"vllm/tool_parsers/llama_tool_parser.py" did not exist on "02f0c7b220422792f5e53de2a7d51d2d3ff2df28"
  1. 25 Nov, 2024 1 commit
  2. 23 Nov, 2024 2 commits
  3. 20 Nov, 2024 1 commit
  4. 13 Nov, 2024 1 commit
  5. 11 Nov, 2024 1 commit
  6. 09 Nov, 2024 1 commit
  7. 07 Nov, 2024 1 commit
  8. 02 Nov, 2024 2 commits
  9. 01 Nov, 2024 1 commit
  10. 20 Oct, 2024 1 commit
  11. 16 Oct, 2024 1 commit
  12. 11 Oct, 2024 1 commit
  13. 08 Oct, 2024 1 commit
  14. 07 Oct, 2024 2 commits
  15. 25 Sep, 2024 1 commit
  16. 23 Sep, 2024 2 commits
  17. 12 Sep, 2024 1 commit
  18. 30 Aug, 2024 1 commit
  19. 21 Aug, 2024 1 commit
  20. 17 Aug, 2024 1 commit
  21. 31 Jul, 2024 1 commit
  22. 30 Jul, 2024 1 commit
  23. 26 Jul, 2024 1 commit
  24. 20 Jul, 2024 1 commit
  25. 09 Jul, 2024 1 commit
  26. 03 Jul, 2024 2 commits
  27. 02 Jul, 2024 2 commits
  28. 28 Jun, 2024 3 commits
  29. 26 Jun, 2024 1 commit
  30. 12 Jun, 2024 1 commit
  31. 03 Jun, 2024 1 commit
  32. 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