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

ci : add env variable in ggml-ci and document the same in SYCL.md (#12736)

Browse Source
This commit is contained in:
Atharva Dubey
2025-04-03 13:12:39 +01:00
committed by GitHub
parent 5f696e88e0
commit 2004644b7a
2 changed files with 9 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
ci/run.sh
View File

@@ -59,6 +59,8 @@ if [ ! -z ${GG_BUILD_SYCL} ]; then
export ONEAPI_DEVICE_SELECTOR="level_zero:0"
# Enable sysman for correct memory reporting
export ZES_ENABLE_SYSMAN=1
# to circumvent precision issues on CPY operations
export SYCL_PROGRAM_COMPILE_OPTIONS="-cl-fp32-correctly-rounded-divide-sqrt"
CMAKE_EXTRA="${CMAKE_EXTRA} -DGGML_SYCL=1 -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx -DGGML_SYCL_F16=ON"
fi

7
docs/backend/SYCL.md
View File

@@ -302,6 +302,10 @@ cmake -B build -DGGML_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx -
cmake --build build --config Release -j -v
```
It is possible to come across some precision issues when running tests that stem from using faster
instructions, which can be circumvented by setting the environment variable `SYCL_PROGRAM_COMPILE_OPTIONS`
as `-cl-fp32-correctly-rounded-divide-sqrt`
#### Nvidia GPU
The SYCL backend depends on [oneMath](https://github.com/uxlfoundation/oneMath) for Nvidia and AMD devices.
@@ -322,6 +326,9 @@ cmake -B build -DGGML_SYCL=ON -DGGML_SYCL_TARGET=NVIDIA -DGGML_SYCL_DEVICE_ARCH=
cmake --build build --config Release -j -v
```
It is possible to come across some precision issues when running tests that stem from using faster
instructions, which can be circumvented by passing the `-fno-fast-math` flag to the compiler.
#### AMD GPU
The SYCL backend depends on [oneMath](https://github.com/uxlfoundation/oneMath) for Nvidia and AMD devices.