Mathis/llamactl
1
0
Fork 0
mirror of https://github.com/lordmathis/llamactl.git synced 2025-11-05 16:44:22 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update Docker run commands to use cached directories and remove unnecessary environment variables

Browse Source
This commit is contained in:
Matúš Námešný
2025-09-28 19:05:43 +02:00
parent b940b38e46
commit 291ec7995f
1 changed files with 1 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
docs/getting-started/installation.md
View File

@@ -109,9 +109,7 @@ docker run -d \
--name llamactl-llamacpp \ --name llamactl-llamacpp \
--gpus all \ --gpus all \
-p 8080:8080 \ -p 8080:8080 \
-v $(pwd)/data/llamacpp:/data \ -v ~/.cache/llama.cpp:/root/.cache/llama.cpp \
-v $(pwd)/models:/models \
-e LLAMACTL_LLAMACPP_COMMAND=llama-server \
llamactl:llamacpp-cuda llamactl:llamacpp-cuda
``` ```
@@ -122,20 +120,10 @@ docker run -d \
--name llamactl-vllm \ --name llamactl-vllm \
--gpus all \ --gpus all \
-p 8080:8080 \ -p 8080:8080 \
-v $(pwd)/data/vllm:/data \
-v $(pwd)/models:/models \
-v ~/.cache/huggingface:/root/.cache/huggingface \ -v ~/.cache/huggingface:/root/.cache/huggingface \
-e LLAMACTL_VLLM_COMMAND=vllm \
-e LLAMACTL_VLLM_ARGS=serve \
llamactl:vllm-cuda 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 ### Option 3: Build from Source
Requirements: Requirements: