Commits · f069f3ea74a6436c5870f792d1dc0cc50ff74380 · OpenDAS / vllm_cscc

"tests/vscode:/vscode.git/clone" did not exist on "77a318bd01adc7881cd73582beae074be47f76d5"

12 Apr, 2025 4 commits
- [Frontend] support matryoshka representation / support embedding API dimensions (#16331) · fbf722c6
  wang.yuqi authored Apr 12, 2025
  
  fbf722c6
- [Feature][V1] Add xgrammar to support minLength, maxLength with test (#16516) · e92d7085
  leon-seidel authored Apr 12, 2025
```
Signed-off-by: Leon Seidel <leon.seidel@fau.de>
```
  e92d7085
- Optimized topk for topk=1 (Llama-4) (#16512) · bd6028d6
  Michael Goin authored Apr 12, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  bd6028d6
- [BugFix] Handle non-contiguous tensors properly when serializing (#16492) · 41cc883c
  Nick Hill authored Apr 11, 2025
```
Signed-off-by: Nick Hill <nhill@redhat.com>
```
  41cc883c
11 Apr, 2025 18 commits
- Bugfix for PixtralHF models without spatial_merge_size (#16513) · 87b836ba
  Michael Goin authored Apr 11, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  87b836ba
- [Bugfix] clean up duplicated code (#16485) · 56c76c2e
  rongfu.leng authored Apr 12, 2025
```
Signed-off-by: Gogs <gogs@fake.local>
Co-authored-by: Gogs <gogs@fake.local>
```
  56c76c2e
- [Kernel] Add tuned FusedMoE kernel config for Llama4 Scout, TP=8 on H100 (#16488) · a3bf8d4a
  Yong Hoon Shin authored Apr 11, 2025
  
  a3bf8d4a
- [Frontend] Added chat templates for LLaMa4 pythonic tool calling (#16463) · 16eda8c4
  Ye (Charlotte) Qi authored Apr 11, 2025
```
Signed-off-by: Ye (Charlotte) Qi <yeq@meta.com>
Co-authored-by: Kai Wu <kaiwu@meta.com>
```
  16eda8c4
- Improve configs - `LoadConfig` (#16422) · cd77382a
  Harry Mellor authored Apr 11, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  cd77382a
- [Bugfix] handle alignment of encoder_seq_lens in mllama.py (#14784) · 71b9cde0
  Travis Johnson authored Apr 11, 2025
```
Signed-off-by: Travis Johnson <tsjohnso@us.ibm.com>
```
  71b9cde0
- [Kernel] Support W8A8 channel-wise weights and per-token activations in triton... · f41647ee
  Michael Goin authored Apr 11, 2025
```
[Kernel] Support W8A8 channel-wise weights and per-token activations in triton fused_moe_kernel (#16366)
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  f41647ee
- [TPU][V1] Make `--disable_chunked_mm_input` mandatory for serving MM models (#16483) · 4d022cbc
  Nicolò Lucchesi authored Apr 11, 2025
```
Signed-off-by: NickLucche <nlucches@redhat.com>
```
  4d022cbc
- Fix erroneous "model doesn't support compile" warning (#16486) · 70de35a8
  Richard Zou authored Apr 11, 2025
```
Signed-off-by: rzou <zou3519@gmail.com>
```
  70de35a8
- [Hardware][Intel-Gaudi] Multi-step scheduling implementation for HPU (#12779) · 34b2cf3b
  Tomasz Zielinski authored Apr 11, 2025
```
Signed-off-by: Tomasz Zielinski <tomasz.zielinski@intel.com>
```
  34b2cf3b
- [Bugfix] Fix bugs of running Quark quantized models (#16236) · 9e90c9f7
  chaow-amd authored Apr 11, 2025
```
Signed-off-by: chaow <chaow@amd.com>
```
  9e90c9f7
- [Kernel] support merge_attn_states CUDA kernel, 3x speedup (#16173) · e9528f6d
  DefTruth authored Apr 11, 2025
```
Signed-off-by: DefTruth <qiustudent_r@163.com>
```
  e9528f6d
- [Misc] Raise error for V1 not supporting Long LoRA. (#16415) · a26f59cc
  Jee Jee Li authored Apr 11, 2025
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  a26f59cc
- Enforce valid max_num_batched_tokens when disable_chunked_mm_input=True (#16447) · aa3b3d76
  Michael Goin authored Apr 11, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  aa3b3d76
- [Core][LoRA][1/N] Add LoRA for EncoderDecoderModelRunner (#15990) · f7030df3
  Jee Jee Li authored Apr 11, 2025
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  f7030df3
- Revert "[Model] use AutoWeightsLoader for deepseek_v2, internlm2" (#16453) · 905e91e9
  DefTruth authored Apr 11, 2025
  
  905e91e9
- [Bugfix] Don't set an upper bound on repetition penalty (#16403) · f8f9c0ba
  Alex Brooks authored Apr 11, 2025
```
Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>
Co-authored-by: Nick Hill <nhill@redhat.com>
```
  f8f9c0ba
- [Llama4] Enable attention temperature tuning by default for long context (>32k) (#16439) · 99ef59cf
  Yong Hoon Shin authored Apr 10, 2025
```
Signed-off-by: Ye (Charlotte) Qi <yeq@meta.com>
Co-authored-by: Ye (Charlotte) Qi <yeq@meta.com>
```
  99ef59cf
10 Apr, 2025 18 commits
- [TPU][V1] Disable per-request seed/Generator (#16172) · 3cc9af88
  Nicolò Lucchesi authored Apr 10, 2025
```
Signed-off-by: NickLucche <nlucches@redhat.com>
```
  3cc9af88
- [VLM] Avoid unnecessary dummy multimodal data during processing (#16416) · 56d4aefa
  Cyrus Leung authored Apr 11, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  56d4aefa
- [V1] Zero-copy tensor/ndarray serialization/transmission (#13790) · dd143ef5
  Nick Hill authored Apr 10, 2025
```
Signed-off-by: Nick Hill <nhill@redhat.com>
```
  dd143ef5
- [Model] Reduce redundant computations in mamba2 blocks for Bamba-9B (#15423) · daefed05
  Chih-Chieh Yang authored Apr 10, 2025
```
Signed-off-by: Chih-Chieh-Yang <7364402+cyang49@users.noreply.github.com>
Co-authored-by: Yu Chin Fabian Lim <flim@sg.ibm.com>
```
  daefed05
- [V1][Spec Decode] Eagle Model loading (#16035) · e8224f3d
  Lily Liu authored Apr 10, 2025
```
Signed-off-by: LiuXiaoxuanPKU <lilyliupku@gmail.com>
```
  e8224f3d
- [V1] Set structured output backend to `auto` by default (#15724) · 9665313c
  Russell Bryant authored Apr 10, 2025
```
Signed-off-by: Russell Bryant <rbryant@redhat.com>
```
  9665313c
- Improve configs - `ParallelConfig` (#16332) · 0c54fc72
  Harry Mellor authored Apr 10, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  0c54fc72
- [TPU][V1] Use `language_model` interface for getting text backbone in MM (#16410) · c1b57855
  Nicolò Lucchesi authored Apr 10, 2025
```
Signed-off-by: NickLucche <nlucches@redhat.com>
```
  c1b57855
- [VLM] Remove `BaseProcessingInfo.get_mm_max_tokens_per_item` (#16408) · 83b824c8
  Cyrus Leung authored Apr 11, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  83b824c8
- Fix the torch version parsing logic (#15857) · 7678fcd5
  Lu Fang authored Apr 10, 2025
  
  7678fcd5
- [Model] Remove image mm limit for LLaMa4 (#16365) · 61de3ef7
  Ye (Charlotte) Qi authored Apr 10, 2025
```
Signed-off-by: Ye (Charlotte) Qi <yeq@meta.com>
```
  61de3ef7
- [Kernel] Use moe_wna16 kernel for compressed tensors wna16 moe models (#16038) · c70cf0fe
  Michael Goin authored Apr 10, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  c70cf0fe
- [Bugfix] Fix validation error for text-only Mllama 3.2 (#16377) · a5d11a54
  Cyrus Leung authored Apr 10, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  a5d11a54
- [Model] use AutoWeightsLoader for deepseek_v2, internlm2 (#16383) · a9bd832f
  Aaron Ang authored Apr 10, 2025
```
Signed-off-by: Aaron Ang <aaron.angyd@gmail.com>
```
  a9bd832f
- [Bugfix][TPU] Fix TPU validate_request (#16369) · baada0e7
  Michael Goin authored Apr 09, 2025
```
Signed-off-by: Michael Goin <mgoin64@gmail.com>
```
  baada0e7
- [misc] use tqdm.auto where appropriate (#16290) · 82eb61dd
  Benjamin Kitor authored Apr 09, 2025
```
Signed-off-by: Benjamin Kitor <bkitor@gigaio.com>
```
  82eb61dd
- [bugfix] Avoid the time consumption caused by creating dummy videos. (#16371) · 4aed0ca6
  Jintao authored Apr 10, 2025
  
  4aed0ca6
- [TPU] Fix dummy loading OOM (#16372) · 1621b252
  Chengji Yao authored Apr 09, 2025
```
Signed-off-by: Chengji Yao <chengjiyao@google.com>
```
  1621b252