public_git/whisper.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/whisper.cpp.git synced 2026-10-17 11:45:38 +02:00
Code Issues Packages Projects Releases Wiki Activity

ggml: add ggml_rope_set_offset (+ metal support) (llama/27120)

Browse Source 
* add params

* cpu kernel

* metal kernel

* add test backend ops

* gate other backends

* ggml: (cuda) support ggml_rope_set_offset (llama/27121)

* rm cuda supports_op guard, fix webgpu clang-format

* ggml: support ggml_rope_set_offset on vulkan (llama/27344)

* ggml: support ggml_rope_set_offset on vulkan

* remove inplace optimization
This commit is contained in:
Xuan-Son Nguyen
2026-08-21 19:23:26 +03:00
committed by Georgi Gerganov
parent d830bd220c
commit 8442c74f56
18 changed files with 244 additions and 110 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-webgpu/ggml-webgpu.cpp
+3 -1
View File
@@ -4472,7 +4472,9 @@ static bool ggml_backend_webgpu_device_supports_op(ggml_backend_dev_t dev, const
supports_op = (op->type == GGML_TYPE_F32 && src0->type == GGML_TYPE_F32) && ggml_is_contiguous_rows(src0);
break;
case GGML_OP_ROPE:
supports_op = op->type == GGML_TYPE_F32 || op->type == GGML_TYPE_F16;
// FIXME: support ggml_rope_set_offset
supports_op =
(op->type == GGML_TYPE_F32 || op->type == GGML_TYPE_F16) && ((const int32_t *) op->op_params)[15] == 0;
break;
case GGML_OP_GLU:
switch (ggml_get_glu_op(op)) {