onnxruntime
d57a7c3e
- Disable quantized Mlas, still not giving good tps
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
115 days ago
Disable quantized Mlas, still not giving good tps
References
asonawane/update
#26091 - Update QMoE kernel with optimizations
Author
apsonawane
Parents
8289fcb1
Loading