SYCL: Add all missing unary kernels (llama/13074)

* SYCL: Add all missing unary kernels

ggml-ci

* decouple kernel launch range from data size using strided loop

* use ciel_div helper for num_blocks
ggml-ci

* clean auto imported header files
This commit is contained in:
Akarshan Biswas
2025-04-28 15:03:25 +05:30
committed by Georgi Gerganov
parent 7017c1d37d
commit 1a76e97c28
4 changed files with 191 additions and 0 deletions

View File

@ -493,5 +493,9 @@ static __dpct_inline__ Tp* get_pointer(sycl::local_accessor<Tp, dim> acc) {
int64_t downsample_sycl_global_range(int64_t accumulate_block_num, int64_t block_size);
constexpr size_t ceil_div(const size_t m, const size_t n) {
return (m + n - 1) / n;
}
bool gpu_has_xmx(sycl::device &dev);
#endif // GGML_SYCL_COMMON_HPP