Enable q4 KV cache and 128K context defaults 64daee6 verified AlexandreScriptsMT commited on 15 days ago
Use absolute llama-server path in entrypoint 6ca36c7 verified AlexandreScriptsMT commited on 15 days ago
Simplify Dockerfile for llama.cpp base image 6280c2f verified AlexandreScriptsMT commited on 15 days ago
Add README for Gemma 4 CPU Basic API Space 12010f8 verified AlexandreScriptsMT commited on 15 days ago
Add Dockerfile for llama.cpp server Space fde826b verified AlexandreScriptsMT commited on 15 days ago