obscura/vllm
2
0
Fork 0
mirror of https://github.com/vllm-project/vllm.git synced 2026-08-18 19:50:17 +00:00
Code Issues Packages Projects Releases Wiki Activity

update GPU json file based on h200 recipes (#43262)

Browse Source 
Signed-off-by: louie-tsai <[email protected]>
This commit is contained in:
Louie Tsai
2026-05-21 03:57:48 +00:00
committed by GitHub
parent 9640970de2
commit 5d041cc1fe
1 changed files with 110 additions and 75 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.buildkite/performance-benchmarks/tests/serving-tests.json
+110 -75
View File
@@ -1,77 +1,112 @@
[
{
"test_name": "serving_llama8B_tp1_sharegpt",
"qps_list": [1, 4, 16, "inf"],
"server_parameters": {
"model": "meta-llama/Meta-Llama-3.1-8B-Instruct",
"tensor_parallel_size": 1,
"disable_log_stats": "",
"load_format": "dummy"
},
"client_parameters": {
"model": "meta-llama/Meta-Llama-3.1-8B-Instruct",
"backend": "vllm",
"dataset_name": "sharegpt",
"dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json",
"temperature": 0,
"num_prompts": 200
}
{
"defaults": {
"qps_list": [
"inf"
],
"max_concurrency_list": [12, 16, 24, 32, 64, 128, 200],
"server_parameters": {
"model": "meta-llama/Llama-3.1-8B-Instruct",
"tensor_parallel_size": 1,
"dtype": "bfloat16"
},
{
"test_name": "serving_llama70B_tp4_sharegpt",
"qps_list": [1, 4, 16, "inf"],
"server_parameters": {
"model": "meta-llama/Meta-Llama-3.1-70B-Instruct",
"tensor_parallel_size": 4,
"disable_log_stats": "",
"load_format": "dummy"
},
"client_parameters": {
"model": "meta-llama/Meta-Llama-3.1-70B-Instruct",
"backend": "vllm",
"dataset_name": "sharegpt",
"dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json",
"temperature": 0,
"num_prompts": 200
}
},
{
"test_name": "serving_mixtral8x7B_tp2_sharegpt",
"qps_list": [1, 4, 16, "inf"],
"server_parameters": {
"model": "mistralai/Mixtral-8x7B-Instruct-v0.1",
"tensor_parallel_size": 2,
"disable_log_stats": "",
"load_format": "dummy"
},
"client_parameters": {
"model": "mistralai/Mixtral-8x7B-Instruct-v0.1",
"backend": "vllm",
"dataset_name": "sharegpt",
"dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json",
"temperature": 0,
"num_prompts": 200
}
},
{
"test_name": "serving_llama70B_tp4_sharegpt_specdecode",
"qps_list": [2],
"server_parameters": {
"model": "meta-llama/Meta-Llama-3.1-70B-Instruct",
"tensor_parallel_size": 4,
"speculative_config": {
"model": "turboderp/Qwama-0.5B-Instruct",
"num_speculative_tokens": 4,
"draft_tensor_parallel_size": 1
}
},
"client_parameters": {
"model": "meta-llama/Meta-Llama-3.1-70B-Instruct",
"backend": "vllm",
"dataset_name": "sharegpt",
"dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json",
"temperature": 0,
"num_prompts": 200
}
"client_parameters": {
"model": "meta-llama/Llama-3.1-8B-Instruct",
"backend": "vllm",
"ignore-eos": "",
"temperature": 0,
"num_prompts": 200
}
]
},
"tests": [
{
"test_name": "serving_llama8B_tp1_sharegpt",
"server_parameters": {
"tensor_parallel_size": 1
},
"client_parameters": {
"dataset_name": "sharegpt",
"dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json"
}
},
{
"dataset_name": "sharegpt",
"dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json"
}
},
{
"test_name": "serving_llama8B_tp1_random_128_128",
"server_parameters": {
"tensor_parallel_size": 1
},
"client_parameters": {
"dataset_name": "random",
"random-input-len": 128,
"random-output-len": 128
}
},
{
"test_name": "serving_llama8B_tp1_random_128_2048",
"server_parameters": {
"tensor_parallel_size": 1
},
"client_parameters": {
"dataset_name": "random",
"random-input-len": 128,
"random-output-len": 2048
}
},
{
"test_name": "serving_llama8B_tp1_random_2048_128",
"server_parameters": {
"tensor_parallel_size": 1
},
"client_parameters": {
"dataset_name": "random",
"random-input-len": 2048,
"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_llama70B_tp4_random_128_128",
"server_parameters": {
"model": "meta-llama/Llama-3.3-70B-Instruct",
"async_scheduling": "",
"no_enable_prefix_caching": "",
"max_num_batched_tokens": 8192
},
"client_parameters": {
"model": "meta-llama/Llama-3.3-70B-Instruct",
"dataset_name": "random",
"random-input-len": 128,
"random-output-len": 128
}
},
{
"test_name": "serving_gemma4-e4b_tp1_random_128_128",
"server_parameters": {
"model": "google/gemma-4-E4B-it",
"enable_auto_tool_choice": "",
"tool_call_parser": "gemma4",
"chat_template": "examples/tool_chat_template_gemma4.jinja",
"reasoning_parser": "gemma4"
},
"client_parameters": {
"model": "google/gemma-4-E4B-it",
"dataset_name": "random",
"random-input-len": 128,
"random-output-len": 128
}
}
]
}