1. 15 Jul, 2024 1 commit
  2. 13 Jul, 2024 1 commit
  3. 12 Jul, 2024 1 commit
  4. 06 Jul, 2024 1 commit
  5. 05 Jul, 2024 1 commit
  6. 03 Jul, 2024 1 commit
  7. 01 Jul, 2024 1 commit
  8. 20 Jun, 2024 1 commit
  9. 13 Jun, 2024 1 commit
  10. 31 May, 2024 1 commit
  11. 28 May, 2024 1 commit
  12. 25 May, 2024 1 commit
  13. 16 May, 2024 1 commit
  14. 15 May, 2024 1 commit
    • SangBin Cho's avatar
      [Core][2/N] Model runner refactoring part 2. Combine prepare prefill / decode... · 65bf2ac1
      SangBin Cho authored
      [Core][2/N] Model runner refactoring part 2. Combine prepare prefill / decode to a single API (#4681)
      
      This PR combines prepare_prompt and prepare_decode into a single API. This PR also coelsce the attn metadata for prefill/decode to a single class and allow to slice them when running attn backend.
      
      It also refactors subquery_start_loc which was not refactored in the previous PR
      65bf2ac1
  15. 08 May, 2024 2 commits
  16. 07 May, 2024 1 commit
  17. 03 May, 2024 1 commit
  18. 02 May, 2024 1 commit
  19. 27 Apr, 2024 1 commit
  20. 18 Apr, 2024 1 commit
  21. 12 Apr, 2024 1 commit
  22. 11 Apr, 2024 2 commits
  23. 10 Apr, 2024 1 commit
  24. 09 Apr, 2024 1 commit
  25. 04 Apr, 2024 1 commit
  26. 03 Apr, 2024 1 commit
  27. 25 Mar, 2024 2 commits