vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

server : add some missing env variables (#9116)

Browse source 
* server : add some missing env variables

* add LLAMA_ARG_HOST to server dockerfile

* also add LLAMA_ARG_CONT_BATCHING
This commit is contained in:
Xuan Son Nguyen 2024-08-27 11:07:01 +02:00 • committed by GitHub
parent 2e59d61c1b
commit a77feb5d71
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
7 changed files with 60 additions and 17 deletions
Download patch file Download diff file Expand all files Collapse all files

2
.devops/llama-server-cuda.Dockerfile
View file

@ -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