Files
llama.cpp/ggml
Alexander HeislerandOliver Simons d9b6be07d0 ggml-cuda: provide static workspace for cuBLAS handles (#26574)
* provide static workspace for cuBLAS handles

* account for concurrent streams when using GGML_CUDA_GRAPH_OPT

* drop cublas_handle overloads and remove direct cublasSetStream calls

* Update ggml/src/ggml-cuda/common.cuh

---------

Co-authored-by: Oliver Simons <osimons@nvidia.com>
2026-08-20 10:27:51 +03:00
..
2024-07-13 18:12:39 +02:00