cuda : support non-contiguous i32 to i32 copy (#17326)

* support non-contiguous i32 to i32 copy * add tests * rename cpy_flt to cpy_scalar and reindent params
2025-11-23 11:13:34 +01:00
parent bc809e9c53
commit 96ac5a2329
4 changed files with 92 additions and 49 deletions
@@ -212,6 +212,6 @@ static __device__ void cpy_blck_f32_iq4_nl(const char * cxi, char * cdsti) {
 }

 template<typename src_t, typename dst_t>
-static __device__ void cpy_1_flt(const char * cxi, char * cdsti) {
+static __device__ void cpy_1_scalar(const char * cxi, char * cdsti) {
    *(dst_t *) cdsti = ggml_cuda_cast<dst_t>(*(const src_t *) cxi);
 }