Quantization of Argmax #10213
int8/uint8 support on CPU for Argmax
54d30e77
Add Kernel Def Hashes for int8/uint8 Argmax
7197e183
Update OperatorKernels.md by gen_opkernel_doc.py
70fbb66c
Exclude ArgMax_int8 for TensorRT
d7713cdc
Quantization tool suuport for Argmax
8bd37fab
yihonglyu
changed the title int8/uint8 support on CPU for Argmax Quantization suuport for Argmax 3 years ago
yihonglyu
changed the title Quantization suuport for Argmax Quantization of Argmax 3 years ago
yufenglee
dismissed these changes
on 2022-01-12
edgchen1
dismissed these changes
on 2022-01-12
Fix line length
98ac4534
yihonglyu
dismissed their stale review
via 98ac4534
3 years ago
yihonglyu
dismissed their stale review
via 98ac4534
3 years ago
edgchen1
approved these changes
on 2022-01-12
yihonglyu
merged
499f1d5f
into master 3 years ago
yihonglyu
deleted the yilyu/xint8_argmax branch 3 years ago
Assignees
No one assigned
Login to write a write a comment.
Login via GitHub