accelerate
29350576
- Fix memory leak in fp8 causing OOM (and potentially 3x vRAM usage) (#2089)
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
2 years ago
Fix memory leak in fp8 causing OOM (and potentially 3x vRAM usage) (#2089) * Fix memory leak * Change when model is moved to cuda * Add from PR * Remove link * Undo original forward link
References
#2089 - Fix memory leak in fp8 causing OOM (and potentially 3x vRAM usage)
Author
muellerzr
Parents
bb6759d6
Loading