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