Commits · b6a136b58c10dde773045c471db762ed09fc7468 · OpenDAS / vllm_cscc

"docker/Dockerfile" did not exist on "855c262a6bcbb392a6e312caa3489648aa3f4a47"

23 Sep, 2025 25 commits
- [CI/Build] Fix disabled v1 attention backend selection test (#25471) · b6a136b5
  Isotr0py authored Sep 23, 2025
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  b6a136b5
- [docs] Benchmark Serving Incorrect Arg (#25474) · 0d9fe260
  vllmellm authored Sep 23, 2025
```
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
```
  0d9fe260
- [Core] Optimize LoRA weight loading (#25403) · 273690a5
  Jee Jee Li authored Sep 23, 2025
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  273690a5
- [Bugfix] Fix idefics3 `tie_word_embeddings` (#25454) · 231c2c63
  Isotr0py authored Sep 23, 2025
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  231c2c63
- [Test]: Hermes tool parser stream output error in Qwen3 case (#25203) · 4322c553
  Andreas Hartel authored Sep 23, 2025
```
Signed-off-by: Andreas Hartel <andreas.hartel@aleph-alpha.com>
```
  4322c553
- [Misc] Move DP for ViT code inside model executor dir (#25459) · babad6e5
  Cyrus Leung authored Sep 23, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  babad6e5
- [Frontend] Add a new xml-based tool parser for qwen3-coder (#25028) · 9383cd6f
  Zhikaiiii authored Sep 23, 2025
```
Signed-off-by: Zhikaiiii <1658973216@qq.com>
```
  9383cd6f
- Handle triton kernel import exception (#25319) · ba8d2165
  Ming Yang authored Sep 23, 2025
```
Signed-off-by: Ming Yang <minos.future@gmail.com>
```
  ba8d2165
- [Model] Enable DP for ViT in Qwen2-VL (#25445) · c98be0a2
  Cyrus Leung authored Sep 23, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  c98be0a2
- [NIXL][OOT platform] support nixl_connector with oot platform and other nixl_backend (#25121) · 5774b0a1
  Chendi.Xue authored Sep 22, 2025
```
Signed-off-by: Chendi Xue <Chendi.Xue@intel.com>
```
  5774b0a1
- [DP/EP][GPTOSS] Use triton matmul-ogs kernels for GPTOSS DP/EP (#24588) · e8db44f8
  Varun Sundar Rabindranath authored Sep 23, 2025
```
Signed-off-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
Co-authored-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
```
  e8db44f8
- [Docs] Fix griffe warnings in vllm/lora/ops (#25369) · fafbe11a
  Michael Yao authored Sep 23, 2025
```
Signed-off-by: windsonsea <haifeng.yao@daocloud.io>
```
  fafbe11a
- [Bugfix] Remove contiguous output req for context parallel MLA (#25414) · 78237e43
  Michael Goin authored Sep 22, 2025
```
Signed-off-by: Michael Goin <mgoin64@gmail.com>
```
  78237e43
- [benchmarks]allow skip ready check for bench serve (#25420) · eea17839
  Lucia Fang authored Sep 22, 2025
```
Signed-off-by: Lu Fang <fanglu@fb.com>
Signed-off-by: Lucia Fang <116399278+luccafong@users.noreply.github.com>
Co-authored-by: Lucia (Lu) Fang <fanglu@meta.com>
```
  eea17839
- [XPU] Fix `compile_size` is `None` case. (#25433) · f225ea7d
  Kunshang Ji authored Sep 23, 2025
```
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
```
  f225ea7d
- [feat] Support MRoPE + YaRN (#25384) · fc97733d
  JJJYmmm authored Sep 23, 2025
```
Signed-off-by: liuye.hj <liuye.hj@alibaba-inc.com>
Co-authored-by: liuye.hj <liuye.hj@alibaba-inc.com>
```
  fc97733d
- [Bug] Fix Long Context OOM Issue (#25290) · 4741239d
  Wentao Ye authored Sep 22, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  4741239d
- [V0 deprecation] Remove `_set_default_args_v0` function (#25409) · c625f904
  Isotr0py authored Sep 23, 2025
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  c625f904
- [V0 deprecation] Remove platform v1 controling interface (#25410) · 6fa78d8f
  Isotr0py authored Sep 23, 2025
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  6fa78d8f
- [Perf] Apply torch.compile for `per_block_cast_to_fp8` (#24611) · 9949aa2e
  Wentao Ye authored Sep 22, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  9949aa2e
- [Performance] Remove input pads in cutlass_mla and optimize v_proj output handling (#25184) · 0b7bed9c
  Alexander Matveev authored Sep 22, 2025
```
Signed-off-by: Alexander Matveev <amatveev@redhat.com>
```
  0b7bed9c
- [BugFix] [DP/EP] Fix slow execution when BS <= DP (#25407) · ac0048c0
  Matthew Bonanni authored Sep 22, 2025
```
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
Co-authored-by: Chris Bamford <chrisbam4d@gmail.com>
```
  ac0048c0
- [Bugfix] Fix missing `clear_connector_metadata` (#25397) · 09019703
  Nicolò Lucchesi authored Sep 23, 2025
```
Signed-off-by: NickLucche <nlucches@redhat.com>
```
  09019703
- [Core] Drop overly aggressive whisper assertion (#25408) · f31ff874
  Russell Bryant authored Sep 22, 2025
```
Signed-off-by: Russell Bryant <rbryant@redhat.com>
```
  f31ff874
- [Bugfix] fix custom op test (#25429) · d588cd24
  Luka Govedič authored Sep 22, 2025
```
Signed-off-by: Luka Govedič <lgovedic@redhat.com>
```
  d588cd24
22 Sep, 2025 15 commits

[Frontend] Responses API MCP tools for built in tools and to pass through headers (#24628) · 45d7d852

Alec S authored Sep 22, 2025


Signed-off-by: Alec Solder <alecs@fb.com>
Signed-off-by: Alec S <10566873+alecsolder@users.noreply.github.com>
Co-authored-by: Alec Solder <alecs@fb.com>
Co-authored-by: Ye (Charlotte) Qi <yeq@meta.com>

45d7d852

[TPU] update torch_xla dependency for PyPI compatibility (#25278) · 8bed1791
Johnny Yang authored Sep 22, 2025
```
Signed-off-by: Johnny Yang <johnnyyang@google.com>
Co-authored-by: Chengji Yao <chengjiyao@google.com>
```
8bed1791
[CI/Build] Skip Qwen3-VL initialization tests until models are actually released (#25394) · f552d5e5
Cyrus Leung authored Sep 23, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
f552d5e5
[KV offload][5/N] Add `CPUOffloadingSpec` (#24251) · 8db29392
Or Ozeri authored Sep 22, 2025
```
Signed-off-by: Or Ozeri <oro@il.ibm.com>
```
8db29392

[torch.compile] Cleanup compilation tests and custom passes, add debug utils,... · d5e0fca2

Luka Govedič authored Sep 22, 2025


[torch.compile] Cleanup compilation tests and custom passes, add debug utils, fix DCE bug (#23091), fix test (#24376), and prep for custom op matching (#24604) (#24542)
Signed-off-by: Luka Govedič <lgovedic@redhat.com>
Signed-off-by: luka <lgovedic@redhat.com>
Signed-off-by: Luka Govedič <ProExpertProg@users.noreply.github.com>

d5e0fca2

[misc] Remove RFC review hours reference (#25416) · 8d0ee5a5
Simon Mo authored Sep 22, 2025

8d0ee5a5

[DP] support torchrun external launcher with Data Parallelism (#24899) · 922979bf

Lucia Fang authored Sep 22, 2025


Signed-off-by: Lu Fang <fanglu@fb.com>
Signed-off-by: Zhuohan Li <zhuohan123@gmail.com>
Co-authored-by: Zhuohan Li <zhuohan123@gmail.com>

922979bf

[CI Failure] Fix fp8 kv cache on <SM90 (#25396) · 239ef0c1
Michael Goin authored Sep 22, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
239ef0c1
[Compiler] Disable Inductor standalone compile by default (#25391) · 1d7f95b8
ElizaWszola authored Sep 22, 2025
```
Signed-off-by: ElizaWszola <ewszola@redhat.com>
```
1d7f95b8

[CLI env var] Add VLLM_FLASH_ATTN_MAX_NUM_SPLITS_FOR_CUDA_GRAPH in env variables (#25274) · cfbee3d0

Daisy-Ma-coder authored Sep 22, 2025


Signed-off-by: qqma <qqma@amazon.com>
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Co-authored-by: qqma <qqma@amazon.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>

cfbee3d0

[EPLB] Reduce EPLB Inference Overhead (#24573) · 06a41334

Bowen Wang authored Sep 22, 2025

Signed-off-by: Bowen Wang <abmfy@icloud.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>

06a41334

[V1][Attention] Split triton_attn in triton-only and rocm specific backends (#24648) · 175811e3
Burkhard Ringlein authored Sep 22, 2025
```
Signed-off-by: Burkhard Ringlein <ngl@zurich.ibm.com>
```
175811e3

[Bugfix] Fix several issues with p2p xPyD in GET type (#23993) · c10101a3

Csrayz authored Sep 22, 2025


Signed-off-by: Csrayz <jover@cmbchina.com>
Signed-off-by: ivyilike <pww123@cmbchina.com>
Co-authored-by: ivyilike <pww123@cmbchina.com>

c10101a3

[Kernel] MI-300X triton moe configs (#23445) · ac243886
Sara-KS authored Sep 22, 2025
```
Signed-off-by: Sara Kokkila Schumacher <saraks@ibm.com>
```
ac243886

Make `mypy` behave like a proper pre-commit hook (#25313) · 3d2c56b7

Harry Mellor authored Sep 22, 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>

3d2c56b7