Commit History
-
Document 128K context and KV cache quantization defaults
Verified signature5717969 -
Enable q4 KV cache and 128K context defaults
Verified signature64daee6 -
Use absolute llama-server path in entrypoint
Verified signature6ca36c7 -
Simplify Dockerfile for llama.cpp base image
Verified signature6280c2f -
Add README for Gemma 4 CPU Basic API Space
Verified signature12010f8 -
Add runtime entrypoint for Gemma 4 API
Verified signature43aaf2b -
Add Dockerfile for llama.cpp server Space
Verified signaturefde826b -
initial commit
Verified signature00bfb44