mikhail/llama.cpp-mtp-turboquant
1
0
Fork 0
Code Issues Pull Requests Actions 29 Packages Projects Releases Wiki Activity

metal : add CONV_TRANSPOSE_2D (#16542)

Browse Source 
* initial: headers and metal-device.cpp updates

* adding conv_transpose_2d

* fix type

* fix type: int32->int64

* Update ggml/src/ggml-metal/ggml-metal.metal

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

* Update ggml/src/ggml-metal/ggml-metal.metal

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

* Update ggml/src/ggml-metal/ggml-metal.metal

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

* add checks for src[0] and src[1]; add type checks

* Update ggml-metal.metal

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

* add more tests, add optimization to threading

* add dynamic memory allocation in metal

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
Ilia Ilmer
2025-10-17 02:33:58 -04:00
committed by GitHub
parent 79967ec596
commit 9ad4f1931e
8 changed files with 198 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-metal/ggml-metal-device.cpp
+25
View File
@@ -1406,6 +1406,31 @@ ggml_metal_pipeline_t ggml_metal_library_get_pipeline_conv_transpose_1d(ggml_met
return res;
}
ggml_metal_pipeline_t ggml_metal_library_get_pipeline_conv_transpose_2d(ggml_metal_library_t lib, const ggml_tensor * op) {
assert(op->op == GGML_OP_CONV_TRANSPOSE_2D);
GGML_ASSERT(ggml_is_contiguous(op->src[0]));
GGML_ASSERT(ggml_is_contiguous(op->src[1]));
GGML_ASSERT(op->src[0]->type == GGML_TYPE_F16 || op->src[0]->type == GGML_TYPE_F32);
GGML_ASSERT(op->src[1]->type == GGML_TYPE_F32);
GGML_ASSERT(op->type == GGML_TYPE_F32);
char base[256];
char name[256];
snprintf(base, 256, "kernel_conv_transpose_2d_%s_%s", ggml_type_name(op->src[0]->type), ggml_type_name(op->src[1]->type));
snprintf(name, 256, "%s", base);
ggml_metal_pipeline_t res = ggml_metal_library_get_pipeline(lib, name);
if (res) {
return res;
}
res = ggml_metal_library_compile_pipeline(lib, base, name, nullptr);
return res;
}
ggml_metal_pipeline_t ggml_metal_library_get_pipeline_upscale(ggml_metal_library_t lib, const ggml_tensor * op) {
assert(op->op == GGML_OP_UPSCALE);