reorder
This commit is contained in:
@@ -13,10 +13,14 @@ set -euo pipefail
|
||||
REMOTE="tour@192.168.1.160"
|
||||
REMOTE_DIR="/media/tour/NVME0/llm"
|
||||
LLAMA_SERVER="$REMOTE_DIR/llama.cpp/build/bin/llama-server"
|
||||
MODEL="$REMOTE_DIR/models/cognitivecomputations_Dolphin3.0-Mistral-24B-Q4_K_M.gguf"
|
||||
# Q8_0: ~24GB — fits entirely on the MI50 32GB, better quality than Q4_K_M
|
||||
# Override: MODEL_FILE=cognitivecomputations_Dolphin3.0-Mistral-24B-Q4_K_M.gguf ./deploy_pose_llm.sh deploy
|
||||
MODEL_FILE="${MODEL_FILE:-cognitivecomputations_Dolphin3.0-Mistral-24B-Q8_0.gguf}"
|
||||
MODEL_URL="https://huggingface.co/bartowski/cognitivecomputations_Dolphin3.0-Mistral-24B-GGUF/resolve/main/${MODEL_FILE}"
|
||||
MODEL="$REMOTE_DIR/models/$MODEL_FILE"
|
||||
PORT="${PORT:-8001}"
|
||||
CTX="${CTX:-4096}"
|
||||
NGL="${NGL:-99}" # GPU layers: 99 = all on GPU
|
||||
CTX="${CTX:-16384}" # Q8 has headroom; bump context from 4096
|
||||
NGL="${NGL:-99}" # all layers on GPU (24GB < 32GB VRAM)
|
||||
|
||||
ACTION="${1:-deploy}"
|
||||
|
||||
@@ -42,8 +46,23 @@ stop_one() {
|
||||
"
|
||||
}
|
||||
|
||||
download_model() {
|
||||
print_header "Downloading $MODEL_FILE to $REMOTE"
|
||||
ssh "$REMOTE" "
|
||||
set -euo pipefail
|
||||
if [ -f '$MODEL' ]; then
|
||||
echo '==> Already exists:'; ls -lh '$MODEL'; exit 0
|
||||
fi
|
||||
echo '==> Downloading ~24GB — this will take a while...'
|
||||
mkdir -p '$REMOTE_DIR/models'
|
||||
wget -c --show-progress -O '${MODEL}.tmp' '$MODEL_URL'
|
||||
mv '${MODEL}.tmp' '$MODEL'
|
||||
echo '==> Done:'; ls -lh '$MODEL'
|
||||
"
|
||||
}
|
||||
|
||||
deploy_one() {
|
||||
print_header "Deploying llama-server on $REMOTE (model: Q4_K_M, ngl=$NGL)"
|
||||
print_header "Deploying llama-server on $REMOTE (model: Q8_0, ngl=$NGL)"
|
||||
|
||||
echo "==> Writing start script..."
|
||||
ssh "$REMOTE" "cat > '$REMOTE_DIR/start_pose_llm.sh'" << EOF
|
||||
@@ -96,9 +115,10 @@ status_one() {
|
||||
}
|
||||
|
||||
case "$ACTION" in
|
||||
deploy) deploy_one ;;
|
||||
stop) stop_one ;;
|
||||
restart) stop_one; deploy_one ;;
|
||||
status) status_one ;;
|
||||
*) echo "Usage: $0 [deploy|stop|restart|status]"; exit 1 ;;
|
||||
deploy) download_model; deploy_one ;;
|
||||
stop) stop_one ;;
|
||||
restart) stop_one; deploy_one ;;
|
||||
status) status_one ;;
|
||||
download) download_model ;;
|
||||
*) echo "Usage: $0 [deploy|stop|restart|status|download]"; exit 1 ;;
|
||||
esac
|
||||
|
||||
Reference in New Issue
Block a user