AmpereComputingAI / ampere_model_library

AML's goal is to make benchmarking of various AI architectures on Ampere CPUs a pleasurable experience :)
https://hub.docker.com/u/amperecomputingai
Apache License 2.0
21 stars 7 forks source link

add stable diffusion from huggingface #254

Closed MarcelWilnicki closed 2 months ago

MarcelWilnicki commented 4 months ago

this is a draft pull request, ignore run1.py file.

example command to run on Ampere:

OPENBLAS_NUM_THREADS=10 AIO_IMPLICIT_FP16_TRANSFORM_FILTER=".*" AIO_NUM_THREADS=128 python run_hf.py -m stabilityai/stable-diffusion-xl-base-1.0 -b 1 --steps 25

example command to run on Intel Sapphire:

ENABLE_BF16_X86=1 AIO_NUM_THREADS=128 DNNL_MAX_CPU_ISA=AVX512_CORE_AMX python run_hf.py -m stabilityai/stable-diffusion-xl-base-1.0 -b 1 --steps 25