1. 31 Aug, 2023 1 commit
  2. 30 Aug, 2023 1 commit
    • Bruce MacDonald's avatar
      subprocess llama.cpp server (#401) · 42998d79
      Bruce MacDonald authored
      * remove c code
      * pack llama.cpp
      * use request context for llama_cpp
      * let llama_cpp decide the number of threads to use
      * stop llama runner when app stops
      * remove sample count and duration metrics
      * use go generate to get libraries
      * tmp dir for running llm
      42998d79
  3. 18 Aug, 2023 1 commit
  4. 10 Aug, 2023 2 commits
  5. 02 Aug, 2023 1 commit
  6. 28 Jul, 2023 3 commits
  7. 27 Jul, 2023 2 commits
  8. 26 Jul, 2023 3 commits
  9. 25 Jul, 2023 1 commit
  10. 21 Jul, 2023 7 commits
  11. 19 Jul, 2023 2 commits
  12. 18 Jul, 2023 3 commits
  13. 17 Jul, 2023 10 commits
  14. 14 Jul, 2023 2 commits
  15. 11 Jul, 2023 1 commit