shane A <shanea@allenai.org>
```
  8d2b8c0f
- [Model][Qwen3VL] Compute `cu_seqlens` on CPU to remove (#26496) · b2155ed3
  Lukas Geiger authored Oct 10, 2025
```
Signed-off-by: Lukas Geiger <lukas.geiger94@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
```
  b2155ed3
- [Bugfix] fixed top_logprobs: -1 does not appear to work as intended (#26470) · 910abdbd
  Chauncey authored Oct 11, 2025
```
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
```
  910abdbd
- [torch.compile] Make inductor partition rules respect splitting_ops #25691 (#25845) · cddce79f
  baonudesifeizhai authored Oct 10, 2025
```
Signed-off-by: baonudesifeizhai <baonudesifeizhai@gmail.com>
Signed-off-by: baonudesifeizhai <85092850+baonudesifeizhai@users.noreply.github.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
```
  cddce79f
- [Metrics] Add test for multi-modal cache stats logging (#26588) · e5192819
  Mark McLoughlin authored Oct 10, 2025
```
Signed-off-by: Mark McLoughlin <markmc@redhat.com>
```
  e5192819
- Silu v2 (#25074) · 7b03584d
  Elvir Crnčević authored Oct 10, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: elvircrn <elvircrn@gmail.com>
Signed-off-by: Elvir Crnčević <elvircrn@gmail.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Varun Sundar Rabindranath <varunsundar08@gmail.com>
```
  7b03584d
- [Bugfix] Make DP padding optional in coordinate_batch_across_dp (#26375) · ae9d0e7d
  Sage Moore authored Oct 10, 2025
```
Signed-off-by: Sage Moore <sage@neuralmagic.com>
```
  ae9d0e7d
- Added test_top_k_per_row to test-pipeline.yaml. (#26569) · 0e67102d
  Daniel Cámpora authored Oct 10, 2025
```
Signed-off-by: Daniel Campora <961215+dcampora@users.noreply.github.com>
```
  0e67102d
- [BugFix][torch.compile] Fix fused_scaled_matmul_reduce_scatter signature for PyTorch 2.8 (#26038) · f4ba2061
  Jason Li authored Oct 10, 2025
```
Signed-off-by: jasonlizhengjian <jasonlizhengjian@gmail.com>
Signed-off-by: <>
Signed-off-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
```
  f4ba2061
- [CI] fix test_run_batch.py::test_completions - AssertionError (#26578) · 1e6848a6
  Chauncey authored Oct 10, 2025
```
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
```
  1e6848a6
- [BugFix] Fix noop elimination edge case (#26394) · 67661375
  Andy Lo authored Oct 10, 2025
```
Signed-off-by: Andy Lo <andy@mistral.ai>
```
  67661375
- [Bugfix] Convert untraceable GroupShape to list for AMD impl (#26535) · 213b6445
  Lucas Kabela authored Oct 10, 2025
```
Signed-off-by: Lucas Kabela <lucaskabela@meta.com>
```
  213b6445
- [NIXL] Ignore abort on already-finished request (#25067) · 784c2311
  Mark McLoughlin authored Oct 10, 2025
```
Signed-off-by: Mark McLoughlin <markmc@redhat.com>
```
  784c2311
- [bugfix][DCP] fix block_size of hash in DCP prefix caching (#26296) · 606b00e8
  Chen Zhang authored Oct 10, 2025
```
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
```
  606b00e8
- [CI] fix ruff format (#26579) · 720d3cd0
  Chauncey authored Oct 10, 2025
```
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
```
  720d3cd0
- Remove LoRA bias support (#25807) · ab196ede
  Ashwin Phadke authored Oct 10, 2025
```
Signed-off-by: Ashwin Phadke <ashwinphadke12@rediffmail.com>
Signed-off-by: Ashwin Phadke <23502062+ashwin-phadke@users.noreply.github.com>
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
```
  ab196ede
- [GPT-OSS] Add support for arrays at tool message content (#25593) · 3ee202ea
  Luis Tomas Bolivar authored Oct 10, 2025
```
Signed-off-by: Luis Tomas Bolivar <ltomasbo@redhat.com>
```
  3ee202ea
- [Metrics] Log multi-modal cache stats and fix reset (#26285) · ad430a67
  Cyrus Leung authored Oct 10, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  ad430a67
- [deepseek] kernel block size for UniformTypeKVCacheSpecs (#26559) · 6f0f570c
  Chen Zhang authored Oct 10, 2025
```
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
```
  6f0f570c
- fix test_simple_inductor_graph_partition (#26522) · b545a0b2
  Boyuan Feng authored Oct 09, 2025
```
Signed-off-by: Boyuan Feng <boyuan@meta.com>
```
  b545a0b2
- [Spec-Decode] Support piecewise cudagraphs for Eagle head (#25109) · 29255cfc
  Lucas Wilkinson authored Oct 10, 2025
```
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
Co-authored-by: Benjamin Chislett <chislett.ben@gmail.com>
```
  29255cfc
- [Chore]: One pythonic tool parser test uses the wrong parser (#26515) · da445560
  Ben Browning authored Oct 10, 2025
```
Signed-off-by: Ben Browning <bbrownin@redhat.com>
```
  da445560
- [Core] Small simplification in `GPUModelRunner._update_states()` (#26508) · aafb99a4
  Nick Hill authored Oct 09, 2025
```
Signed-off-by: Nick Hill <nhill@redhat.com>
```
  aafb99a4
- [DP][ray] Support different VLLM_RAY_DP_PACK_STRATEGY (#23849) · 757fa4a4
  Rui Qiao authored Oct 09, 2025
```
Signed-off-by: Rui Qiao <ruisearch42@gmail.com>
```
  757fa4a4
09 Oct, 2025 7 commits
- Refactor MistralTokenizer (#26358) · c6187f55
  Julien Denize authored Oct 10, 2025
```
Signed-off-by: Julien Denize <julien.denize@mistral.ai>
```
  c6187f55
- [CI] Fix Pre-commit Issue Cannot determine type of "rank" and "world_size" (#26448) · 8983e021
  Wentao Ye authored Oct 09, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  8983e021
- [Bug] Fix modular_kernel: ZeroDivisionError: integer division or modulo by zero (#26528) · 1ee35382
  Wentao Ye authored Oct 09, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  1ee35382
- [Bugfix] Fix CUDA graph selection bug in FlashInfer at high concurrency (#26499) · 6e783bc5
  Benjamin Chislett authored Oct 09, 2025
```
Signed-off-by: Benjamin Chislett <bchislett@nvidia.com>
```
  6e783bc5
- [UX] Add FlashInfer as default CUDA dependency (#26443) · c9d33c60
  Michael Goin authored Oct 09, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
```
  c9d33c60
- [Core] Remove unused `prev_sampled_token_ids_invalid_indices` input batch field (#26514) · 2e54db4d
  Nick Hill authored Oct 09, 2025
```
Signed-off-by: Nick Hill <nhill@redhat.com>
```
  2e54db4d
- [Flashinfer][gpt-oss] Support FP8-qkv Flashinfer TRTLLM Sinks Attention (#25674) · 44f633db
  elvischenv authored Oct 10, 2025
```
Signed-off-by: elvischenv <219235043+elvischenv@users.noreply.github.com>
```
  44f633db