public_git/whisper.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/whisper.cpp.git synced 2026-10-09 15:55:37 +02:00
Code Issues Packages Projects Releases Wiki Activity

vulkan: support all backend tests for SQR/SQRT/SIN/COS/CLAMP/LEAKY_RELU/NORM (llama/24582)

Browse Source 
* vulkan: make SQR/SQRT/SIN/COS/CLAMP/LEAKY_RELU use unary.comp

* vulkan: make NORM support noncontig

* add noncontiguous row test cases for norm/l2_norm, handle this in the CPU backend and l2_norm.comp

* fix supports_op for cuda and webgpu
This commit is contained in:
Jeff Bolz
2026-06-26 16:03:57 +03:00
committed by Georgi Gerganov
parent 1fdbfb19eb
commit 3fc2c57a63
14 changed files with 145 additions and 193 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-webgpu/ggml-webgpu.cpp
+1 -1
View File
@@ -4270,7 +4270,7 @@ static bool ggml_backend_webgpu_device_supports_op(ggml_backend_dev_t dev, const
case GGML_OP_RMS_NORM:
case GGML_OP_NORM:
case GGML_OP_L2_NORM:
supports_op = op->type == GGML_TYPE_F32 && src0->type == GGML_TYPE_F32;
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;