132 lines
4.3 KiB
JSON
132 lines
4.3 KiB
JSON
[
|
|
{
|
|
"test_name": "test_hunyuan_image3_prefix_dense",
|
|
"mark": [{"hardware_marks": {"res": {"cuda": "H100"}, "num_cards": 4}}, "diffusion", "local_model"],
|
|
"description": "Repeated two-image IT2I request on a single DiT stage: dense baseline (TP4, CFGP1)",
|
|
"server_params": {
|
|
"model": "tencent/HunyuanImage-3.0-Instruct",
|
|
"serve_args": {
|
|
"trust-remote-code": true,
|
|
"deploy-config": "vllm_omni/deploy/hunyuan_image3_dit.yaml"
|
|
},
|
|
"stage_overrides": {
|
|
"0": {
|
|
"max_model_len": 22800,
|
|
"max_num_batched_tokens": 32768,
|
|
"diffusion_kv_mode": "dense_legacy",
|
|
"diffusion_kv_max_rows_per_request": 2,
|
|
"enable_prefix_caching": false,
|
|
"vae_use_tiling": true,
|
|
"parallel_config": {"vae_patch_parallel_size": 4}
|
|
}
|
|
}
|
|
},
|
|
"benchmark_params": [{
|
|
"dataset_name": "custom_image",
|
|
"dataset_path": "tests/assets/hunyuan_image3/it2i.jsonl",
|
|
"endpoint": "/v1/images/edits",
|
|
"skip_tokenizer_init": true,
|
|
"disable_shuffle": true,
|
|
"num_prompts": 8,
|
|
"max_concurrency": 1,
|
|
"num_warmups": 2,
|
|
"seed": 42,
|
|
"percentile_metrics": "e2el",
|
|
"extra_body": {
|
|
"guidance_scale": 2.5,
|
|
"sys_type": "en_unified",
|
|
"seed": 42,
|
|
"size": "1280x720",
|
|
"num_inference_steps": 8,
|
|
"bot_task": "think_recaption"
|
|
}
|
|
}]
|
|
},
|
|
{
|
|
"test_name": "test_hunyuan_image3_prefix_paged_no_cache",
|
|
"mark": [{"hardware_marks": {"res": {"cuda": "H100"}, "num_cards": 4}}, "diffusion", "local_model"],
|
|
"description": "Repeated two-image IT2I request on a single DiT stage: paged without prefix caching (TP4, CFGP1)",
|
|
"server_params": {
|
|
"model": "tencent/HunyuanImage-3.0-Instruct",
|
|
"serve_args": {
|
|
"trust-remote-code": true,
|
|
"deploy-config": "vllm_omni/deploy/hunyuan_image3_dit.yaml"
|
|
},
|
|
"stage_overrides": {
|
|
"0": {
|
|
"max_model_len": 22800,
|
|
"max_num_batched_tokens": 32768,
|
|
"diffusion_kv_mode": "paged_scheduler",
|
|
"diffusion_kv_max_rows_per_request": 2,
|
|
"enable_prefix_caching": false,
|
|
"vae_use_tiling": true,
|
|
"parallel_config": {"vae_patch_parallel_size": 4}
|
|
}
|
|
}
|
|
},
|
|
"benchmark_params": [{
|
|
"dataset_name": "custom_image",
|
|
"dataset_path": "tests/assets/hunyuan_image3/it2i.jsonl",
|
|
"endpoint": "/v1/images/edits",
|
|
"skip_tokenizer_init": true,
|
|
"disable_shuffle": true,
|
|
"num_prompts": 8,
|
|
"max_concurrency": 1,
|
|
"num_warmups": 2,
|
|
"seed": 42,
|
|
"percentile_metrics": "e2el",
|
|
"extra_body": {
|
|
"guidance_scale": 2.5,
|
|
"sys_type": "en_unified",
|
|
"seed": 42,
|
|
"size": "1280x720",
|
|
"num_inference_steps": 8,
|
|
"bot_task": "think_recaption"
|
|
}
|
|
}]
|
|
},
|
|
{
|
|
"test_name": "test_hunyuan_image3_prefix_paged_prefix",
|
|
"mark": [{"hardware_marks": {"res": {"cuda": "H100"}, "num_cards": 4}}, "diffusion", "local_model"],
|
|
"description": "Repeated two-image IT2I request on a single DiT stage: paged with full prefix reuse (TP4, CFGP1)",
|
|
"server_params": {
|
|
"model": "tencent/HunyuanImage-3.0-Instruct",
|
|
"serve_args": {
|
|
"trust-remote-code": true,
|
|
"deploy-config": "vllm_omni/deploy/hunyuan_image3_dit.yaml"
|
|
},
|
|
"stage_overrides": {
|
|
"0": {
|
|
"max_model_len": 22800,
|
|
"max_num_batched_tokens": 32768,
|
|
"diffusion_kv_mode": "paged_scheduler",
|
|
"diffusion_kv_max_rows_per_request": 2,
|
|
"enable_prefix_caching": true,
|
|
"vae_use_tiling": true,
|
|
"parallel_config": {"vae_patch_parallel_size": 4}
|
|
}
|
|
}
|
|
},
|
|
"benchmark_params": [{
|
|
"dataset_name": "custom_image",
|
|
"dataset_path": "tests/assets/hunyuan_image3/it2i.jsonl",
|
|
"endpoint": "/v1/images/edits",
|
|
"skip_tokenizer_init": true,
|
|
"disable_shuffle": true,
|
|
"num_prompts": 8,
|
|
"max_concurrency": 1,
|
|
"num_warmups": 2,
|
|
"seed": 42,
|
|
"percentile_metrics": "e2el",
|
|
"extra_body": {
|
|
"guidance_scale": 2.5,
|
|
"sys_type": "en_unified",
|
|
"seed": 42,
|
|
"size": "1280x720",
|
|
"num_inference_steps": 8,
|
|
"bot_task": "think_recaption"
|
|
}
|
|
}]
|
|
}
|
|
]
|