Commits · 55d6d3fdb8a08aec7c0b09be95c4982705921ab3 · OpenDAS / vllm_cscc · GitLab

21 Apr, 2025 6 commits
- [Bugfix] Fix GLM rotary_dim issue and support v1 (#16912) · 55d6d3fd
  Isotr0py authored Apr 21, 2025
```
Signed-off-by: isotr0py <2037008807@qq.com>
```
  55d6d3fd
- [Misc] Refactor platform to get device specific stream and event (#14411) · 7272bfae
  Shanshan Shen authored Apr 21, 2025
```
Signed-off-by: shen-shanshan <467638484@qq.com>
```
  7272bfae
- [Misc] fix collect_env version parse (#15267) · d9ac9e3d
  wangxiyuan authored Apr 21, 2025
```
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
```
  d9ac9e3d
- Restore buffers when wake up from level 2 sleep (#16564) (#16889) · d41faaf9
  Han Zhang authored Apr 21, 2025
```
Signed-off-by: Han <zh950713@gmail.com>
```
  d41faaf9
- [Bugfix] Fix distributed bug in Qwen2.5-VL & Qwen2.5-Omni (#16907) · 26c04065
  Yang Fan authored Apr 21, 2025
  
  26c04065
- [Bugfix] Fix v1/spec_decode/test_ngram.py (#16895) · bb3605db
  qizixi authored Apr 20, 2025
```
Signed-off-by: qizixi <qizixi@meta.com>
```
  bb3605db
20 Apr, 2025 2 commits
- [easy] Pass compile_fx only the config patches (#16845) · fe742aef
  Richard Zou authored Apr 20, 2025
```
Signed-off-by: rzou <zou3519@gmail.com>
```
  fe742aef
- Improve configs - `CacheConfig` (#16835) · 4b07d368
  Harry Mellor authored Apr 20, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  4b07d368
19 Apr, 2025 9 commits
- Serialize tensors using int8 views (#16866) · 87aaadef
  Staszek Paśko authored Apr 19, 2025
```
Signed-off-by: Staszek Pasko <staszek@gmail.com>
Co-authored-by: Nick Hill <nhill@redhat.com>
```
  87aaadef
- Log how much time loading a compiled artifact takes (#16848) · 682e0b6d
  Richard Zou authored Apr 19, 2025
```
Signed-off-by: rzou <zou3519@gmail.com>
```
  682e0b6d
- [VLM] Clean up models (#16873) · 205d84aa
  Cyrus Leung authored Apr 19, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  205d84aa
- [Model] Qwen2.5-Omni Cleanup (#16872) · 5124f5bf
  Roger Wang authored Apr 19, 2025
  
  5124f5bf
- [Model] Refactor Phi-4-multimodal to use merged processor and support V1 (#15477) · 83f3c3bd
  Isotr0py authored Apr 19, 2025
```
Signed-off-by: Isotr0py <2037008807@qq.com>
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  83f3c3bd
- [V1][Misc] stop update prefix cache stats when logs_stats is disabled (#16460) · d9737ca1
  vie-serendipity authored Apr 19, 2025
```
Signed-off-by: vie-serendipity <2733147505@qq.com>
```
  d9737ca1
- [Frontend] Add sampling params to `v1/audio/transcriptions` endpoint (#16591) · 2ef0dc53
  Nicolò Lucchesi authored Apr 19, 2025
```
Signed-off-by: Jannis Schönleber <joennlae@gmail.com>
Signed-off-by: NickLucche <nlucches@redhat.com>
Co-authored-by: Jannis Schönleber <joennlae@gmail.com>
```
  2ef0dc53
- [rocm][MI300] llama4 maverick fp8 moe config tp8 (#16847) · 1d4680fa
  Divakar Verma authored Apr 19, 2025
```
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
```
  1d4680fa
- [Model][VLM] Add Qwen2.5-Omni model support (thinker only) (#15130) · 2c1bd848
  Yang Fan authored Apr 19, 2025
```
Signed-off-by: fyabc <suyang.fy@alibaba-inc.com>
Signed-off-by: Roger Wang <ywang@roblox.com>
Co-authored-by: Roger Wang <136131678+ywang96@users.noreply.github.com>
Co-authored-by: Roger Wang <ywang@roblox.com>
Co-authored-by: Xiong Wang <wangxiongts@163.com>
```
  2c1bd848
18 Apr, 2025 11 commits
- [New Model]: Snowflake Arctic Embed (Family) (#16649) · 3d3ab368
  wang.yuqi authored Apr 18, 2025
  
  3d3ab368
- Fix `nullable_kvs` fallback (#16837) · 686623c5
  Harry Mellor authored Apr 18, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  686623c5
- [Misc] Clean up Kimi-VL (#16833) · aadb6565
  Cyrus Leung authored Apr 18, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  aadb6565
- [Model] use AutoWeightsLoader for BigCode, GPT-J (#16823) · 87e067de
  Jonghyun Choe authored Apr 18, 2025
```
Signed-off-by: Jonghyun Choe <andy.choe729@gmail.com>
```
  87e067de
- [Bugfix] fix pp for llama4 (#16746) · e31045f9
  Lucia Fang authored Apr 17, 2025
```
Signed-off-by: Lu Fang <fanglu@fb.com>
```
  e31045f9
- [ROCm] [Attention] Cleanup ROCm output passing (#16431) · aaec845f
  Luka Govedič authored Apr 18, 2025
```
Signed-off-by: Luka Govedič <lgovedic@redhat.com>
```
  aaec845f
- [Misc] add collect_env to cli and docker image (#16759) · 7bdfd29a
  rongfu.leng authored Apr 18, 2025
```
Signed-off-by: rongfu.leng <rongfu.leng@daocloud.io>
```
  7bdfd29a
- Improve-mm-and-pooler-and-decoding-configs (#16789) · e78587a6
  Harry Mellor authored Apr 18, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  e78587a6
- [BugFix] Accuracy fix for llama4 int4 - improperly casted scales (#16801) · 7eb42556
  Lucas Wilkinson authored Apr 18, 2025
```
Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>
```
  7eb42556
- [V1][Structured Output] Minor modification to `_validate_structured_output()` (#16748) · 30ed81b7
  Shanshan Shen authored Apr 18, 2025
```
Signed-off-by: shen-shanshan <467638484@qq.com>
```
  30ed81b7
- [Doc] Improve help examples for `--compilation-config` (#16729) · c16fb5da
  Cyrus Leung authored Apr 18, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  c16fb5da
17 Apr, 2025 12 commits
- [Attention] Update to lastest FA3 code (#13111) · 183dad7a
  Lucas Wilkinson authored Apr 17, 2025
```
Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>
```
  183dad7a
- [P/D][V1] KV Connector API V1 (#15960) · 3408e471
  Yihua Cheng authored Apr 17, 2025
```
Signed-off-by: ApostaC <yihua98@uchicago.edu>
Signed-off-by: rshaw@neuralmagic.com <robertgshaw2@gmail.com>
Signed-off-by: remi <remi@mistral.ai>
Co-authored-by: rshaw@neuralmagic.com <robertgshaw2@gmail.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
Co-authored-by: Rémi Delacourt <54138269+Flechman@users.noreply.github.com>
Co-authored-by: Tyler Michael Smith <tysmith@redhat.com>
```
  3408e471
- [MLA] Simplification to batch P/D reordering (#16673) · 0377b831
  Nick Hill authored Apr 17, 2025
```
Signed-off-by: Nick Hill <nhill@redhat.com>
```
  0377b831
- [V1][Metrics] Fix http metrics middleware (#15894) · e4755f7f
  Mark McLoughlin authored Apr 17, 2025
  
  e4755f7f
- [ROCM] enable aiter fused moe kernel for llama4 bf16 checkpoints (#16674) · 92edf358
  Sijia(Jackson) Chen authored Apr 17, 2025
  
  92edf358
- [V1][TPU] Enable Top K (#15489) · eb5819b2
  Nicolò Lucchesi authored Apr 17, 2025
```
Signed-off-by: NickLucche <nlucches@redhat.com>
Signed-off-by: Hyesoo Yang <hyeygit@gmail.com>
Co-authored-by: Hyesoo Yang <hyeygit@gmail.com>
```
  eb5819b2
- [TPU][V1] Fix padding recompilation when `max-num-batched-tokens` is not even (#16726) · 5989f468
  Nicolò Lucchesi authored Apr 17, 2025
```
Signed-off-by: NickLucche <nlucches@redhat.com>
```
  5989f468
- [Model] use AutoWeightsLoader for olmoe,opt,orion,persimmon,phi3_small (#16548) · 5125d72f
  rongfu.leng authored Apr 18, 2025
```
Signed-off-by: rongfu.leng <rongfu.leng@daocloud.io>
```
  5125d72f
- [Kernel] Add fp8_w8a8 fused MoE kernel tuning configs for DeepSeek V3/R1 on NVIDIA H20 (#16753) · a018e555
  Ximingwang-09 authored Apr 18, 2025
```
Signed-off-by: ximing.wxm <ximing.wxm@antgroup.com>
Co-authored-by: ximing.wxm <ximing.wxm@antgroup.com>
```
  a018e555
- [Bugfix]Fix index out of range error in api server log (#16787) · 6211b922
  Robin authored Apr 18, 2025
```
Signed-off-by: WangErXiao <863579016@qq.com>
```
  6211b922
- [V1][Perf] Faster incremental detokenization (#15137) · 05fcd1b4
  Nick Hill authored Apr 17, 2025
```
Signed-off-by: Nick Hill <nhill@redhat.com>
```
  05fcd1b4
- Improve configs - `TokenizerPoolConfig` + `DeviceConfig` (#16603) · d27ea940
  Harry Mellor authored Apr 17, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  d27ea940