Commits · 88faa466d788e25082c02dc9688931d7976361f9 · OpenDAS / vllm_cscc · GitLab

01 Aug, 2025 13 commits
- [CI] Initial tests for SM100 Blackwell runner (#21877) · 88faa466
  Michael Goin authored Aug 01, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  88faa466
- Add lora test for tp>1 case for TPU. (#21970) · d84b97a3
  XiongfeiWei authored Aug 01, 2025
```
Signed-off-by: Xiongfei Wei <isaacwxf23@gmail.com>
```
  d84b97a3
- Enable headless models for pooling in the Transformers backend (#21767) · 38c8bce8
  Harry Mellor authored Aug 01, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  38c8bce8
- [Bugfix] fix when skip tokenizer init (#21922) · b879ecd6
  rongfu.leng authored Aug 02, 2025
```
Signed-off-by: rongfu.leng <rongfu.leng@daocloud.io>
```
  b879ecd6
- [Bugfix] Fix glm4.1v video inference issue (#22067) · 3f8e9521
  Isotr0py authored Aug 02, 2025
```
Signed-off-by: Isotr0py <2037008807@qq.com>
```
  3f8e9521
- Deprecate `--disable-log-requests` and replace with `--enable-log-requests` (#21739) · 2d7b09b9
  Harry Mellor authored Aug 01, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  2d7b09b9
- feat(multimodal): Add customizable background color for RGBA to RGB conversion (#22052) · 0a6d305e
  Gamhang authored Aug 01, 2025
```
Signed-off-by: Jinheng Li <ahengljh@gmail.com>
Co-authored-by: Jinheng Li <ahengljh@gmail.com>
```
  0a6d305e
- Fix `get_kwargs` for case where type hint is `list[Union[str, type]]` (#22016) · fb0e0d46
  Harry Mellor authored Aug 01, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  fb0e0d46
- [Speculative Decoding] Add `speculators` config support (#21345) · dfbc1f88
  Dipika Sikka authored Aug 01, 2025
  
  dfbc1f88
- [Misc] Automatically resolve HF processor init kwargs (#22005) · 82de9b9d
  Cyrus Leung authored Aug 01, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  82de9b9d
- [Bugfix] Fix: Fix multi loras with tp >=2 and LRU cache (#20873) · ad57f23f
  Charent authored Aug 01, 2025
```
Signed-off-by: charent <19562666+charent@users.noreply.github.com>
```
  ad57f23f
- [Refactor] Remove Duplicate `per_block_cast_to_fp8`, Remove Dependencies of DeepGEMM (#21787) · 37006420
  Wentao Ye authored Jul 31, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  37006420
- Add DeepGEMM to Dockerfile in vllm-base image (#21533) · e360316a
  Matthew Bonanni authored Jul 31, 2025
```
Signed-off-by: Matthew Bonanni <mbonanni001@gmail.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
```
  e360316a
31 Jul, 2025 8 commits
- Add FlashInfer allreduce RMSNorm Quant fusion (#21069) · 6e672daf
  Ilya Markov authored Jul 31, 2025
```
Signed-off-by: ilmarkov <imarkov@redhat.com>
Signed-off-by: ilmarkov <markovilya197@gmail.com>
Co-authored-by: ilmarkov <imarkov@redhat.com>
```
  6e672daf
- [Misc] Add unit tests for chunked local attention (#21692) · 71470bc4
  Yong Hoon Shin authored Jul 31, 2025
```
Signed-off-by: Yong Hoon Shin <yhshin@meta.com>
```
  71470bc4
- [Meta] Official Eagle mm support, first enablement on llama4 (#20788) · 9e0726e5
  zhiweiz authored Jul 31, 2025
```
Signed-off-by: morgendave <morgendave@gmail.com>
Co-authored-by: Roger Wang <hey@rogerw.me>
```
  9e0726e5
- [Model] Add step3 vl (#21998) · 94846416
  Song authored Jul 31, 2025
```
Signed-off-by: oliveryuan <yuansong@step.ai>
Co-authored-by: oliveryuan <yuansong@step.ai>
```
  94846416
- [BugFix] Fix case where `collective_rpc` returns `None` (#22006) · 5daffe7c
  Nick Hill authored Jul 31, 2025
```
Signed-off-by: Nick Hill <nhill@redhat.com>
```
  5daffe7c
- [Model][CI] Let more pooling models support v1 (#21747) · 2836dd73
  wang.yuqi authored Jul 31, 2025
```
Signed-off-by: wang.yuqi <noooop@126.com>
```
  2836dd73
- [Bugfix]: fix metadata file copy in test_sharded_state_loader (#21830) · 3e36fcbe
  Ning Xie authored Jul 31, 2025
```
Signed-off-by: Andy Xie <andy.xning@gmail.com>
```
  3e36fcbe
- [CI Bugfix] Fix CI OOM for `test_shared_storage_connector_hashes` (#21973) · 055bd397
  Michael Goin authored Jul 30, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  055bd397
30 Jul, 2025 14 commits
- [Core] Move EngineCoreRequest to Request conversion out of EngineCore (#21627) · ca9e2be3
  Zebing Lin authored Jul 30, 2025
```
Signed-off-by: linzebing <linzebing1995@gmail.com>
```
  ca9e2be3
- [Feature] Add async tensor parallelism for scaled mm (#20155) · 287f527f
  cascade authored Jul 30, 2025
```
Signed-off-by: cascade812 <cascade812@outlook.com>
```
  287f527f
- [Misc] Support more collective_rpc return types (#21845) · 56bd537d
  Nick Hill authored Jul 30, 2025
```
Signed-off-by: Nick Hill <nhill@redhat.com>
```
  56bd537d
- feat(distributed): add `get_required_kvcache_layout` class method to kv connector api (#20433) · f4135232
  wxsm authored Jul 31, 2025
```
Signed-off-by: wxsm <wxsms@foxmail.com>
```
  f4135232
- [Bugfix] SharedStorage Connector for V1 PD multimodal (#21611) · 4904e53c
  Chenguang Zheng authored Jul 31, 2025
```
Signed-off-by: fake0fan <645327136@qq.com>
Signed-off-by: herotai214 <herotai214@gmail.com>
Co-authored-by: herotai214 <herotai214@gmail.com>
```
  4904e53c
- [CI/Build] Fix registry tests (#21934) · 004203e9
  Cyrus Leung authored Jul 31, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  004203e9
- [Bugfix] Fix TypeError in scheduler when comparing mixed request_id types (#21816) · 5c765aec
  633WHU authored Jul 30, 2025
```
Signed-off-by: chiliu <chiliu@paypal.com>
Co-authored-by: chiliu <chiliu@paypal.com>
```
  5c765aec
- Override attention metadata for fast prefill in some KV sharing setups (#21590) · ad510309
  Yong Hoon Shin authored Jul 30, 2025
```
Signed-off-by: Yong Hoon Shin <yhshin@meta.com>
```
  ad510309
- [Bugfix] Fix OOM tests in initialization test (#21921) · 6e599eeb
  Isotr0py authored Jul 30, 2025
```
Signed-off-by: Isotr0py <2037008807@qq.com>
```
  6e599eeb
- [Misc] Improve code readability of KVCacheManager (#21673) · 8f4a1c9a
  Ruixiang Tan authored Jul 30, 2025
```
Signed-off-by: tanruixiang <tanruixiang0104@gmail.com>
Signed-off-by: Ruixiang Tan <819464715@qq.com>
Signed-off-by: GitHub <noreply@github.com>
```
  8f4a1c9a
- [Test] Add Benchmark and Unit Test for `per_token_group_quant` (#21860) · 0271c2ff
  Wentao Ye authored Jul 30, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  0271c2ff
- [Tests] Fixing bug inside MultiModalProfiler. (#21842) · 54779523
  Varun Vinayak Shenoy authored Jul 30, 2025
```
Signed-off-by: Varun Shenoy <varun.vinayak.shenoy@oracle.com>
```
  54779523
- [Frontend] Add LLM.reward specific to reward models (#21720) · 65f311ce
  wang.yuqi authored Jul 30, 2025
```
Signed-off-by: wang.yuqi <noooop@126.com>
```
  65f311ce
- [v1][attention] Support Hybrid Allocator + FlashInfer (#21412) · 555e7225
  Chen Zhang authored Jul 29, 2025
```
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
```
  555e7225
29 Jul, 2025 4 commits
- [Bugfix] Fix workspace buffer None issue for Flashinfer TRTLLM Backend (#21525) · 58b11b24
  elvischenv authored Jul 29, 2025
```
Signed-off-by: elvischenv <219235043+elvischenv@users.noreply.github.com>
```
  58b11b24
- [Bugfix] VLLM_V1 supports passing other compilation levels (#19340) · 04e38500
  Richard Zou authored Jul 29, 2025
```
Signed-off-by: Richard Zou <zou3519@gmail.com>
```
  04e38500
- [KVCache] Make KVCacheSpec hashable (#21791) · 755fa8b6
  Chen Zhang authored Jul 29, 2025
```
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
```
  755fa8b6
- [V0 deprecation] Guided decoding (#21347) · 37efc63b
  Reza Barazesh authored Jul 29, 2025
```
Signed-off-by: Reza Barazesh <rezabarazesh@meta.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  37efc63b
28 Jul, 2025 1 commit
- [Kernel] SM90 CUTLASS FP8 GEMM: add support for swap AB + kernel tuning (#20396) · c6c9122d
  lyrisz authored Jul 28, 2025
```
Signed-off-by: Faqin Zhong <faqin.zhong@gmail.com>
Co-authored-by: Duncan Moss <djm.moss@gmail.com>
```
  c6c9122d