ggml
c32c9dcc
- cuda : implement bf16 cpy ops and enable bf16 cont (llama/14763)
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
1 year ago
cuda : implement bf16 cpy ops and enable bf16 cont (llama/14763) * implement bf16 cpy ops and enable bf16 cont * deduplicate copy functions * deduplicate checks
References
#1311 - sync : llama.cpp
Author
CISC
Committer
ggerganov
Parents
f08563f7
Loading