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

more models for vLLM Benchmark Suite (#35086)

Browse Source 
Signed-off-by: louie-tsai <louie.tsai@intel.com>
This commit is contained in:
Louie Tsai
2026-03-11 20:36:51 -07:00
committed by GitHub
parent 8647c6cf51
commit 17852aa503
8 changed files with 801 additions and 120 deletions
Download Patch File Download Diff File Expand all files Collapse all files

37
.buildkite/performance-benchmarks/tests/serving-tests-cpu-asr.json Normal file
View File

@@ -0,0 +1,37 @@
{
"defaults": {
"qps_list": [
"inf"
],
"max_concurrency_list": [12, 16, 24, 32, 64, 128, 200],
"server_environment_variables": {
"VLLM_RPC_TIMEOUT": 100000,
"VLLM_ENGINE_ITERATION_TIMEOUT_S": 120
},
"server_parameters": {
"dtype": "bfloat16",
"model": "openai/whisper-large-v3-turbo"
},
"client_parameters": {
"model": "openai/whisper-large-v3-turbo",
"backend": "openai-audio",
"endpoint": "/v1/audio/transcriptions",
"dataset_name": "hf",
"dataset_path": "openslr/librispeech_asr",
"hf_subset": "clean",
"hf_split": "test",
"no_stream": "",
"no_oversample": "",
"num_prompts": 200
}
},
"tests": [
{
"test_name": "serving_whisper_large_v3_turbo_librispeech_clean_tp1",
"server_parameters": {
"tensor_parallel_size": 1
},
"client_parameters": {}
}
]
}

72
.buildkite/performance-benchmarks/tests/serving-tests-cpu-text.json
View File

@@ -149,6 +149,39 @@
"random-output-len": 128
}
},
{
"test_name": "serving_llama8B_tp1_random_2048_2048",
"server_parameters": {
"tensor_parallel_size": 1
},
"client_parameters": {
"dataset_name": "random",
"random-input-len": 2048,
"random-output-len": 2048
}
},
{
"test_name": "serving_llama8B_tp2_random_2048_2048",
"server_parameters": {
"tensor_parallel_size": 2
},
"client_parameters": {
"dataset_name": "random",
"random-input-len": 2048,
"random-output-len": 2048
}
},
{
"test_name": "serving_llama8B_tp4_random_2048_2048",
"server_parameters": {
"tensor_parallel_size": 4
},
"client_parameters": {
"dataset_name": "random",
"random-input-len": 2048,
"random-output-len": 2048
}
},
{
"test_name": "serving_llama8B_int4_tp1_random_128_128",
"server_parameters": {
@@ -188,6 +221,45 @@
"random-output-len": 128
}
},
{
"test_name": "serving_llama8B_int8_tp1_random_128_128",
"server_parameters": {
"model": "RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a8",
"tensor_parallel_size": 1
},
"client_parameters": {
"model": "RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a8",
"dataset_name": "random",
"random-input-len": 128,
"random-output-len": 128
}
},
{
"test_name": "serving_llama8B_int8_tp2_random_128_128",
"server_parameters": {
"model": "RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a8",
"tensor_parallel_size": 2
},
"client_parameters": {
"model": "RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a8",
"dataset_name": "random",
"random-input-len": 128,
"random-output-len": 128
}
},
{
"test_name": "serving_llama8B_int8_tp4_random_128_128",
"server_parameters": {
"model": "RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a8",
"tensor_parallel_size": 4
},
"client_parameters": {
"model": "RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a8",
"dataset_name": "random",
"random-input-len": 128,
"random-output-len": 128
}
},
{
"test_name": "serving_llama3B_tp1_random_128_128",
"server_parameters": {

39
.buildkite/performance-benchmarks/tests/serving-tests-cpu.json
View File

@@ -72,17 +72,6 @@
"random-output-len": 128
}
},
{
"test_name": "serving_llama8B_tp4_random_128_128",
"server_parameters": {
"tensor_parallel_size": 4
},
"client_parameters": {
"dataset_name": "random",
"random-input-len": 128,
"random-output-len": 128
}
},
{
"test_name": "serving_llama8B_tp1_random_128_2048",
"server_parameters": {
@@ -105,17 +94,6 @@
"random-output-len": 2048
}
},
{
"test_name": "serving_llama8B_tp4_random_128_2048",
"server_parameters": {
"tensor_parallel_size": 4
},
"client_parameters": {
"dataset_name": "random",
"random-input-len": 128,
"random-output-len": 2048
}
},
{
"test_name": "serving_llama8B_tp1_random_2048_128",
"server_parameters": {
@@ -139,14 +117,25 @@
}
},
{
"test_name": "serving_llama8B_tp4_random_2048_128",
"test_name": "serving_llama8B_tp1_random_2048_2048",
"server_parameters": {
"tensor_parallel_size": 4
"tensor_parallel_size": 1
},
"client_parameters": {
"dataset_name": "random",
"random-input-len": 2048,
"random-output-len": 128
"random-output-len": 2048
}
},
{
"test_name": "serving_llama8B_tp2_random_2048_2048",
"server_parameters": {
"tensor_parallel_size": 2
},
"client_parameters": {
"dataset_name": "random",
"random-input-len": 2048,
"random-output-len": 2048
}
}
]