c121428c58
- llm-proxy.py v4: aggregator with classify/compress endpoints, gemma4 backend - classifier-server.py: Llama 3.2 1B query complexity classifier - compress-server.py: token-budget compression middleware - start-proxy.sh / start.sh: launcher scripts
7 lines
151 B
Bash
Executable File
7 lines
151 B
Bash
Executable File
#!/bin/bash
|
|
pkill -f llm-proxy.py 2>/dev/null
|
|
sleep 1
|
|
cd /home/mfritsche/npu
|
|
nohup python3 llm-proxy.py > proxy.log 2>&1 &
|
|
echo "proxy started PID $!"
|