tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-18 05:56:00 -04:00
Code Issues Packages Projects Releases Wiki Activity

ggml : support bcast ggml_soft_max_ext, ggml_flash_attn_ext (#14435)

Browse Source 
ggml-ci
This commit is contained in:
Georgi Gerganov
2025-06-27 21:50:57 +03:00
parent 307e79d33d
commit ec68e84c32
11 changed files with 250 additions and 156 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
ggml/src/ggml-sycl/ggml-sycl.cpp
View File

@@ -4395,9 +4395,15 @@ static bool ggml_backend_sycl_device_supports_op(ggml_backend_dev_t dev, const g
return true;
case GGML_OP_CONT:
return op->src[0]->type != GGML_TYPE_BF16;
case GGML_OP_DIAG_MASK_INF:
case GGML_OP_SOFT_MAX:
return true;
// TODO: support batching
if (op->src[0]->ne[3] != 1) {
return false;
}
// TODO: support broadcast
// ref: https://github.com/ggml-org/llama.cpp/pull/14435
return !op->src[1] || (op->src[1]->ne[2] == 1 && op->src[1]->ne[3] == 1);
case GGML_OP_DIAG_MASK_INF:
case GGML_OP_ROPE:
case GGML_OP_IM2COL:
return true;