auto-round
7094c76e
- test(ark): stabilize MoE prefill perf benchmark; remove misleading 100x speedups
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
35 days ago
test(ark): stabilize MoE prefill perf benchmark; remove misleading 100x speedups
References
#1813 - Add moe prefill/ decode with int2/int4/int8 sym /asym and fp8 e4m3 e5m2
Author
Copilot
Parents
70ab28ea
Loading