CUDA: optimize FA for GQA + large batches (#12014)

Browse Source

...

This commit is contained in:

Johannes Gäßler

2025-02-22 12:20:17 +01:00

committed by GitHub

parent 335eb04a91

commit 5fa07c2f93

32 changed files with 940 additions and 411 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

810

ggml/src/ggml-cuda/fattn-mma-f16.cuh

File diff suppressed because it is too large Load Diff