Commits · 07b8fae219b1fff51ef115c38c44b51395be5bb5 · OpenDAS / vllm_cscc

"docs/source/features/multimodal_inputs.md" did not exist on "843b222723b659e4b80d71d3ffb4944266af1d74"

26 Jun, 2025 2 commits
- [Bug Fix] Fix address/port already in use error for deep_ep test (#20094) · c894c5dc
  Wentao Ye authored Jun 26, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  c894c5dc
- [CPU] Fix torch version in x86 CPU backend (#19258) · 0567c824
  Li, Jiang authored Jun 26, 2025
```
Signed-off-by: jiang1.li <jiang1.li@intel.com>
```
  0567c824
25 Jun, 2025 8 commits
- [Fix] Support cls pooling in ModernBertPooler (#20067) · 23a04e08
  lsz05 authored Jun 26, 2025
```
Signed-off-by: shengzhe.li <shengzhe.li@sbintuitions.co.jp>
```
  23a04e08
- [Quantization] Add compressed-tensors emulations support for NVFP4 (#19879) · 02c97d9a
  Dipika Sikka authored Jun 25, 2025
```
Signed-off-by: Dipika Sikka <dipikasikka1@gmail.com>
Signed-off-by: Dipika <dipikasikka1@gmail.com>
```
  02c97d9a
- [V1][Speculative Decoding] Fix DeepSeek MTP (#20022) · 8359f4c8
  cjackal authored Jun 26, 2025
```
Signed-off-by: cjackal <44624812+cjackal@users.noreply.github.com>
```
  8359f4c8
- [Kernels][Bugfix] Use torch op for all kernels in FusedMoE forward. Add... · 015fab8c
  bnellnm authored Jun 25, 2025
```
[Kernels][Bugfix] Use torch op for all kernels in FusedMoE forward.  Add additional testing for cudagraphs. (#19717)
Signed-off-by: Bill Nell <bnell@redhat.com>
```
  015fab8c
- [Refactor] Remove duplicate `ceil_div` (#20023) · 879f69be
  Wentao Ye authored Jun 25, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  879f69be
- Revert "Fix(models/siglip): Add compatibility for Gemma models quantized by... · 2273ec32
  Isotr0py authored Jun 25, 2025
```
Revert "Fix(models/siglip): Add compatibility for Gemma models quantized by llm-compressor" (#20030)
```
  2273ec32
- Revert "[Feature] Integrate new deepgemm (#19820)" (#20049) · a6c4b87f
  Wentao Ye authored Jun 24, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  a6c4b87f
- [Llama4] Update `attn_temperature_tuning` (#19997) · 1afa9948
  Brayden Zhong authored Jun 24, 2025
```
Signed-off-by: Brayden Zhong <b8zhong@uwaterloo.ca>
```
  1afa9948
24 Jun, 2025 3 commits
- use .dev for version comparison with pytorch nightly release (#20031) · c01d1c5a
  Boyuan Feng authored Jun 24, 2025
```
Signed-off-by: Boyuan Feng <boyuan@meta.com>
```
  c01d1c5a
- [Feature] Integrate new deepgemm (#19820) · c6e3bba8
  Wentao Ye authored Jun 24, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
```
  c6e3bba8
- [PERF] Speedup of MRoPE prepare inputs (#19939) · 9a3b8832
  Vadim Gimpelson authored Jun 24, 2025
```
Signed-off-by: Vadim Gimpelson <vadim.gimpelson@centml.ai>
```
  9a3b8832
23 Jun, 2025 5 commits
- Feat Dynamic Quantization for MoE Layers in GPTQ Marlin Backend (#19395) · dd2ccf8d
  Jun-Howie authored Jun 24, 2025
  
  dd2ccf8d
- [Bugfix][v1] Fix step pooler implementation and step pooling usage in v1 (#19956) · 61f4fc5d
  Isotr0py authored Jun 24, 2025
```
Signed-off-by: Isotr0py <2037008807@qq.com>
```
  61f4fc5d
- [EP+DP] Optimize the little operations in the DeepGEMM + DeepEP low latency case (#19885) · 68aaeb37
  Tyler Michael Smith authored Jun 23, 2025
```
Signed-off-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
Signed-off-by: Tyler Michael Smith <tysmith@redhat.com>
Co-authored-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
```
  68aaeb37
- [Doc] Update V1 status for decoder-only embedding models (#19952) · 5111642a
  Isotr0py authored Jun 23, 2025
```
Signed-off-by: Isotr0py <2037008807@qq.com>
```
  5111642a
- Fix(models/siglip): Add compatibility for Gemma models quantized by llm-compressor (#19643) · 493c2753
  Vensen authored Jun 23, 2025
```
Signed-off-by: Vensenmu <vensenmu@gmail.com>
```
  493c2753
22 Jun, 2025 1 commit
- [BugFix] Add an env to disable moe chunking to work around compile incompatibility (#19642) · 33d51f59
  Ye (Charlotte) Qi authored Jun 22, 2025
```
Signed-off-by: Ye (Charlotte) Qi <yeq@meta.com>
```
  33d51f59
21 Jun, 2025 3 commits
- [Multimodal] Optimize Qwen2/2.5-VL startup time (#19756) · 2c5302fa
  Woosuk Kwon authored Jun 21, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
Signed-off-by: Roger Wang <hey@rogerw.me>
Co-authored-by: Roger Wang <hey@rogerw.me>
```
  2c5302fa
- [New model support]Support Tarsier2 (#19887) · c3bf9bad
  汪志鹏 authored Jun 21, 2025
```
Signed-off-by: 汪志鹏 <wangzhipeng628@gmail.com>
```
  c3bf9bad
- [Bugfix] Fix bnb 8bit model weights loading (#19917) · 6f170f11
  Isotr0py authored Jun 21, 2025
```
Signed-off-by: Isotr0py <2037008807@qq.com>
```
  6f170f11
20 Jun, 2025 4 commits
- [custom_op][vllm-plugin] update custom_op class to use op_registry (#19164) · 7e8977fc
  Chendi.Xue authored Jun 20, 2025
```
Signed-off-by: Chendi.Xue <chendi.xue@intel.com>
```
  7e8977fc
- [Model] GPT2ForSequenceClassification model (#19663) · f1e840e8
  Adrian authored Jun 20, 2025
```
Signed-off-by: nie3e <adrcwiek@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
```
  f1e840e8
- [Bugfix] Enable PP with AITER+V1 (#19822) · e3a3e4db
  qli88 authored Jun 19, 2025
```
Signed-off-by: Qiang Li <qiang.li2@amd.com>
```
  e3a3e4db
- [Chore]: qwen3-moe-type-hints-mistake (#19860) · e41bf15c
  Xerxes authored Jun 20, 2025
```
Co-authored-by: xinnan.hou <hxn02029096@alibaba-inc.com>
```
  e41bf15c
19 Jun, 2025 5 commits
- [ROCm] [AITER] [Bugfix] Patch for AITER commit `648764942e552a8bb5fe16026703716a81f05374` (#18990) · 2de12be4
  TJian authored Jun 18, 2025
```
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
```
  2de12be4
- Mark invariant normalizer in Gemma as non-persistent (#19788) · 83ca9ae4
  Yu-Hang "Maxin" Tang authored Jun 18, 2025
```
Signed-off-by: Yu-Hang Tang <Tang.Maxin@gmail.com>
```
  83ca9ae4
- [Bugfix] Fix the linter (#19826) · b1098b40
  Lu Fang authored Jun 19, 2025
```
Signed-off-by: Lu Fang <lufang@fb.com>
```
  b1098b40
- Support embedding models in V1 (#16188) · 799397ee
  Maximilien de Bayser authored Jun 19, 2025
```
Signed-off-by: Max de Bayser <mbayser@br.ibm.com>
Signed-off-by: Max de Bayser <maxdebayser@gmail.com>
Signed-off-by: 22quinn <33176974+22quinn@users.noreply.github.com>
Co-authored-by: 22quinn <33176974+22quinn@users.noreply.github.com>
```
  799397ee
- [Quantization] Modify the logic of BNB double quantization (#19742) · 49599150
  Jee Jee Li authored Jun 19, 2025
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  49599150
18 Jun, 2025 3 commits
- [Multimodal] Use fast processor for Qwen2/2.5-VL (#19789) · d49adea1
  Woosuk Kwon authored Jun 18, 2025
  
  d49adea1
- [Core] More fixes to MultiModalEmbeddings type handling (#19715) · 14fdd21d
  Russell Bryant authored Jun 18, 2025
```
Signed-off-by: Russell Bryant <rbryant@redhat.com>
```
  14fdd21d
- [v1] Support mamba2 (#19327) · a89209b7
  Chen Zhang authored Jun 19, 2025
```
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
```
  a89209b7
17 Jun, 2025 3 commits
- [Perf] Optimize `moe_align_block_size` CUDA kernel (#19572) · ffb2cd6b
  Wentao Ye authored Jun 17, 2025
```
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
```
  ffb2cd6b
- [Bugfix] Update multimodel models mapping to fit new checkpoint after Transformers v4.52 (#19151) · ca94d7fa
  Isotr0py authored Jun 17, 2025
```
Signed-off-by: Isotr0py <2037008807@qq.com>
```
  ca94d7fa
- [DOC] fix doc typos (#19600) · 5b3ad5ec
  Di Liu authored Jun 17, 2025
```
Signed-off-by: Di Liu <liu-di@sjtu.edu.cn>
```
  5b3ad5ec
16 Jun, 2025 3 commits
- [Quantization] Remove FP4 emulation; Fall-back to marlin for device < 100 (#19563) · 6bc7b573
  Dipika Sikka authored Jun 16, 2025
  
  6bc7b573
- [V1] Change return type on get_multimodal_embeddings() (#19446) · 90f9c2eb
  Russell Bryant authored Jun 16, 2025
```
Signed-off-by: Russell Bryant <rbryant@redhat.com>
```
  90f9c2eb
- [Model] Add support for MiniMaxM1ForCausalLM (shares architecture with... · 387bdf0a
  qscqesze authored Jun 17, 2025
```
[Model] Add support for MiniMaxM1ForCausalLM (shares architecture with MiniMaxText01ForCausalLM) (#19677)
Signed-off-by: QscQ <qscqesze@gmail.com>
```
  387bdf0a