CUDA: Fixed OpenLLaMA 3b mmq, reduced compile time (#2590)

Browse source

...

This commit is contained in:

Johannes Gäßler 2023-08-13 00:24:45 +02:00 • committed by GitHub

parent b19edd54d5

commit f64d44a9b9

No known key found for this signature in database

GPG key ID: 4AEE18F83AFDEB23

2 changed files with 587 additions and 391 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

976

ggml-cuda.cu

View file

File diff suppressed because it is too large Load diff