af21e94a29
* Add benchmark README for ChatQnA Signed-off-by: lvliang-intel <liang1.lv@intel.com> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * add benchmark.yaml Signed-off-by: lvliang-intel <liang1.lv@intel.com> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * update yaml path Signed-off-by: lvliang-intel <liang1.lv@intel.com> * fix preci issue Signed-off-by: lvliang-intel <liang1.lv@intel.com> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * update title Signed-off-by: lvliang-intel <liang1.lv@intel.com> --------- Signed-off-by: lvliang-intel <liang1.lv@intel.com> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
56 lines
2.2 KiB
YAML
56 lines
2.2 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
|
|
concurrent_level: 5 # The concurrency level, adjustable based on requirements
|
|
user_queries: ${USER_QUERIES} # Number of test requests at each concurrency level
|
|
random_prompt: false # Use random prompts if true, fixed prompts if false
|
|
run_time: 60m # The max total run time for the test suite
|
|
collect_service_metric: false # Collect service metrics if true, do not collect service metrics if false
|
|
data_visualization: false # Generate data visualization if true, do not generate data visualization if false
|
|
llm_model: "Intel/neural-chat-7b-v3-3" # The LLM model used for the test
|
|
test_output_dir: "${TEST_OUTPUT_DIR}" # The directory to store the test output
|
|
|
|
test_cases:
|
|
chatqna:
|
|
embedding:
|
|
run_test: false
|
|
service_name: "embedding-svc" # Replace with your service name
|
|
embedserve:
|
|
run_test: false
|
|
service_name: "embedding-dependency-svc" # Replace with your service name
|
|
retriever:
|
|
run_test: false
|
|
service_name: "retriever-svc" # Replace with your service name
|
|
parameters:
|
|
search_type: "similarity"
|
|
k: 4
|
|
fetch_k: 20
|
|
lambda_mult: 0.5
|
|
score_threshold: 0.2
|
|
reranking:
|
|
run_test: false
|
|
service_name: "reranking-svc" # Replace with your service name
|
|
parameters:
|
|
top_n: 1
|
|
rerankserve:
|
|
run_test: false
|
|
service_name: "reranking-dependency-svc" # Replace with your service name
|
|
llm:
|
|
run_test: false
|
|
service_name: "llm-svc" # Replace with your service name
|
|
parameters:
|
|
max_new_tokens: 128
|
|
temperature: 0.01
|
|
top_k: 10
|
|
top_p: 0.95
|
|
repetition_penalty: 1.03
|
|
streaming: true
|
|
llmserve:
|
|
run_test: false
|
|
service_name: "llm-dependency-svc" # Replace with your service name
|
|
e2e:
|
|
run_test: true
|
|
service_name: "chatqna-backend-server-svc" # Replace with your service name
|