1. 23 Jan, 2025 1 commit
  2. 16 Dec, 2024 1 commit
  3. 13 Dec, 2024 1 commit
  4. 03 Dec, 2024 1 commit
  5. 01 Dec, 2024 1 commit
  6. 02 Nov, 2024 1 commit
  7. 01 Nov, 2024 1 commit
  8. 22 Oct, 2024 1 commit
  9. 19 Oct, 2024 1 commit
  10. 18 Oct, 2024 1 commit
  11. 21 Sep, 2024 1 commit
  12. 19 Sep, 2024 1 commit
  13. 18 Sep, 2024 1 commit
  14. 17 Sep, 2024 1 commit
  15. 20 Aug, 2024 1 commit
  16. 19 Aug, 2024 2 commits
  17. 16 Aug, 2024 1 commit
  18. 09 Aug, 2024 1 commit
  19. 06 Aug, 2024 1 commit
  20. 25 Jul, 2024 1 commit
  21. 17 Jul, 2024 1 commit
  22. 09 Jul, 2024 1 commit
  23. 02 Jul, 2024 1 commit
  24. 26 Jun, 2024 1 commit
  25. 15 Jun, 2024 1 commit
  26. 13 Jun, 2024 1 commit
  27. 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
  28. 13 May, 2024 1 commit
  29. 09 May, 2024 1 commit
  30. 08 May, 2024 1 commit
  31. 07 May, 2024 1 commit
  32. 04 May, 2024 1 commit
  33. 03 May, 2024 1 commit
  34. 29 Apr, 2024 1 commit
  35. 26 Apr, 2024 1 commit
  36. 16 Apr, 2024 1 commit
  37. 11 Apr, 2024 1 commit
  38. 09 Apr, 2024 1 commit
  39. 03 Apr, 2024 1 commit