anodyine/vllm-omni
1
0 Fork 0
Code Issues 4 Pull Requests 2 Actions Packages Projects Releases Wiki Activity

[Perf][CI] Add MiniMax-H3 4xH100 diffusion perf config (#5836)

Browse Source 
Signed-off-by: David Chen <530634352@qq.com>
This commit is contained in:
WeiQing Chen authored and GitHub committed 2026-08-07 00:12:07 +08:00
1 parent 62bf8d630d
commit a874b8e09b
5 files changed
+427 -10
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

tests/dfx/perf/scripts/run_diffusion_benchmark.py
+46 -2
View File
@@ -350,10 +350,49 @@ def _kill_process_tree(pid: int) -> None:
def _resolve_offline_model(model: str) -> str:
"""Under HF_HUB_OFFLINE, resolve a HF repo id to its local snapshot dir."""
"""Resolve a model string to a local directory.
Local paths pass through unchanged. HF repo ids are resolved to their local
snapshot dir when ``HF_HUB_OFFLINE`` is set. ``repo_id/subfolder`` (e.g.
``MiniMaxAI/MiniMax-H3/FL2VA``) is resolved to the matching partition
subfolder of the snapshot, downloading only that subfolder when online.
"""
import huggingface_hub
if not model or os.path.isdir(model) or not huggingface_hub.constants.HF_HUB_OFFLINE:
if not model or os.path.isdir(model):
return model
# MiniMax-H3 custom code uses relative imports across files, which breaks
# when the HF cache snapshot is symlinked (``get_class_from_dynamic_module``
# resolves ``realpath`` into the blobs dir). Mirror the accuracy test's env
# overrides so CI / local runs can point at a materialized partition. The
# repo-root key (used with ``--task-type fl2va|ref2va``) expects a
# materialized root containing the FL2VA/Ref2VA subfolders.
model_env_overrides = {
"MiniMaxAI/MiniMax-H3": "VLLM_TEST_MINIMAX_H3_MODEL",
"MiniMaxAI/MiniMax-H3/FL2VA": "VLLM_TEST_MINIMAX_H3_FL2VA_MODEL",
"MiniMaxAI/MiniMax-H3/Ref2VA": "VLLM_TEST_MINIMAX_H3_REF2VA_MODEL",
}
env_name = model_env_overrides.get(model)
if env_name:
env_model = os.environ.get(env_name)
if env_model:
return env_model
parts = model.split("/")
if len(parts) >= 3:
repo_id = "/".join(parts[:2])
subfolder = "/".join(parts[2:])
from huggingface_hub import snapshot_download
snapshot_root = snapshot_download(
repo_id,
allow_patterns=[f"{subfolder}/**"],
local_files_only=huggingface_hub.constants.HF_HUB_OFFLINE,
)
return str(Path(snapshot_root) / subfolder)
if not huggingface_hub.constants.HF_HUB_OFFLINE:
return model
from huggingface_hub import snapshot_download
@@ -387,6 +426,11 @@ class DiffusionServer:
def _start_server(self) -> None:
env = os.environ.copy()
env["VLLM_WORKER_MULTIPROC_METHOD"] = "spawn"
# Give each run its own writable video-storage dir. The server default
# (/tmp/storage) may be missing or not writable on shared hosts / CI.
storage_path = Path(os.environ.get("VLLM_OMNI_STORAGE_PATH", str(BENCHMARK_RESULT_DIR / "storage")))
storage_path.mkdir(parents=True, exist_ok=True)
env["VLLM_OMNI_STORAGE_PATH"] = str(storage_path)
cmd = [
sys.executable,
tests/dfx/perf/tests/test_minimax_h3_vllm_omni.json
+295
View File
@@ -0,0 +1,295 @@
[
{
"test_name": "test_minimax_h3_t2v_4gpu",
"mark": [
{
"hardware_marks": {
"res": {
"cuda": "H100"
},
"num_cards": 4
}
},
"full_model",
"diffusion"
],
"description": "MiniMax-H3 T2VA text-to-video+audio on 4 GPUs (USP4 + HSDP4, encoder-TP4, VAE-PP4 tile)",
"server_type": "vllm-omni",
"benchmark_endpoint": "/v1/videos",
"server_params": {
"model": "MiniMaxAI/MiniMax-H3",
"serve_args": {
"trust-remote-code": true,
"task-type": "fl2va",
"num-gpus": 4,
"usp": 4,
"ring": 1,
"use-hsdp": true,
"hsdp-shard-size": 4,
"text-encoder-tp-size": 4,
"vae-patch-parallel-size": 4,
"vae-parallel-mode": "tile",
"vae-use-tiling": true,
"diffusion-attention-backend": "FLASH_ATTN",
"stage-init-timeout": 1800,
"init-timeout": 1800,
"enable-diffusion-pipeline-profiler": true
}
},
"benchmark_params": [
{
"name": "1344x768_frames209_steps8",
"dataset": "random",
"task": "t2v",
"num-prompts": 3,
"max-concurrency": 1,
"warmup-requests": 1,
"warmup-concurrency": 1,
"seed": 42,
"random-request-config": [
{
"width": 1344,
"height": 768,
"prompt": "Cinematic drone shot pushing through misty mountain ridges at sunrise, golden light catching the clouds, slow and smooth.",
"num_inference_steps": 8,
"num_frames": 209,
"fps": 24,
"weight": 1
}
],
"extra-body": {
"flow_shift": 12.0,
"extra_params": "{\"task\":\"t2va\",\"duration\":8.7,\"aspect_ratio\":\"16:9\",\"audio_flow_shift\":3.0}"
},
"baseline": {
"H100": {
"throughput_qps": 0.0211,
"latency_mean": 38.3252,
"peak_memory_mb_mean": 54219.6
}
}
}
]
},
{
"test_name": "test_minimax_h3_ti2v_4gpu",
"mark": [
{
"hardware_marks": {
"res": {
"cuda": "H100"
},
"num_cards": 4
}
},
"full_model",
"diffusion"
],
"description": "MiniMax-H3 FL2VA first-frame image-to-video+audio on 4 GPUs (USP4 + HSDP4, encoder-TP4, VAE-PP4 tile)",
"server_type": "vllm-omni",
"benchmark_endpoint": "/v1/videos",
"server_params": {
"model": "MiniMaxAI/MiniMax-H3",
"serve_args": {
"trust-remote-code": true,
"task-type": "fl2va",
"num-gpus": 4,
"usp": 4,
"ring": 1,
"use-hsdp": true,
"hsdp-shard-size": 4,
"text-encoder-tp-size": 4,
"vae-patch-parallel-size": 4,
"vae-parallel-mode": "tile",
"vae-use-tiling": true,
"diffusion-attention-backend": "FLASH_ATTN",
"stage-init-timeout": 1800,
"init-timeout": 1800,
"enable-diffusion-pipeline-profiler": true
}
},
"benchmark_params": [
{
"name": "1344x768_frames209_steps8",
"dataset": "random",
"task": "ti2v",
"num-prompts": 3,
"max-concurrency": 1,
"warmup-requests": 1,
"warmup-concurrency": 1,
"seed": 42,
"random-request-config": [
{
"width": 1344,
"height": 768,
"prompt": "Continue the scene: the camera slowly pushes in on the subject as the background city lights drift and blur, with the actor singing softly and emotionally.",
"num_inference_steps": 8,
"num_frames": 209,
"fps": 24,
"weight": 1
}
],
"extra-body": {
"flow_shift": 12.0,
"extra_params": "{\"task\":\"fl2va\",\"duration\":8.7,\"audio_flow_shift\":3.0}"
},
"num-input-images": 1,
"baseline": {
"H100": {
"throughput_qps": 0.0212,
"latency_mean": 38.1385,
"peak_memory_mb_mean": 54622.8
}
}
}
]
},
{
"test_name": "test_minimax_h3_v2v_4gpu",
"mark": [
{
"hardware_marks": {
"res": {
"cuda": "H100"
},
"num_cards": 4
}
},
"full_model",
"diffusion"
],
"description": "MiniMax-H3 Ref2VA video-reference-to-video+audio on 4 GPUs (USP4 + HSDP4, encoder-TP4, VAE-PP4 tile)",
"server_type": "vllm-omni",
"benchmark_endpoint": "/v1/videos",
"server_params": {
"model": "MiniMaxAI/MiniMax-H3",
"serve_args": {
"trust-remote-code": true,
"task-type": "ref2va",
"num-gpus": 4,
"usp": 4,
"ring": 1,
"use-hsdp": true,
"hsdp-shard-size": 4,
"text-encoder-tp-size": 4,
"vae-patch-parallel-size": 4,
"vae-parallel-mode": "tile",
"vae-use-tiling": true,
"diffusion-attention-backend": "FLASH_ATTN",
"stage-init-timeout": 1800,
"init-timeout": 1800,
"enable-diffusion-pipeline-profiler": true
}
},
"benchmark_params": [
{
"name": "1344x768_frames209_steps8",
"dataset": "random",
"task": "v2v",
"num-prompts": 3,
"max-concurrency": 1,
"warmup-requests": 1,
"warmup-concurrency": 1,
"seed": 42,
"random-request-config": [
{
"width": 1344,
"height": 768,
"prompt": "Restyle the reference footage into a cinematic night scene with neon reflections, keeping the same camera motion and subject.",
"num_inference_steps": 8,
"num_frames": 209,
"fps": 24,
"weight": 1
}
],
"extra-body": {
"flow_shift": 12.0,
"extra_params": "{\"task\":\"ref2va\",\"duration\":8.7,\"aspect_ratio\":\"16:9\",\"audio_flow_shift\":3.0}"
},
"baseline": {
"H100": {
"throughput_qps": 0.0077,
"latency_mean": 105.7508,
"peak_memory_mb_mean": 55180.8
}
}
}
]
},
{
"test_name": "test_minimax_h3_t2v_dlo_4gpu",
"mark": [
{
"hardware_marks": {
"res": {
"cuda": "H100"
},
"num_cards": 4
}
},
"full_model",
"diffusion"
],
"description": "MiniMax-H3 T2VA with 4-card distributed layerwise offload (DLO), 8 denoise steps (USP4 + HSDP4, encoder-TP4, VAE-PP4 tile)",
"server_type": "vllm-omni",
"benchmark_endpoint": "/v1/videos",
"server_params": {
"model": "MiniMaxAI/MiniMax-H3",
"serve_args": {
"trust-remote-code": true,
"task-type": "fl2va",
"num-gpus": 4,
"usp": 4,
"ring": 1,
"use-hsdp": true,
"hsdp-shard-size": 4,
"text-encoder-tp-size": 4,
"vae-patch-parallel-size": 4,
"vae-parallel-mode": "tile",
"vae-use-tiling": true,
"diffusion-attention-backend": "FLASH_ATTN",
"stage-init-timeout": 1800,
"init-timeout": 1800,
"enable-diffusion-pipeline-profiler": true,
"enable-distributed-layerwise-offload": true,
"dlo-no-use-allgather": true,
"dlo-resident-layers": 8,
"enforce-eager": true
}
},
"benchmark_params": [
{
"name": "1344x768_frames209_steps8",
"dataset": "random",
"task": "t2v",
"num-prompts": 3,
"max-concurrency": 1,
"warmup-requests": 1,
"warmup-concurrency": 1,
"seed": 42,
"random-request-config": [
{
"width": 1344,
"height": 768,
"prompt": "Cinematic drone shot pushing through misty mountain ridges at sunrise, golden light catching the clouds, slow and smooth.",
"num_inference_steps": 8,
"num_frames": 209,
"fps": 24,
"weight": 1
}
],
"extra-body": {
"flow_shift": 12.0,
"extra_params": "{\"task\":\"t2va\",\"duration\":8.7,\"aspect_ratio\":\"16:9\",\"audio_flow_shift\":3.0}"
},
"baseline": {
"H100": {
"throughput_qps": 0.0212,
"latency_mean": 38.2089,
"peak_memory_mb_mean": 36218.4
}
}
}
]
}
]