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

1
llama_stack/templates/bedrock/doc_template.md
View file

@ -50,6 +50,7 @@ This method allows you to get started quickly without having to build the distri
LLAMA_STACK_PORT=5001
docker run \
-it \
--pull always \
-p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
llamastack/distribution-{{ name }} \
--port $LLAMA_STACK_PORT \

1
llama_stack/templates/cerebras/doc_template.md
View file

@ -42,6 +42,7 @@ This method allows you to get started quickly without having to build the distri
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-{{ name }} \

4
llama_stack/templates/dell/doc_template.md
View file

@ -43,6 +43,7 @@ export CUDA_VISIBLE_DEVICES=0
export LLAMA_STACK_PORT=8321
docker run --rm -it \
--pull always \
--network host \
-v $HOME/.cache/huggingface:/data \
-e HF_TOKEN=$HF_TOKEN \
@ -66,6 +67,7 @@ export SAFETY_MODEL=meta-llama/Llama-Guard-3-1B
export CUDA_VISIBLE_DEVICES=1
docker run --rm -it \
--pull always \
--network host \
-v $HOME/.cache/huggingface:/data \
-e HF_TOKEN=$HF_TOKEN \
@ -108,6 +110,7 @@ This method allows you to get started quickly without having to build the distri
```bash
docker run -it \
--pull always \
--network host \
-p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
-v $HOME/.llama:/root/.llama \
@ -135,6 +138,7 @@ export SAFETY_MODEL=meta-llama/Llama-Guard-3-1B
docker run \
-it \
--pull always \
-p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
-v $HOME/.llama:/root/.llama \
-v ./llama_stack/templates/tgi/run-with-safety.yaml:/root/my-run.yaml \

1
llama_stack/templates/fireworks/doc_template.md
View file

@ -52,6 +52,7 @@ This method allows you to get started quickly without having to build the distri
LLAMA_STACK_PORT=5001
docker run \
-it \
--pull always \
-p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
llamastack/distribution-{{ name }} \
--port $LLAMA_STACK_PORT \

1
llama_stack/templates/groq/doc_template.md
View file

@ -52,6 +52,7 @@ This method allows you to get started quickly without having to build the distri
LLAMA_STACK_PORT=5001
docker run \
-it \
--pull always \
-p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
llamastack/distribution-{{ name }} \
--port $LLAMA_STACK_PORT \

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

@ -68,6 +68,7 @@ This method allows you to get started quickly without having to build the distri
LLAMA_STACK_PORT=5001
docker run \
-it \
--pull always \
-p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
-v ~/.llama:/root/.llama \
llamastack/distribution-{{ name }} \
@ -80,6 +81,7 @@ If you are using Llama Stack Safety / Shield APIs, use:
```bash
docker run \
-it \
--pull always \
-p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
-v ~/.llama:/root/.llama \
llamastack/distribution-{{ name }} \

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

@ -70,6 +70,7 @@ This method allows you to get started quickly without having to build the distri
LLAMA_STACK_PORT=5001
docker run \
-it \
--pull always \
-p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
-v ~/.llama:/root/.llama \
llamastack/distribution-{{ name }} \
@ -82,6 +83,7 @@ If you are using Llama Stack Safety / Shield APIs, use:
```bash
docker run \
-it \
--pull always \
-p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
-v ~/.llama:/root/.llama \
llamastack/distribution-{{ name }} \

1
llama_stack/templates/nvidia/doc_template.md
View file

@ -42,6 +42,7 @@ This method allows you to get started quickly without having to build the distri
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-{{ name }} \

2
llama_stack/templates/ollama/doc_template.md
View file

@ -63,6 +63,7 @@ This method allows you to get started quickly without having to build the distri
export LLAMA_STACK_PORT=5001
docker run \
-it \
--pull always \
-p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
-v ~/.llama:/root/.llama \
llamastack/distribution-{{ name }} \
@ -80,6 +81,7 @@ 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/ollama/run-with-safety.yaml:/root/my-run.yaml \

4
llama_stack/templates/remote-vllm/doc_template.md
View file

@ -36,6 +36,7 @@ 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 \
@ -58,6 +59,7 @@ 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 \
@ -85,6 +87,7 @@ 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-{{ name }} \
@ -106,6 +109,7 @@ 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 \

1
llama_stack/templates/sambanova/doc_template.md
View file

@ -52,6 +52,7 @@ This method allows you to get started quickly without having to build the distri
LLAMA_STACK_PORT=5001
docker run \
-it \
--pull always \
-p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
llamastack/distribution-{{ name }} \
--port $LLAMA_STACK_PORT \

4
llama_stack/templates/tgi/doc_template.md
View file

@ -38,6 +38,7 @@ export INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct
export CUDA_VISIBLE_DEVICES=0
docker run --rm -it \
--pull always \
-v $HOME/.cache/huggingface:/data \
-p $INFERENCE_PORT:$INFERENCE_PORT \
--gpus $CUDA_VISIBLE_DEVICES \
@ -58,6 +59,7 @@ export SAFETY_MODEL=meta-llama/Llama-Guard-3-1B
export CUDA_VISIBLE_DEVICES=1
docker run --rm -it \
--pull always \
-v $HOME/.cache/huggingface:/data \
-p $SAFETY_PORT:$SAFETY_PORT \
--gpus $CUDA_VISIBLE_DEVICES \
@ -81,6 +83,7 @@ This method allows you to get started quickly without having to build the distri
LLAMA_STACK_PORT=5001
docker run \
-it \
--pull always \
-p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
llamastack/distribution-{{ name }} \
--port $LLAMA_STACK_PORT \
@ -97,6 +100,7 @@ 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/tgi/run-with-safety.yaml:/root/my-run.yaml \

1
llama_stack/templates/together/doc_template.md
View file

@ -52,6 +52,7 @@ This method allows you to get started quickly without having to build the distri
LLAMA_STACK_PORT=5001
docker run \
-it \
--pull always \
-p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
llamastack/distribution-{{ name }} \
--port $LLAMA_STACK_PORT \