onnxruntime
523d70f6
- Improve Transformer Benchmark for FP16 (#3970)
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
5 years ago
Improve Transformer Benchmark for FP16 (#3970) Disable ORT in offline optimization script (ORT could generate some fused ops (like FusedGemm) which cannot be converted to fp16). Remove some models from benchmark until we have optimizations for them.
References
#3970 - Fix Transformer Benchmark for FP16
Author
tianleiwu
Parents
0d11649b
Loading