mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-08-21 17:33:12 +00:00
2c06b24c77
# What does this PR do? 1. Add our own benchmark script instead of locust (doesn't support measuring streaming latency well) 2. Simplify k8s deployment 3. Add a simple profile script for locally running server ## Test Plan ❮ ./run-benchmark.sh --target stack --duration 180 --concurrent 10 ============================================================ BENCHMARK RESULTS ============================================================ Total time: 180.00s Concurrent users: 10 Total requests: 1636 Successful requests: 1636 Failed requests: 0 Success rate: 100.0% Requests per second: 9.09 Response Time Statistics: Mean: 1.095s Median: 1.721s Min: 0.136s Max: 3.218s Std Dev: 0.762s Percentiles: P50: 1.721s P90: 1.751s P95: 1.756s P99: 1.796s Time to First Token (TTFT) Statistics: Mean: 0.037s Median: 0.037s Min: 0.023s Max: 0.211s Std Dev: 0.011s TTFT Percentiles: P50: 0.037s P90: 0.040s P95: 0.044s P99: 0.055s Streaming Statistics: Mean chunks per response: 64.0 Total chunks received: 104775
108 lines
3.1 KiB
YAML
108 lines
3.1 KiB
YAML
version: '2'
|
|
image_name: kubernetes-benchmark-demo
|
|
apis:
|
|
- agents
|
|
- inference
|
|
- telemetry
|
|
- tool_runtime
|
|
- vector_io
|
|
providers:
|
|
inference:
|
|
- provider_id: vllm-inference
|
|
provider_type: remote::vllm
|
|
config:
|
|
url: ${env.VLLM_URL:=http://localhost:8000/v1}
|
|
max_tokens: ${env.VLLM_MAX_TOKENS:=4096}
|
|
api_token: ${env.VLLM_API_TOKEN:=fake}
|
|
tls_verify: ${env.VLLM_TLS_VERIFY:=true}
|
|
- provider_id: sentence-transformers
|
|
provider_type: inline::sentence-transformers
|
|
config: {}
|
|
vector_io:
|
|
- provider_id: ${env.ENABLE_CHROMADB:+chromadb}
|
|
provider_type: remote::chromadb
|
|
config:
|
|
url: ${env.CHROMADB_URL:=}
|
|
kvstore:
|
|
type: postgres
|
|
host: ${env.POSTGRES_HOST:=localhost}
|
|
port: ${env.POSTGRES_PORT:=5432}
|
|
db: ${env.POSTGRES_DB:=llamastack}
|
|
user: ${env.POSTGRES_USER:=llamastack}
|
|
password: ${env.POSTGRES_PASSWORD:=llamastack}
|
|
agents:
|
|
- provider_id: meta-reference
|
|
provider_type: inline::meta-reference
|
|
config:
|
|
persistence_store:
|
|
type: postgres
|
|
host: ${env.POSTGRES_HOST:=localhost}
|
|
port: ${env.POSTGRES_PORT:=5432}
|
|
db: ${env.POSTGRES_DB:=llamastack}
|
|
user: ${env.POSTGRES_USER:=llamastack}
|
|
password: ${env.POSTGRES_PASSWORD:=llamastack}
|
|
responses_store:
|
|
type: postgres
|
|
host: ${env.POSTGRES_HOST:=localhost}
|
|
port: ${env.POSTGRES_PORT:=5432}
|
|
db: ${env.POSTGRES_DB:=llamastack}
|
|
user: ${env.POSTGRES_USER:=llamastack}
|
|
password: ${env.POSTGRES_PASSWORD:=llamastack}
|
|
telemetry:
|
|
- provider_id: meta-reference
|
|
provider_type: inline::meta-reference
|
|
config:
|
|
service_name: "${env.OTEL_SERVICE_NAME:=\u200B}"
|
|
sinks: ${env.TELEMETRY_SINKS:=console}
|
|
tool_runtime:
|
|
- provider_id: brave-search
|
|
provider_type: remote::brave-search
|
|
config:
|
|
api_key: ${env.BRAVE_SEARCH_API_KEY:+}
|
|
max_results: 3
|
|
- provider_id: tavily-search
|
|
provider_type: remote::tavily-search
|
|
config:
|
|
api_key: ${env.TAVILY_SEARCH_API_KEY:+}
|
|
max_results: 3
|
|
- provider_id: rag-runtime
|
|
provider_type: inline::rag-runtime
|
|
config: {}
|
|
- provider_id: model-context-protocol
|
|
provider_type: remote::model-context-protocol
|
|
config: {}
|
|
metadata_store:
|
|
type: postgres
|
|
host: ${env.POSTGRES_HOST:=localhost}
|
|
port: ${env.POSTGRES_PORT:=5432}
|
|
db: ${env.POSTGRES_DB:=llamastack}
|
|
user: ${env.POSTGRES_USER:=llamastack}
|
|
password: ${env.POSTGRES_PASSWORD:=llamastack}
|
|
table_name: llamastack_kvstore
|
|
inference_store:
|
|
type: postgres
|
|
host: ${env.POSTGRES_HOST:=localhost}
|
|
port: ${env.POSTGRES_PORT:=5432}
|
|
db: ${env.POSTGRES_DB:=llamastack}
|
|
user: ${env.POSTGRES_USER:=llamastack}
|
|
password: ${env.POSTGRES_PASSWORD:=llamastack}
|
|
models:
|
|
- metadata:
|
|
embedding_dimension: 384
|
|
model_id: all-MiniLM-L6-v2
|
|
provider_id: sentence-transformers
|
|
model_type: embedding
|
|
- model_id: ${env.INFERENCE_MODEL}
|
|
provider_id: vllm-inference
|
|
model_type: llm
|
|
vector_dbs: []
|
|
datasets: []
|
|
scoring_fns: []
|
|
benchmarks: []
|
|
tool_groups:
|
|
- toolgroup_id: builtin::websearch
|
|
provider_id: tavily-search
|
|
- toolgroup_id: builtin::rag
|
|
provider_id: rag-runtime
|
|
server:
|
|
port: 8323
|