ver4a/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

change the reorder tensor from init to execute OP (#13003)

Browse source
This commit is contained in:
Neo Zhang Jianyu 2025-04-25 17:37:51 +08:00 • committed by GitHub
parent 553a5c3a9f
commit 514c45608f
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 61 additions and 65 deletions
Download patch file Download diff file Expand all files Collapse all files

1
ggml/src/ggml-sycl/common.hpp
View file

@ -313,7 +313,6 @@ struct ggml_backend_sycl_context {
int device;
std::string name;
optimize_feature opt_feature;
bool optimized_graph=false;
queue_ptr qptrs[GGML_SYCL_MAX_DEVICES][GGML_SYCL_MAX_STREAMS] = { { nullptr } };