text-generation-inference
c20025db
- Add fp8 kv cache for ROCm (#2856)
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
336 days ago
Add fp8 kv cache for ROCm (#2856) * add fp8 kv cache for rocm * improvements * update log statement * remove bookkeeping field
References
#2856 - Add fp8 kv cache for ROCm
Author
mht-sharma
Parents
de19e7e8
Loading