Skip to content

fix wrong parameter in cmd in readme-sycl.md #6755

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 1 commit into from
Apr 19, 2024
Merged

fix wrong parameter in cmd in readme-sycl.md #6755

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
11 changes: 5 additions & 6 deletions README-sycl.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -229,12 +229,11 @@ 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 --build .. -DLLAMA_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx -DLLAMA_SYCL_F16=ON
# Or without "--build", run "make" next
# 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
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This line should not start with #.

Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

FP16 is not recommended. It has worse performance in most of case than fp32.
so, mark by #

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I see, excellent observation. That is not a good way to notate that, though. I think the # should be removed and add to the comment above something like: . Not generally recommended.

Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

In fact, this cmd is copied from the example/sycl/build.sh at beginning.
But next editor don't know it and modify it again and again. :)


# Option 2: Use FP32 by default
cmake --build .. -DLLAMA_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx
cmake .. -DLLAMA_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx

#build all binary
cmake --build . --config Release -j -v
Expand All @@ -252,10 +251,10 @@ export CPLUS_INCLUDE_DIR=/path/to/oneMKL/include:$CPLUS_INCLUDE_DIR
mkdir -p build && cd build

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

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