Lumpiasty/llama.cpp
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

ggml : add support for CPU f16->f16 GGML_OP_SET_ROWS (#25344)

Browse Source 
* ggml : add support for CPU f16->f16 GGML_OP_SET_ROWS

* ggml : add missing type checks in f16 GGML_OP_SET_ROWS

* ggml : merge ggml_compute_forward_set_rows_f32() and ggml_compute_forward_set_rows_f16() into ggml_compute_forward_set_rows_impl()

* chore : replace assert() with GGML_ASSERT()

---------

Co-authored-by: Stanisław Szymczyk <sszymczy@gmail.com>
This commit is contained in:
fairydreaming
2026-07-08 11:46:28 +08:00
committed by GitHub
co-authored by Stanisław Szymczyk
parent 931ca30bef
commit 68a521b591
3 changed files with 59 additions and 28 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml.c
+1 -1
View File
@@ -3926,7 +3926,7 @@ struct ggml_tensor * ggml_set_rows(
GGML_ASSERT(b->ne[2] % c->ne[1] == 0);
GGML_ASSERT(b->ne[3] % c->ne[2] == 0);
GGML_ASSERT(c->ne[3] == 1);
GGML_ASSERT(b->type == GGML_TYPE_F32);
GGML_ASSERT(b->type == GGML_TYPE_F32 || b->type == GGML_TYPE_F16);
GGML_ASSERT(c->type == GGML_TYPE_I64 || c->type == GGML_TYPE_I32);
GGML_ASSERT(ggml_is_contiguous_rows(a));