diff options
| author | slaren <2141330+slaren@users.noreply.github.com> | 2023-04-20 20:49:53 +0200 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2023-04-20 20:49:53 +0200 |
| commit | 2005469ea130cf920c50175d4f47a87bfd8aaf4d (patch) | |
| tree | 73f089b971c19eb8e1f6f5e3c38fff175048729f /ggml-cuda.h | |
| parent | 8a1756abdf1f48cb4dcb898bc8fbe9102ef49dc6 (diff) | |
Add Q4_3 support to cuBLAS (#1086)
Diffstat (limited to 'ggml-cuda.h')
| -rw-r--r-- | ggml-cuda.h | 1 |
1 files changed, 1 insertions, 0 deletions
diff --git a/ggml-cuda.h b/ggml-cuda.h index 646caaf..be14060 100644 --- a/ggml-cuda.h +++ b/ggml-cuda.h @@ -5,6 +5,7 @@ extern "C" { void dequantize_row_q4_0_cuda(const void * vx, float * y, int k, cudaStream_t stream); void dequantize_row_q4_1_cuda(const void * vx, float * y, int k, cudaStream_t stream); void dequantize_row_q4_2_cuda(const void * vx, float * y, int k, cudaStream_t stream); +void dequantize_row_q4_3_cuda(const void * vx, float * y, int k, cudaStream_t stream); #ifdef __cplusplus } |