Skip to content

GitLab

"vllm/model_executor/models/yi.py" did not exist on "c9d5b6d4a8b3f51ff6c9eee7eb52bb5149d89b6a"
Switch branch/tag
  1. 03 Jan, 2024 1 commit
  3. 17 Dec, 2023 1 commit
  5. 15 Dec, 2023 1 commit
  7. 30 Nov, 2023 1 commit
  9. 28 Nov, 2023 1 commit
  11. 24 Nov, 2023 1 commit
  13. 21 Nov, 2023 1 commit
  15. 20 Nov, 2023 1 commit
  17. 19 Nov, 2023 1 commit
  19. 16 Nov, 2023 1 commit
    • Zhuohan Li's avatar
      TP/quantization/weight loading refactor part 2 - Refactor quantized linear... · 7076fa1c
      Zhuohan Li authored 
      TP/quantization/weight loading refactor part 2 - Refactor quantized linear logic and extend quantization support to all models (#1622)

Refactor the tensor parallelism, quantization, and weight-loading codes.

Summary of the new features enabled by this PR:
- **All models** are able to be quantized with AWQ and SqueezeLLM, and [soon GPTQ](https://github.com/vllm-project/vllm/pull/1580).
- Model loading code became much simpler.
- Support model parallelism for all MQA/GQA models when the number of key/value heads is smaller than the tensor parallel size.
      7076fa1c
  21. 02 Oct, 2023 1 commit
  23. 13 Sep, 2023 1 commit
  25. 07 Sep, 2023 1 commit
  27. 05 Sep, 2023 1 commit
  29. 03 Jul, 2023 1 commit
  31. 17 Jun, 2023 1 commit
  33. 25 May, 2023 1 commit
  35. 24 May, 2023 1 commit
  37. 19 May, 2023 1 commit
  39. 15 May, 2023 3 commits
  41. 09 May, 2023 1 commit
  43. 05 May, 2023 1 commit
  45. 04 May, 2023 1 commit
  47. 03 May, 2023 1 commit
  49. 28 Apr, 2023 1 commit
  51. 09 Apr, 2023 1 commit
  53. 02 Apr, 2023 2 commits
  55. 30 Mar, 2023 2 commits
  57. 21 Mar, 2023 1 commit
  59. 10 Mar, 2023 1 commit
  61. 25 Feb, 2023 1 commit
  63. 23 Feb, 2023 3 commits
  65. 22 Feb, 2023 1 commit
  67. 09 Feb, 2023 1 commit