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

metal : add count_equal op (#18314)

Browse Source 
* add count equal for metal

* remove trailing whitespace

* updated doc ops table

* changed shmem to i32

* added multi tg and templating

* removed BLAS support from Metal docs

* Apply suggestions from code review

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* add memset to set dst to 0

* metal : cleanup

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
gatbontonpc
2025-12-31 10:39:48 +02:00
committed by GitHub
co-authored by Georgi Gerganov
parent ecc343de63
commit 9a6369bb60
9 changed files with 585 additions and 324 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-metal/ggml-metal-device.m
+5
View File
@@ -1023,6 +1023,11 @@ bool ggml_metal_device_supports_op(ggml_metal_device_t dev, const struct ggml_te
return has_simdgroup_reduction && ggml_is_contiguous_rows(op->src[0]);
case GGML_OP_L2_NORM:
return has_simdgroup_reduction && (op->ne[0] % 4 == 0 && ggml_is_contiguous_1(op->src[0]));
case GGML_OP_COUNT_EQUAL:
return has_simdgroup_reduction &&
op->src[0]->type == GGML_TYPE_I32 &&
op->src[1]->type == GGML_TYPE_I32 &&
op->type == GGML_TYPE_I64;
case GGML_OP_ARGMAX:
return has_simdgroup_reduction;
case GGML_OP_NORM: