1. 23 Jan, 2025 1 commit
  2. 25 Nov, 2024 1 commit
  3. 20 Nov, 2024 1 commit
  4. 18 Nov, 2024 1 commit
  5. 14 Nov, 2024 1 commit
  6. 06 Nov, 2024 2 commits
  7. 28 Oct, 2024 1 commit
  8. 22 Oct, 2024 1 commit
  9. 18 Sep, 2024 1 commit
  10. 12 Aug, 2024 1 commit
  11. 29 Jul, 2024 1 commit
  12. 27 Jul, 2024 1 commit
  13. 16 Jul, 2024 1 commit
  14. 15 Jul, 2024 1 commit
  15. 13 Jul, 2024 1 commit
  16. 12 Jul, 2024 1 commit
  17. 05 Jul, 2024 1 commit
  18. 03 Jul, 2024 1 commit
  19. 01 Jul, 2024 1 commit
  20. 13 Jun, 2024 1 commit
  21. 31 May, 2024 1 commit
  22. 28 May, 2024 1 commit
  23. 25 May, 2024 1 commit
  24. 16 May, 2024 1 commit
  25. 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
  26. 08 May, 2024 2 commits
  27. 07 May, 2024 1 commit
  28. 03 May, 2024 1 commit
  29. 02 May, 2024 1 commit
  30. 27 Apr, 2024 1 commit
  31. 18 Apr, 2024 1 commit
  32. 12 Apr, 2024 1 commit
  33. 11 Apr, 2024 2 commits
  34. 10 Apr, 2024 1 commit
  35. 09 Apr, 2024 1 commit
  36. 04 Apr, 2024 1 commit
  37. 03 Apr, 2024 1 commit