Davide Polonio 8ab4213b62 feat(ollama): add persistence in Ollama container ...

Re-enable qwen3.5:9b and qwen3.5:9bctxSmall using fresh unsloth/Qwen3.5-9B-GGUF
quantization, which uses the correct rope.dimension_sections format (4 elements)
compatible with this llama.cpp build. Both models include the mmproj for
multimodal support. The old Ollama-extracted GGUF (mrope_sections, 3 elements)
has been removed.

2026-04-10 10:57:34 +02:00

..

Caddyfile

feat(ollama): migrate from Ollama to llama.cpp + llama-swap

2026-04-09 23:14:43 +02:00

docker-compose.yml

fix(ollama): restrict to RX 9070 XT, restore mmproj

2026-04-10 00:09:12 +02:00

Dockerfile

feat(ollama): migrate from Ollama to llama.cpp + llama-swap

2026-04-09 23:14:43 +02:00

llama-swap.yaml

feat(ollama): add persistence in Ollama container

2026-04-10 10:57:34 +02:00