phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-07-21 12:09:40 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix: Default to port 8321 everywhere (#1734)

Browse source 
As titled, moved all instances of 5001 to 8321
This commit is contained in:
Hardik Shah 2025-03-20 15:50:41 -07:00 • committed by GitHub
parent 581e8ae562
commit 127bac6869
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
56 changed files with 2352 additions and 2305 deletions
Download patch file Download diff file Expand all files Collapse all files

4
distributions/ollama/compose.yaml
View file

@ -51,14 +51,14 @@ services:
- ~/local/llama-stack/:/app/llama-stack-source
- ./run${SAFETY_MODEL:+-with-safety}.yaml:/root/my-run.yaml
ports:
- "${LLAMA_STACK_PORT:-5001}:${LLAMA_STACK_PORT:-5001}"
- "${LLAMA_STACK_PORT:-8321}:${LLAMA_STACK_PORT:-8321}"
environment:
- INFERENCE_MODEL=${INFERENCE_MODEL}
- SAFETY_MODEL=${SAFETY_MODEL:-}
- OLLAMA_URL=http://ollama:11434
entrypoint: >
python -m llama_stack.distribution.server.server /root/my-run.yaml \
--port ${LLAMA_STACK_PORT:-5001}
--port ${LLAMA_STACK_PORT:-8321}
deploy:
restart_policy:
condition: on-failure

4
distributions/remote-vllm/compose.yaml
View file

@ -84,9 +84,9 @@ services:
- SQLITE_STORE_DIR=${SQLITE_STORE_DIR:-$HOME/.llama/distributions/remote-vllm}
- SAFETY_MODEL=${SAFETY_MODEL:-meta-llama/Llama-Guard-3-1B}
ports:
- "${LLAMA_STACK_PORT:-5001}:${LLAMA_STACK_PORT:-5001}"
- "${LLAMA_STACK_PORT:-8321}:${LLAMA_STACK_PORT:-8321}"
# Hack: wait for vLLM server to start before starting docker
entrypoint: bash -c "sleep 60; python -m llama_stack.distribution.server.server --yaml_config /root/llamastack-run-remote-vllm.yaml --port 5001"
entrypoint: bash -c "sleep 60; python -m llama_stack.distribution.server.server --yaml_config /root/llamastack-run-remote-vllm.yaml --port 8321"
deploy:
restart_policy:
condition: on-failure

2
distributions/tgi/compose.yaml
View file

@ -83,7 +83,7 @@ services:
- ~/.llama:/root/.llama
- ./run${TGI_SAFETY_MODEL:+-with-safety}.yaml:/root/my-run.yaml
ports:
- "${LLAMA_STACK_PORT:-5001}:${LLAMA_STACK_PORT:-5001}"
- "${LLAMA_STACK_PORT:-8321}:${LLAMA_STACK_PORT:-8321}"
# Hack: wait for TGI server to start before starting docker
entrypoint: bash -c "sleep 60; python -m llama_stack.distribution.server.server --yaml_config /root/my-run.yaml"
restart_policy: