phoenix-oss/llama-stack
1
0
Fork 0
forked from phoenix-oss/llama-stack-mirror
Code Pull requests Releases Packages 2 Activity Actions

fix: docker run with --pull always to fetch the latest image (#1733)

Browse source 
As titled
This commit is contained in:
Hardik Shah 2025-03-20 15:35:48 -07:00 • committed by GitHub
parent f95bc29ca9
commit 581e8ae562
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
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 \
@ -71,6 +72,7 @@ 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 \
@ -98,6 +100,7 @@ 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 \
@ -119,6 +122,7 @@ 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 \