CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-28 08:31:25 +00:00
Code Issues Packages Projects Releases Wiki Activity

[SYCL] Fix windows build and inference (#8003)

Browse Source 
* add sycl preset

* fix debug link error. fix windows crash

* update README
This commit is contained in:
luoyu-intel
2024-06-20 13:19:05 +00:00
committed by GitHub
parent d50f8897a7
commit de391e4c80
7 changed files with 230 additions and 244 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
ggml-sycl.cpp
View File

@@ -4911,7 +4911,7 @@ static void ggml_sycl_cpy(ggml_backend_sycl_context & ctx, const ggml_tensor *sr
GGML_ASSERT(ggml_nbytes(src0) <= INT_MAX);
GGML_ASSERT(ggml_nbytes(src1) <= INT_MAX);
GGML_TENSOR_BINARY_OP_LOCALS;
GGML_TENSOR_BINARY_OP_LOCALS01;
SYCL_CHECK(ggml_sycl_set_device(ctx.device));
queue_ptr main_stream = ctx.stream();