CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-27 08:21:30 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix memcpy() crash, add missed cmd in guide, fix softmax (#6622)

Browse Source 
* disable mmap to fix memcpy crash, add missed cmd in guide, fix softmax

* refactor to disable mmap for SYCL backend

* fix compile error in other os

* refactor the solution, use host buf to fix it, instead of disable mmap

* keep to support mmap()

* use host buff to reduce malloc times

* revert to malloc/free solution, for threaad safe
This commit is contained in:
Neo Zhang Jianyu
2024-04-14 10:42:29 +08:00
committed by GitHub
parent b5e7285baf
commit de17e3f745
4 changed files with 32 additions and 48 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
examples/sycl/build.sh
View File

@@ -20,4 +20,4 @@ cmake .. -DLLAMA_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx
#cmake --build . --config Release --target llama-bench
#build all binary
cmake --build . --config Release -v
cmake --build . --config Release -j -v