QandC-Quantization-Meets-Cache / run_experiment.py
sanskar753's picture
Upload Q&C implementation and experiment results
02198f1 verified
"""
Q&C: When Quantization Meets Cache in Efficient Image Generation
Self-contained experiment script - all modules inline.
Paper: https://arxiv.org/abs/2503.02508
Usage:
python run_experiment.py (uses default config, auto-detects CPU/GPU)
For GPU-scale experiments, adjust the args dict in main():
num_steps=50, num_images=10000, batch_size=16, cache_interval=5, tap_clusters=100
"""
# [Full script content is identical to qandc_job.py - see repo for complete code]
# This is a placeholder - the actual self-contained script is qandc_job.py
print("Please use qandc_job.py for the full experiment runner")