sleepy/llama.cpp
1
0
Fork 0
Code Issues 11 Pull Requests Actions 114 Packages Projects Releases Wiki Activity

CANN: add BF16 support for core operators (#20152)

Browse Source 
* CANN: add BF16 support for core operators

Add BF16 (bfloat16) type support to the CANN backend for the following
operators: MUL_MAT, MUL_MAT_ID, GET_ROWS, SET_ROWS, CPY, CONT, and
OUT_PROD. This enables BF16 models to run on Ascend NPUs.

* CANN: skip NZ weight format for BF16 and add 310P compile guards

NZ weight format conversion does not support BF16 tensors, skip it
in set_tensor, get_alloc_size and mul_mat. Remove BF16 from MUL_MAT_ID
and OUT_PROD as there are no BF16 use cases. Add #ifndef ASCEND_310P
guards for all BF16 operator support since 310P does not support BF16.
This commit is contained in:
hipudding
2026-03-20 17:08:39 +08:00
committed by GitHub
parent 6d99b44c7e
commit 1af9dab32b
2 changed files with 34 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-cann/aclnn_ops.cpp
+9 -3
View File
@@ -1788,9 +1788,11 @@ void ggml_cann_get_rows(ggml_backend_cann_context & ctx, ggml_tensor * dst) {
ggml_tensor * src0 = dst->src[0]; // src
ggml_tensor * src1 = dst->src[1]; // index
GGML_ASSERT(dst->type == GGML_TYPE_F32 || dst->type == GGML_TYPE_F16);
GGML_ASSERT(dst->type == GGML_TYPE_F32 || dst->type == GGML_TYPE_F16
|| dst->type == GGML_TYPE_BF16);
switch (src0->type) {
case GGML_TYPE_BF16:
case GGML_TYPE_F16:
case GGML_TYPE_F32:
if (src0->type == dst->type) {
@@ -1881,6 +1883,7 @@ void ggml_cann_set_rows(ggml_backend_cann_context & ctx, ggml_tensor * dst) {
break;
}
case GGML_TYPE_F16:
case GGML_TYPE_BF16:
{
acl_tensor_ptr acl_src0 = ggml_cann_create_tensor(src0);
ggml_cann_pool_alloc src_buffer_allocator(ctx.pool(), ggml_nelements(src0) * sizeof(uint16_t));
@@ -1891,7 +1894,7 @@ void ggml_cann_set_rows(ggml_backend_cann_context & ctx, ggml_tensor * dst) {
src_trans_nb[i] = src_trans_nb[i - 1] * src0->ne[i - 1];
}
acl_tensor_ptr src_trans_tensor = ggml_cann_create_tensor(
src_trans_buffer, ACL_FLOAT16, ggml_type_size(dst->type), src0->ne, src_trans_nb, GGML_MAX_DIMS);
src_trans_buffer, ggml_cann_type_mapping(dst->type), ggml_type_size(dst->type), src0->ne, src_trans_nb, GGML_MAX_DIMS);
aclnn_cast(ctx, acl_src0.get(), src_trans_tensor.get(), ggml_cann_type_mapping(dst->type));
aclnn_index_copy_4d(ctx, src_trans_buffer, src0->ne, src_trans_nb, dst->data, dst->ne, dst->nb, src1,
dst->type);
@@ -1965,7 +1968,7 @@ static void ggml_cann_mat_mul_fp(ggml_backend_cann_context & ctx, ggml_tensor *
// Only check env once.
static bool weight_to_nz = parse_bool(get_env_as_lowercase("GGML_CANN_WEIGHT_NZ").value_or("on"));
if (weight_to_nz && is_matmul_weight(weight)) {
if (weight_to_nz && weight->type != GGML_TYPE_BF16 && is_matmul_weight(weight)) {
acl_weight_tensor = ggml_cann_create_tensor(weight, transpose_ne, transpose_nb, n_dims, ACL_FORMAT_FRACTAL_NZ);
} else {
acl_weight_tensor = ggml_cann_create_tensor(weight, transpose_ne, transpose_nb, n_dims, ACL_FORMAT_ND);
@@ -2146,6 +2149,9 @@ void ggml_cann_mul_mat(ggml_backend_cann_context & ctx, ggml_tensor * dst) {
switch (type) {
case GGML_TYPE_F32:
case GGML_TYPE_F16:
#ifndef ASCEND_310P
case GGML_TYPE_BF16:
#endif
ggml_cann_mat_mul_fp(ctx, dst);
break;
case GGML_TYPE_Q4_0: