owen/worker-vllm
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

done

Browse Source
This commit is contained in:
Jorg Doku
2023-08-25 18:26:28 -05:00
parent e3cdd46a99
commit 51d231c37a
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
Dockerfile
+2 -2
View File
@@ -31,7 +31,7 @@ RUN --mount=type=cache,target=/root/.cache/pip \
ADD src .
# Quick temporary updates
RUN pip install git+https://github.com/runpod/runpod-python@main#egg=runpod --compile
RUN pip install git+https://github.com/runpod/runpod-python@a1#egg=runpod --compile
# Prepare the models inside the docker image
ARG HUGGING_FACE_HUB_TOKEN=
@@ -55,7 +55,7 @@ ENV TRANSFORMERS_CACHE="/runpod-volume/huggingface-cache/hub"
# Download the models
RUN mkdir -p /model
# RUN MODEL_NAME=$MODEL_NAME MODEL_REVISION=$MODEL_REVISION MODEL_BASE_PATH=$MODEL_BASE_PATH HUGGING_FACE_HUB_TOKEN=$HUGGING_FACE_HUB_TOKEN python -u /download_model.py
RUN MODEL_NAME=$MODEL_NAME MODEL_REVISION=$MODEL_REVISION MODEL_BASE_PATH=$MODEL_BASE_PATH HUGGING_FACE_HUB_TOKEN=$HUGGING_FACE_HUB_TOKEN python -u /download_model.py
# Start the handler
CMD STREAMING=$STREAMING MODEL_NAME=$MODEL_NAME MODEL_BASE_PATH=$MODEL_BASE_PATH TOKENIZER=$TOKENIZER python -u /handler.py