biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Benchmark Suite] improve cpu Benchmark Suite tests and comparison report for 0.12.0 (#30994)

Browse Source 
Signed-off-by: Tsai, Louie <louie.tsai@intel.com>
This commit is contained in:
Louie Tsai
2025-12-25 00:51:45 -08:00
committed by GitHub
parent ba25a65992
commit f15185fbdb
4 changed files with 666 additions and 222 deletions
Download Patch File Download Diff File Expand all files Collapse all files

43
.buildkite/performance-benchmarks/tests/serving-tests-cpu.json
View File

@@ -19,10 +19,8 @@
"block_size": 128,
"trust_remote_code": "",
"disable_log_stats": "",
"enforce_eager": "",
"max_num_batched_tokens": 2048,
"max_num_seqs": 256,
"load_format": "dummy"
"max_num_seqs": 256
},
"client_parameters": {
"model": "meta-llama/Llama-3.1-8B-Instruct",
@@ -151,6 +149,45 @@
"random-output-len": 128
}
},
{
"test_name": "serving_llama8B_int4_tp1_random_128_128",
"server_parameters": {
"model": "hugging-quants/Meta-Llama-3.1-8B-Instruct-AWQ-INT4",
"tensor_parallel_size": 1
},
"client_parameters": {
"model": "hugging-quants/Meta-Llama-3.1-8B-Instruct-AWQ-INT4",
"dataset_name": "random",
"random-input-len": 128,
"random-output-len": 128
}
},
{
"test_name": "serving_llama8B_int4_tp2_random_128_128",
"server_parameters": {
"model": "hugging-quants/Meta-Llama-3.1-8B-Instruct-AWQ-INT4",
"tensor_parallel_size": 2
},
"client_parameters": {
"model": "hugging-quants/Meta-Llama-3.1-8B-Instruct-AWQ-INT4",
"dataset_name": "random",
"random-input-len": 128,
"random-output-len": 128
}
},
{
"test_name": "serving_llama8B_int4_tp4_random_128_128",
"server_parameters": {
"model": "hugging-quants/Meta-Llama-3.1-8B-Instruct-AWQ-INT4",
"tensor_parallel_size": 4
},
"client_parameters": {
"model": "hugging-quants/Meta-Llama-3.1-8B-Instruct-AWQ-INT4",
"dataset_name": "random",
"random-input-len": 128,
"random-output-len": 128
}
},
{
"test_name": "serving_llama3B_tp1_random_128_128",
"server_parameters": {