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