Markus Fritsche c121428c58 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

.gitignore

Initial commit: Boltzmann LLM proxy with compression + classifier middleware

2026-06-15 15:12:25 +02:00

classifier-server.py

Initial commit: Boltzmann LLM proxy with compression + classifier middleware

2026-06-15 15:12:25 +02:00

compress-server.py

Initial commit: Boltzmann LLM proxy with compression + classifier middleware

2026-06-15 15:12:25 +02:00

download-models.sh

Initial commit: Boltzmann LLM proxy with compression + classifier middleware

2026-06-15 15:12:25 +02:00

launch-qwen35-npu.sh

Initial commit: Boltzmann LLM proxy with compression + classifier middleware

2026-06-15 15:12:25 +02:00

llm-proxy.py

Initial commit: Boltzmann LLM proxy with compression + classifier middleware

2026-06-15 15:12:25 +02:00

start-proxy.sh

Initial commit: Boltzmann LLM proxy with compression + classifier middleware

2026-06-15 15:12:25 +02:00

start.sh

Initial commit: Boltzmann LLM proxy with compression + classifier middleware

2026-06-15 15:12:25 +02:00

S

Description

Boltzmann LLM proxy with compression + classifier middleware

66 KiB

Languages

Python 96.5%

Shell 3.5%