llama.cpp
b7ddc8bf
- cuda : fix out-of-bounds-access in `mul_mat_vec_q`
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
1 year ago
cuda : fix out-of-bounds-access in `mul_mat_vec_q` ggml-ci
References
#4990 - ggml : add IQ2 to test-backend-ops + refactoring
Author
ggerganov
Parents
36feaeb4
Loading