8000 Commits · lamini-ai/vllm · GitHub

This repository was archived by the owner on Jun 13, 2025. It is now read-only.

Repository navigation

Commits

Commits on Mar 12, 2025
- Update README.md
  edamamez
  authored
  ada2b16
- Update LICENSE
  edamamez
  committed
  c2831ea
- Merge pull request #13 from lamini-ai/ez-lora-load-chat-completion
  edamamez
  authored
  5f7d97d
- Add lora loading to chat completions
  edamamez
  committed
  6a24059
Commits on Mar 11, 2025
- Add LICENSE
  edamamez
  committed
  aaa72e1
Commits on Mar 10, 2025
- update xgrammar == 0.1.7
  haofrank
  committed
  d2697a0
Commits on Feb 24, 2025
- Update README.md
  edamamez
  authored
  c1c4dd0
Commits on Feb 8, 2025
- Update README.md
  edamamez
  authored
  0f13a37
- Move to Lamini README
  edamamez
  committed
  305fe2c
- Create README.md
  
  yx-lamini
  authored and
  edamamez
  committed
  0d7305a
- Update README.md
  edamamez
  committed
  a1c0010
- [Lamini] Update README
  edamamez
  committed
  11da797
- Add implicit LoRA loading and unloading for completions
  edamamez
  committed
  74d8ec6
Commits on Feb 6, 2025
- [Misc] Improve error message for incorrect pynvml (#12809)
  youkaichao
  authored
  0408efc
- [Misc] Remove duplicated DeepSeek V2/V3 model definition (#12793)
  mgoin
  authored
  449d1bc
- Improve `TransformersModel` UX (#12785)
  hmellor
  authored
  1a6fcad
- [Bugfix] Fix the test_ultravox.py's license (#12806)
  houseroad
  authored
  56534cd
- [Model] LoRA Support for Ultravox model (#11253)
  thedebugger
  authored
  d88506d
- [Misc][Easy] Remove the space from the file name
  houseroad
  authored
  9cdea30
- [Bugfix] Better FP8 supported defaults
  LucasWilkinson
  authored
  76abd0c
- [ROCm][Kernel] Using the correct warp_size value
  gshtras
  authored
  5b19b93
- [VLM] Update compatibility with transformers 4.49
  DarkLight1337
  authored
  75404d0
Commits on Feb 5, 2025

0