We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
1 parent 9f584d3 commit 32e6898Copy full SHA for 32e6898
1 file changed
ggml/src/ggml-cuda/common.cuh
@@ -110,8 +110,6 @@
110
# define GGML_CUDA_USE_CUB
111
#endif // !defined(GGML_USE_HIP) && !defined(GGML_USE_MUSA) && CUDART_VERSION >= 11070
112
113
-size_t ggml_cuda_flash_attn_ext_get_alloc_size(int device, const ggml_tensor * dst);
114
-
115
// PDL host-side support (cudaLaunchKernelEx) requires CUDART >= 11.8.
116
// However, this has been bugged in CTK < 12.3 for MSVC builds, see
117
// https://github.com/ggml-org/llama.cpp/pull/22522#discussion_r3302393293
0 commit comments