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",