Commits · 34120f5acd693924cc783dfaa33733afbe9ae8b0 · OpenDAS / vllm_cscc

"fern/pages/backends/vllm/LMCache-Integration.md" did not exist on "784da90ed06c31a460454023f8b59aa42a5ea3e6"

30 Apr, 2025 1 commit
- [V1][Feature] Enable Speculative Decoding with Structured Outputs (#14702) · 34120f5a
  Benjamin Chislett authored Apr 29, 2025
```
Signed-off-by: Benjamin Chislett <benjamin.chislett@centml.ai>
Signed-off-by: Benjamin Chislett <chislett.ben@gmail.com>
```
  34120f5a
29 Apr, 2025 22 commits
- [V1][Spec Decode] Apply torch.compile & cudagraph to EAGLE (#17211) · 70788bdb
  Bryan Lu authored Apr 29, 2025
```
Signed-off-by: Bryan Lu <yuzhelu@amazon.com>
```
  70788bdb
- Simplify (and fix) passing of guided decoding backend options (#17008) · a6977dbd
  Harry Mellor authored Apr 29, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  a6977dbd
- [Bugfix] Fix Minicpm-O-int4 GPTQ model inference (#17397) · 2fa2a50b
  Isotr0py authored Apr 30, 2025
```
Signed-off-by: Isotr0py <2037008807@qq.com>
```
  2fa2a50b
- fix gemma3 results all zero (#17364) · d3cf61b8
  Qiming Zhang authored Apr 29, 2025
```
Signed-off-by: mayuyuace <qiming1.zhang@intel.com>
```
  d3cf61b8
- [Bugfix] add qwen3 reasoning-parser fix content is None when disable … (#17369) · a39203f9
  mofanke authored Apr 30, 2025
```
Signed-off-by: mofanke <mofanke@gmail.com>
```
  a39203f9
- [V1] Remove num_input_tokens from attn_metadata (#17193) · 24e6ad3f
  Chen Zhang authored Apr 30, 2025
```
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
```
  24e6ad3f
- Improve literal dataclass field conversion to argparse argument (#17391) · 2ef5d106
  Harry Mellor authored Apr 29, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  2ef5d106
- Fix: Spelling of inference (#17387) · 0ed27ef6
  a2q1p authored Apr 30, 2025
  
  0ed27ef6
- Transformers backend tweaks (#17365) · 900edfa8
  Harry Mellor authored Apr 29, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  900edfa8
- [Frontend] Support `chat_template_kwargs` in `LLM.chat` (#17356) · 88ad9ec6
  Cyrus Leung authored Apr 29, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  88ad9ec6
- [Bugfix] Clean up MiniMax-VL and fix processing (#17354) · 00ee37ef
  Cyrus Leung authored Apr 29, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  00ee37ef
- [Model] Ignore rotary embed load for Cohere model (#17319) · 97cc8729
  Ekagra Ranjan authored Apr 29, 2025
  
  97cc8729
- [Fix] Documentation spacing in compilation config help text (#17342) · 193e78e3
  Hyogeun Oh (오효근) authored Apr 29, 2025
```
Signed-off-by: Zerohertz <ohg3417@gmail.com>
```
  193e78e3
- [Misc]Use a platform independent interface to obtain the device attributes (#17100) · bdb2cdda
  ponix-j authored Apr 29, 2025
  
  bdb2cdda
- [Misc] Move config fields to MultiModalConfig (#17343) · ebb3930d
  Cyrus Leung authored Apr 29, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  ebb3930d
- [Model] support MiniMax-VL-01 model (#16328) · cde384cd
  qscqesze authored Apr 29, 2025
```
Signed-off-by: qingjun <qingjun@minimaxi.com>
```
  cde384cd
- [Bugfix] Add contiguous call inside rope kernel wrapper (#17091) · 17eb306f
  Zhengyuan Su (苏政渊) authored Apr 29, 2025
```
Signed-off-by: 苏政渊 <suzhengyuan@moonshot.cn>
Co-authored-by: 苏政渊 <suzhengyuan@moonshot.cn>
```
  17eb306f
- Ignore `'<string>'` filepath (#17330) · 165cb563
  Richard Zou authored Apr 28, 2025
```
Signed-off-by: rzou <zou3519@gmail.com>
```
  165cb563
- [model] make llama4 compatible with pure dense layers (#17315) · b4ac4fa0
  Lucia Fang authored Apr 28, 2025
```
Signed-off-by: Lucia Fang <fanglu@fb.com>
```
  b4ac4fa0
- [V1][Spec Decode] Make Eagle model arch config driven (#17323) · e1360005
  Ekagra Ranjan authored Apr 28, 2025
  
  e1360005
- implement Structural Tag with Guidance backend (#17333) · 86d9fc29
  Michał Moskal authored Apr 28, 2025
```
Signed-off-by: Michal Moskal <michal@moskal.me>
```
  86d9fc29
- [Optim] Compute multimodal hash only once per item (#17314) · 506475de
  Cyrus Leung authored Apr 29, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  506475de
28 Apr, 2025 17 commits
- [Model] Add tuned triton fused_moe configs for Qwen3Moe (#17328) · 8fc88d63
  Michael Goin authored Apr 28, 2025
```
Signed-off-by: mgoin <mgoin64@gmail.com>
```
  8fc88d63
- Support loading transformers models with named parameters (#16868) · 6e74fd49
  Alex Wu authored Apr 28, 2025
```
Signed-off-by: Alex <alexwu@character.ai>
```
  6e74fd49
- [Model] Qwen3 Dense FP8 Compat Fixes (#17318) · dcbac4cb
  Simon Mo authored Apr 28, 2025
```
Signed-off-by: simon-mo <xmo@berkeley.edu>
```
  dcbac4cb
- [Bugfix] Fix moe weight losing all extra attrs after `process_weights_after_loading`. (#16854) · ed246203
  Charlie Fu authored Apr 28, 2025
```
Signed-off-by: charlifu <charlifu@amd.com>
```
  ed246203
- [BugFix] Fix cascade attention - RuntimeError: scheduler_metadata must have... · cc5befbc
  Lucas Wilkinson authored Apr 28, 2025
```
[BugFix] Fix cascade attention - RuntimeError: scheduler_metadata must have shape (metadata_size) (#17283)
Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>
```
  cc5befbc
- [Security] Don't bind tcp zmq socket to all interfaces (#17197) · a0304dc5
  Russell Bryant authored Apr 28, 2025
```
Signed-off-by: Russell Bryant <rbryant@redhat.com>
```
  a0304dc5
- Explicitly explain quant method override ordering and ensure all overrides are ordered (#17256) · c7941cca
  Harry Mellor authored Apr 28, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  c7941cca
- Make name of `compressed-tensors` quant method consistent across vLLM (#17255) · b6dd32aa
  Harry Mellor authored Apr 28, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  b6dd32aa
- Improve conversion from dataclass configs to argparse arguments (#17303) · f9488694
  Harry Mellor authored Apr 28, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  f9488694
- [Misc] Clean up Qwen2.5-Omni code (#17301) · 8b464d96
  Cyrus Leung authored Apr 28, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  8b464d96
- [Misc] Minor typo/grammar in `platforms/interface.py` (#17307) · 889ebb26
  Nicolò Lucchesi authored Apr 28, 2025
```
Signed-off-by: NickLucche <nlucches@redhat.com>
```
  889ebb26
- [Bugfix] Add missing `get_language_model` to new MLLMs (#17300) · 344e193b
  Cyrus Leung authored Apr 28, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  344e193b
- Add missing class docstring for `PromptAdapterConfig` (#17302) · fb1c933a
  Harry Mellor authored Apr 28, 2025
```
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
```
  fb1c933a
- Update tpu_worker.py 's typo (#17288) · 72c5b972
  idouba authored Apr 28, 2025
  
  72c5b972
- [Model] Add Granite Speech Support (#16246) · fa93cd9f
  Alex Brooks authored Apr 28, 2025
```
Signed-off-by: Alex-Brooks <Alex.brooks@ibm.com>
Signed-off-by: Alex-Brooks <Alex.Brooks@ibm.com>
```
  fa93cd9f
- [Core] Remove legacy input mapper/processor from V0 (#15686) · aec9674d
  Cyrus Leung authored Apr 28, 2025
```
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
```
  aec9674d
- [Minor][Models] Pass partial_rotary_factor parameter to rope (#17266) · 7fcc4223
  Wanrui Dai authored Apr 28, 2025
```
Signed-off-by: evian <eviantai@u.nus.edu>
Co-authored-by: evian <eviantai@u.nus.edu>
```
  7fcc4223