phoenix-oss/llama-stack
1
0
Fork 0
forked from phoenix-oss/llama-stack-mirror
Code Pull requests Releases Packages 2 Activity Actions

update requiements
All checks were successful
Build and Push playground container / build-playground (push) Successful in 2m7s
Details
Build and Push container / build (push) Successful in 4m32s
Details

Browse source
This commit is contained in:
Angel Nunez Mencias 2025-06-02 02:34:19 +02:00
parent 51816af52e
commit a77b554bcf
Signed by: angel.nunez
SSH key fingerprint: SHA256:z1nFAg1v1AfbhEHrgBetByUJUwziv2R2f4VyN75opcg
2 changed files with 4 additions and 12 deletions
Download patch file Download diff file Expand all files Collapse all files

12
kvant_start_local.sh
View file

@ -1,12 +1,7 @@
#!/usr/bin/env bash #!/usr/bin/env bash
export INFERENCE_MODEL="inference-llama4-maverick"
export EMBEDDING_MODEL="inference-bge-m3"
export EMBEDDING_DIMENSION="1024"
export LLAMA_STACK_PORT=8321 export LLAMA_STACK_PORT=8321
export OPENAI_BASE_URL=https://maas.ai-2.kvant.cloud/v1 # VLLM_API_TOKEN= env file
# OPENAI_API_KEY= env file
export VLLM_MAX_TOKENS=125000
# KEYCLOAK_CLIENT_SECRET= env file # KEYCLOAK_CLIENT_SECRET= env file
@ -19,7 +14,4 @@ docker run -it \
distribution-kvant:dev \ distribution-kvant:dev \
-m llama_stack.distribution.server.server --config /root/.llama/config.yaml \ -m llama_stack.distribution.server.server --config /root/.llama/config.yaml \
--port $LLAMA_STACK_PORT \ --port $LLAMA_STACK_PORT \
--env VLLM_URL=$OPENAI_BASE_URL \
--env INFERENCE_MODEL=$INFERENCE_MODEL \
--env EMBEDDING_MODEL=$EMBEDDING_MODEL \
--env EMBEDDING_DIMENSION=$EMBEDDING_DIMENSION \

4
llama_stack/distribution/ui/requirements.txt
View file

@ -1,5 +1,5 @@
llama-stack>=0.2.1 llama-stack>=0.2.9
llama-stack-client>=0.2.1 llama-stack-client>=0.2.9
pandas pandas
streamlit streamlit
streamlit-option-menu streamlit-option-menu