mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-08-18 05:56:00 -04:00
[SYCL] refactor (#6408)
* seperate lower precision GEMM from the main files * fix workgroup size hardcode
This commit is contained in:
@@ -14,5 +14,10 @@
|
||||
#define GGML_SYCL_BACKEND_HPP
|
||||
|
||||
#include "common.hpp"
|
||||
#include "convert.hpp"
|
||||
#include "dequantize.hpp"
|
||||
#include "dmmv.hpp"
|
||||
#include "mmq.hpp"
|
||||
#include "mmvq.hpp"
|
||||
|
||||
#endif // GGML_SYCL_BACKEND_HPP
|
||||
|
Reference in New Issue
Block a user