dearwolf/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2025-06-29 14:14:59 +00:00
Code Issues Projects Releases Packages Wiki Activity

Bump llama.cpp to support full CUDA offload

Browse source
This commit is contained in:
mudler 2023-06-18 00:16:08 +02:00
parent 9b498dc76a
commit a9559fa8ce
2 changed files with 4 additions and 7 deletions
Download patch file Download diff file Expand all files Collapse all files

9
Dockerfile
View file

@ -41,10 +41,6 @@ ENV NVIDIA_VISIBLE_DEVICES=all
WORKDIR /build WORKDIR /build
COPY Makefile .
RUN make get-sources
COPY go.mod .
RUN make prepare
COPY . . COPY . .
RUN make build RUN make build
@ -62,12 +58,13 @@ RUN if [ "${FFMPEG}" = "true" ]; then \
WORKDIR /build WORKDIR /build
COPY . .
RUN make prepare-sources
COPY --from=builder /build/local-ai ./ COPY --from=builder /build/local-ai ./
COPY entrypoint.sh .
# Define the health check command # Define the health check command
HEALTHCHECK --interval=1m --timeout=10m --retries=10 \ HEALTHCHECK --interval=1m --timeout=10m --retries=10 \
CMD curl -f $HEALTHCHECK_ENDPOINT || exit 1 CMD curl -f $HEALTHCHECK_ENDPOINT || exit 1
EXPOSE 8080 EXPOSE 8080
ENTRYPOINT [ "/build/entrypoint.sh" ] ENTRYPOINT [ "/build/entrypoint.sh" ]

2
Makefile
View file

@ -3,7 +3,7 @@ GOTEST=$(GOCMD) test
GOVET=$(GOCMD) vet GOVET=$(GOCMD) vet
BINARY_NAME=local-ai BINARY_NAME=local-ai
GOLLAMA_VERSION?=5f1620443a59c5531b5a15a16cd68f600a8437e9 GOLLAMA_VERSION?=7ad833b67070fd3ec46d838f5e38d21111013f98
GPT4ALL_REPO?=https://github.com/nomic-ai/gpt4all GPT4ALL_REPO?=https://github.com/nomic-ai/gpt4all
GPT4ALL_VERSION?=b004c53a7bba182cd4483d95ba9e1f68d8e56da3 GPT4ALL_VERSION?=b004c53a7bba182cd4483d95ba9e1f68d8e56da3
GOGGMLTRANSFORMERS_VERSION?=01b8436f44294d0e1267430f9eda4460458cec54 GOGGMLTRANSFORMERS_VERSION?=01b8436f44294d0e1267430f9eda4460458cec54