Files
GenAIExamples/ChatQnA/benchmark/performance/kubernetes/intel/gaudi/benchmark.yaml
2025-01-06 13:25:55 +08:00

69 lines
3.2 KiB
YAML

# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: Apache-2.0
test_suite_config: # Overall configuration settings for the test suite
examples: ["chatqna"] # The specific test cases being tested, e.g., chatqna, codegen, codetrans, faqgen, audioqna, visualqna
deployment_type: ${DEPLOYMENT_TYPE} # Default is "k8s", can also be "docker"
service_ip: ${SERVICE_IP} # Leave as None for k8s, specify for Docker
service_port: ${SERVICE_PORT} # Leave as None for k8s, specify for Docker
warm_ups: ${WARMUP} # Number of test requests for warm-up
run_time: 60m # The max total run time for the test suite
seed: # The seed for all RNGs
user_queries: ${USER_QUERIES} # Number of test requests at each concurrency level
query_timeout: 120 # Number of seconds to wait for a simulated user to complete any executing task before exiting. 120 sec by defeult.
random_prompt: false # Use random prompts if true, fixed prompts if false
collect_service_metric: false # Collect service metrics if true, do not collect service metrics if false
data_visualization: false # Generate data visualization if true, do not generate data visualization if false
llm_model: "Intel/neural-chat-7b-v3-3" # The LLM model used for the test
test_output_dir: "${TEST_OUTPUT_DIR}" # The directory to store the test output
load_shape: # Tenant concurrency pattern
name: ${LOAD_SHAPE} # poisson or constant(locust default load shape)
params: # Loadshape-specific parameters
constant: # Constant load shape specific parameters, activate only if load_shape.name is constant
concurrent_level: ${CONCURRENT_LEVEL} # If user_queries is specified, concurrent_level is target number of requests per user. If not, it is the number of simulated users
poisson: # Poisson load shape specific parameters, activate only if load_shape.name is poisson
arrival_rate: ${ARRIVAL_RATE} # Request arrival rate
test_cases:
chatqna:
embedding:
run_test: false
service_name: "chatqna-embedding-usvc" # Replace with your service name
embedserve:
run_test: false
service_name: "chatqna-tei" # Replace with your service name
retriever:
run_test: false
service_name: "chatqna-retriever-usvc" # Replace with your service name
parameters:
search_type: "similarity"
k: 1
fetch_k: 20
lambda_mult: 0.5
score_threshold: 0.2
reranking:
run_test: false
service_name: "chatqna-reranking-usvc" # Replace with your service name
parameters:
top_n: 1
rerankserve:
run_test: false
service_name: "chatqna-teirerank" # Replace with your service name
llm:
run_test: false
service_name: "chatqna-llm-uservice" # Replace with your service name
parameters:
max_tokens: 128
temperature: 0.01
top_k: 10
top_p: 0.95
repetition_penalty: 1.03
stream: true
llmserve:
run_test: false
service_name: "chatqna-tgi" # Replace with your service name
e2e:
run_test: true
service_name: "chatqna" # Replace with your service name
k: 1