phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-17 16:32:38 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix doc

Browse source
This commit is contained in:
Xi Yan 2024-12-10 10:20:20 -08:00
parent fa68ded07c
commit d4141eb9a4
4 changed files with 8 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

2
llama_stack/templates/meta-reference-quantized-gpu/doc_template.md
View file

@ -52,6 +52,7 @@ LLAMA_STACK_PORT=5001
docker run \
-it \
-p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
-v ~/.llama:/root/.llama \
llamastack/distribution-{{ name }} \
--port $LLAMA_STACK_PORT \
--env INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct
@ -63,6 +64,7 @@ If you are using Llama Stack Safety / Shield APIs, use:
docker run \
-it \
-p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
-v ~/.llama:/root/.llama \
llamastack/distribution-{{ name }} \
--port $LLAMA_STACK_PORT \
--env INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct \