Enabled gemm-precision in wasm test page

- This increases the inference speed while providing
   models as bytes to the translation engine
   (it wasn't needed while providing models as files)
This commit is contained in:
Abhishek Aggarwal 2021-04-29 16:52:05 +02:00 committed by abhi-agg
parent d82e01eda4
commit f3a257d40b

View File

@ -127,6 +127,7 @@ skip-cost: true
cpu-threads: 0
quiet: true
quiet-translation: true
gemm-precision: int8shift
`;
// TODO: Use in model config when wormhole is enabled: