whisper.cpp
c4268297
- CUDA: fix crash with partial offloading of MoE (llama/13439)
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
284 days ago
CUDA: fix crash with partial offloading of MoE (llama/13439)
References
#3148 - sync : ggml
Author
JohannesGaessler
Committer
ggerganov
Parents
0b1962a1
Loading