vllm/cacheflow/model_executor/parallel_utils
2023-05-09 15:30:12 -07:00
..
tensor_parallel Refactor system architecture (#82) 2023-05-09 15:30:12 -07:00
__init__.py Refactor system architecture (#82) 2023-05-09 15:30:12 -07:00
parallel_state.py Refactor system architecture (#82) 2023-05-09 15:30:12 -07:00
README.md Refactor system architecture (#82) 2023-05-09 15:30:12 -07:00
utils.py Refactor system architecture (#82) 2023-05-09 15:30:12 -07:00

The files in this folder are ported from Megatron-LM. We only keep the codes that are used in inference.