]> git.djapps.eu Git - pkg/ggml/sources/ggml/commit
metal : use FA-vec kernel up to batch size 20 (llama/13496)
authorGeorgi Gerganov <redacted>
Tue, 13 May 2025 15:04:39 +0000 (18:04 +0300)
committerGeorgi Gerganov <redacted>
Mon, 19 May 2025 10:37:56 +0000 (13:37 +0300)
commit5a025a3dc05d0f354473c561b4b43d243d1fca8d
tree6d00a133958f61d2f951db77b5296a1ea68c408e
parent2a28871c2af1be030cfd6353b7cf364e5b5fdd70
metal : use FA-vec kernel up to batch size 20 (llama/13496)

* batched-bench : fix pp batch contents

* metal : optimize multi-sequence FA vec kernel

ggml-ci

* metal : use FA-vec kernel up to batch size 20

ggml-ci
src/ggml-metal/ggml-metal.m