Commits · cebc22f3b674e58fa004625c6afe5a6ec6f2d9de · OpenDAS / vllm_cscc

24 May, 2025 3 commits
- [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
- [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
23 May, 2025 14 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
- [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] 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
- [CI] fix kv_cache_type argument (#18594) · cd821ea5
  Ning Xie authored May 23, 2025
```
Signed-off-by: Andy Xie <andy.xning@gmail.com>
```
  cd821ea5
- [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
- [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
- [Bugfix] Set `KVTransferConfig.engine_id` in post_init (#18576) · e44d8ce8
  lkchen authored May 22, 2025
```
Signed-off-by: Linkun Chen <github@lkchen.net>
```
  e44d8ce8
- 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
- Re-submit: Fix: Proper RGBA -> RGB conversion for PIL images. (#18569) · 04eb88dc
  Chenheli Hua authored May 22, 2025
```
Signed-off-by: Chenheli Hua <huachenheli@outlook.com>
```
  04eb88dc
- [AMD] [P/D] Compute num gpus for ROCm correctly in run_accuracy_test.sh (#18568) · 46791e1b
  rasmith authored May 22, 2025
```
Signed-off-by: Randall Smith <Randall.Smith@amd.com>
```
  46791e1b
- [Frontend] [Core] Add Tensorizer support for V1, LoRA adapter serialization... · c32e249a
  Sanger Steel authored May 22, 2025
```
[Frontend] [Core] Add Tensorizer support for V1, LoRA adapter serialization and deserialization (#17926)
Signed-off-by: Sanger Steel <sangersteel@gmail.com>
```
  c32e249a
22 May, 2025 8 commits

[Frontend][Bug Fix] Update llama4 pythonic jinja template and llama4_pythonic parser (#17917) · c91fe7b1
Kai Wu authored May 22, 2025
```
Signed-off-by: Kai Wu <kaiwu@meta.com>
```
c91fe7b1

[Build/CI] Fix CUDA 11.8 build (#17679) · 6e588da0

Tyler Michael Smith authored May 22, 2025


Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>
Signed-off-by: Tyler Michael Smith <tysmith@redhat.com>
Co-authored-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>

6e588da0

[Bugfix] make `test_openai_schema.py` pass (#18224) · 1f3a1200

David Xia authored May 22, 2025


Signed-off-by: David Xia <david@davidxia.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>

1f3a1200

[CI/Build] Update bamba test model location (#18544) · ca86a7cf
Harry Mellor authored May 22, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
ca86a7cf
[Bugfix] Add kwargs to RequestOutput __init__ to be forward compatible (#18513) · a35a4947
lkchen authored May 22, 2025
```
Signed-off-by: Linkun <github@lkchen.net>
```
a35a4947

Order sequence ids + config update to support specifying custom quantization layers (#18279) · fa72f9a8

aws-elaineyz authored May 22, 2025


Signed-off-by: Elaine Zhao <elaineyz@amazon.com>
Co-authored-by: Tailin Pan <tailinpa@amazon.com>
Co-authored-by: Rishabh Rajesh <rishyraj@amazon.com>
Co-authored-by: Yishan McNabb <yishanm@amazon.com>
Co-authored-by: Patrick Lange <patlange@amazon.com>
Co-authored-by: Maxwell Goldberg <mgld@amazon.com>
Co-authored-by: Aakash Shetty <sheaak@amazon.com>

fa72f9a8

[Bugfix] Fix LoRA test (#18518) · db5a29ba
Jee Jee Li authored May 22, 2025
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
db5a29ba
[CI] Fix race condition with StatelessProcessGroup.barrier (#18506) · 6e0fd34d
Russell Bryant authored May 21, 2025
```
Signed-off-by: Russell Bryant <rbryant@redhat.com>
```
6e0fd34d

21 May, 2025 6 commits
- Revert "[v1] Support multiple KV cache groups in GPU model runner (#17945) (#18459) · bb0a3112
  Mark McLoughlin authored May 21, 2025
```
Signed-off-by: Mark McLoughlin <markmc@redhat.com>
```
  bb0a3112
- [ROCm][Kernel][V1] Enable AMD Radeon GPU Custom Paged Attention on v1 (#17004) · dd5fa7e0
  Hosang authored May 21, 2025
```
Signed-off-by: Hosang Yoon <hosang.yoon@amd.com>
```
  dd5fa7e0
- [Bugfix] Reduce moe_sum test size to avoid OOM (#18484) · c6c10ca9
  bnellnm authored May 21, 2025
```
Signed-off-by: Bill Nell <bnell@redhat.com>
```
  c6c10ca9
- [MODEL] FalconH1 (#18406) · eca18691
  Dhia Eddine Rhaiem authored May 21, 2025
```
Signed-off-by: dhia.rhaiem <dhia.rhaiem@tii.ae>
Co-authored-by: younesbelkada <younesbelkada@gmail.com>
Co-authored-by: Ilyas Chahed <ilyas.chahed@tii.ae>
Co-authored-by: Jingwei Zuo <jingwei.zuo@tii.ae>
```
  eca18691
- [Bugfix][Failing Test] Fix test_events.py (#18460) · 61acfc45
  Rabi Mishra authored May 21, 2025
```
Signed-off-by: rabi <ramishra@redhat.com>
```
  61acfc45
- [Bug] Fix moe_sum signature (#18440) · 92247c52
  bnellnm authored May 21, 2025
```
Signed-off-by: Bill Nell <bnell@redhat.com>
```
  92247c52
20 May, 2025 5 commits
- [Minor] Rename quantization nvfp4 to modelopt_fp4 (#18356) · f4a8a374
  Michael Goin authored May 20, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  f4a8a374
- [CI] Add mteb testing to test the accuracy of the embedding model (#17175) · 86847700
  wang.yuqi authored May 20, 2025
  
  86847700
- [Misc] Add LoRA code owner (#18387) · 6b35cb10
  Jee Jee Li authored May 20, 2025
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  6b35cb10
- [Core] [Bugfix]: tensor parallel with prompt embeds (#18171) · 9609327f
  Nan Qin authored May 19, 2025
```
Signed-off-by: Nan2018 <nan@protopia.ai>
Co-authored-by: Andrew Sansom <andrew@protopia.ai>
```
  9609327f
- [Misc] Allow `AutoWeightsLoader` to skip loading weights with specific substr in name (#18358) · f07a673e
  Isotr0py authored May 20, 2025
```
Signed-off-by: Isotr0py <2037008807@qq.com>
```
  f07a673e
19 May, 2025 4 commits

Neuron up mistral (#18222) · dc1440cf
Satyajith Chilappagari authored May 19, 2025
```
Signed-off-by: Satyajith Chilappagari <satchill@amazon.com>
```
dc1440cf
[Feature]Add support for models quantized with AutoRound (#17850) · e2ee1e8e
Wenhua Cheng authored May 20, 2025
```
Signed-off-by: wenhuach21 <wenhua.cheng@intel.com>
```
e2ee1e8e
[Quantization] Pool model support bitsandbytes (#18087) · 6781af56
Jee Jee Li authored May 20, 2025
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
6781af56

Feature/vllm/input embedding completion api (#17590) · 221cfc2f

Nan Qin authored May 18, 2025


Signed-off-by: Andrew Sansom <andrew@protopia.ai>
Signed-off-by: Nan2018 <nan@protopia.ai>
Co-authored-by: 临景 <linjing.yx@alibaba-inc.com>
Co-authored-by: Bryce1010 <bryceyx@gmail.com>
Co-authored-by: Andrew Sansom <andrew@protopia.ai>
Co-authored-by: Andrew Sansom <qthequartermasterman@gmail.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>

221cfc2f