@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / 2d867b55fa
Fork 0

A high-throughput and memory-efficient inference and serving engine for LLMs

Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git

Synced Nov 17, 08:00 UTC

fixed tensor parallel is not defined (#564)

MoeedDar committed Jul 25, 2023 at 22:16 UTC 2d867b55fa17840b50709fa12106e9fd6b2f527d
1 file changed -3
vllm/model_executor/parallel_utils/__init__.py
-3
@@ -1,9 +1,6 @@
1 import vllm.model_executor.parallel_utils.parallel_state
2 import vllm.model_executor.parallel_utils.tensor_parallel
3
4 -# Alias parallel_state as mpu, its legacy name
5 -mpu = parallel_state
6 -
4 __all__ = [
5 "parallel_state",
6 "tensor_parallel",