Compare commits
2 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| 12b69fb718 | |||
| f91a8b2462 |
@@ -2,7 +2,29 @@ ARG BASE_TAG=server-cuda
|
|||||||
FROM ghcr.io/ggml-org/llama.cpp:${BASE_TAG}
|
FROM ghcr.io/ggml-org/llama.cpp:${BASE_TAG}
|
||||||
|
|
||||||
# has to be after the FROM
|
# has to be after the FROM
|
||||||
ARG LS_VER=89
|
ARG LS_VER=170
|
||||||
|
|
||||||
|
# Set default UID/GID arguments
|
||||||
|
ARG UID=10001
|
||||||
|
ARG GID=10001
|
||||||
|
ARG USER_HOME=/app
|
||||||
|
|
||||||
|
# Add user/group
|
||||||
|
ENV HOME=$USER_HOME
|
||||||
|
RUN if [ $UID -ne 0 ]; then \
|
||||||
|
if [ $GID -ne 0 ]; then \
|
||||||
|
addgroup --system --gid $GID app; \
|
||||||
|
fi; \
|
||||||
|
adduser --system --no-create-home --uid $UID --gid $GID \
|
||||||
|
--home $USER_HOME app; \
|
||||||
|
fi
|
||||||
|
|
||||||
|
# Handle paths
|
||||||
|
RUN mkdir --parents $HOME /app
|
||||||
|
RUN chown --recursive $UID:$GID $HOME /app
|
||||||
|
|
||||||
|
# Switch user
|
||||||
|
USER $UID:$GID
|
||||||
|
|
||||||
WORKDIR /app
|
WORKDIR /app
|
||||||
RUN \
|
RUN \
|
||||||
@@ -10,7 +32,7 @@ RUN \
|
|||||||
tar -zxf llama-swap_"${LS_VER}"_linux_amd64.tar.gz && \
|
tar -zxf llama-swap_"${LS_VER}"_linux_amd64.tar.gz && \
|
||||||
rm llama-swap_"${LS_VER}"_linux_amd64.tar.gz
|
rm llama-swap_"${LS_VER}"_linux_amd64.tar.gz
|
||||||
|
|
||||||
COPY config.example.yaml /app/config.yaml
|
COPY --chown=$UID:$GID config.example.yaml /app/config.yaml
|
||||||
|
|
||||||
HEALTHCHECK CMD curl -f http://localhost:8080/ || exit 1
|
HEALTHCHECK CMD curl -f http://localhost:8080/ || exit 1
|
||||||
ENTRYPOINT [ "/app/llama-swap", "-config", "/app/config.yaml" ]
|
ENTRYPOINT [ "/app/llama-swap", "-config", "/app/config.yaml" ]
|
||||||
@@ -733,6 +733,14 @@ func (s *statusResponseWriter) statusUpdates(ctx context.Context) {
|
|||||||
s.wg.Add(1)
|
s.wg.Add(1)
|
||||||
defer s.wg.Done()
|
defer s.wg.Done()
|
||||||
|
|
||||||
|
// Recover from panics caused by client disconnection
|
||||||
|
// Note: recover() only works within the same goroutine, so we need it here
|
||||||
|
defer func() {
|
||||||
|
if r := recover(); r != nil {
|
||||||
|
s.process.proxyLogger.Debugf("<%s> statusUpdates recovered from panic (likely client disconnect): %v", s.process.ID, r)
|
||||||
|
}
|
||||||
|
}()
|
||||||
|
|
||||||
defer func() {
|
defer func() {
|
||||||
duration := time.Since(s.start)
|
duration := time.Since(s.start)
|
||||||
s.sendLine(fmt.Sprintf("\nDone! (%.2fs)", duration.Seconds()))
|
s.sendLine(fmt.Sprintf("\nDone! (%.2fs)", duration.Seconds()))
|
||||||
|
|||||||
Reference in New Issue
Block a user