We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent 16af49c commit 7c1213eCopy full SHA for 7c1213e
docker/Dockerfile.rocm
@@ -114,12 +114,6 @@ ENV TOKENIZERS_PARALLELISM=false
114
# ENV that can improve safe tensor loading, and end-to-end time
115
ENV SAFETENSORS_FAST_GPU=1
116
117
-# User-friendly environment setting for multi-processing to avoid below RuntimeError.
118
-# RuntimeError: Cannot re-initialize CUDA in forked subprocess. To use CUDA with multiprocessing,
119
-# you must use the 'spawn' start method
120
-# See https://pytorch.org/docs/stable/notes/multiprocessing.html#cuda-in-multiprocessing
121
-ENV VLLM_WORKER_MULTIPROC_METHOD=spawn
122
-
123
# Performance environment variable.
124
ENV HIP_FORCE_DEV_KERNARG=1
125
0 commit comments