mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-11-15 11:17:31 +00:00
[SYCL] refactor soft_max, add soft_max_back (#16472)
* refactor to support soft_max_ext * fix error and support soft_max_back * rm unused functions * fix format issue --------- Co-authored-by: Zhang Jianyu <zhang.jianyu@outlook.com>
This commit is contained in:
@@ -15,6 +15,10 @@
|
||||
|
||||
#include "common.hpp"
|
||||
|
||||
#define SYCL_SOFT_MAX_BLOCK_SIZE 1024
|
||||
|
||||
void ggml_sycl_op_soft_max(ggml_backend_sycl_context &ctx, ggml_tensor *dst);
|
||||
|
||||
void ggml_sycl_op_soft_max_back(ggml_backend_sycl_context & ctx, ggml_tensor * dst);
|
||||
|
||||
#endif // GGML_SYCL_SOFTMAX_HPP
|
||||
|
||||
Reference in New Issue
Block a user