auto-round
8416f9f3
- test(ark): switch MoE prefill baseline to single torch.bmm
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
11 days ago
test(ark): switch MoE prefill baseline to single torch.bmm
References
#1813 - Add moe prefill/ decode with int2/int4/int8 sym /asym and fp8 e4m3 e5m2
Author
Copilot
Parents
045b26b3
Loading