TP/quantization/weight loading refactor part 1 - Simplify parallel linear logic (#1181)

This commit is contained in:
Zhuohan Li
2023-10-02 15:36:09 -07:00
committed by GitHub
parent 84e4e37d14
commit ba0bfd40e2
42 changed files with 819 additions and 1547 deletions

View File

@@ -28,4 +28,4 @@ jobs:
pip install pylint==2.8.2
- name: Analysing the code with pylint
run: |
pylint vllm
pylint vllm tests

View File

@@ -28,4 +28,4 @@ jobs:
pip install toml==0.10.2
- name: Running yapf
run: |
yapf --diff --recursive vllm --exclude 'vllm/model_executor/parallel_utils/**'
yapf --diff --recursive vllm tests