llama.cpp
600a3664
- Corrected: changed s13 = src1->nb[3] instead of nb[2] (#18724)
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
14 days ago
Corrected: changed s13 = src1->nb[3] instead of nb[2] (#18724)
References
#18724 - Corrected: In ggml_cuda_mul_mat_q(), s13 is declared incorrectly to nb[2] instead of nb[3]
Author
michaelw9999
Parents
ea23c159
Loading