text-generation-inference
1dd34666
- Clarify FP8-Marlin use on capability 8.9 (#2940)
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
329 days ago
Clarify FP8-Marlin use on capability 8.9 (#2940) The log message stated that the GPU does not support FP8 on capability 8.9. However we use FP8-Marlin on that capability because it is faster.
References
#2940 - Clarify FP8-Marlin use on capability 8.9
Author
danieldk
Parents
1d3c9beb
Loading