Hugging Face's logo

amd-shark
/
sdxl-quant-int8

Transformers
Inference Endpoints
Model card Files Community
2
sdxl-quant-int8

Commit History

NVIDIA All sym, guidance scale 8
209043a
verified

GiusFra commited on

NVIDIA All sym, guidance scale 8
dc6d4e1
verified

GiusFra commited on

NVIDIA All sym, guidance scale 8
799135a
verified

GiusFra commited on

NVIDIA All sym, guidance scale 8
9888c6c
verified

GiusFra commited on

MI250 QKV fused and all layers sym, guidance scale 8
6c705ea
verified

GiusFra commited on

MI250 QKV fused and all layers sym, guidance scale 8
743d6f9
verified

GiusFra commited on

MI250 QKV fused and all linear layers sym, guidance scale 7.5, calib steps 12
abd5384
verified

GiusFra commited on

MI250 QKV fused and all linear layers sym, guidance scale 7.5, calib steps 12
660100c
verified

GiusFra commited on

MI250 QKV fused and all linear layers sym, guidance scale 7.5
48152a7
verified

GiusFra commited on

MI250 QKV fused and all linear layers sym, guidance scale 7.5
45f8cad
verified

GiusFra commited on

MI250 QKV fused and all linear layers sym, guidance scale 7.5, no conv_out
d30c97c
verified

GiusFra commited on

MI250 QKV fused and all linear layers sym, guidance scale 7.5, no conv_out
8ec75e6
verified

GiusFra commited on

MI250 QKV fused and all linear layers sym, guidance scale 7.5
ac0d882
verified

GiusFra commited on

MI250 QKV fused and all linear layers sym, guidance scale 7.5
0570b3e
verified

GiusFra commited on

MI250 QKV fused and all linear layers sym, guidance scale 7.5
cb00591
verified

GiusFra commited on

QKV fused and all linear layers sym, guidance scale 7.5
70da055
verified

GiusFra commited on

QKV fused and all linear layers sym, guidance scale 7.5
4128ea1
verified

GiusFra commited on

QKV fused and all linear layers sym
51fa88e
verified

GiusFra commited on

QKV fused and all linear layers sym
5d000b6
verified

GiusFra commited on

QKV fused and sym
f20a0bf
verified

GiusFra commited on

QKV fused and sym
881d80b
verified

GiusFra commited on

Full symmetric
ed4e81d
verified

GiusFra commited on

Full symmetric
1e690df
verified

GiusFra commited on

QKV fused and all linear layers sym
3cee2a6
verified

GiusFra commited on

QKV fused and all linear layers sym
cf48f0f
verified

GiusFra commited on

QKV fused and sym
6f44cfb
verified

GiusFra commited on

QKV fused and sym
b175bf6
verified

GiusFra commited on

Fused QKV quant_params.json with zp
7e99883
verified

GiusFra commited on

Added vae weights with FP16 fix.
2de7ba8

nickfraser commited on

Fused QKV safetensor with zp
0339659
verified

GiusFra commited on

Fused QKV safetensor
348012d
verified

GiusFra commited on

Fused QKV quant_params.json
a793c5a
verified

GiusFra commited on

Fix model loading
7f81513
verified

GiusFra commited on

Update quant params structure (#2)
6b62ce4
verified

nickfraser commited on

Reference inputs
17638f5
verified

GiusFra commited on

Updated quant_params
fb3aa3b
verified

GiusFra commited on

Updated params.safetensors
36c8b73
verified

GiusFra commited on

Output reference tensors
6e61570
verified

GiusFra commited on

Quantization script
ecec5b7
verified

GiusFra commited on

Remove potential overflow / saturation error.
161df88

nickfraser commited on

Added comments - highlight possible overflow situation
3f5851c

nickfraser commited on

Updated math model to target int8 x int8 kernels.
4024f9d

nickfraser commited on

Updated QOp model to fuse SmoothQuant scales with input quantization
dca9b6e

nickfraser commited on

Output reference tensors
8e3c05a
verified

GiusFra commited on

Add config.json from stable-diffusion-xl-base-1.0/unet
54be8be

Stella Laurenzo commited on

Upload params.safetensors with huggingface_hub
1dad0d1
verified

GiusFra commited on

add missing smoothquant factors
99e9d19
verified

GiusFra commited on

update quant_params with correct shapes
d6a388a
verified

GiusFra commited on

Fix: set `keepdim=True`
9ab1060

nickfraser commited on