mikhail/llama.cpp-mtp-turboquant
1
0
Fork 0
Code Issues Pull Requests Actions 28 Packages Projects Releases Wiki Activity

metal : add cumsum (#17305)

Browse Source
This commit is contained in:
Georgi Gerganov
2025-11-17 11:51:13 +02:00
committed by GitHub
parent 2376b7758c
commit 1a139644a8
9 changed files with 406 additions and 79 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-metal/ggml-metal-device.cpp
+38
View File
@@ -318,6 +318,44 @@ ggml_metal_pipeline_t ggml_metal_library_get_pipeline_sum_rows(ggml_metal_librar
return res;
}
ggml_metal_pipeline_t ggml_metal_library_get_pipeline_cumsum_blk(ggml_metal_library_t lib, const ggml_tensor * op) {
GGML_ASSERT(op->op == GGML_OP_CUMSUM);
char base[256];
char name[256];
snprintf(base, 256, "kernel_cumsum_blk_%s", ggml_type_name(op->src[0]->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_cumsum_add(ggml_metal_library_t lib, const ggml_tensor * op) {
GGML_ASSERT(op->op == GGML_OP_CUMSUM);
char base[256];
char name[256];
snprintf(base, 256, "kernel_cumsum_add_%s", ggml_type_name(op->src[0]->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_soft_max(ggml_metal_library_t lib, const ggml_tensor * op) {
GGML_ASSERT(!op->src[1] || op->src[1]->type == GGML_TYPE_F16 || op->src[1]->type == GGML_TYPE_F32);