Commits · 5952d8ab61a39eefd3617b7d46b7a6bd87f51259 · OpenDAS / vllm_cscc · GitLab

15 Mar, 2025 8 commits
- [Attention] Get rid of mla cache alignment (#14842) · 5952d8ab
  Lucas Wilkinson authored Mar 15, 2025
```
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
```
  5952d8ab
- [CPU] Support FP8 KV cache (#14741) · a2ae4965
  Li, Jiang authored Mar 15, 2025
```
Signed-off-by: jiang1.li <jiang1.li@intel.com>
```
  a2ae4965
- [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
- [Bugfix][V1] Fix flashinfer sampling (#14815) · acaea3bb
  DefTruth authored Mar 15, 2025
  
  acaea3bb
- [Bugfix] Fix torch_xla in V0 which can't handle None seed introduced … (#14844) · dd344e03
  yarongmu-google authored Mar 14, 2025
```
Signed-off-by: Yarong Mu <ymu@google.com>
```
  dd344e03
14 Mar, 2025 19 commits
- Update to torch==2.6.0 (#12721) · 14f301b5
  Michael Goin authored Mar 14, 2025
```
Signed-off-by: mgoin <michael@neuralmagic.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: luka <luka@neuralmagic.com>
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Co-authored-by: DarkLight1337 <tlleungac@connect.ust.hk>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  14f301b5
- [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
- [Frontend] track server_load (#13950) · 73deea2f
  daniel-salib authored Mar 14, 2025
  
  73deea2f
- [Frontend] Fix log message to use http vs https (#14774) · 0b0d6421
  Russell Bryant authored Mar 14, 2025
```
Signed-off-by: Russell Bryant <rbryant@redhat.com>
```
  0b0d6421
- [V1] Fix vocab size calculation for structured output (#14826) · 1140991a
  Russell Bryant authored Mar 14, 2025
```
Signed-off-by: Russell Bryant <rbryant@redhat.com>
```
  1140991a
- [BugFix]: properly catch templating error when preprocess input (#13976) · fd8e055f
  Guillaume Calmettes authored Mar 14, 2025
```
Signed-off-by: Guillaume Calmettes <gcalmettes@scaleway.com>
```
  fd8e055f
- [VLM] Various cleanup and fixes (#14806) · ab93f136
  Cyrus Leung authored Mar 14, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  ab93f136
- [V1][Minor] Minor code cleanup for scheduling metrics (#14800) · c77620d2
  Woosuk Kwon authored Mar 14, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  c77620d2
- [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
- [Misc][Minor] Simplify `SamplingParams.__post_init__()` (#14772) · 4059adc3
  Nick Hill authored Mar 13, 2025
```
Signed-off-by: Nick Hill <nhill@redhat.com>
```
  4059adc3
- [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
- [Kernel] [V1] Further optimizations to ROCm (Triton) Backend to better handle GQA. (#14431) · fb4c7f8e
  Thomas Parnell authored Mar 14, 2025
```
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
Co-authored-by: Jan van Lunteren <jvl@zurich.ibm.com>
Co-authored-by: Burkhard Ringlein <ngl@zurich.ibm.com>
Co-authored-by: Chih-Chieh Yang <chih.chieh.yang@ibm.com>
```
  fb4c7f8e
- [Kernel] LoRA - Enable CUDAGraphs for V1 (#14626) · 0b1cfa61
  Varun Sundar Rabindranath authored Mar 13, 2025
```
Signed-off-by: Varun Sundar Rabindranath <varun@neuralmagic.com>
Co-authored-by: Varun Sundar Rabindranath <varun@neuralmagic.com>
```
  0b1cfa61
- [V1] Temporarily disable FlashInfer Rejection Sampler (#14788) · 32ef4983
  Woosuk Kwon authored Mar 13, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  32ef4983
- [V1] Move OOM check into sampler run (#14728) · ad19c8a0
  Roger Wang authored Mar 13, 2025
```
Signed-off-by: Roger Wang <ywang@roblox.com>
Co-authored-by: Simon Mo <simon.mo@hey.com>
```
  ad19c8a0
- [V1] TPU - Enable prefix caching by default (#14773) · 7888e1d0
  Alexander Matveev authored Mar 13, 2025
  
  7888e1d0
- [Doc] Fix typo in documentation (#14783) · 3fb17d26
  yasu52 authored Mar 13, 2025
```
Signed-off-by: yasu52 <tsuguro4649@gmail.com>
```
  3fb17d26
13 Mar, 2025 13 commits
- [Attention] Remove slow setattr in MLA (#14769) · d47807ba
  Lucas Wilkinson authored Mar 13, 2025
```
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
```
  d47807ba
- [V1] Detokenizer: Respect Stop Tokens + not include_stop_str_in_output (#14624) · 02fcaa3d
  afeldman-nm authored Mar 13, 2025
```
Signed-off-by: Andrew Feldman <afeldman@neuralmagic.com>
```
  02fcaa3d
- [V1][Core] using cached vocab_size for Structured Outputs (#14630) · 8a4a2efc
  Aaron Pham authored Mar 13, 2025
```
Signed-off-by: Aaron Pham <contact@aarnphm.xyz>
```
  8a4a2efc
- [V1][Minor] Minor enhancements on scheduler (#14732) · 01b3fd0a
  Woosuk Kwon authored Mar 13, 2025
```
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
```
  01b3fd0a
- [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
- [V1][TPU] Add assertion on multi-step-scheduler (#14707) · 1bc3b739
  Siyuan Liu authored Mar 12, 2025
```
Signed-off-by: Siyuan Liu <lsiyuan@google.com>
```
  1bc3b739
- [Config][Disaggregated] Add timeout configuration for the torch.store and add... · 1bd32bc8
  Mathis Felardos authored Mar 13, 2025
```
[Config][Disaggregated] Add timeout configuration for the torch.store and add KVTransferConfig.kv_connector_extra_config (#14367)
Signed-off-by: Mathis Felardos <mathis@mistral.ai>
```
  1bd32bc8
- [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