onnxruntime
6f86c4db
- Quantize LSTM (#5595)
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
5 years ago
Quantize LSTM (#5595) Quantize LSTM: 1. dynamically quantizes MatMul inside the LSTM. It doesn't quantize activation function. 2. support per-channel on the input weight and recurrent weight.
References
#5595 - Quantize LSTM
Author
yufenglee
Parents
c2a993e7
Loading