phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-18 02:49:49 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

benchmark, local test, ttft, duration

Browse source 
# What does this PR do?


## Test Plan
# What does this PR do?


## Test Plan
# What does this PR do?


## Test Plan
# What does this PR do?


## Test Plan
This commit is contained in:
Eric Huang 2025-08-15 10:54:20 -07:00
parent f66ae3b3b1
commit 244ff9efbd
13 changed files with 633 additions and 328 deletions
Download patch file Download diff file Expand all files Collapse all files

23
docs/source/distributions/k8s-benchmark/apply.sh
View file

@ -8,7 +8,6 @@
# Deploys the benchmark-specific components on top of the base k8s deployment (../k8s/apply.sh).
export MOCK_INFERENCE_PORT=8080
export STREAM_DELAY_SECONDS=0.005
export POSTGRES_USER=llamastack
@ -20,14 +19,7 @@ export SAFETY_MODEL=meta-llama/Llama-Guard-3-1B
export MOCK_INFERENCE_MODEL=mock-inference
# Use llama-stack-benchmark-service as the benchmark server
export LOCUST_HOST=http://llama-stack-benchmark-service:8323
export LOCUST_BASE_PATH=/v1/openai/v1
# Use vllm-service as the benchmark server
# export LOCUST_HOST=http://vllm-server:8000
# export LOCUST_BASE_PATH=/v1
export MOCK_INFERENCE_URL=openai-mock-service:8080
export BENCHMARK_INFERENCE_MODEL=$INFERENCE_MODEL
@ -35,13 +27,6 @@ set -euo pipefail
set -x
# Deploy benchmark-specific components
# Deploy OpenAI mock server
kubectl create configmap openai-mock --from-file=openai-mock-server.py \
--dry-run=client -o yaml | kubectl apply --validate=false -f -
envsubst < openai-mock-deployment.yaml | kubectl apply --validate=false -f -
# Create configmap with our custom stack config
kubectl create configmap llama-stack-config --from-file=stack_run_config.yaml \
--dry-run=client -o yaml > stack-configmap.yaml
@ -49,9 +34,3 @@ kubectl apply --validate=false -f stack-configmap.yaml
# Deploy our custom llama stack server (overriding the base one)
envsubst < stack-k8s.yaml.template | kubectl apply --validate=false -f -
# Deploy Locust load testing
kubectl create configmap locust-script --from-file=locustfile.py \
--dry-run=client -o yaml | kubectl apply --validate=false -f -
envsubst < locust-k8s.yaml | kubectl apply --validate=false -f -