llama.cpp
8fb40637 - use CUDA_CHECK

Login via GitHub
Home
Pricing
FAQ
Install

Login via GitHub

Commit

98 days ago

use CUDA_CHECK

References

#25271 - ggml, server: add ggml_backend_dev_reset() for sleep mode

Author

ngxson

ngxson

Parents

FAQ Terms Privacy Refunds Impressum

Loading