8000 History for vllm/core - yx-lamini/vllm · GitHub

Repository navigation

Commits

History for

Commits on Dec 19, 2024
- [Misc] Remove unused vllm/block.py (#11336)
  Ghjk94522
  authored
  e461c26
Commits on Dec 14, 2024
- [Performance][Core] Optimize the performance of evictor v1 and v2 by applying a priority queue and lazy deletion (#7209)
  llsj14
  authored
  8869368
Commits on Dec 13, 2024
- [Core] support LoRA and prompt adapter in content-based hashing for Block Manager v2 prefix caching (#8240)
  llsj14
  authored
  c31d4a5
Commits on Dec 11, 2024
- [Doc] Update docs to refer to pooling models (#11093)
  DarkLight1337
  authored
  cad5c0a
- [Misc] Split up pooling tasks (#10820)
  DarkLight1337
  authored
  8f10d5e
- [Misc] LoRA + Chunked Prefill (#9057)
  aurickq
  authored
  d5c5154
Commits on Nov 26, 2024
- [Bugfix] Fix for Spec model TP + Chunked Prefill (#10232)
  
  andoorve
  and
  sroy745
  authored
  db66e01
Commits on Nov 25, 2024
- Support Cross encoder models (#10400)
  
  maxdebayser
  and
  flaviabeo
  authored
  214efc2
Commits on Nov 23, 2024
- Prefix Cache Aware Scheduling [1/n] (#10128)
  rickyyx
  authored
  4634a89
Commits on Nov 11, 2024
- [Doc] fix doc string typo in block_manager `swap_out` function (#10212)
  yyccli
  authored
  36fc439
Commits on Nov 7, 2024
- [Feature] [Spec decode]: Combine chunked prefill with speculative decoding (#9291)
  NickLucche
  authored
  9d43afc
Commits on Nov 6, 2024
- [Hardware][Intel-Gaudi] Add Intel Gaudi (HPU) inference backend (#6143)
  
  authored
  a02a50e
- [CI/Build] drop support for Python 3.8 EOL (#8464)
  aarnphm
  authored
  21063c1
Commits on Nov 1, 2024
- [Core][VLM] Add precise multi-modal placeholder tracking (#8346)
  petersalas
  authored
  6c0b7f5
- [Core] Refactor: Clean up unused argument in Scheduler._preempt (#9696)
  andrejonasson
  authored
  4581d2c
Commits on Oct 24, 2024
- [core] simplify seq group code (#9569)
  
  youkaichao
  and
  zhuohan123
  authored
  4fdc581
Commits on Oct 22, 2024
- [Core] Remove evictor_v1 (#9572)
  KuntaiDu
  authored
  ca30c3c
Commits on Oct 18, 2024
- [Model] Add user-configurable task for models that support both generation and embedding (#9424)
  DarkLight1337
  authored
  051eaf6
Commits on Oct 17, 2024
- [Core] Deprecating block manager v1 and make block manager v2 default (#8704)
  KuntaiDu
  authored
  81ede99
Commits on Oct 16, 2024
- [CI/Build] mypy: Resolve some errors from checking vllm/engine (#9267)
  russellb
  authored
  776dbd7
Commits on Oct 11, 2024
- [Doc] Remove outdated comment to avoid misunderstanding (#9287)
  homeffjy
  authored
  1a18238
- [Model] Support Mamba (#6484)
  tlrmchlsmth
  authored
  7342a7d
- [misc] hide best_of from engine (#9261)
  
  youkaichao
  and
  LunrEclipse
  authored
  cbc2ef5
Commits on Oct 8, 2024
- [Core][Frontend] Add Support for Inference Time mm_processor_kwargs (#9131)
  alex-jw-brooks
  authored
  a3691b6
Commits on Oct 7, 2024
Commits on Oct 2, 2024
- [Core] Combined support for multi-step scheduling, chunked prefill & prefix caching (#8804)
  
  authored
  563649a
Commits on Sep 29, 2024
- [Misc] Fix typo in BlockSpaceManagerV1 (#8944)
  juncheoll
  authored
  1fb9c1b
- [Bugfix] Block manager v2 with preemption and lookahead slots (#8824)
  sroy745
  authored
  5bf8789
Commits on Sep 27, 2024
- [Core] Multi-Step + Single Step Prefills via Chunked Prefill code path (#8378)
  
  varun-sundar-rabindranath
  and
  Varun Sundar Rabindranath
  authored
  c2ec430
Commits on Sep 25, 2024
- [Misc] Fix minor typo in scheduler (#8765)
  wooyeonlee0
  authored
  8fae5ed
- [Core] Adding Priority Scheduling (#5958)
  apatke
  authored
  6da1ab6
Commits on Sep 18, 2024
- [CI/Build] Update Ruff version (#8469)
  
  aarnphm
  and
  DarkLight1337
  authored
  9d104b5
Commits on Sep 8, 2024
- [Bugfix] Fix async postprocessor in case of preemption (#8267)
  alexm-redhat
  authored
  4ef41b8

0