Commits · aaaec52ad9073ee5b80bced5d848fbff27ca64c0 · OpenDAS / vllm_cscc · GitLab

17 Mar, 2025 4 commits
- [Bugfix][Model] Mixtral: use unused head_dim config argument (#14961) · aaaec52a
  Quentin authored Mar 17, 2025
```
Signed-off-by: Quentin Torroba <quentin.torroba@mistral.ai>
```
  aaaec52a
- [Bugfix] Fix precommit - line too long in pixtral.py (#14960) · e1eb45d3
  Tyler Michael Smith authored Mar 17, 2025
```
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  e1eb45d3
- Add patch merger (#14957) · d20b0c13
  Patrick von Platen authored Mar 17, 2025
  
  d20b0c13
- [Bugfix] Fix Ultravox on V1 (#14929) · 868a8c5b
  Cyrus Leung authored Mar 17, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  868a8c5b
16 Mar, 2025 3 commits
- [Bugfix] Explicitly disable Phi-4-multimodal in V1 (#14889) · e53b1350
  Cyrus Leung authored Mar 17, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  e53b1350
- [Kernel] Add more tuned configs (#14877) · 71c1e071
  Simon Mo authored Mar 15, 2025
```
Signed-off-by: simon-mo <simon.mo@hey.com>
```
  71c1e071
- [VLM] Clean up Phi-4-MM ViT implementation (#14812) · def232e1
  Isotr0py authored Mar 16, 2025
```
Signed-off-by: Isotr0py <2037008807@qq.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
```
  def232e1
15 Mar, 2025 7 commits
- [VLM] Merged multi-modal processor for Pixtral (#12211) · 61c6a5a7
  Rémi Delacourt authored Mar 15, 2025
```
Signed-off-by: remi <remi@mistral.ai>
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  61c6a5a7
- [VLM] Limit multimodal input cache by memory (#14805) · 3556a414
  Cyrus Leung authored Mar 15, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  3556a414
- [Bugfix] EAGLE output norm bug (#14464) · 9ed6ee92
  Bryan Lu authored Mar 14, 2025
```
Signed-off-by: Bryan Lu <yuzhelu@amazon.com>
```
  9ed6ee92
- [V1] V1 Enablement Oracle (#13726) · d4d93db2
  Robert Shaw authored Mar 15, 2025
```
Signed-off-by: rshaw@neuralmagic.com <rshaw@neuralmagic.com>
Co-authored-by: rshaw@neuralmagic.com <rshaw@neuralmagic.com>
Co-authored-by: Nicolò Lucchesi <nlucches@redhat.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
Co-authored-by: Michael Goin <michael@neuralmagic.com>
```
  d4d93db2
- [Misc] Remove misleading message in gemma2 and gemma3 (#14850) · 97ac781c
  Isotr0py authored Mar 15, 2025
```
Signed-off-by: Isotr0py <2037008807@qq.com>
```
  97ac781c
- Disable outlines cache by default (#14837) · 776dcec8
  Russell Bryant authored Mar 14, 2025
  
  776dcec8
- Revert "[Model] Mamba2 Prefill Performance Tweaks: Fixing Flurry of U… (#14848) · ccf02fcb
  Tyler Michael Smith authored Mar 14, 2025
  
  ccf02fcb
14 Mar, 2025 6 commits
- [Model] Mamba2 Prefill Performance Tweaks: Fixing Flurry of Unnecessary Memory Copies (#14778) · fe66b347
  Chih-Chieh Yang authored Mar 14, 2025
```
Signed-off-by: Chih-Chieh-Yang <7364402+cyang49@users.noreply.github.com>
```
  fe66b347
- [VLM] Various cleanup and fixes (#14806) · ab93f136
  Cyrus Leung authored Mar 14, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  ab93f136
- [Misc] Gemma3ForConditionalGeneration supports LoRA (#14797) · 989ecd20
  Jee Jee Li authored Mar 14, 2025
```
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
```
  989ecd20
- [Misc] Clean up type annotation for `SupportsMultiModal` (#14794) · 601bd326
  Cyrus Leung authored Mar 14, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  601bd326
- [Attention] MLA get rid of materialization (#14770) · 9532c498
  Lucas Wilkinson authored Mar 14, 2025
```
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
```
  9532c498
- [Bugfix][IPEX] Add `VLLM_CPU_MOE_PREPACK` to allow disabling MoE prepack when... · 95d680b8
  Thien Tran authored Mar 14, 2025
```
[Bugfix][IPEX] Add `VLLM_CPU_MOE_PREPACK` to allow disabling MoE prepack when CPU does not support it (#14681)
Signed-off-by: Thien Tran <gau.nernst@yahoo.com.sg>
```
  95d680b8
13 Mar, 2025 9 commits
- [Attention] Remove slow setattr in MLA (#14769) · d47807ba
  Lucas Wilkinson authored Mar 13, 2025
```
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
```
  d47807ba
- [Bugfix] Fix prompt format of GLM4V (#14539) · f53a0586
  Cyrus Leung authored Mar 13, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  f53a0586
- [VLM] Support loading InternVideo2.5 models as original InternVLChatModel (#14738) · b1cc4dfe
  Isotr0py authored Mar 13, 2025
```
Signed-off-by: Isotr0py <2037008807@qq.com>
```
  b1cc4dfe
- [VLM] Support pan-and-scan for Gemma3 multi-modal processor (#14672) · 38240392
  Cyrus Leung authored Mar 13, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Signed-off-by: Roger Wang <ywang@roblox.com>
Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
Co-authored-by: Roger Wang <ywang@roblox.com>
```
  38240392
- [Bugfix] Fix chunked prefill for GGUF (#14666) · 55211b01
  Szymon Ożóg authored Mar 13, 2025
```
Signed-off-by: SzymonOzog <szymon.ozog@aleph-alpha.com>
```
  55211b01
- [Quant] Bamba SupportsQuant (#14698) · 5d043c16
  Kyle Sayers authored Mar 13, 2025
```
Signed-off-by: Kyle Sayers <kylesayrs@gmail.com>
```
  5d043c16
- [Quant] BartModel SupportsQuant (#14699) · 36d1ccb2
  Kyle Sayers authored Mar 13, 2025
```
Signed-off-by: Kyle Sayers <kylesayrs@gmail.com>
```
  36d1ccb2
- [BugFix][TritonMLA] Process weights after model loading for GGUF (#14555) · 128bf752
  TY-AMD authored Mar 13, 2025
```
Signed-off-by: TianyuanWu <Tianyuan.Wu@amd.com>
```
  128bf752
- [ROCm][FP8] Fix for adjustments needed only for fnuz (#14689) · a94a699c
  Gregory Shtrasberg authored Mar 12, 2025
```
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
```
  a94a699c
12 Mar, 2025 7 commits
- [Bugfix] Missing thumbnail from NVLM-D processor (#14633) · 4a754fcf
  ameyanjarlekar authored Mar 12, 2025
```
Signed-off-by: ameyanjarlekar <aanjarlekar@nvidia.com>
```
  4a754fcf
- [Model] Add support for Gemma 3 (#14660) · c0c25e25
  Woosuk Kwon authored Mar 12, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
Signed-off-by: Roger Wang <ywang@roblox.com>
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
Co-authored-by: Roger Wang <ywang@roblox.com>
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  c0c25e25
- [CPU] Upgrade CPU backend to torch-2.6 (#13381) · ff47aab0
  Li, Jiang authored Mar 12, 2025
```
Signed-off-by: jiang1.li <jiang1.li@intel.com>
Co-authored-by: Isotr0py <2037008807@qq.com>
```
  ff47aab0
- [Kernel] Add ModelOpt FP4 Checkpoint Support (#12520) · debd6bbf
  Pavani Majety authored Mar 11, 2025
```
Signed-off-by: Pavani Majety <pmajety@nvidia.com>
```
  debd6bbf
- [Kernel] GGUF MoE kernel (#14613) · e22ee1e7
  Szymon Ożóg authored Mar 12, 2025
```
Signed-off-by: SzymonOzog <szymon.ozog@aleph-alpha.com>
```
  e22ee1e7
- [Core] Refactor `QKVCrossParallelLinear` implementation to support BNB 4-bit quantization (#14545) · e392d858
  Isotr0py authored Mar 12, 2025
```
Signed-off-by: Isotr0py <2037008807@qq.com>
```
  e392d858
- [Model] Extend Ultravox to accept audio longer than 30s (#13631) · 80e78d02
  Farzad Abdolhosseini authored Mar 11, 2025
```
Signed-off-by: Farzad Abdolhosseini <farzad@fixie.ai>
```
  80e78d02
11 Mar, 2025 4 commits
- dynamic distpatch of fp8 kernels (#14245) · a1c8f379
  Jeff Daily authored Mar 11, 2025
```
Signed-off-by: Jeff Daily <jeff.daily@amd.com>
```
  a1c8f379
- [VLM] Cleanup siglip legacy code and fix broken paligemma multimodal processor (#14602) · 1477ffc3
  Isotr0py authored Mar 11, 2025
```
Signed-off-by: Isotr0py <2037008807@qq.com>
```
  1477ffc3
- [Perf]:Optimize qwen2-vl to reduce cudaMemcpyAsync (#14377) · 70b808fe
  yexin(叶鑫) authored Mar 11, 2025
```
Signed-off-by: cynthieye <987073381@qq.com>
```
  70b808fe
- [Bugfix] Fix FP16 overflow for DeepSeek V2 (#13232) · c982ac57
  Concurrensee authored Mar 10, 2025
```
Signed-off-by: Yida Wu <yida.wu@amd.com>
```
  c982ac57