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

vLLM Benchmark suite improvement (#22119)

Browse Source 
Signed-off-by: Tsai, Louie <louie.tsai@intel.com>
Signed-off-by: Louie Tsai <louie.tsai@intel.com>
Co-authored-by: Li, Jiang <bigpyj64@gmail.com>
This commit is contained in:
Louie Tsai
2025-08-14 00:12:17 -07:00
committed by GitHub
parent a353bd083d
commit 00e3f9da46
10 changed files with 447 additions and 147 deletions
Download Patch File Download Diff File Expand all files Collapse all files

52
.buildkite/nightly-benchmarks/tests/serving-tests-cpu-snc3.json
View File

@@ -1,7 +1,8 @@
[
{
"test_name": "serving_llama8B_pp1_sharegpt",
"qps_list": [1, 4, 16, "inf"],
"qps_list": ["inf"],
"max_concurrency_list": [12, 16, 24, 32, 64, 128, 200],
"server_environment_variables": {
"VLLM_RPC_TIMEOUT": 100000,
"VLLM_ALLOW_LONG_MAX_MODEL_LEN": 1,
@@ -10,7 +11,7 @@
"VLLM_CPU_KVCACHE_SPACE": 40
},
"server_parameters": {
"model": "meta-llama/Meta-Llama-3.1-8B-Instruct",
"model": "meta-llama/Llama-3.1-8B-Instruct",
"pipeline_parallel_size": 1,
"dtype": "bfloat16",
"distributed_executor_backend": "mp",
@@ -23,17 +24,17 @@
"load_format": "dummy"
},
"client_parameters": {
"model": "meta-llama/Meta-Llama-3.1-8B-Instruct",
"model": "meta-llama/Llama-3.1-8B-Instruct",
"backend": "vllm",
"dataset_name": "sharegpt",
"dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json",
"max_concurrency": 60,
"num_prompts": 200
}
},
{
"test_name": "serving_llama8B_pp3_sharegpt",
"qps_list": [1, 4, 16, "inf"],
"qps_list": ["inf"],
"max_concurrency_list": [12, 16, 24, 32, 64, 128, 200],
"server_environment_variables": {
"VLLM_RPC_TIMEOUT": 100000,
"VLLM_ALLOW_LONG_MAX_MODEL_LEN": 1,
@@ -42,7 +43,7 @@
"VLLM_CPU_KVCACHE_SPACE": 40
},
"server_parameters": {
"model": "meta-llama/Meta-Llama-3.1-8B-Instruct",
"model": "meta-llama/Llama-3.1-8B-Instruct",
"pipeline_parallel_size": 3,
"dtype": "bfloat16",
"distributed_executor_backend": "mp",
@@ -55,17 +56,17 @@
"load_format": "dummy"
},
"client_parameters": {
"model": "meta-llama/Meta-Llama-3.1-8B-Instruct",
"model": "meta-llama/Llama-3.1-8B-Instruct",
"backend": "vllm",
"dataset_name": "sharegpt",
"dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json",
"max_concurrency": 60,
"num_prompts": 200
}
},
{
"test_name": "serving_llama8B_tp2pp6_sharegpt",
"qps_list": [1, 4, 16, "inf"],
"test_name": "serving_llama8B_tp2pp3_sharegpt",
"qps_list": ["inf"],
"max_concurrency_list": [12, 16, 24, 32, 64, 128, 200],
"server_environment_variables": {
"VLLM_RPC_TIMEOUT": 100000,
"VLLM_ALLOW_LONG_MAX_MODEL_LEN": 1,
@@ -74,7 +75,7 @@
"VLLM_CPU_KVCACHE_SPACE": 40
},
"server_parameters": {
"model": "meta-llama/Meta-Llama-3.1-8B-Instruct",
"model": "meta-llama/Llama-3.1-8B-Instruct",
"tensor_parallel_size": 2,
"pipeline_parallel_size": 3,
"dtype": "bfloat16",
@@ -88,17 +89,17 @@
"load_format": "dummy"
},
"client_parameters": {
"model": "meta-llama/Meta-Llama-3.1-8B-Instruct",
"model": "meta-llama/Llama-3.1-8B-Instruct",
"backend": "vllm",
"dataset_name": "sharegpt",
"dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json",
"max_concurrency": 60,
"num_prompts": 200
}
},
{
"test_name": "serving_llama8B_pp1_random_128_128",
"qps_list": [1, 4, 16, "inf"],
"qps_list": ["inf"],
"max_concurrency_list": [12, 16, 24, 32, 64, 128, 200, 1000],
"server_environment_variables": {
"VLLM_RPC_TIMEOUT": 100000,
"VLLM_ALLOW_LONG_MAX_MODEL_LEN": 1,
@@ -107,7 +108,7 @@
"VLLM_CPU_KVCACHE_SPACE": 40
},
"server_parameters": {
"model": "meta-llama/Meta-Llama-3.1-8B-Instruct",
"model": "meta-llama/Llama-3.1-8B-Instruct",
"pipeline_parallel_size": 1,
"dtype": "bfloat16",
"distributed_executor_backend": "mp",
@@ -121,28 +122,28 @@
"load_format": "dummy"
},
"client_parameters": {
"model": "meta-llama/Meta-Llama-3.1-8B-Instruct",
"model": "meta-llama/Llama-3.1-8B-Instruct",
"backend": "vllm",
"dataset_name": "random",
"random-input-len": 128,
"random-output-len": 128,
"ignore-eos": "",
"max_concurrency": 1000,
"num_prompts": 1000
}
},
{
"test_name": "serving_llama8B_pp3_random_128_128",
"qps_list": [1, 4, 16, "inf"],
"qps_list": ["inf"],
"max_concurrency_list": [12, 16, 24, 32, 64, 128, 200, 1000],
"server_environment_variables": {
"VLLM_RPC_TIMEOUT": 100000,
"VLLM_ALLOW_LONG_MAX_MODEL_LEN": 1,
"VLLM_ENGINE_ITERATION_TIMEOUT_S": 120,
"VLLM_CPU_SGL_KERNEL:": 1,
"VLLM_CPU_SGL_KERNEL": 1,
"VLLM_CPU_KVCACHE_SPACE": 40
},
"server_parameters": {
"model": "meta-llama/Meta-Llama-3.1-8B-Instruct",
"model": "meta-llama/Llama-3.1-8B-Instruct",
"pipeline_parallel_size": 3,
"dtype": "bfloat16",
"distributed_executor_backend": "mp",
@@ -156,19 +157,19 @@
"load_format": "dummy"
},
"client_parameters": {
"model": "meta-llama/Meta-Llama-3.1-8B-Instruct",
"model": "meta-llama/Llama-3.1-8B-Instruct",
"backend": "vllm",
"dataset_name": "random",
"random-input-len": 128,
"random-output-len": 128,
"ignore-eos": "",
"max_concurrency": 1000,
"num_prompts": 1000
}
},
{
"test_name": "serving_llama8B_tp2pp3_random_128_128",
"qps_list": [1, 4, 16, "inf"],
"qps_list": ["inf"],
"max_concurrency_list": [12, 16, 24, 32, 64, 128, 200, 1000],
"server_environment_variables": {
"VLLM_RPC_TIMEOUT": 100000,
"VLLM_ALLOW_LONG_MAX_MODEL_LEN": 1,
@@ -177,7 +178,7 @@
"VLLM_CPU_KVCACHE_SPACE": 40
},
"server_parameters": {
"model": "meta-llama/Meta-Llama-3.1-8B-Instruct",
"model": "meta-llama/Llama-3.1-8B-Instruct",
"tensor_parallel_size": 2,
"pipeline_parallel_size": 3,
"dtype": "bfloat16",
@@ -192,13 +193,12 @@
"load_format": "dummy"
},
"client_parameters": {
"model": "meta-llama/Meta-Llama-3.1-8B-Instruct",
"model": "meta-llama/Llama-3.1-8B-Instruct",
"backend": "vllm",
"dataset_name": "random",
"random-input-len": 128,
"random-output-len": 128,
"ignore-eos": "",
"max_concurrency": 1000,
"num_prompts": 1000
}
}