1. 03 Jan, 2025 1 commit
  2. 01 Jan, 2025 1 commit
  3. 20 Dec, 2024 1 commit
  4. 18 Nov, 2024 1 commit
  5. 22 Sep, 2024 1 commit
  6. 02 Sep, 2024 1 commit
  7. 09 Aug, 2024 1 commit
  8. 30 Jul, 2024 1 commit
  9. 19 Jul, 2024 1 commit
  10. 01 Jul, 2024 1 commit
  11. 18 Jun, 2024 1 commit
  12. 11 Jun, 2024 1 commit
  13. 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
  14. 08 May, 2024 1 commit
  15. 23 Apr, 2024 1 commit
  16. 25 Mar, 2024 1 commit
  17. 09 Mar, 2024 1 commit
  18. 09 Jan, 2024 1 commit