Commits · 07ea184f00c1dc2dbc163efc7dc1ac91e98d9ed5 · OpenDAS / vllm_cscc · GitLab

29 Jan, 2026 4 commits
- [ez] Delete more torch version checks <= 2.8 (#33288) · 07ea184f
  Angela Yi authored Jan 28, 2026
```
Signed-off-by: angelayi <yiangela7@gmail.com>
```
  07ea184f
- [Misc] Add orozery to CODEOWNERS (core, kv_transfer, kv_offload) (#33227) · a663b218
  Or Ozeri authored Jan 29, 2026
```
Signed-off-by: Or Ozeri <oro@il.ibm.com>
```
  a663b218
- [Bugfix] Register fp8 cutlass_group_gemm as supported for only SM90+SM100 (#33285) · 1bd47d6e
  Michael Goin authored Jan 28, 2026
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  1bd47d6e
- [UX] Remove noisy CT UnquantizedLinearMethod warn (#33273) · 141cd439
  Michael Goin authored Jan 28, 2026
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  141cd439
28 Jan, 2026 34 commits
- [ModelRunner V2] Misc code simplification and cleanup (#33266) · 6bf3b46d
  Nick Hill authored Jan 28, 2026
```
Signed-off-by: Nick Hill <nickhill123@gmail.com>
```
  6bf3b46d
- [7/N][Attention][Docs] Add documentation for attention backends (#32477) · 77c4f45c
  Matthew Bonanni authored Jan 28, 2026
```
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
```
  77c4f45c
- [UX] Enable nested configs in config yaml files (#33193) · ca196918
  Michael Goin authored Jan 28, 2026
  
  ca196918
- [Bugfix] Add missing encoder only guard for do_kv_cache_update (#33269) · ab597c86
  Gregory Shtrasberg authored Jan 28, 2026
```
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
```
  ab597c86
- [ez] Remove checks for torch version <= 2.8 (#33209) · 4197168e
  Angela Yi authored Jan 28, 2026
```
Signed-off-by: angelayi <yiangela7@gmail.com>
```
  4197168e
- Use aiter triton fused_add_rmsnorm_pad for gpt-oss (#30976) · 59bcc5b6
  Rohan Potdar authored Jan 28, 2026
```
Signed-off-by: Rohan138 <rohanpotdar138@gmail.com>
```
  59bcc5b6
- [Feature] Fully support for async scheduling + PP, 30.8% E2E throughput... · 3e440786
  Wentao Ye authored Jan 28, 2026
```
[Feature] Fully support for async scheduling + PP, 30.8% E2E throughput improvement, 31.8% TPOT improvement (#32618)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Signed-off-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
```
  3e440786
- [CI] Change GPU key to device key for B200 test (#33275) · 8bdd3979
  Kevin H. Luu authored Jan 28, 2026
```
Signed-off-by: khluu <khluu000@gmail.com>
```
  8bdd3979
- [Perf] Optimize `moe_permute` for CUTLASS FP8 (#32892) · c4e744db
  Wentao Ye authored Jan 28, 2026
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  c4e744db
- [CI] Whisper tests `enforce_eager=False` (#33098) · 8ebf372e
  Nicolò Lucchesi authored Jan 28, 2026
```
Signed-off-by: NickLucche <nlucches@redhat.com>
```
  8ebf372e
- [lora/moe] Avoid extra intermediate buffer & Python slicing in expand phase... · f210f0b7
  cwazai authored Jan 29, 2026
```
[lora/moe] Avoid extra intermediate buffer & Python slicing in expand phase when split_k == 1 (#32774)
Signed-off-by: 陈建华 <1647430658@qq.com>
```
  f210f0b7
- [Benchmark] Add startup benchmarking to buildkite run (#33183) · 392c5af4
  Bin Bao authored Jan 28, 2026
```
Signed-off-by: Bin Bao <binbao@meta.com>
```
  392c5af4
- [Quantization][Deprecation] Remove Marlin 24 (#32688) · af9b69f9
  Robert Shaw authored Jan 28, 2026
```
Signed-off-by: Robert Shaw <robshaw@redhat.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  af9b69f9
- [Misc] Provide a DeepSeek ReasoningParser with thinking enabled by default (#33221) · 8e5e40da
  Chauncey authored Jan 28, 2026
```
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
```
  8e5e40da
- Revert "Enable Cross layers KV cache layout at NIXL Connector (#30207)" (#33241) · 2e8de867
  Or Ozeri authored Jan 28, 2026
```
Signed-off-by: Or Ozeri <oro@il.ibm.com>
Co-authored-by: Kevin H. Luu <khluu000@gmail.com>
```
  2e8de867
- [Quantization][Deprecation] Remove BitBlas (#32683) · 247d1a32
  Robert Shaw authored Jan 28, 2026
```
Signed-off-by: Robert Shaw <robshaw@redhat.com>
Signed-off-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>
```
  247d1a32
- [CI] Update job dependency syntax for Intel and AMD jobs (#33240) · ecb4f822
  Kevin H. Luu authored Jan 28, 2026
```
Signed-off-by: khluu <khluu000@gmail.com>
```
  ecb4f822
- [CI] Update job dependency for hardware and CPU jobs (#33237) · 59140907
  Kevin H. Luu authored Jan 28, 2026
```
Signed-off-by: khluu <khluu000@gmail.com>
```
  59140907
- [CI] Enable mypy import following for `vllm/compilation` (#33199) · f1acbd68
  Harry Mellor authored Jan 28, 2026
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  f1acbd68
- [XPU]disable test_acceptance_length UT (#33226) · 9581185d
  Yan Ma authored Jan 28, 2026
  
  9581185d
- [Docs] Simplify CPU x86 Docker build documentation (#33071) · 2dd359f9
  Maryam Tahhan authored Jan 28, 2026
```
Signed-off-by: Maryam Tahhan <mtahhan@redhat.com>
```
  2dd359f9
- [ROCm] Enabling forward_includes_kv_cache on ROCm MHA backends (#33106) · 22ad6495
  Gregory Shtrasberg authored Jan 28, 2026
```
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
```
  22ad6495
- Adds FunAudioChat multimodal audio model support (#2) (#33058) · 36d450e3
  ramos authored Jan 28, 2026
```
Signed-off-by: ramos <49182011+nemoramo@users.noreply.github.com>
Signed-off-by: mayufeng <mayufeng@example.com>
Co-authored-by: mayufeng <mayufeng@example.com>
```
  36d450e3
- [Bugfix] Lazy import NgramProposer in GPU model runner (#32821) · a2b877df
  22quinn authored Jan 27, 2026
```
Signed-off-by: 22quinn <33176974+22quinn@users.noreply.github.com>
```
  a2b877df
- Don't use `min_pixels`/`max_pixels` from Qwen2VL's processor (#33208) · 35fb0b86
  Harry Mellor authored Jan 28, 2026
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  35fb0b86
- Add flake8-implicit-str-concat rules to Ruff (#33191) · 2eb673a0
  Harry Mellor authored Jan 28, 2026
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  2eb673a0
- Relax protobuf library version constraints (#33202) · a97b5e20
  Jeffrey Wang authored Jan 27, 2026
```
Signed-off-by: Jeffrey Wang <jeffreywang@anyscale.com>
```
  a97b5e20
- [ROCm][CI] Add TORCH_NCCL_BLOCKING_WAIT For Distributed Tests (A100) (#32891) · 911b51b6
  Micah Williamson authored Jan 27, 2026
```
Signed-off-by: Micah Williamson <micah.williamson@amd.com>
```
  911b51b6
- [Feature]: Container image WORKDIR consistency (#33159) · 604e3b87
  Xinan Miao authored Jan 28, 2026
```
Signed-off-by: SouthWest7 <am1ao@qq.com>
Co-authored-by: SouthWest7 <am1ao@qq.com>
```
  604e3b87
- [Docs] Use definition lists for CLI reference docs (#33186) · 706f123b
  Harry Mellor authored Jan 28, 2026
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Ashwin Phadke <23502062+ashwin-phadke@users.noreply.github.com>
```
  706f123b
- [docs] Improve tlparse section (#33211) · fb7abfc1
  Angela Yi authored Jan 27, 2026
```
Signed-off-by: angelayi <yiangela7@gmail.com>
```
  fb7abfc1
- [CI] minor fixes to pipeline generator and tests (#33151) · 5d3d6e44
  Kevin H. Luu authored Jan 27, 2026
```
Signed-off-by: khluu <khluu000@gmail.com>
```
  5d3d6e44
- [Model Runner V2] Use a different stream for grammar bitmask h2d copy (#33059) · 46ec6d71
  Woosuk Kwon authored Jan 27, 2026
```
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
Co-authored-by: Nick Hill <nhill@redhat.com>
```
  46ec6d71
- Add attention benchmarking tools (#26835) · e82fa448
  Matthew Bonanni authored Jan 27, 2026
```
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: Claude <noreply@anthropic.com>
```
  e82fa448
27 Jan, 2026 2 commits
- [torch.compile] Speed up MOE handling in forward_context (#33184) · d9aa39a3
  Richard Zou authored Jan 27, 2026
```
Signed-off-by: Richard Zou <zou3519@gmail.com>
```
  d9aa39a3
- [Perf] Optimize dcp allocate tensor (#33102) · 3a6d5cbe
  Wentao Ye authored Jan 27, 2026
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  3a6d5cbe