Skip to content

optimized fused_grouped_topk SYCL kernel for MoE expert routing #253

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

Open
xiaolong-intel wants to merge 15 commits into
base: main
Choose a base branch
from
+799 −469
Open

optimized fused_grouped_topk SYCL kernel for MoE expert routing #253

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
15 commits
Select commit Hold shift + click to select a range
33c6817
optimizing grouped_topk_multi_group SYCL kernel for MoE routing
xiaolong-intel Apr 2, 2026
cd261dd
optimizing `fused_grouped_topk` SYCL kernel for MoE expert routing
xiaolong-intel Apr 3, 2026
1fb5daa
Update fused_grouped_topk.cpp
xiaolong-intel Apr 3, 2026
38b33d1
import vllm_xpu_kernels._moe_C in fused_moe_interface.py
xiaolong-intel Apr 3, 2026
4df072b
Update torch_bindings.cpp
xiaolong-intel Apr 7, 2026
5b20f0c
Update grouped_topk_op.py
xiaolong-intel Apr 7, 2026
fb0b037
Modify to make the code more standardized
xiaolong-intel Apr 8, 2026
81ef579
Update utils.h
xiaolong-intel Apr 9, 2026
1f6c091
Removed unnecessary modifications and made changes to the precision c…
xiaolong-intel Apr 10, 2026
be52c90
pre-commit check
xiaolong-intel Apr 10, 2026
c6d6790
Revert unintended oneDNN and moe_ops.h changes
xiaolong-intel Apr 29, 2026
de7497f
add optimization for single group
xiaolong-intel May 21, 2026
2bc9f69
change kernel launch method
xiaolong-intel May 26, 2026
3a551f9
pre-commit check
xiaolong-intel May 26, 2026
01db691
Correct the operator results to make them consistent with torch
xiaolong-intel May 27, 2026
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
2 changes: 1 addition & 1 deletion benchmark/benchmark_grouped_topk.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -209,4 +209,4 @@ def benchmark(
args = parser.parse_args()

benchmark = get_benchmark()
benchmark.run(print_data=True, save_path=args.save_path)
benchmark.run(print_data=True, save_path=args.save_path)
Copy link
Copy Markdown
Member

@jikunshang jikunshang Apr 9, 2026

Choose a reason for hiding this comment

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

pls add blank line

Loading
Loading