1. 25 May, 2024 1 commit
  2. 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
  3. 13 May, 2024 1 commit
  4. 08 May, 2024 2 commits
  5. 07 May, 2024 1 commit
  6. 03 May, 2024 1 commit
  7. 23 Apr, 2024 1 commit
  8. 11 Apr, 2024 1 commit
  9. 03 Apr, 2024 1 commit
  10. 25 Mar, 2024 1 commit