llama : refactor tensor offloading as callback

Browse Source

...

This commit is contained in:

Georgi Gerganov

2023-10-29 12:35:07 +02:00

parent da936188d8

commit 15267192c0

1 changed files with 704 additions and 726 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download Patch File Download Diff File Expand all files Collapse all files

llama.cpp

+704 -726

File diff suppressed because it is too large Load Diff