phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2026-01-03 12:12:15 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Docker run with allways pull to fetch the latest

Browse source
This commit is contained in:
Hardik Shah 2025-03-20 15:30:04 -07:00
parent ea6a4a14ce
commit 7dd7ef701e
31 changed files with 57 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

4
docs/source/distributions/self_hosted_distro/remote-vllm.md
View file

@ -49,6 +49,7 @@ export INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct
export CUDA_VISIBLE_DEVICES=0
docker run \
--pull always \
--runtime nvidia \
--gpus $CUDA_VISIBLE_DEVICES \
-v ~/.cache/huggingface:/root/.cache/huggingface \
@ -69,6 +70,7 @@ export SAFETY_MODEL=meta-llama/Llama-Guard-3-1B
export CUDA_VISIBLE_DEVICES=1
docker run \
--pull always \
--runtime nvidia \
--gpus $CUDA_VISIBLE_DEVICES \
-v ~/.cache/huggingface:/root/.cache/huggingface \
@ -96,6 +98,7 @@ export LLAMA_STACK_PORT=5001
docker run \
-it \
--pull always \
-p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
-v ./run.yaml:/root/my-run.yaml \
llamastack/distribution-remote-vllm \
@ -117,6 +120,7 @@ cd /path/to/llama-stack
docker run \
-it \
--pull always \
-p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
-v ~/.llama:/root/.llama \
-v ./llama_stack/templates/remote-vllm/run-with-safety.yaml:/root/my-run.yaml \