CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-11 10:36:54 +00:00
Code Issues Packages Projects Releases Wiki Activity

SYCL: Refactor and enable FP16 in binary broadcast OPs (#12975)

Browse Source 
* SYCL: refactor move to a separate file

* Fix binbcast

* Remove duplicates

* fix include formatting

* fix typo
This commit is contained in:
Akarshan Biswas
2025-04-18 19:27:56 +05:30
committed by GitHub
parent b9154ecff9
commit 8d66005763
7 changed files with 393 additions and 372 deletions
Download Patch File Download Diff File Expand all files Collapse all files

39
ggml/src/ggml-sycl/binbcast.hpp Normal file
View File

@@ -0,0 +1,39 @@
#ifndef GGML_SYCL_BINBCAST_HPP
#define GGML_SYCL_BINBCAST_HPP
#include "common.hpp"
static __dpct_inline__ float op_repeat(const float a, const float b) {
return b;
GGML_UNUSED(a);
}
static __dpct_inline__ float op_add(const float a, const float b) {
return a + b;
}
static __dpct_inline__ float op_sub(const float a, const float b) {
return a - b;
}
static __dpct_inline__ float op_mul(const float a, const float b) {
return a * b;
}
static __dpct_inline__ float op_div(const float a, const float b) {
return a / b;
}
void ggml_sycl_add(ggml_backend_sycl_context & ctx, ggml_tensor * dst);
void ggml_sycl_sub(ggml_backend_sycl_context & ctx, ggml_tensor * dst);
void ggml_sycl_mul(ggml_backend_sycl_context & ctx, ggml_tensor * dst);
void ggml_sycl_div(ggml_backend_sycl_context & ctx, ggml_tensor * dst);
void ggml_sycl_repeat(ggml_backend_sycl_context & ctx, ggml_tensor * dst);
#endif //GGML_SYCL_BINBCAST_HPP