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
docs/source/distributions/self_hosted_distro/bedrock.md
View file

@ -56,6 +56,7 @@ 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-bedrock \
--port $LLAMA_STACK_PORT \

1
docs/source/distributions/self_hosted_distro/cerebras.md
View file

@ -48,6 +48,7 @@ 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-cerebras \

4
docs/source/distributions/self_hosted_distro/dell-tgi.md
View file

@ -53,7 +53,7 @@ docker compose down
#### Start Dell-TGI server locally
```
docker run -it --shm-size 1g -p 80:80 --gpus 4 \
docker run -it --pull always --shm-size 1g -p 80:80 --gpus 4 \
-e NUM_SHARD=4
-e MAX_BATCH_PREFILL_TOKENS=32768 \
-e MAX_INPUT_TOKENS=8000 \
@ -65,7 +65,7 @@ registry.dell.huggingface.co/enterprise-dell-inference-meta-llama-meta-llama-3.1
#### Start Llama Stack server pointing to TGI server
```
docker run --network host -it -p 8321:8321 -v ./run.yaml:/root/my-run.yaml --gpus=all llamastack/distribution-tgi --yaml_config /root/my-run.yaml
docker run --pull always --network host -it -p 8321:8321 -v ./run.yaml:/root/my-run.yaml --gpus=all llamastack/distribution-tgi --yaml_config /root/my-run.yaml
```
Make sure in you `run.yaml` file, you inference provider is pointing to the correct TGI server endpoint. E.g.

4
docs/source/distributions/self_hosted_distro/dell.md
View file

@ -55,6 +55,7 @@ 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 \
@ -78,6 +79,7 @@ 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 \
@ -120,6 +122,7 @@ 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 \
@ -147,6 +150,7 @@ 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
docs/source/distributions/self_hosted_distro/fireworks.md
View file

@ -66,6 +66,7 @@ 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-fireworks \
--port $LLAMA_STACK_PORT \

1
docs/source/distributions/self_hosted_distro/groq.md
View file

@ -61,6 +61,7 @@ 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-groq \
--port $LLAMA_STACK_PORT \

2
docs/source/distributions/self_hosted_distro/meta-reference-gpu.md
View file

@ -80,6 +80,7 @@ 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-meta-reference-gpu \
@ -92,6 +93,7 @@ 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-meta-reference-gpu \

2
docs/source/distributions/self_hosted_distro/meta-reference-quantized-gpu.md
View file

@ -80,6 +80,7 @@ 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-meta-reference-quantized-gpu \
@ -92,6 +93,7 @@ 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-meta-reference-quantized-gpu \

1
docs/source/distributions/self_hosted_distro/nvidia.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-nvidia \

2
docs/source/distributions/self_hosted_distro/ollama.md
View file

@ -74,6 +74,7 @@ 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-ollama \
@ -91,6 +92,7 @@ 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
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 \

1
docs/source/distributions/self_hosted_distro/sambanova.md
View file

@ -62,6 +62,7 @@ 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-sambanova \
--port $LLAMA_STACK_PORT \

4
docs/source/distributions/self_hosted_distro/tgi.md
View file

@ -50,6 +50,7 @@ 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 \
@ -70,6 +71,7 @@ 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 \
@ -93,6 +95,7 @@ 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-tgi \
--port $LLAMA_STACK_PORT \
@ -109,6 +112,7 @@ 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
docs/source/distributions/self_hosted_distro/together.md
View file

@ -67,6 +67,7 @@ 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-together \
--port $LLAMA_STACK_PORT \