Skip to content

Add env var based model selector #5

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
Simon-Count wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Add env var based model selector #5

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
46 changes: 30 additions & 16 deletions ci.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,3 +1,4 @@
schemaVersion: v0.2
prepare:
steps:
- name: Clone repository
Expand All @@ -8,23 +9,36 @@ prepare:
- name: Build Llama Cpp
command: cd llama.cpp && if [ -v NV_LIBCUBLAS_VERSION ]; then echo 'Make for
gpu' && cmake -B build -DGGML_CUDA=ON && cmake --build build --config
Release; else echo 'Make for cpu' && cmake -B build -DLLAMA_CURL=OFF && cmake --build
build --config Release -j 8 ; fi
Release; else echo 'Make for cpu' && cmake -B build -DLLAMA_CURL=OFF &&
cmake --build build --config Release -j 8 ; fi
- name: Download model
command: "[ -f
/home/user/app/llama.cpp/models/Meta-Llama-3.1-8B-Instruct-Q4_K_M.gguf ]
|| wget -P /home/user/app/llama.cpp/models
https://huggingface.co/lmstudio-community/Meta-Llama-3.1-8B-Instruct-GG\
UF/resolve/main/Meta-Llama-3.1-8B-Instruct-Q4_K_M.gguf"
command: MODEL_URL="https://huggingface.co/lmstudio-community/Meta-Llama-3.1-8B-Instruct-GGUF/resolve/main/Meta-Llama-3.1-8B-Instruct-Q4_K_M.gguf";
if [ -n "$HF_GGUF_URL" ]; then MODEL_URL="$HF_GGUF_URL"; fi;
MODEL_FILENAME=$(basename "$MODEL_URL"); [ -f
/home/user/app/llama.cpp/models/"$MODEL_FILENAME" ] || wget -P
/home/user/app/llama.cpp/models "$MODEL_URL"
test:
steps: []
run:
steps:
- name: Run
command: cd llama.cpp && if [ -v NV_LIBCUBLAS_VERSION ]; then echo 'Starting gpu
server' && ./build/bin/llama-server -m
./models/Meta-Llama-3.1-8B-Instruct-Q4_K_M.gguf -c 30000 --port 3000
--host 0.0.0.0 -ngl 35; else echo 'Starting cpu server'
&& ./build/bin/llama-server -m
./models/Meta-Llama-3.1-8B-Instruct-Q4_K_M.gguf -c 30000 --port 3000
--host 0.0.0.0 -t 8; fi
app:
steps:
- name: Run
command: if [ -n "$HF_GGUF_URL" ]; then MODEL_FILE_REF=$(basename
"$HF_GGUF_URL"); else
MODEL_FILE_REF="Meta-Llama-3.1-8B-Instruct-Q4_K_M.gguf"; fi;
MODEL_PATH="./models/$MODEL_FILE_REF"; cd llama.cpp && if [ -v
NV_LIBCUBLAS_VERSION ]; then echo 'Starting gpu server' &&
./build/bin/llama-server -m $MODEL_PATH -c 30000 --port 3000 --host
0.0.0.0 -ngl 35; else echo 'Starting cpu server' &&
./build/bin/llama-server -m $MODEL_PATH -c 30000 --port 3000 --host
0.0.0.0 -t 8; fi
plan: 21
replicas: 1
network:
ports:
- port: 3000
isPublic: false
paths:
- port: 3000
path: /
stripPath: false