Skip to content

add models #42

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 6 commits into
base: main
Choose a base branch
from
+589 −2
Open

add models #42

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
539b9fd
add gemma-3-27b-it and qwen3_30B-A3B
BoyuanFeng Jun 22, 2025
3d3bdec
fix test name
BoyuanFeng Jun 23, 2025
d532ab7
Merge branch 'main' into bf/add-gemma-qwen
BoyuanFeng Jul 19, 2025
21a97da
add more models to cuda and rocm benchmarks
BoyuanFeng Jul 19, 2025
1acfd13
rename test
BoyuanFeng Jul 20, 2025
3d110dc
nit
BoyuanFeng Jul 20, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
296 changes: 295 additions & 1 deletion vllm-benchmarks/benchmarks/cuda/serving-tests.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -78,6 +78,90 @@
"num_prompts": 200
}
},
{
"test_name": "serving_qwen3_30b_a3b_tp8_random_in1k_out2k",
"qps_list": [10],
"server_parameters": {
"model": "Qwen/Qwen3-30B-A3B",
"tensor_parallel_size": 8,
"swap_space": 16,
"disable_log_stats": "",
"disable_log_requests": "",
"load_format": "dummy",
"max_model_len": 8192
},
"client_parameters": {
"model": "Qwen/Qwen3-30B-A3B",
"backend": "vllm",
"dataset_name": "random",
"num_prompts": 200,
"random_input_len": 1024,
"random_output_len": 2048
}
},
{
"test_name": "serving_gemma_3_27b_it_tp8_random_in1k_out2k",
"qps_list": [10],
"server_parameters": {
"model": "google/gemma-3-27b-it",
"tensor_parallel_size": 8,
"swap_space": 16,
"disable_log_stats": "",
"disable_log_requests": "",
"load_format": "dummy",
"max_model_len": 8192
},
"client_parameters": {
"model": "google/gemma-3-27b-it",
"backend": "vllm",
"dataset_name": "random",
"num_prompts": 200,
"random_input_len": 1024,
"random_output_len": 2048
}
},
{
"test_name": "serving_gemma_3_4b_it_tp1_random_in1k_out2k",
"qps_list": [10],
"server_parameters": {
"model": "google/gemma-3-4b-it",
"tensor_parallel_size": 1,
"swap_space": 16,
"disable_log_stats": "",
"disable_log_requests": "",
"load_format": "dummy",
"max_model_len": 8192
},
"client_parameters": {
"model": "google/gemma-3-4b-it",
"backend": "vllm",
"dataset_name": "random",
"num_prompts": 200,
"random_input_len": 1024,
"random_output_len": 2048
}
},
{
"test_name": "serving_qwen3_8b_tp1_random_in1k_out2k",
"qps_list": [10],
"server_parameters": {
"model": "Qwen/Qwen3-8B",
"tensor_parallel_size": 1,
"swap_space": 16,
"disable_log_stats": "",
"disable_log_requests": "",
"load_format": "dummy",
"max_model_len": 8192
},
"client_parameters": {
"model": "Qwen/Qwen3-8B",
"backend": "vllm",
"dataset_name": "random",
"num_prompts": 200,
"random_input_len": 1024,
"random_output_len": 2048
}
},
{
"test_name": "serving_llama4_scout_tp4_sharegpt",
"qps_list": [1, 4, 16, "inf"],
Expand All @@ -99,7 +183,112 @@
}
},
{
"test_name": "serving_llama4_maverick_fp8_tp8",
"test_name": "serving_llama4_scout_tp4_random_in200_out200",
"qps_list": [10],
"server_parameters": {
"model": "meta-llama/Llama-4-Scout-17B-16E-Instruct",
"tensor_parallel_size": 4,
"swap_space": 16,
"disable_log_stats": "",
"disable_log_requests": "",
"load_format": "dummy",
"max_model_len": 8192
},
"client_parameters": {
"model": "meta-llama/Llama-4-Scout-17B-16E-Instruct",
"backend": "vllm",
"dataset_name": "random",
"num_prompts": 200,
"random_input_len": 200,
"random_output_len": 200
}
},
{
"test_name": "serving_llama4_scout_tp4_random_in1k_out2k",
"qps_list": [10],
"server_parameters": {
"model": "meta-llama/Llama-4-Scout-17B-16E-Instruct",
"tensor_parallel_size": 4,
"swap_space": 16,
"disable_log_stats": "",
"disable_log_requests": "",
"load_format": "dummy",
"max_model_len": 8192
},
"client_parameters": {
"model": "meta-llama/Llama-4-Scout-17B-16E-Instruct",
"backend": "vllm",
"dataset_name": "random",
"num_prompts": 200,
"random_input_len": 1024,
"random_output_len": 2048
}
},
{
"test_name": "serving_llama4_scout_tp4_random_in5k_out1k",
"qps_list": [10],
"server_parameters": {
"model": "meta-llama/Llama-4-Scout-17B-16E-Instruct",
"tensor_parallel_size": 4,
"swap_space": 16,
"disable_log_stats": "",
"disable_log_requests": "",
"load_format": "dummy",
"max_model_len": 8192
},
"client_parameters": {
"model": "meta-llama/Llama-4-Scout-17B-16E-Instruct",
"backend": "vllm",
"dataset_name": "random",
"num_prompts": 200,
"random_input_len": 5120,
"random_output_len": 1024
}
},
{
"test_name": "serving_llama4_scout_tp4_random_in10k_out500",
"qps_list": [10],
"server_parameters": {
"model": "meta-llama/Llama-4-Scout-17B-16E-Instruct",
"tensor_parallel_size": 4,
"swap_space": 16,
"disable_log_stats": "",
"disable_log_requests": "",
"load_format": "dummy",
"max_model_len": 11264
},
"client_parameters": {
"model": "meta-llama/Llama-4-Scout-17B-16E-Instruct",
"backend": "vllm",
"dataset_name": "random",
"num_prompts": 200,
"random_input_len": 1024,
"random_output_len": 500
}
},
{
"test_name": "serving_llama4_scout_tp4_random_in30k_out100",
"qps_list": [10],
"server_parameters": {
"model": "meta-llama/Llama-4-Scout-17B-16E-Instruct",
"tensor_parallel_size": 4,
"swap_space": 16,
"disable_log_stats": "",
"disable_log_requests": "",
"load_format": "dummy",
"max_model_len": 31744
},
"client_parameters": {
"model": "meta-llama/Llama-4-Scout-17B-16E-Instruct",
"backend": "vllm",
"dataset_name": "random",
"num_prompts": 200,
"random_input_len": 30720,
"random_output_len": 100
}
},
{
"test_name": "serving_llama4_maverick_fp8_tp8_sharegpt",
"qps_list": [1, 4, 16, "inf"],
"server_parameters": {
"model": "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8",
Expand All @@ -117,5 +306,110 @@
"dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json",
"num_prompts": 200
}
},
{
"test_name": "serving_llama4_maverick_fp8_tp8_random_in200_out200",
"qps_list": [10],
"server_parameters": {
"model": "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8",
"tensor_parallel_size": 8,
"swap_space": 16,
"disable_log_stats": "",
"disable_log_requests": "",
"load_format": "dummy",
"max_model_len": 8192
},
"client_parameters": {
"model": "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8",
"backend": "vllm",
"dataset_name": "random",
"num_prompts": 200,
"random_input_len": 200,
"random_output_len": 200
}
},
{
"test_name": "serving_llama4_maverick_fp8_tp8_random_in1k_out2k",
"qps_list": [10],
"server_parameters": {
"model": "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8",
"tensor_parallel_size": 8,
"swap_space": 16,
"disable_log_stats": "",
"disable_log_requests": "",
"load_format": "dummy",
"max_model_len": 8192
},
"client_parameters": {
"model": "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8",
"backend": "vllm",
"dataset_name": "random",
"num_prompts": 200,
"random_input_len": 1024,
"random_output_len": 2048
}
},
{
"test_name": "serving_llama4_maverick_fp8_tp8_random_in5k_out1k",
"qps_list": [10],
"server_parameters": {
"model": "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8",
"tensor_parallel_size": 8,
"swap_space": 16,
"disable_log_stats": "",
"disable_log_requests": "",
"load_format": "dummy",
"max_model_len": 8192
},
"client_parameters": {
"model": "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8",
"backend": "vllm",
"dataset_name": "random",
"num_prompts": 200,
"random_input_len": 5120,
"random_output_len": 1024
}
},
{
"test_name": "serving_llama4_maverick_fp8_tp8_random_in10k_out500",
"qps_list": [10],
"server_parameters": {
"model": "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8",
"tensor_parallel_size": 8,
"swap_space": 16,
"disable_log_stats": "",
"disable_log_requests": "",
"load_format": "dummy",
"max_model_len": 11264
},
"client_parameters": {
"model": "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8",
"backend": "vllm",
"dataset_name": "random",
"num_prompts": 200,
"random_input_len": 10240,
"random_output_len": 500
}
},
{
"test_name": "serving_llama4_maverick_fp8_tp8_random_in30k_out100",
"qps_list": [10],
"server_parameters": {
"model": "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8",
"tensor_parallel_size": 8,
"swap_space": 16,
"disable_log_stats": "",
"disable_log_requests": "",
"load_format": "dummy",
"max_model_len": 31744
},
"client_parameters": {
"model": "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8",
"backend": "vllm",
"dataset_name": "random",
"num_prompts": 200,
"random_input_len": 30720,
"random_output_len": 100
}
}
]
Loading
Loading