neural-compressor icon indicating copy to clipboard operation
neural-compressor copied to clipboard

smooth quant pattern is incomplete at folding=True

Open wenhuach21 opened this issue 1 year ago • 0 comments

for llama, 2 patterns have not been detected, mlp.down_proj->mlp.up_proj, .self_attn.o_proj->module.self_attn.v_proj

for opt, self_attn.out_proj->self_attn.v_proj

wenhuach21 avatar Jul 18 '23 08:07 wenhuach21