Lumpiasty b0f20de80b qwen3.6 and cleanup of llama-swap config ...

- Deleting unused models
- Cleaned up, unified and fixed qwen3.5 sampling params to thinking and non-thinking params, no futrher differentiation
- kv cache quant q4_0 everywhere

2026-04-23 00:43:37 +02:00

..

configs

qwen3.6 and cleanup of llama-swap config

2026-04-23 00:43:37 +02:00

auth-proxy.yaml

Update caddy Docker tag to v2.11.2

2026-03-13 04:00:10 +01:00

deployment.yaml

Update ghcr.io/mostlygeek/llama-swap Docker tag to v204

2026-04-22 02:01:04 +00:00

ingress.yaml

move all ingresses to new nginx ingress

2026-03-13 04:00:07 +01:00

kustomization.yaml

migrate llama models to ssd

2026-03-13 04:00:10 +01:00

namespace.yaml

llama-swap

2026-03-13 04:00:07 +01:00

pvc-ssd.yaml

increase pvc for llama to 300 Gi

2026-04-04 22:49:26 +02:00

secret.yaml

get rid of openrouter proxying via llama-swap

2026-04-04 02:39:26 +02:00