[Enhancement]modify profiling.md (#3051)

Signed-off-by: bjf-frz <frz123db@gmail.com>
This commit is contained in:
bjf-frz authored and GitHub committed 2026-04-24 16:30:24 +08:00
1 parent 678af19240
commit e24f86ae2e
8 files changed
+261 -97

No files matched your search

@@ -87,9 +87,11 @@ For more options, run:
"""
import argparse
import json
import os
import time
from pathlib import Path
from typing import Any
import torch
from PIL import Image
@@ -101,6 +103,16 @@ from vllm_omni.outputs import OmniRequestOutput
from vllm_omni.platforms import current_omni_platform
def parse_profiler_config(value: str) -> dict[str, Any]:
try:
config = json.loads(value)
except json.JSONDecodeError as e:
raise argparse.ArgumentTypeError(f"--profiler-config must be valid JSON: {e}") from e
if not isinstance(config, dict):
raise argparse.ArgumentTypeError("--profiler-config must be a JSON object")
return config
def parse_args() -> argparse.Namespace:
parser = argparse.ArgumentParser(description="Edit an image with Qwen-Image-Edit.")
parser.add_argument(
@@ -360,6 +372,12 @@ def parse_args() -> argparse.Namespace:
action="store_true",
help="Enable diffusion pipeline profiler to display stage durations.",
)
parser.add_argument(
"--profiler-config",
type=parse_profiler_config,
default=None,
help='JSON profiler config for torch/cuda profiling, e.g. \'{"profiler":"torch","torch_profiler_dir":"./perf"}\'.',
)
return parser.parse_args()
@@ -425,11 +443,11 @@ def main():
enforce_eager=args.enforce_eager,
enable_cpu_offload=args.enable_cpu_offload,
enable_diffusion_pipeline_profiler=args.enable_diffusion_pipeline_profiler,
profiler_config=args.profiler_config,
)
print("Pipeline loaded")
# Check if profiling is requested via environment variable
profiler_enabled = bool(os.getenv("VLLM_TORCH_PROFILER_DIR"))
profiler_enabled = args.profiler_config is not None
# Time profiling for generation
print(f"\n{'=' * 60}")