Files
vllm-omni/tests/dfx/perf/tests/test_cosmos3_vllm_omni.json
T

289 lines
7.4 KiB
JSON

[
{
"test_name": "test_cosmos3_t2i_official_demo_2gpu",
"mark": [
{
"hardware_marks": {
"res": {
"cuda": [
"H100",
"B200"
]
},
"num_cards": 2
}
},
"full_model",
"diffusion"
],
"description": "Cosmos3-Nano text-to-image official demo workload on 2 GPUs",
"server_params": {
"model": "nvidia/Cosmos3-Nano",
"serve_args": {
"cfg-parallel-size": 2,
"use-hsdp": true,
"hsdp-shard-size": 2,
"vae-patch-parallel-size": 2,
"vae-use-tiling": true,
"model-class-name": "Cosmos3OmniDiffusersPipeline",
"no-guardrails": true,
"stage-init-timeout": 900,
"init-timeout": 1200,
"enable-diffusion-pipeline-profiler": true
}
},
"benchmark_params": [
{
"name": "1024x1024_steps4",
"dataset_name": "random",
"tokenizer": "gpt2",
"endpoint": "/v1/images/generations",
"num_prompts": 3,
"max_concurrency": 1,
"random_input_len": 8,
"random_output_len": 1,
"percentile_metrics": "e2el",
"extra_body": {
"width": 1024,
"height": 1024,
"num_inference_steps": 4,
"seed": 42,
"guidance_scale": 7.0,
"flow_shift": 3.0,
"guardrails": false
},
"baseline": {
"H100": {
"request_throughput": 1.1958,
"mean_e2el_ms": 843.0,
"mean_peak_memory_mb": 80000.0
}
}
}
]
},
{
"test_name": "test_cosmos3_t2v_official_demo_2gpu",
"mark": [
{
"hardware_marks": {
"res": {
"cuda": [
"H100",
"B200"
]
},
"num_cards": 2
}
},
"full_model",
"diffusion"
],
"description": "Cosmos3-Nano text-to-video official demo workload on 2 GPUs",
"server_params": {
"model": "nvidia/Cosmos3-Nano",
"serve_args": {
"cfg-parallel-size": 2,
"use-hsdp": true,
"hsdp-shard-size": 2,
"vae-patch-parallel-size": 2,
"vae-use-tiling": true,
"model-class-name": "Cosmos3OmniDiffusersPipeline",
"no-guardrails": true,
"stage-init-timeout": 900,
"init-timeout": 1200,
"enable-diffusion-pipeline-profiler": true
}
},
"benchmark_params": [
{
"name": "1280x720_frames189_steps4",
"dataset_name": "random",
"tokenizer": "gpt2",
"endpoint": "/v1/videos",
"num_prompts": 3,
"max_concurrency": 1,
"random_input_len": 8,
"random_output_len": 1,
"percentile_metrics": "e2el",
"extra_body": {
"width": 1280,
"height": 720,
"num_inference_steps": 4,
"num_frames": 189,
"fps": 24,
"seed": 42,
"guidance_scale": 6.0,
"flow_shift": 10.0,
"max_sequence_length": 4096,
"guardrails": false,
"use_resolution_template": false,
"use_duration_template": false
},
"baseline": {
"H100": {
"request_throughput": 0.0307,
"mean_e2el_ms": 32766.5,
"mean_peak_memory_mb": 28762.4762
}
}
}
]
},
{
"test_name": "test_cosmos3_i2v_official_demo_2gpu",
"mark": [
{
"hardware_marks": {
"res": {
"cuda": [
"H100",
"B200"
]
},
"num_cards": 2
}
},
"full_model",
"diffusion"
],
"description": "Cosmos3-Nano image-to-video official demo workload on 2 GPUs",
"server_params": {
"model": "nvidia/Cosmos3-Nano",
"serve_args": {
"cfg-parallel-size": 2,
"use-hsdp": true,
"hsdp-shard-size": 2,
"vae-patch-parallel-size": 2,
"vae-use-tiling": true,
"model-class-name": "Cosmos3OmniDiffusersPipeline",
"no-guardrails": true,
"stage-init-timeout": 900,
"init-timeout": 1200,
"enable-diffusion-pipeline-profiler": true
}
},
"benchmark_params": [
{
"name": "1280x720_frames189_steps4",
"dataset_name": "random-mm",
"tokenizer": "gpt2",
"endpoint": "/v1/videos",
"num_prompts": 3,
"max_concurrency": 1,
"random_input_len": 8,
"random_output_len": 1,
"random_range_ratio": 0.0,
"percentile_metrics": "e2el",
"random_mm_base_items_per_request": 1,
"random_mm_num_mm_items_range_ratio": 0,
"random_mm_limit_mm_per_prompt": {
"image": 1
},
"random_mm_bucket_config": {
"(720, 1280, 1)": 1.0
},
"extra_body": {
"width": 1280,
"height": 720,
"num_inference_steps": 4,
"num_frames": 189,
"fps": 24,
"seed": 42,
"guidance_scale": 6.0,
"flow_shift": 10.0,
"max_sequence_length": 4096,
"guardrails": false
},
"baseline": {
"H100": {
"request_throughput": 0.0305,
"mean_e2el_ms": 33100.9,
"mean_peak_memory_mb": 29441.1429
}
}
}
]
},
{
"test_name": "test_cosmos3_v2v_official_demo_2gpu",
"mark": [
{
"hardware_marks": {
"res": {
"cuda": [
"H100",
"B200"
]
},
"num_cards": 2
}
},
"full_model",
"diffusion"
],
"description": "Cosmos3-Nano video-to-video official demo workload on 2 GPUs",
"server_params": {
"model": "nvidia/Cosmos3-Nano",
"serve_args": {
"cfg-parallel-size": 2,
"use-hsdp": true,
"hsdp-shard-size": 2,
"vae-patch-parallel-size": 2,
"vae-use-tiling": true,
"model-class-name": "Cosmos3OmniDiffusersPipeline",
"no-guardrails": true,
"stage-init-timeout": 900,
"init-timeout": 1200,
"enable-diffusion-pipeline-profiler": true
}
},
"benchmark_params": [
{
"name": "1280x720_frames189_steps4",
"dataset_name": "random-mm",
"tokenizer": "gpt2",
"endpoint": "/v1/videos",
"num_prompts": 3,
"max_concurrency": 1,
"random_input_len": 8,
"random_output_len": 1,
"random_range_ratio": 0.0,
"percentile_metrics": "e2el",
"random_mm_base_items_per_request": 1,
"random_mm_num_mm_items_range_ratio": 0,
"random_mm_limit_mm_per_prompt": {
"video": 1
},
"random_mm_bucket_config": {
"(720, 1280, 189)": 1.0
},
"extra_body": {
"width": 1280,
"height": 720,
"num_inference_steps": 4,
"num_frames": 189,
"fps": 24,
"seed": 42,
"guidance_scale": 6.0,
"flow_shift": 10.0,
"max_sequence_length": 4096,
"guardrails": false,
"condition_frame_indexes_vision": [
0,
1
],
"condition_video_keep": "first"
},
"baseline": {
"H100": {
"request_throughput": 0.0299,
"mean_e2el_ms": 33925.0,
"mean_peak_memory_mb": 29443.1429
}
}
}
]
}
]