ggml : support bcast ggml_soft_max_ext, ggml_flash_attn_ext (#14435)

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

View File

@@ -2187,7 +2187,6 @@ static bool ggml_backend_cann_supports_op(ggml_backend_dev_t dev,
case GGML_OP_SQRT:
case GGML_OP_CLAMP:
case GGML_OP_DIAG_MASK_INF:
case GGML_OP_SOFT_MAX:
case GGML_OP_SUM_ROWS:
case GGML_OP_ARGSORT:
case GGML_OP_ACC:
@@ -2205,6 +2204,10 @@ static bool ggml_backend_cann_supports_op(ggml_backend_dev_t dev,
case GGML_OP_PAD_REFLECT_1D:
case GGML_OP_COUNT_EQUAL:
return true;
case GGML_OP_SOFT_MAX:
// 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_FLASH_ATTN_EXT:{
// derived from [ggml-cuda.cu]
if(op->src[1]->type != GGML_TYPE_F16 || op->src[2]->type != GGML_TYPE_F16){
@@ -2227,6 +2230,8 @@ static bool ggml_backend_cann_supports_op(ggml_backend_dev_t dev,
// DeepSeek MLA
return false;
}
// TODO: support broadcast
// ref: https://github.com/ggml-org/llama.cpp/pull/14435
if (op->src[0]->ne[3] != 1) {
return false;
}