Initial commit: Boltzmann LLM proxy with compression + classifier middleware

- 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
2026-06-15 15:12:25 +02:00
commit c121428c58
8 changed files with 712 additions and 0 deletions
@@ -0,0 +1,6 @@
+#!/bin/bash
+pkill -f llamafile 2>/dev/null
+sleep 1
+cd /home/mfritsche/npu
+nohup ./llamafile --server -m qwen2.5-coder-1.5b-q4_k_m.gguf -c 32768 -t 4 --host 0.0.0.0 --port 8081 > llamafile.log 2>&1 &
+echo started PID $!