happyz
/
llama.cpp
mirror of https://github.com/ggerganov/llama.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

cont : fix

This commit is contained in:
Georgi Gerganov 2026-03-10 12:36:56 +02:00
parent 46c693dcb9
commit c6b76caf94
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
ggml/src/ggml-cuda/ggml-cuda.cu
View File

@ -4999,7 +4999,7 @@ static bool ggml_backend_cuda_device_supports_op(ggml_backend_dev_t dev, const g
#ifdef GGML_USE_MUSA
return false;
#else
// KDA is faster using the AR kernel even when n_tokens >= 512.
// KDA is faster using the AR kernel even when n_tokens >= 512
//TODO: Add chunked kernel
return op->src[0]->ne[2] == 1 || op->src[3]->ne[0] == op->src[2]->ne[0];
#endif // GGML_USE_MUSA