CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-27 08:21:30 +00:00
Code Issues Packages Projects Releases Wiki Activity

ggml : fix FA mask dim 2 and 3 (#14505)

Browse Source 
* ggml : fix FA mask dim 2 and 3

ggml-ci

* backends : unsupport batched FA in CUDA and Vulkan

ggml-ci

* vulkan : disable FA for mask->ne[2] != 1
This commit is contained in:
Georgi Gerganov
2025-07-03 10:46:57 +03:00
committed by GitHub
parent d4cdd9c1c3
commit 9067487c44
9 changed files with 26 additions and 15 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
ggml/include/ggml.h
View File

@@ -1983,15 +1983,16 @@ extern "C" {
#define GGML_KQ_MASK_PAD 64
// q: [n_embd_k, n_batch, n_head, ne3]
// k: [n_embd_k, n_kv, n_head_kv, ne3]
// v: [n_embd_v, n_kv, n_head_kv, ne3] !! not transposed !!
// mask: [n_kv, n_batch_pad, ne32, 1] !! n_batch_pad = GGML_PAD(n_batch, GGML_KQ_MASK_PAD) !!
// res: [n_embd_v, n_head, n_batch, ne3] !! permuted !!
// q: [n_embd_k, n_batch, n_head, ne3 ]
// k: [n_embd_k, n_kv, n_head_kv, ne3 ]
// v: [n_embd_v, n_kv, n_head_kv, ne3 ] !! not transposed !!
// mask: [n_kv, n_batch_pad, ne32, ne33] !! n_batch_pad = GGML_PAD(n_batch, GGML_KQ_MASK_PAD) !!
// res: [n_embd_v, n_head, n_batch, ne3 ] !! permuted !!
//
// broadcast:
// n_head % n_head_kv == 0
// ne3 % ne32 == 0
// n_head % ne32 == 0
// ne3 % ne33 == 0
//
GGML_API struct ggml_tensor * ggml_flash_attn_ext(
struct ggml_context * ctx,