diff --git a/docker-compose.yml b/docker-compose.yml index c81eb5b..1baebca 100644 --- a/docker-compose.yml +++ b/docker-compose.yml @@ -23,6 +23,7 @@ services: --n-gpu-layers ${LLAMA_GPU_LAYERS:-999} --ctx-size ${LLAMA_CTX_SIZE:-262144} --parallel ${LLAMA_PARALLEL:-2} + --kv-unified --flash-attn on --cache-type-k q8_0 --cache-type-v q8_0