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