270 lines
6.9 KiB
JSON
270 lines
6.9 KiB
JSON
[
|
|
{
|
|
"test_name": "test_cosmos3_t2i_official_demo_2gpu",
|
|
"mark": [
|
|
{
|
|
"hardware_marks": {
|
|
"res": {
|
|
"cuda": "H100"
|
|
},
|
|
"num_cards": 2
|
|
}
|
|
},
|
|
"full_model",
|
|
"diffusion"
|
|
],
|
|
"description": "Cosmos3-Nano text-to-image official demo workload on 2 GPUs",
|
|
"server_type": "vllm-omni",
|
|
"benchmark_endpoint": "/v1/images/generations",
|
|
"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": "random",
|
|
"task": "t2i",
|
|
"width": 1024,
|
|
"height": 1024,
|
|
"num-inference-steps": 4,
|
|
"num-prompts": 3,
|
|
"max-concurrency": 1,
|
|
"seed": 42,
|
|
"extra-body": {
|
|
"guidance_scale": 7.0,
|
|
"flow_shift": 3.0,
|
|
"guardrails": false
|
|
},
|
|
"baseline": {
|
|
"H100": {
|
|
"throughput_qps": 1.1958,
|
|
"latency_mean": 0.843,
|
|
"peak_memory_mb_mean": 80000.0
|
|
}
|
|
}
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"test_name": "test_cosmos3_t2v_official_demo_2gpu",
|
|
"mark": [
|
|
{
|
|
"hardware_marks": {
|
|
"res": {
|
|
"cuda": "H100"
|
|
},
|
|
"num_cards": 2
|
|
}
|
|
},
|
|
"full_model",
|
|
"diffusion"
|
|
],
|
|
"description": "Cosmos3-Nano text-to-video official demo workload on 2 GPUs",
|
|
"server_type": "vllm-omni",
|
|
"benchmark_endpoint": "/v1/videos",
|
|
"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": "random",
|
|
"task": "t2v",
|
|
"num-prompts": 3,
|
|
"max-concurrency": 1,
|
|
"seed": 42,
|
|
"random-request-config": [
|
|
{
|
|
"width": 1280,
|
|
"height": 720,
|
|
"prompt": "A robot arm is cleaning a plate in the kitchen.",
|
|
"num_inference_steps": 4,
|
|
"num_frames": 189,
|
|
"fps": 24,
|
|
"weight": 1
|
|
}
|
|
],
|
|
"extra-body": {
|
|
"guidance_scale": 6.0,
|
|
"flow_shift": 10.0,
|
|
"max_sequence_length": 4096,
|
|
"guardrails": false,
|
|
"use_resolution_template": false,
|
|
"use_duration_template": false
|
|
},
|
|
"baseline": {
|
|
"H100": {
|
|
"throughput_qps": 0.0307,
|
|
"latency_mean": 32.7665,
|
|
"peak_memory_mb_mean": 28762.4762
|
|
}
|
|
}
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"test_name": "test_cosmos3_i2v_official_demo_2gpu",
|
|
"mark": [
|
|
{
|
|
"hardware_marks": {
|
|
"res": {
|
|
"cuda": "H100"
|
|
},
|
|
"num_cards": 2
|
|
}
|
|
},
|
|
"full_model",
|
|
"diffusion"
|
|
],
|
|
"description": "Cosmos3-Nano image-to-video official demo workload on 2 GPUs",
|
|
"server_type": "vllm-omni",
|
|
"benchmark_endpoint": "/v1/videos",
|
|
"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": "random",
|
|
"task": "i2v",
|
|
"num-prompts": 3,
|
|
"max-concurrency": 1,
|
|
"num-input-images": 1,
|
|
"seed": 42,
|
|
"random-request-config": [
|
|
{
|
|
"width": 1280,
|
|
"height": 720,
|
|
"prompt": "The scene comes to life with smooth, natural motion.",
|
|
"num_inference_steps": 4,
|
|
"num_frames": 189,
|
|
"fps": 24,
|
|
"weight": 1
|
|
}
|
|
],
|
|
"extra-body": {
|
|
"guidance_scale": 6.0,
|
|
"flow_shift": 10.0,
|
|
"max_sequence_length": 4096,
|
|
"guardrails": false
|
|
},
|
|
"baseline": {
|
|
"H100": {
|
|
"throughput_qps": 0.0305,
|
|
"latency_mean": 33.1009,
|
|
"peak_memory_mb_mean": 29441.1429
|
|
}
|
|
}
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"test_name": "test_cosmos3_v2v_official_demo_2gpu",
|
|
"mark": [
|
|
{
|
|
"hardware_marks": {
|
|
"res": {
|
|
"cuda": "H100"
|
|
},
|
|
"num_cards": 2
|
|
}
|
|
},
|
|
"full_model",
|
|
"diffusion"
|
|
],
|
|
"description": "Cosmos3-Nano video-to-video official demo workload on 2 GPUs",
|
|
"server_type": "vllm-omni",
|
|
"benchmark_endpoint": "/v1/videos",
|
|
"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": "random",
|
|
"task": "v2v",
|
|
"num-prompts": 3,
|
|
"max-concurrency": 1,
|
|
"seed": 42,
|
|
"random-request-config": [
|
|
{
|
|
"width": 1280,
|
|
"height": 720,
|
|
"prompt": "Continue the same scene with smooth natural motion.",
|
|
"num_inference_steps": 4,
|
|
"num_frames": 189,
|
|
"fps": 24,
|
|
"weight": 1
|
|
}
|
|
],
|
|
"extra-body": {
|
|
"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": {
|
|
"throughput_qps": 0.0299,
|
|
"latency_mean": 33.925,
|
|
"peak_memory_mb_mean": 29443.1429
|
|
}
|
|
}
|
|
}
|
|
]
|
|
}
|
|
]
|