llama.cpp
2759ccdb
- CUDA: avoid mul + bias fusion when doing fusion (#16935)
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
40 days ago
CUDA: avoid mul + bias fusion when doing fusion (#16935)
References
#16935 - CUDA: avoid mul + bias fusion when buffers are split
Author
am17an
Parents
c5023daf
Loading