dschlueter
3cf9ef928b
Beide Rollen (Coder + Judge) auf einem llama.cpp-Server (Port 8001). switchModel wechselt zwischen qwen3.5-coder und qwen3.5-judge via llama-cpp-single-Provider ohne Server-Neustart. start-single.sh startet den gemeinsamen Server, GPU wählbar per GPU_DEVICE-Env-Variable. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
34 lines
902 B
Bash
Executable file
34 lines
902 B
Bash
Executable file
#!/usr/bin/env bash
|
|
|
|
check_server() {
|
|
local NAME="$1"
|
|
local PORT="$2"
|
|
local ALIAS="$3"
|
|
|
|
printf "%-28s" "$NAME (Port $PORT):"
|
|
|
|
# Docker-Status
|
|
if docker ps --format '{{.Names}}' | grep -q "^${NAME}\$"; then
|
|
printf " Container=\033[32mRUNNING\033[0m"
|
|
elif docker ps -a --format '{{.Names}}' | grep -q "^${NAME}\$"; then
|
|
printf " Container=\033[33mSTOPPED\033[0m"
|
|
else
|
|
printf " Container=\033[31mNOT FOUND\033[0m"
|
|
echo
|
|
return
|
|
fi
|
|
|
|
# HTTP-Erreichbarkeit
|
|
if curl -s --max-time 3 "http://localhost:${PORT}/health" >/dev/null 2>&1 || \
|
|
curl -s --max-time 3 "http://localhost:${PORT}/v1/models" >/dev/null 2>&1; then
|
|
printf " HTTP=\033[32mOK\033[0m"
|
|
else
|
|
printf " HTTP=\033[31mNOT READY\033[0m"
|
|
fi
|
|
|
|
echo
|
|
}
|
|
|
|
echo "=== LLaMA-Server Status ==="
|
|
check_server "qwen36-27b-coder" 8001 "qwen3.5-coder"
|
|
check_server "qwen36-27b-judge" 8002 "qwen3.5-judge"
|