server : add some missing env variables (#9116)
* server : add some missing env variables * add LLAMA_ARG_HOST to server dockerfile * also add LLAMA_ARG_CONT_BATCHING
This commit is contained in:
parent
2e59d61c1b
commit
a77feb5d71
7 changed files with 60 additions and 17 deletions
|
@ -24,6 +24,8 @@ ENV CUDA_DOCKER_ARCH=${CUDA_DOCKER_ARCH}
|
|||
ENV GGML_CUDA=1
|
||||
# Enable cURL
|
||||
ENV LLAMA_CURL=1
|
||||
# Must be set to 0.0.0.0 so it can listen to requests from host machine
|
||||
ENV LLAMA_ARG_HOST=0.0.0.0
|
||||
|
||||
RUN make -j$(nproc) llama-server
|
||||
|
||||
|
|
|
@ -26,6 +26,8 @@ RUN apt-get update && \
|
|||
COPY --from=build /app/build/bin/llama-server /llama-server
|
||||
|
||||
ENV LC_ALL=C.utf8
|
||||
# Must be set to 0.0.0.0 so it can listen to requests from host machine
|
||||
ENV LLAMA_ARG_HOST=0.0.0.0
|
||||
|
||||
HEALTHCHECK CMD [ "curl", "-f", "http://localhost:8080/health" ]
|
||||
|
||||
|
|
|
@ -39,6 +39,8 @@ ENV GPU_TARGETS=${ROCM_DOCKER_ARCH}
|
|||
ENV GGML_HIPBLAS=1
|
||||
ENV CC=/opt/rocm/llvm/bin/clang
|
||||
ENV CXX=/opt/rocm/llvm/bin/clang++
|
||||
# Must be set to 0.0.0.0 so it can listen to requests from host machine
|
||||
ENV LLAMA_ARG_HOST=0.0.0.0
|
||||
|
||||
# Enable cURL
|
||||
ENV LLAMA_CURL=1
|
||||
|
|
|
@ -23,6 +23,8 @@ RUN cp /app/build/bin/llama-server /llama-server && \
|
|||
rm -rf /app
|
||||
|
||||
ENV LC_ALL=C.utf8
|
||||
# Must be set to 0.0.0.0 so it can listen to requests from host machine
|
||||
ENV LLAMA_ARG_HOST=0.0.0.0
|
||||
|
||||
HEALTHCHECK CMD [ "curl", "-f", "http://localhost:8080/health" ]
|
||||
|
||||
|
|
|
@ -21,6 +21,8 @@ RUN apt-get update && \
|
|||
COPY --from=build /app/llama-server /llama-server
|
||||
|
||||
ENV LC_ALL=C.utf8
|
||||
# Must be set to 0.0.0.0 so it can listen to requests from host machine
|
||||
ENV LLAMA_ARG_HOST=0.0.0.0
|
||||
|
||||
HEALTHCHECK CMD [ "curl", "-f", "http://localhost:8080/health" ]
|
||||
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue