Add Qwen2.5 tokenizer compatibility engine and runner workflow
This commit is contained in:
12
Dockerfile
Normal file
12
Dockerfile
Normal file
@@ -0,0 +1,12 @@
|
||||
ARG BASE_IMAGE=harbor.4pd.io/dooke/vllm/vllm/vllm-openai:v0.11.0
|
||||
FROM ${BASE_IMAGE}
|
||||
|
||||
COPY engine_compat.py /opt/modelhub/engine_compat.py
|
||||
COPY vllm_wrapper.sh /opt/modelhub/vllm_wrapper.sh
|
||||
|
||||
RUN set -eu; \
|
||||
python3 -m py_compile /opt/modelhub/engine_compat.py; \
|
||||
vllm_bin="$(command -v vllm)"; \
|
||||
mv "$vllm_bin" "$(dirname "$vllm_bin")/vllm_real"; \
|
||||
cp /opt/modelhub/vllm_wrapper.sh "$vllm_bin"; \
|
||||
chmod 0755 "$vllm_bin" /opt/modelhub/engine_compat.py
|
||||
Reference in New Issue
Block a user