llama.cpp
32dd62ee
- llama-mmap : avoid a second full-size copy of each tensor with direct-io (#29749)
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
50 days ago
llama-mmap : avoid a second full-size copy of each tensor with direct-io (#29749) Assisted-by: Claude Co-authored-by: Pranesh Gonegandla <pgonegandla@nvidia.com>
References
#29749 - Avoid a second full-size copy of each tensor with direct-io
Author
praneshgo
Parents
f11d642a
Loading