Skip to content

[SYCL] Windows default build instructions without -DLLAMA_SYCL_F16 flag activated #6767

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 6 commits into from
Apr 23, 2024
Merged

[SYCL] Windows default build instructions without -DLLAMA_SYCL_F16 flag activated #6767

Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
e1f6992
Fix FP32/FP16 build instructions
aahouzi Apr 19, 2024
8cf382b
Fix typo
aahouzi Apr 19, 2024
9a426b6
Recommended build instruction
aahouzi Apr 19, 2024
62d80e2
Recommended build instruction
aahouzi Apr 19, 2024
330ee57
Recommended build instruction
aahouzi Apr 19, 2024
8415893
Add comments in Intel GPU linux
aahouzi Apr 19, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
20 changes: 12 additions & 8 deletions README-sycl.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -229,12 +229,12 @@ source /opt/intel/oneapi/setvars.sh
# Build LLAMA with MKL BLAS acceleration for intel GPU
mkdir -p build && cd build

# Option 1: Use FP16 for better performance in long-prompt inference
#cmake .. -DLLAMA_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx -DLLAMA_SYCL_F16=ON

# Option 2: Use FP32 by default
# Option 1: Use FP32 (recommended for better performance in most cases)
cmake .. -DLLAMA_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx

# Option 2: Use FP16
cmake .. -DLLAMA_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx -DLLAMA_SYCL_F16=ON

#build all binary
cmake --build . --config Release -j -v
```
Expand All @@ -250,12 +250,12 @@ export CPLUS_INCLUDE_DIR=/path/to/oneMKL/include:$CPLUS_INCLUDE_DIR
# Build LLAMA with Nvidia BLAS acceleration through SYCL
mkdir -p build && cd build

# Option 1: Use FP16 for better performance in long-prompt inference
cmake .. -DLLAMA_SYCL=ON -DLLAMA_SYCL_TARGET=NVIDIA -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx -DLLAMA_SYCL_F16=ON

# Option 2: Use FP32 by default
# Option 1: Use FP32 (recommended for better performance in most cases)
cmake .. -DLLAMA_SYCL=ON -DLLAMA_SYCL_TARGET=NVIDIA -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx

# Option 2: Use FP16
cmake .. -DLLAMA_SYCL=ON -DLLAMA_SYCL_TARGET=NVIDIA -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx -DLLAMA_SYCL_F16=ON

#build all binary
cmake --build . --config Release -j -v

Expand Down Expand Up @@ -416,6 +416,10 @@ mkdir -p build
cd build
@call "C:\Program Files (x86)\Intel\oneAPI\setvars.bat" intel64 --force

# Option 1: Use FP32 (recommended for better performance in most cases)
cmake -G "MinGW Makefiles" .. -DLLAMA_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icx -DCMAKE_BUILD_TYPE=Release

# Option 2: Or FP16
cmake -G "MinGW Makefiles" .. -DLLAMA_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icx -DCMAKE_BUILD_TYPE=Release -DLLAMA_SYCL_F16=ON

make -j
Expand Down