public_git
/
whisper.cpp
mirror of https://github.com/ggml-org/whisper.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Fix too relaxed check on CUDA "fast copy" (can_be_transposed) condition (llama/17332) 

* Fix too relaxed check on CUDA "fast copy" (can_be_transposed) condition

* Argh.

* Making CISC happy ;)

* Integrate CONT tests

* Use loopy loop

* Skip new tests for (B)F16 for now.
This commit is contained in:
Piotr Wilkin (ilintar) 2025-11-19 10:36:33 +01:00 committed by Georgi Gerganov
parent 2097a9c1bd
commit 746cbed20a
No known key found for this signature in database
GPG Key ID: 449E073F9DC10735
1 changed files with 2 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
ggml/src/ggml-cuda/cpy.cu
View File

@ -384,7 +384,8 @@ void ggml_cuda_cpy(ggml_backend_cuda_context & ctx, const ggml_tensor * src0, gg
char * src1_ddc = (char *) src1->data;
const bool contiguous_srcs = ggml_is_contiguous(src0) && ggml_is_contiguous(src1);
const bool can_be_transposed = nb01 == (int64_t)ggml_element_size(src0) && src0->ne[3] == 1;
const bool can_be_transposed = nb01 == (int64_t)ggml_element_size(src0) &&
src0->ne[3] == 1 && nb02 == ne00 * ne01 * (int64_t)ggml_element_size(src0);
if (src0->type == src1->type && contiguous_srcs) {
GGML_ASSERT(ggml_nbytes(src0) == ggml_nbytes(src1));