1. 09 Apr, 2024 1 commit
  2. 05 Apr, 2024 1 commit
  3. 03 Apr, 2024 1 commit
  4. 02 Apr, 2024 1 commit
  5. 29 Mar, 2024 1 commit
  6. 28 Mar, 2024 2 commits
  7. 27 Mar, 2024 2 commits
  8. 25 Mar, 2024 3 commits
  9. 22 Mar, 2024 1 commit
  10. 20 Mar, 2024 4 commits
  11. 18 Mar, 2024 1 commit
  12. 17 Mar, 2024 1 commit
  13. 11 Mar, 2024 1 commit
  14. 09 Mar, 2024 1 commit
  15. 08 Mar, 2024 1 commit
  16. 07 Mar, 2024 1 commit
  17. 05 Mar, 2024 1 commit
  18. 04 Mar, 2024 1 commit
  19. 02 Mar, 2024 1 commit
  20. 28 Feb, 2024 1 commit
  21. 21 Feb, 2024 1 commit
  22. 18 Feb, 2024 1 commit
  23. 14 Feb, 2024 2 commits
  24. 13 Feb, 2024 2 commits
    • Terry's avatar
      Add LoRA support for Mixtral (#2831) · 2a543d6e
      Terry authored
      * add mixtral lora support
      
      * formatting
      
      * fix incorrectly ported logic
      
      * polish tests
      
      * minor fixes and refactoring
      
      * minor fixes
      
      * formatting
      
      * rename and remove redundant logic
      
      * refactoring
      
      * refactoring
      
      * minor fix
      
      * minor refactoring
      
      * fix code smell
      2a543d6e
    • Woosuk Kwon's avatar
      Use CuPy for CUDA graphs (#2811) · a463c333
      Woosuk Kwon authored
      a463c333
  25. 01 Feb, 2024 1 commit
  26. 31 Jan, 2024 1 commit
  27. 29 Jan, 2024 1 commit
  28. 27 Jan, 2024 1 commit
  29. 23 Jan, 2024 1 commit
  30. 22 Jan, 2024 1 commit
  31. 19 Jan, 2024 1 commit