EngineX-Ascend/enginex-ascend-910-llama.cpp
10
0
Fork 0
Code Issues Pull Requests Actions 4 Projects Releases Wiki Activity

metal : add support for non-padded FA KV (#16148)

Browse Source 
* metal : pad K, V and Mask when needed

* cont : simplify

* cuda : add TODO about KV padding requirement

* metal : add comments

* metal : remove mask padding requirement
This commit is contained in:
Georgi Gerganov
2025-10-07 08:23:30 +03:00
committed by GitHub
parent 1d6092fc72
commit 0a319bb75e
9 changed files with 460 additions and 72 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
ggml/src/ggml-metal/ggml-metal-ops.h
View File

@@ -39,6 +39,7 @@ size_t ggml_metal_op_mul_mat_id_extra_ids(const struct ggml_tensor * op);
// return true if we should use the FA vector kernel for this op
bool ggml_metal_op_flash_attn_ext_use_vec(const struct ggml_tensor * op);
size_t ggml_metal_op_flash_attn_ext_extra_pad(const struct ggml_tensor * op);
size_t ggml_metal_op_flash_attn_ext_extra_tmp(const struct ggml_tensor * op);
int ggml_metal_op_concat (ggml_metal_op_t ctx, int idx);