1. 25 Mar, 2025 1 commit
  2. 19 Mar, 2025 1 commit
  3. 13 Mar, 2025 1 commit
  4. 07 Mar, 2025 1 commit
  5. 25 Feb, 2025 2 commits
  6. 24 Feb, 2025 4 commits
  7. 20 Feb, 2025 1 commit
  8. 19 Feb, 2025 4 commits
  9. 06 Feb, 2025 6 commits
  10. 28 Jan, 2025 2 commits
  11. 23 Jan, 2025 3 commits
  12. 22 Jan, 2025 1 commit
  13. 14 Jan, 2025 3 commits
  14. 17 Dec, 2024 2 commits
  15. 11 Dec, 2024 1 commit
  16. 10 Dec, 2024 2 commits
  17. 05 Dec, 2024 2 commits
    • Matthew Douglas's avatar
      Release 0.45.0 · 64d382da
      Matthew Douglas authored
      64d382da
    • Matthew Douglas's avatar
      LLM.int8() Refactoring: Part 1 (#1401) · 81e6345d
      Matthew Douglas authored
      
      
      * Start of int8 refactor: remove col32/col_ampere/col_turing transforms in new igemmlt implementation
      
      * Fix unintended change
      
      * New naive mm_dequant kernel for row-major; cleanup
      
      * fix
      
      * int8 refactor: initial sparse decomp, cleanup
      
      * Int8 refactoring: remove separate NO_CUBLASLT build; more cleanup
      
      * int8: inference optimizations, some cleanup
      
      * int8: more tests passing, cleanup
      
      * int8 - more cleanup, most tests passing
      
      * int8: specify CUDA stream for int8 ops
      
      * perf: reduce overhead from getting cudaStream ptr
      
      * Mark some functions for deprecation.
      
      * int8 sparse decomp: small perf improvement
      
      * update setup.py
      
      * Update bitsandbytes/autograd/_functions.py
      Co-authored-by: default avatarAarni Koskela <akx@iki.fi>
      
      * Update bitsandbytes/functional.py
      Co-authored-by: default avatarAarni Koskela <akx@iki.fi>
      
      * Update bitsandbytes/functional.py
      Co-authored-by: default avatarAarni Koskela <akx@iki.fi>
      
      * Update bitsandbytes/research/autograd/_functions.py
      ...
      81e6345d
  18. 02 Dec, 2024 1 commit
  19. 19 Nov, 2024 1 commit
  20. 14 Nov, 2024 1 commit