apiversion: modelslim_v1
metadata:
config_id: default-w8a8
score: 50
verified_model_types: [ ]
label:
w_bit: 8
a_bit: 8
is_sparse: False
kv_cache: False
spec:
process:
- type: "iter_smooth"
include:
- "*"
- type: "linear_quant"
qconfig:
act:
scope: "per_token"
dtype: "int8"
symmetric: True
method: "minmax"
weight:
scope: "per_channel"
dtype: "int8"
symmetric: True
method: "minmax"
include: [ "*" ]
runner: "model_wise"
save:
- type: "ascendv1_saver"
part_file_size: 4