clip : use FA (#16837)

* clip : use FA

* cont : add warning about unsupported ops

* implement "auto" mode for clip flash attn

* clip : print more detailed op support info during warmup

* cont : remove obsolete comment [no ci]

* improve debugging message

* trailing space

* metal : remove stray return

---------

Co-authored-by: Xuan Son Nguyen <son@huggingface.co>
This commit is contained in:
Georgi Gerganov
2025-11-02 21:21:48 +01:00
committed by GitHub
co-authored by Xuan Son Nguyen
parent cd5e3b5754
commit 2f966b8ed8
9 changed files with 194 additions and 43 deletions
+1
View File
@@ -707,6 +707,7 @@ bool ggml_metal_device_supports_op(ggml_metal_device_t dev, const struct ggml_te
if (op->src[0]->ne[0] != 32 &&
op->src[0]->ne[0] != 40 &&
op->src[0]->ne[0] != 64 &&
op->src[0]->ne[0] != 72 &&
op->src[0]->ne[0] != 80 &&
op->src[0]->ne[0] != 96 &&
op->src[0]->ne[0] != 112 &&