jdelony/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-06-27 23:50:20 -05:00
Code Issues Packages Projects Releases Wiki Activity

sycl : Make GGML_SYCL_F16=ON the default (#23996)

Browse Source 
* Add -cl-fp32-correctly-rounded-divide-sqrt to F16=ON builds

Signed-off-by: Todd Malsbary <todd.malsbary@intel.com>

* Make GGML_SYCL_F16=ON the default

Signed-off-by: Todd Malsbary <todd.malsbary@intel.com>

* Leave F32 the default

F16 remains explictly set for example and Dockerfile builds.

Signed-off-by: Todd Malsbary <todd.malsbary@intel.com>

* Revert changes to examples/sycl/build scripts

Signed-off-by: Todd Malsbary <todd.malsbary@intel.com>

---------

Signed-off-by: Todd Malsbary <todd.malsbary@intel.com>
This commit is contained in:
Todd Malsbary 2026-06-15 22:34:02 -07:00 committed by GitHub
parent ad39ccaa19
commit 4196b477da
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 15 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
.devops/intel.Dockerfile
View File

@ -7,7 +7,7 @@ ARG APP_REVISION=N/A
FROM docker.io/intel/deep-learning-essentials:$ONEAPI_VERSION AS build
ARG GGML_SYCL_F16=OFF
ARG GGML_SYCL_F16=ON
ARG LEVEL_ZERO_VERSION=1.28.2
ARG LEVEL_ZERO_UBUNTU_VERSION=u24.04
RUN apt-get update && \
@ -24,7 +24,8 @@ COPY . .
RUN if [ "${GGML_SYCL_F16}" = "ON" ]; then \
echo "GGML_SYCL_F16 is set" \
&& export OPT_SYCL_F16="-DGGML_SYCL_F16=ON"; \
&& export OPT_SYCL_F16="-DGGML_SYCL_F16=ON" \
&& export SYCL_PROGRAM_COMPILE_OPTIONS="-cl-fp32-correctly-rounded-divide-sqrt"; \
fi && \
echo "Building with dynamic libs" && \
cmake -B build -DGGML_NATIVE=OFF -DGGML_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx -DGGML_BACKEND_DL=ON -DGGML_CPU_ALL_VARIANTS=ON -DLLAMA_BUILD_TESTS=OFF ${OPT_SYCL_F16} && \

22
docs/backend/SYCL.md
View File

@ -253,6 +253,7 @@ When targeting an intel GPU, the user should expect one or more devices among th
#### Intel GPU
```sh
# Uses FP32, consider using FP16 for better performance in most cases
./examples/sycl/build.sh
```
@ -262,12 +263,12 @@ or
# Export relevant ENV variables
source /opt/intel/oneapi/setvars.sh
# Option 1: Use FP32 (recommended for better performance in most cases)
cmake -B build -DGGML_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx
# Option 2: Use FP16
# Option 1: Use FP16 (recommended for better performance in most cases)
cmake -B build -DGGML_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx -DGGML_SYCL_F16=ON
# Option 2: Use FP32
cmake -B build -DGGML_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx
# build all binary
cmake --build build --config Release -j -v
```
@ -469,6 +470,7 @@ Choose one of following methods to build from source code.
##### Option 1: Script
```sh
# Uses FP32, consider using FP16 for better performance in most cases
.\examples\sycl\win-build-sycl.bat
```
@ -479,11 +481,11 @@ On the oneAPI command line window, step into the llama.cpp main directory and ru
```
@call "C:\Program Files (x86)\Intel\oneAPI\setvars.bat" intel64 --force
# Option 1: Use FP32 (recommended for better performance in most cases)
cmake -B build -G "Ninja" -DGGML_SYCL=ON -DCMAKE_C_COMPILER=cl -DCMAKE_CXX_COMPILER=icx -DCMAKE_BUILD_TYPE=Release
# Option 1: Use FP16 (recommended for better performance in most cases)
cmake -B build -G "Ninja" -DGGML_SYCL=ON -DCMAKE_C_COMPILER=cl -DCMAKE_CXX_COMPILER=icx -DCMAKE_BUILD_TYPE=Release -DGGML_SYCL_F16=ON
# Option 2: Or FP16
cmake -B build -G "Ninja" -DGGML_SYCL=ON -DCMAKE_C_COMPILER=cl -DCMAKE_CXX_COMPILER=icx -DCMAKE_BUILD_TYPE=Release -DGGML_SYCL_F16=ON
# Option 2: Or FP32
cmake -B build -G "Ninja" -DGGML_SYCL=ON -DCMAKE_C_COMPILER=cl -DCMAKE_CXX_COMPILER=icx -DCMAKE_BUILD_TYPE=Release
cmake --build build --config Release -j
```
@ -491,10 +493,10 @@ cmake --build build --config Release -j
Or, use CMake presets to build:
```sh
cmake --preset x64-windows-sycl-release
cmake -DGGML_SYCL_F16=ON --preset x64-windows-sycl-release
cmake --build build-x64-windows-sycl-release -j --target llama-completion
cmake -DGGML_SYCL_F16=ON --preset x64-windows-sycl-release
cmake --preset x64-windows-sycl-release
cmake --build build-x64-windows-sycl-release -j --target llama-completion
cmake --preset x64-windows-sycl-debug