Commits · 9ea7f1abf3c015c5e560da099ad347e88b4a517d · OpenDAS / vllm_cscc

"vscode:/vscode.git/clone" did not exist on "5340b0e2214ec71117e7f0a953cf3033e3194d2a"

24 May, 2025 11 commits
- fix(regression): clone from reference items (#18662) · 9ea7f1ab
  Aaron Pham authored May 24, 2025
```
Signed-off-by: Aaron Pham <contact@aarnphm.xyz>
```
  9ea7f1ab
- [BugFix] Fix import error for fused_moe (#18642) · b9018a3f
  wangxiyuan authored May 24, 2025
```
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
```
  b9018a3f
- [MISC] typo fix and clean import (#18664) · 4ceafb62
  Ning Xie authored May 24, 2025
```
Signed-off-by: Andy Xie <andy.xning@gmail.com>
```
  4ceafb62
- [Doc] Reorganize user guide (#18661) · 1cb194a0
  Cyrus Leung authored May 24, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  1cb194a0
- [Model] use AutoWeightsLoader for gpt2 (#18625) · 2cd4d58d
  ztang2370 authored May 24, 2025
```
Signed-off-by: zt2370 <ztang2370@gmail.com>
```
  2cd4d58d
- [V1][Spec Decode] Support multi-layer eagle draft model (#18030) · c1e4a405
  qizixi authored May 24, 2025
```
Signed-off-by: qizixi <qizixi@meta.com>
```
  c1e4a405
- [Model] Add support for Qwen2.5-Omni-7B-AWQ (Qwen2_5OmniForConditionalGeneration) (#18647) · a8593205
  Yuanhao WU authored May 24, 2025
  
  a8593205
- [Frontend] improve vllm serve --help display (#18643) · 441dc63a
  Reid authored May 24, 2025
```
Signed-off-by: reidliu41 <reid201711@gmail.com>
Co-authored-by: reidliu41 <reid201711@gmail.com>
```
  441dc63a
- [V1][Spec Decode] Small refactors to improve eagle bookkeeping performance (#18424) · d55e446d
  qizixi authored May 23, 2025
```
Signed-off-by: qizixi <qizixi@meta.com>
```
  d55e446d
- FIX MOE issue in AutoRound format (#18586) · ec82c3e3
  Wenhua Cheng authored May 24, 2025
```
Signed-off-by: wenhuach21 <wenhua.cheng@intel.com>
```
  ec82c3e3
- config.py: Clarify that only local GGUF checkpoints are supported. (#18623) · 45ab403a
  Mathieu Borderé authored May 24, 2025
```
Signed-off-by: Mathieu Bordere <mathieu@letmetweakit.com>
```
  45ab403a
23 May, 2025 29 commits
- [Bugfix][Nixl] Fix Preemption Bug (#18631) · 2b10ba74
  Robert Shaw authored May 23, 2025
```
Signed-off-by: rshaw@neuralmagic.com <robertgshaw2@gmail.com>
```
  2b10ba74
- [Bugfix] Migrate to REGEX Library to prevent catastrophic backtracking (#18454) · 4fc1bf81
  Feng XiaoLong authored May 24, 2025
```
Signed-off-by: Crucifixion-Fxl <xmufxl@gmail.com>
Co-authored-by: Crucifixion-Fxl <xmufxl@gmail.com>
```
  4fc1bf81
- [ModelOpt] Introduce VLLM_MAX_TOKENS_PER_EXPERT_FP4_MOE env var to control... · f2036734
  Pavani Majety authored May 23, 2025
```
[ModelOpt] Introduce VLLM_MAX_TOKENS_PER_EXPERT_FP4_MOE env var to control blockscale tensor allocation (#18160)
Signed-off-by: Pavani Majety <pmajety@nvidia.com>
```
  f2036734
- [Doc] Update references to doc files (#18637) · 7d921649
  Cyrus Leung authored May 24, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  7d921649
- [CI] Enable test_initialization to run on V1 (#16736) · 0ddf88e1
  Michael Goin authored May 23, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  0ddf88e1
- [V1] Support Deepseek MTP (#18435) · 2628a69e
  Jiayi Yao authored May 23, 2025
```
Signed-off-by: Rui Qiao <ruisearch42@gmail.com>
Signed-off-by: YaoJiayi <120040070@link.cuhk.edu.cn>
Co-authored-by: Rui Qiao <ruisearch42@gmail.com>
```
  2628a69e
- [Doc] Fix top-level API links/docs (#18621) · 273cb3b4
  Cyrus Leung authored May 24, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  273cb3b4
- [v1] Redo "Support multiple KV cache groups in GPU model runner (#17945)" (#18593) · 6550114c
  Chen Zhang authored May 24, 2025
```
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
```
  6550114c
- Refactor pplx init logic to make it modular (prepare for deepep) (#18200) · 6a7988c5
  youkaichao authored May 23, 2025
```
Signed-off-by: youkaichao <youkaichao@gmail.com>
```
  6a7988c5
- Include private attributes in API documentation (#18614) · d4c29197
  Harry Mellor authored May 23, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  d4c29197
- [Bugfix] Fix transformers model impl ignored for mixtral quant (#18602) · 6220f3c6
  Tristan Leclercq authored May 23, 2025
```
Signed-off-by: Tristan Leclercq <tristanleclercq@gmail.com>
```
  6220f3c6
- Replace `{func}` with mkdocs style links (#18610) · 2edb533a
  Harry Mellor authored May 23, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  2edb533a
- [Hardware][CPU] Update intel_extension_for_pytorch 2.7.0 and move to... · 7ab056c2
  Kay Yan authored May 23, 2025
```
[Hardware][CPU] Update intel_extension_for_pytorch 2.7.0 and move to `requirements/cpu.txt`  (#18542)
Signed-off-by: Kay Yan <kay.yan@daocloud.io>
```
  7ab056c2
- [V0][Bugfix] Fix parallel sampling performance regression when guided decoding is enabled (#17731) · e493e485
  Madeesh Kannan authored May 23, 2025
```
Signed-off-by: Madeesh Kannan <shadeMe@users.noreply.github.com>
Co-authored-by: Russell Bryant <rbryant@redhat.com>
```
  e493e485
- [Bugfix][Model] Fix baichuan model loader for tp (#18597) · 4ce64e2d
  Mengqing Cao authored May 23, 2025
```
Signed-off-by: Mengqing Cao <cmq0113@163.com>
```
  4ce64e2d
- Revert "[V1] [Bugfix] eagle bugfix and enable correct lm_head for multimodal (#18034)" (#18600) · fbb13a2c
  Cyrus Leung authored May 23, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  fbb13a2c
- Migrate docs from Sphinx to MkDocs (#18145) · a1fe24d9
  Harry Mellor authored May 23, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  a1fe24d9
- [Feature][V1]: suupports cached_tokens in response usage (#18149) · b046cf79
  Chauncey authored May 23, 2025
```
Co-authored-by: simon-mo <xmo@berkeley.edu>
```
  b046cf79
- [Feature]Add async tensor parallelism using compilation pass (#17882) · 71ea614d
  cascade authored May 23, 2025
```
Signed-off-by: cascade812 <cascade812@outlook.com>
```
  71ea614d
- [V1] [Bugfix] eagle bugfix and enable correct lm_head for multimodal (#18034) · 4c611348
  RonaldBXu authored May 23, 2025
```
Signed-off-by: Ronald Xu <ronaldxu@amazon.com>
```
  4c611348
- [Hardware] correct method signatures for HPU,ROCm,XPU (#18551) · 60cad94b
  Ning Xie authored May 23, 2025
```
Signed-off-by: Andy Xie <andy.xning@gmail.com>
```
  60cad94b
- [Misc] Replace `cuda` hard code with `current_platform` (#16983) · 9c1baa5b
  Shanshan Shen authored May 23, 2025
```
Signed-off-by: shen-shanshan <467638484@qq.com>
```
  9c1baa5b
- [Neuron] Remove bypass on EAGLEConfig and add a test (#18514) · ed5d4082
  aws-elaineyz authored May 22, 2025
```
Signed-off-by: Elaine Zhao <elaineyz@amazon.com>
```
  ed5d4082
- [Spec Decode] Make EAGLE3 draft token ID mapping optional (#18488) · 583507d1
  Benjamin Chislett authored May 22, 2025
```
Signed-off-by: Benjamin Chislett <benjamin.chislett@centml.ai>
Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  583507d1
- [Bugfix] Set `KVTransferConfig.engine_id` in post_init (#18576) · e44d8ce8
  lkchen authored May 22, 2025
```
Signed-off-by: Linkun Chen <github@lkchen.net>
```
  e44d8ce8
- [BugFix] Increase TP execute_model timeout (#18558) · 93ecb813
  Nick Hill authored May 22, 2025
```
Signed-off-by: Nick Hill <nhill@redhat.com>
```
  93ecb813
- [Misc] refactor: simplify input validation and num_requests handling in _convert_v1_inputs (#18482) · fae453f8
  CYJiang authored May 23, 2025
```
Signed-off-by: googs1025 <googs1025@gmail.com>
```
  fae453f8
- Enable hybrid attention models for Transformers backend (#18494) · 4b0da7b6
  Harry Mellor authored May 23, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  4b0da7b6
- [V1][Spec Decoding] Use model_loader.get_model() to load models (#18273) · c6b636f9
  Mark McLoughlin authored May 23, 2025
```
Signed-off-by: Mark McLoughlin <markmc@redhat.com>
```
  c6b636f9