1. 15 Jun, 2024 1 commit
  2. 13 Jun, 2024 1 commit
  3. 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
  4. 13 May, 2024 1 commit
  5. 09 May, 2024 1 commit
  6. 08 May, 2024 1 commit
  7. 07 May, 2024 1 commit
  8. 04 May, 2024 1 commit
  9. 03 May, 2024 1 commit
  10. 29 Apr, 2024 1 commit
  11. 26 Apr, 2024 1 commit
  12. 16 Apr, 2024 1 commit
  13. 11 Apr, 2024 1 commit
  14. 09 Apr, 2024 1 commit
  15. 03 Apr, 2024 1 commit
  16. 28 Mar, 2024 1 commit
  17. 25 Mar, 2024 4 commits
  18. 22 Mar, 2024 1 commit
  19. 20 Mar, 2024 2 commits
  20. 09 Mar, 2024 1 commit
  21. 04 Mar, 2024 1 commit
  22. 01 Feb, 2024 1 commit
  23. 23 Jan, 2024 1 commit
  24. 22 Jan, 2024 1 commit
  25. 18 Jan, 2024 1 commit
  26. 03 Jan, 2024 1 commit
  27. 03 Dec, 2023 1 commit
  28. 20 Nov, 2023 1 commit
  29. 08 Nov, 2023 1 commit