Commits · d022115cc603ed5985996f85460c3be5c7ae749e · OpenDAS / vllm_cscc · GitLab

22 May, 2025 5 commits
- [Bugfix] Inconsistent token calculation compared to HF in llava family (#18479) · d022115c
  youngrok cha authored May 22, 2025
```
Signed-off-by: jaycha <jaycha@ncsoft.com>
```
  d022115c
- Intialize io_thread_pool attribute in the beginning. (#18331) · acb54ca8
  Rabi Mishra authored May 22, 2025
```
Signed-off-by: rabi <ramishra@redhat.com>
```
  acb54ca8
- [CI] Fix race condition with StatelessProcessGroup.barrier (#18506) · 6e0fd34d
  Russell Bryant authored May 21, 2025
```
Signed-off-by: Russell Bryant <rbryant@redhat.com>
```
  6e0fd34d
- [MISC] update project urls in pyproject.toml (#18519) · 176d62e4
  Ning Xie authored May 22, 2025
```
Signed-off-by: Andy Xie <andy.xning@gmail.com>
```
  176d62e4
- [FalconH1] Fix output dtype in RMSNorm fallback path for Falcon-H1 (e.g. 0.5B) (#18500) · 20bd6f4d
  Dhia Eddine Rhaiem authored May 22, 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>
```
  20bd6f4d
21 May, 2025 19 commits
- [Bugfix] Consistent ascii handling in tool parsers (#17704) · 1f079540
  Sebastian Schoennenbeck authored May 21, 2025
```
Signed-off-by: Sebastian Schönnenbeck <sebastian.schoennenbeck@comma-soft.com>
```
  1f079540
- [FEAT][ROCm] Upgrade AITER MLA v1 backend (#18338) · 94d8ec8d
  vllmellm authored May 22, 2025
```
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
```
  94d8ec8d
- 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
- [Misc] Update deprecation message for `--enable-reasoning` (#18404) · 2b161045
  Hyogeun Oh (오효근) authored May 21, 2025
  
  2b161045
- [Build] fix Dockerfile shell (#18402) · 371376f9
  Kebe authored May 21, 2025
  
  371376f9
- [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
- [Doc] fix arg docstring in linear layers (#18410) · c154d893
  GiantCroc authored May 21, 2025
```
Signed-off-by: giantcroc <1204449533@qq.com>
```
  c154d893
- [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
- [Misc] refactor disaggregated-prefill-v1 example (#18474) · 107f5fc4
  Reid authored May 21, 2025
```
Signed-off-by: reidliu41 <reid201711@gmail.com>
Co-authored-by: reidliu41 <reid201711@gmail.com>
```
  107f5fc4
- [V1] Fix general plugins not loaded in engine for multiproc (#18326) · 907f935d
  Yong Hoon Shin authored May 21, 2025
```
Signed-off-by: Yong Hoon Shin <yhshin@meta.com>
```
  907f935d
- [Frontend] deprecate `--device` arg (#18399) · 5d7f5452
  Kebe authored May 21, 2025
```
Signed-off-by: Kebe <mail@kebe7jun.com>
```
  5d7f5452
- [Misc] MultiConnector._connectors type (#18423) · cd8dfc6d
  Nicolò Lucchesi authored May 21, 2025
```
Signed-off-by: nicklucche <nlucches@redhat.com>
```
  cd8dfc6d
- [Bugfix][Failing Test] Fix nixl connector test when promt size < block size (#18429) · d06dd72b
  wwl2755 authored May 21, 2025
```
Signed-off-by: wwl2755 <wangwenlong2755@gmail.com>
```
  d06dd72b
- Revert "[Bugfix] Fix MRoPE Errors in the Qwen-VL Model When Processing Pure Text (#18407)" (#18456) · ad0012a0
  Cyrus Leung authored May 21, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  ad0012a0
- [Bug] Fix moe_sum signature (#18440) · 92247c52
  bnellnm authored May 21, 2025
```
Signed-off-by: Bill Nell <bnell@redhat.com>
```
  92247c52
- [Bugfix] config.head_dim is now explicitly set to None (#18432) · 0c15c2e4
  Gregory Shtrasberg authored May 21, 2025
```
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
```
  0c15c2e4
- [TPU] Re-enable the Pallas MoE kernel (#18025) · 3b17ea26
  Michael Goin authored May 20, 2025
```
Signed-off-by: Michael Goin <mgoin64@gmail.com>
```
  3b17ea26
20 May, 2025 14 commits
- fix:Build torch wheel inline rather than picking from nightly (#18351) · 23baa218
  Dilip Gowda Bhagavan authored May 21, 2025
```
Signed-off-by: Dilip Gowda Bhagavan <dilip.bhagavan@ibm.com>
```
  23baa218
- [Kernel] update comment for KV shape in unified triton attn (#18099) · 980a1724
  Percy authored May 20, 2025
```
Signed-off-by: haochengxia <xhc_1007@163.com>
```
  980a1724
- [Model] use AutoWeightsLoader for bloom (#18300) · e1f5a71e
  Calvin Chen authored May 21, 2025
```
Signed-off-by: calvin chen <120380290@qq.com>
```
  e1f5a71e
- [Minor] Rename quantization nvfp4 to modelopt_fp4 (#18356) · f4a8a374
  Michael Goin authored May 20, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  f4a8a374
- [Misc] refactor prompt embedding examples (#18405) · 8f55962a
  Reid authored May 20, 2025
```
Signed-off-by: reidliu41 <reid201711@gmail.com>
Co-authored-by: reidliu41 <reid201711@gmail.com>
```
  8f55962a
- [Bugfix] Fix MRoPE Errors in the Qwen-VL Model When Processing Pure Text (#18407) · be48360c
  燃 authored May 20, 2025
```
Co-authored-by: 松灵 <wpf272043@alibaba-inc.com>
```
  be48360c
- [CI] Add mteb testing to test the accuracy of the embedding model (#17175) · 86847700
  wang.yuqi authored May 20, 2025
  
  86847700
- Update cpu.txt (#18398) · d6c86d09
  汪志鹏 authored May 20, 2025
```
Signed-off-by: 汪志鹏 <wangzhipeng628@gmail.com>
```
  d6c86d09
- [Misc] Add LoRA code owner (#18387) · 6b35cb10
  Jee Jee Li authored May 20, 2025
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  6b35cb10
- [doc] update env variable export (#18391) · 1b1e8e05
  Reid authored May 20, 2025
```
Signed-off-by: reidliu41 <reid201711@gmail.com>
Co-authored-by: reidliu41 <reid201711@gmail.com>
```
  1b1e8e05
- [Bugfix] fix adding bias twice in ipex GPTQ quantization (#18363) · bca55b55
  Random Fly authored May 20, 2025
```
Signed-off-by: rand-fly <randfly@outlook.com>
```
  bca55b55
- [release] Change dockerhub username for TPU release (#18389) · d9813967
  Kevin H. Luu authored May 19, 2025
  
  d9813967
- [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 2 commits
- [neuron] fix authorization issue (#18364) · d565e097
  Liangfu Chen authored May 19, 2025
```
Signed-off-by: Liangfu Chen <liangfc@amazon.com>
```
  d565e097
- fix CUDA_check redefinition in #17918 (#18287) · 258bf621
  Lucia Fang authored May 19, 2025
```
Signed-off-by: Lucia Fang <fanglu@fb.com>
Co-authored-by: Lucia (Lu) Fang <fanglu@meta.com>
```
  258bf621