millaguie/llama.cpp
1
0 Fork 0
Code Issues Pull Requests Actions 29 Packages Projects Releases Wiki Activity

sycl : support to malloc memory on device more than 4GB, update the doc and script (#17566)

Browse Source 
Co-authored-by: Neo Zhang Jianyu <jianyu.zhang@intel.com>
This commit is contained in:
Neo ZhangandNeo Zhang Jianyu authored and GitHub committed 2025-11-29 14:59:44 +02:00
1 parent f698a79c63
commit 7d2add51d8
7 files changed
+33 -9
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

ggml/src/ggml-sycl/cpy.cpp
-3
View File
@@ -515,9 +515,6 @@ void ggml_sycl_cpy(ggml_backend_sycl_context & ctx, const ggml_tensor * src0, co
const int64_t ne = ggml_nelements(src0);
GGML_ASSERT(ne == ggml_nelements(src1));
GGML_ASSERT(ggml_nbytes(src0) <= INT_MAX);
GGML_ASSERT(ggml_nbytes(src1) <= INT_MAX);
GGML_TENSOR_BINARY_OP_LOCALS01;
SYCL_CHECK(ggml_sycl_set_device(ctx.device));