phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-06-28 02:53:30 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Update remote vllm docs

Browse source
This commit is contained in:
Ashwin Bharambe 2024-11-18 16:34:33 -08:00
parent fb15ff4a97
commit afa4f0b19f
2 changed files with 18 additions and 12 deletions
Download patch file Download diff file Expand all files Collapse all files

15
docs/source/getting_started/distributions/self_hosted_distro/remote-vllm.md
View file

@ -88,7 +88,7 @@ docker run \
/root/my-run.yaml \
--port $LLAMA_STACK_PORT \
--env INFERENCE_MODEL=$INFERENCE_MODEL \
--env VLLM_URL=http://host.docker.internal:$INFERENCE_PORT \
--env VLLM_URL=http://host.docker.internal:$INFERENCE_PORT/v1
```
If you are using Llama Stack Safety / Shield APIs, use:
@ -105,9 +105,9 @@ docker run \
/root/my-run.yaml \
--port $LLAMA_STACK_PORT \
--env INFERENCE_MODEL=$INFERENCE_MODEL \
--env VLLM_URL=http://host.docker.internal:$INFERENCE_PORT \
--env VLLM_URL=http://host.docker.internal:$INFERENCE_PORT/v1 \
--env SAFETY_MODEL=$SAFETY_MODEL \
--env VLLM_SAFETY_URL=http://host.docker.internal:$SAFETY_PORT
--env VLLM_SAFETY_URL=http://host.docker.internal:$SAFETY_PORT/v1
```
@ -126,16 +126,19 @@ llama stack build --template remote-vllm --image-type conda
llama stack run ./run.yaml \
--port $LLAMA_STACK_PORT \
--env INFERENCE_MODEL=$INFERENCE_MODEL \
--env VLLM_URL=http://127.0.0.1:$INFERENCE_PORT
--env VLLM_URL=http://127.0.0.1:$INFERENCE_PORT/v1
```
If you are using Llama Stack Safety / Shield APIs, use:
```bash
export SAFETY_PORT=8081
export SAFETY_MODEL=meta-llama/Llama-Guard-3-1B
llama stack run ./run-with-safety.yaml \
--port $LLAMA_STACK_PORT \
--env INFERENCE_MODEL=$INFERENCE_MODEL \
--env VLLM_URL=http://127.0.0.1:$INFERENCE_PORT \
--env VLLM_URL=http://127.0.0.1:$INFERENCE_PORT/v1 \
--env SAFETY_MODEL=$SAFETY_MODEL \
--env VLLM_SAFETY_URL=http://127.0.0.1:$SAFETY_PORT
--env VLLM_SAFETY_URL=http://127.0.0.1:$SAFETY_PORT/v1
```

15
llama_stack/templates/remote-vllm/doc_template.md
View file

@ -80,7 +80,7 @@ docker run \
/root/my-run.yaml \
--port $LLAMA_STACK_PORT \
--env INFERENCE_MODEL=$INFERENCE_MODEL \
--env VLLM_URL=http://host.docker.internal:$INFERENCE_PORT \
--env VLLM_URL=http://host.docker.internal:$INFERENCE_PORT/v1
```
If you are using Llama Stack Safety / Shield APIs, use:
@ -97,9 +97,9 @@ docker run \
/root/my-run.yaml \
--port $LLAMA_STACK_PORT \
--env INFERENCE_MODEL=$INFERENCE_MODEL \
--env VLLM_URL=http://host.docker.internal:$INFERENCE_PORT \
--env VLLM_URL=http://host.docker.internal:$INFERENCE_PORT/v1 \
--env SAFETY_MODEL=$SAFETY_MODEL \
--env VLLM_SAFETY_URL=http://host.docker.internal:$SAFETY_PORT
--env VLLM_SAFETY_URL=http://host.docker.internal:$SAFETY_PORT/v1
```
@ -118,16 +118,19 @@ llama stack build --template remote-vllm --image-type conda
llama stack run ./run.yaml \
--port $LLAMA_STACK_PORT \
--env INFERENCE_MODEL=$INFERENCE_MODEL \
--env VLLM_URL=http://127.0.0.1:$INFERENCE_PORT
--env VLLM_URL=http://127.0.0.1:$INFERENCE_PORT/v1
```
If you are using Llama Stack Safety / Shield APIs, use:
```bash
export SAFETY_PORT=8081
export SAFETY_MODEL=meta-llama/Llama-Guard-3-1B
llama stack run ./run-with-safety.yaml \
--port $LLAMA_STACK_PORT \
--env INFERENCE_MODEL=$INFERENCE_MODEL \
--env VLLM_URL=http://127.0.0.1:$INFERENCE_PORT \
--env VLLM_URL=http://127.0.0.1:$INFERENCE_PORT/v1 \
--env SAFETY_MODEL=$SAFETY_MODEL \
--env VLLM_SAFETY_URL=http://127.0.0.1:$SAFETY_PORT
--env VLLM_SAFETY_URL=http://127.0.0.1:$SAFETY_PORT/v1
```