Commits · 65a5910ce35f889740bddb2e19dad35c83278873 · OpenDAS / vllm_cscc

"vscode:/vscode.git/clone" did not exist on "94cbe0a328131b487d2b5a9b1843fd4a0102d827"

21 Sep, 2025 12 commits
- [Optimization] Cache chat template result when processor fails to be loaded (#25341) · 65a5910c
  Cyrus Leung authored Sep 21, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  65a5910c
- [Bugfix] Typos in error message for missing model config file (#25339) · 9aea7373
  Simon Danielsson authored Sep 21, 2025
```
Signed-off-by: simondanielsson <simon.danielsson99@hotmail.com>
```
  9aea7373
- [MM][Perf] Minor Optimization on Qwen3-VL `fast_pos_embed_interpolate` (#25337) · 30d08911
  Roger Wang authored Sep 21, 2025
```
Signed-off-by: Roger Wang <hey@rogerw.io>
```
  30d08911
- [V1] Add sliding window support to Flex Attention backend (#24089) · cf56cf78
  Isotr0py authored Sep 21, 2025
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  cf56cf78
- [V0 Deprecation] Remove V0 MP executor (#25329) · 7ed82d19
  Woosuk Kwon authored Sep 20, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  7ed82d19
- [V0 Deprecation] Remove from_seq_group methods (#25330) · 12dbd834
  Woosuk Kwon authored Sep 20, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  12dbd834
- [Multi Modal][Performance] Fused Q,K's apply_rope in more models (#25005) · 035fd2bd
  Wenlong Wang authored Sep 20, 2025
```
Signed-off-by: wwl2755 <wangwenlong2755@gmail.com>
Co-authored-by: Roger Wang <hey@rogerw.io>
```
  035fd2bd
- [V0 Deprecation] Remove V0 model runner base & simplify worker base (#25328) · 1cd885bd
  Woosuk Kwon authored Sep 20, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  1cd885bd
- [V0 Deprecation] Remove V0 core (#25321) · c99db8c8
  Woosuk Kwon authored Sep 20, 2025
```
Signed-off-by: Woosuk Kwon <woosuk@thinkingmachines.ai>
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  c99db8c8
- [Chore] Remove unused sampler in models (#25324) · 572ddf83
  Woosuk Kwon authored Sep 20, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  572ddf83
- [V0 Deprecation] Remove V0 Output Processor (#25320) · 86647d1c
  Woosuk Kwon authored Sep 20, 2025
```
Signed-off-by: Woosuk Kwon <woosuk@thinkingmachines.ai>
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  86647d1c
- [V0 Deprecation] Remove LLMEngine (#25033) · 52c2a8d4
  Woosuk Kwon authored Sep 20, 2025
```
Signed-off-by: Woosuk Kwon <woosuk@thinkingmachines.ai>
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  52c2a8d4
20 Sep, 2025 20 commits
- [Docs] Fix warnings in vllm/profiler and vllm/transformers_utils (#25220) · 367a480b
  Michael Yao authored Sep 21, 2025
```
Signed-off-by: windsonsea <haifeng.yao@daocloud.io>
```
  367a480b
- [Core] Enable sharded state loader for V1 engine and enhance test coverage (#25308) · d88918e4
  lirong authored Sep 20, 2025
```
Signed-off-by: pengdrumli <pengdrumli@tencent.com>
```
  d88918e4
- [Model] Cleanup InternViT's data parallel implementation (#25306) · 3c713a97
  Isotr0py authored Sep 20, 2025
```
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
```
  3c713a97
- Generate _ModelInfo properties file when loading to improve loading speed (#23558) · bf8b26ca
  Manoel Marques authored Sep 20, 2025
```
Signed-off-by: Manoel Marques <manoel.marques@ibm.com>
Signed-off-by: Manoel Marques <manoelmrqs@gmail.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
```
  bf8b26ca
- [Docs] Fix warnings in mkdocs build (continued) (#25042) · 032d661d
  Wenlong Wang authored Sep 20, 2025
```
Signed-off-by: wwl2755 <wangwenlong2755@gmail.com>
```
  032d661d
- [CI Failure] Disable FlashInfer RoPE to unblock CI (#25299) · e08a3a3f
  Michael Goin authored Sep 20, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  e08a3a3f
- [V1] Support `LLM.apply_model` (#18465) · 3d9a1d2d
  Cyrus Leung authored Sep 20, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  3d9a1d2d
- [Bugfix] Fix Qwen3-VL-MoE weight loading for EP (#25300) · be874c02
  Roger Wang authored Sep 20, 2025
```
Signed-off-by: Roger Wang <hey@rogerw.io>
```
  be874c02
- [Hybrid Allocator] Support full attention with different hidden size (#25101) · 9607d5eb
  Chen Zhang authored Sep 19, 2025
```
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
```
  9607d5eb
- [Optimization] Avoid repeated model architecture conversion for pooling models (#25261) · c60e6137
  Cyrus Leung authored Sep 20, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  c60e6137
- [Bugfix] fix tool call arguments is empty (#25223) · f91480b2
  Chauncey authored Sep 20, 2025
```
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
Co-authored-by: xin.li <xin.li@daocloud.io>
```
  f91480b2
- [BUG FIX][NON-CUDA]quick fix to avoid call cudagraph_unsafe in attention (#25298) · 6c5f82e5
  Chendi.Xue authored Sep 19, 2025
```
Signed-off-by: Chendi Xue <Chendi.Xue@intel.com>
```
  6c5f82e5
- [BugFix] Exclude self when checking for port collision (#25286) · b7f186bb
  Nick Hill authored Sep 19, 2025
```
Signed-off-by: Nick Hill <nhill@redhat.com>
```
  b7f186bb
- [BUGFIX] GPTQ quantization compatibility for Qwen3 Next MOE models (AutoGPTQ... · 36429096
  JartX authored Sep 20, 2025
```
[BUGFIX] GPTQ quantization compatibility for Qwen3 Next MOE models (AutoGPTQ and AutoRound-GPTQ) (#25268)
Signed-off-by: JartX <sagformas@epdcenter.es>
```
  36429096
- Improve weight loading for encoder models in Transformers backend (#25289) · c308501c
  Harry Mellor authored Sep 20, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  c308501c
- [Misc] Support more collective_rpc return types (#25294) · 535d8005
  Nick Hill authored Sep 19, 2025
```
Signed-off-by: Nick Hill <nhill@redhat.com>
```
  535d8005
- [BugFix] Ensure appropriate guards in destructors (#25284) · a25ade5d
  Nick Hill authored Sep 19, 2025
```
Signed-off-by: Nick Hill <nhill@redhat.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
```
  a25ade5d
- [torch.compile] CUDAGraph Inductor partition integration (#24281) · 8945b001
  Boyuan Feng authored Sep 19, 2025
```
Signed-off-by: Boyuan Feng <boyuan@meta.com>
Signed-off-by: Boyuan Feng <fby.1994@gmail.com>
Signed-off-by: boyuanfeng <boyuan@meta.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
```
  8945b001
- Don't skip special tokens with hermes-style tool calling (#25281) · a36c6758
  Maximilien de Bayser authored Sep 19, 2025
```
Signed-off-by: Max de Bayser <mbayser@br.ibm.com>
```
  a36c6758
- [Bugfix] Remove VLLM_TEST_DYNAMO_FULLGRAPH_CAPTURE #2969 (#25090) · 3da17c2c
  Lucas Kabela authored Sep 19, 2025
```
Signed-off-by: Lucas Kabela <lucaskabela@meta.com>
```
  3da17c2c
19 Sep, 2025 8 commits

[BugFix] Fix async scheduling CPU tensor race take 2 (#25279) · 14c14327
Nick Hill authored Sep 19, 2025
```
Signed-off-by: Nick Hill <nhill@redhat.com>
```
14c14327
allow disable flashinfer prefill (#25276) · ee7a66dd
Lucia Fang authored Sep 19, 2025
```
Signed-off-by: Lu Fang <fanglu@fb.com>
```
ee7a66dd

Enable modelopt gemma3 nvfp4/fp8, make workflow more robust (#22771) · 431535b5

Zhiyu authored Sep 19, 2025


Signed-off-by: Zhiyu Cheng <zhiyuc@nvidia.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>

431535b5

[Frontend] Responses API messages out, just harmony for now (#24985) · e69e0b8b

Alec S authored Sep 19, 2025


Signed-off-by: Alec Solder <alecs@fb.com>
Co-authored-by: Alec Solder <alecs@fb.com>
Co-authored-by: Ye (Charlotte) Qi <yeq@meta.com>

e69e0b8b

Fix: Correct FusedMoE layer reference in auto_round quantization (#24818) · ddc90483

David-Wen authored Sep 20, 2025

Signed-off-by: David-Wen <18927700430@163.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

ddc90483

[BugFix] Make FlashInferMetadataBuilder non-blocking (#25040) · b1a63d1b
nvjullin authored Sep 20, 2025
```
Signed-off-by: Julien Lin <jullin@nvidia.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
```
b1a63d1b

[Perf] Use FlashInfer RoPE for RotaryEmbedding.forward_cuda when available (#21126) · 48ecb443

Michael Goin authored Sep 19, 2025


Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>

48ecb443

[Bugfix] Fix chunked a2_scales in modular kernels (#25264) · 4bdf4002
bnellnm authored Sep 19, 2025
```
Signed-off-by: Bill Nell <bnell@redhat.com>
```
4bdf4002