Commits · 313ae8c16a86a5e7922d17c9adf7b4aadbe28904 · OpenDAS / vllm_cscc

"tests/distributed/test_quick_all_reduce.py" did not exist on "e489ad7a210f4234db696d1f2749d5f3662fa65b"

15 Jul, 2025 28 commits
- [Deprecation] Remove everything scheduled for removal in v0.10.0 (#20979) · 313ae8c1
  Harry Mellor authored Jul 15, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  313ae8c1
- [CI/Build] Fix wrong path in Transformers Nightly Models Test (#20994) · c847e34b
  Cyrus Leung authored Jul 15, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  c847e34b
- Voxtral (#20970) · e7e3e6d2
  Patrick von Platen authored Jul 15, 2025
```
Signed-off-by: Patrick von Platen <patrick.v.platen@gmail.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
```
  e7e3e6d2
- [v1][core] Support for attention free models (#20811) · 4ffd963f
  Christian Pinto authored Jul 15, 2025
```
Signed-off-by: Christian Pinto <christian.pinto@ibm.com>
```
  4ffd963f
- [Deprecation] Remove `TokenizerPoolConfig` (#20968) · 56fe4bed
  Harry Mellor authored Jul 15, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  56fe4bed
- [doc] Add more details for Ray-based DP (#20948) · d9127818
  Rui Qiao authored Jul 15, 2025
```
Signed-off-by: Rui Qiao <ruisearch42@gmail.com>
```
  d9127818
- [MISC] Add init files for python package (#20908) · 20149d84
  Li Wang authored Jul 15, 2025
```
Signed-off-by: wangli <wangli858794774@gmail.com>
```
  20149d84
- [V1] [Hybrid] Refactor mamba state shape calculation; enable V1 via cli (#20840) · 3534c39a
  Thomas Parnell authored Jul 15, 2025
```
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
```
  3534c39a
- [TPU] Optimize kv cache update kernel (#20415) · c586b556
  Yifei Teng authored Jul 15, 2025
```
Signed-off-by: Yifei Teng <tengyifei88@gmail.com>
```
  c586b556
- [Docs] Improve documentation for ray cluster launcher helper script (#20602) · 33d56000
  Ricardo Decal authored Jul 15, 2025
```
Signed-off-by: Ricardo Decal <rdecal@anyscale.com>
```
  33d56000
- [frontend] Refactor CLI Args for a better modular integration (#20206) · f148c44c
  kourosh hakhamaneshi authored Jul 15, 2025
```
Signed-off-by: Kourosh Hakhamaneshi <kourosh@anyscale.com>
```
  f148c44c
- [Docs] Improve documentation for RLHF example (#20598) · 235bfd5d
  Ricardo Decal authored Jul 15, 2025
```
Signed-off-by: Ricardo Decal <rdecal@anyscale.com>
```
  235bfd5d
- [frontend] Add --help=page option for paginated help output (#20961) · 68d28e37
  Reid authored Jul 15, 2025
```
Signed-off-by: reidliu41 <reid201711@gmail.com>
```
  68d28e37
- [Misc] Refactor AllReduceFusionPass. Remove parameter (#20918) · 37a7d5d7
  Ilya Markov authored Jul 15, 2025
```
Signed-off-by: ilmarkov <imarkov@redhat.com>
Co-authored-by: ilmarkov <imarkov@redhat.com>
```
  37a7d5d7
- Implement Async Scheduling (#19970) · d4d30940
  Woosuk Kwon authored Jul 14, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  d4d30940
- [Model] Add AutoWeightsLoader support for BERT, RoBERTa (#20534) · 85bd6599
  Jennifer He authored Jul 15, 2025
```
Signed-off-by: Jennifer He <islandhe@gmail.com>
Signed-off-by: <islandhe@gmail.com>
Signed-off-by: Jen H <islandhe@gmail.com>
```
  85bd6599
- [cold start] replace VLLM_COMPILE_DEPYF with debug_dump_dir (#20940) · 91b3d190
  Boyuan Feng authored Jul 14, 2025
```
Signed-off-by: Boyuan Feng <boyuan@meta.com>
```
  91b3d190
- [Doc] Clearer mistral3 and pixtral model support description (#20926) · fc017915
  Isotr0py authored Jul 15, 2025
```
Signed-off-by: Isotr0py <2037008807@qq.com>
```
  fc017915
- [Bugfix] Switch bailout logic for kv-cache-dtype with SM100 Flashinfer (#20934) · 9ad0a458
  Pavani Majety authored Jul 14, 2025
```
Signed-off-by: Pavani Majety <pmajety@nvidia.com>
```
  9ad0a458
- Enabled BnB NF4 inference on Gaudi (#20172) · 016b8d1b
  Ruheena Suhani Shaik authored Jul 15, 2025
```
Signed-off-by: Ruheena Suhani Shaik <rsshaik@habana.ai>
```
  016b8d1b
- [CI] Fix flaky `test_streaming_response` test (#20913) · 80305c1b
  Nicolò Lucchesi authored Jul 15, 2025
```
Signed-off-by: NickLucche <nlucches@redhat.com>
```
  80305c1b
- feat: add image zoom to improve image viewing experience (#20763) · 37e2ecac
  Reid authored Jul 15, 2025
```
Signed-off-by: reidliu41 <reid201711@gmail.com>
```
  37e2ecac
- [Docs] Add Kuberay to deployment integrations (#20592) · 054c8657
  Ricardo Decal authored Jul 14, 2025
```
Signed-off-by: Ricardo Decal <rdecal@anyscale.com>
```
  054c8657
- Use w8a8 quantized matmul Pallas kernel (#19170) · d4170fad
  XiongfeiWei authored Jul 14, 2025
```
Signed-off-by: Xiongfei Wei <isaacwxf23@gmail.com>
```
  d4170fad
- [CI/Build] Split Entrypoints Test into LLM and API Server (#20945) · 946aadb4
  Michael Goin authored Jul 15, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  946aadb4
- [Bugfix] Fix incorrect dispatch for CutlassBlockScaledGroupedGemm and DeepGEMM (#20933) · bcdfb2a3
  Michael Goin authored Jul 15, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  bcdfb2a3
- [BugFix] VLLM_DISABLE_COMPILE_CACHE=1 should disable all reads and writes from the cache (#20942) · ba8c3000
  Richard Zou authored Jul 14, 2025
```
Signed-off-by: Richard Zou <zou3519@gmail.com>
```
  ba8c3000
- SM100 Cutlass MLA decode with unrestricted num_heads (< 128) for DeepSeek TP (#20769) · 8cdc3712
  Alexander Matveev authored Jul 14, 2025
```
Signed-off-by: Alexander Matveev <amatveev@redhat.com>
```
  8cdc3712
14 Jul, 2025 12 commits
- Fall back if flashinfer comm module not found (#20936) · 61e20828
  Yong Hoon Shin authored Jul 14, 2025
```
Signed-off-by: Yong Hoon Shin <yhshin@meta.com>
```
  61e20828
- [Docs] remove outdated performance benchmark (#20935) · 55e1c66d
  Kuntai Du authored Jul 14, 2025
```
Signed-off-by: Kuntai Du <kuntai@uchicago.edu>
```
  55e1c66d
- Fix overflow indexing in causal_conv1d kernel (#20938) · 86f3ac21
  Thomas Parnell authored Jul 14, 2025
```
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
```
  86f3ac21
- [Misc] Relax translations tests (#20856) · 149f2435
  Nicolò Lucchesi authored Jul 14, 2025
```
Signed-off-by: NickLucche <nlucches@redhat.com>
```
  149f2435
- [Misc] ModularKernel : Perform WeightAndReduce inside TritonExperts & DeepGemmExperts (#20725) · c0569dbc
  Varun Sundar Rabindranath authored Jul 15, 2025
```
Signed-off-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
Co-authored-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
```
  c0569dbc
- Add benchmark dataset for mlperf llama tasks (#20338) · 8bb43b9c
  Michael Goin authored Jul 15, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  8bb43b9c
- Change default model to Qwen3-0.6B (#20335) · 55975621
  Tyler Michael Smith authored Jul 14, 2025
```
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
```
  55975621
- [CI/Build] Add Transformers nightly tests in CI (#20924) · 6d0cf239
  Isotr0py authored Jul 15, 2025
```
Signed-off-by: Isotr0py <2037008807@qq.com>
```
  6d0cf239
- [Misc] Clean up Aimv2 config registration in Ovis config (#20921) · 3fc96443
  Isotr0py authored Jul 14, 2025
```
Signed-off-by: Isotr0py <2037008807@qq.com>
```
  3fc96443
- [CI] Update codeowner for compilation code (#20929) · 0caf61c0
  Lu Fang authored Jul 14, 2025
```
Signed-off-by: Lu Fang <lufang@fb.com>
```
  0caf61c0
- [CI] cc folks on changes to vllm/compilation (#20925) · 66762465
  Richard Zou authored Jul 14, 2025
```
Signed-off-by: Richard Zou <zou3519@gmail.com>
```
  66762465
- [Model] Add Ling implementation (#20680) · 38efa282
  ant-yy authored Jul 14, 2025
```
Signed-off-by: vito.yy <vito.yy@antgroup.com>
```
  38efa282