From 291ec7995f0c80f4d272601d99c020138e194ed9 Mon Sep 17 00:00:00 2001 From: LordMathis Date: Sun, 28 Sep 2025 19:05:43 +0200 Subject: [PATCH] Update Docker run commands to use cached directories and remove unnecessary environment variables --- docs/getting-started/installation.md | 14 +------------- 1 file changed, 1 insertion(+), 13 deletions(-) diff --git a/docs/getting-started/installation.md b/docs/getting-started/installation.md index f4d4b3d..703ab0b 100644 --- a/docs/getting-started/installation.md +++ b/docs/getting-started/installation.md @@ -109,9 +109,7 @@ docker run -d \ --name llamactl-llamacpp \ --gpus all \ -p 8080:8080 \ - -v $(pwd)/data/llamacpp:/data \ - -v $(pwd)/models:/models \ - -e LLAMACTL_LLAMACPP_COMMAND=llama-server \ + -v ~/.cache/llama.cpp:/root/.cache/llama.cpp \ llamactl:llamacpp-cuda ``` @@ -122,20 +120,10 @@ docker run -d \ --name llamactl-vllm \ --gpus all \ -p 8080:8080 \ - -v $(pwd)/data/vllm:/data \ - -v $(pwd)/models:/models \ -v ~/.cache/huggingface:/root/.cache/huggingface \ - -e LLAMACTL_VLLM_COMMAND=vllm \ - -e LLAMACTL_VLLM_ARGS=serve \ llamactl:vllm-cuda ``` -**Docker-Specific Configuration:** -- Set `LLAMACTL_LLAMACPP_COMMAND=llama-server` to use the pre-installed llama-server -- Set `LLAMACTL_VLLM_COMMAND=vllm` to use the pre-installed vLLM -- Volume mount `/data` for llamactl data and `/models` for your model files -- Use `--gpus all` for GPU access - ### Option 3: Build from Source Requirements: