Skip to content

added support for MLA decode #139

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
airMeng merged 13 commits into from
Apr 7, 2026
Merged

added support for MLA decode #139

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
13 commits
Select commit Hold shift + click to select a range
6036817
added support for MLA decode
pralay-das Mar 17, 2026
bbcb634
fix reorder impl issue
pralay-das Mar 18, 2026
87e44b2
remove unnecessary import
pralay-das Mar 26, 2026
654cc4a
Split MLADecode template instantiations into per-kernel compilation u…
pralay-das Mar 27, 2026
a88885d
updated benchamark tests
pralay-das Mar 27, 2026
133bb7d
refactor code
pralay-das Mar 28, 2026
5c33209
refactor code
pralay-das Mar 30, 2026
2e4f810
removed unnecessary copy operation
pralay-das Mar 30, 2026
7013975
added benchmark script in github workflows
pralay-das Mar 31, 2026
13d0b54
change name from cutlass_mla -> flash_mla,
pralay-das Apr 4, 2026
b9c33d4
Merge branch 'main' into dev/pralay/mla
pralay-das Apr 4, 2026
7a106a7
added test file in ci
pralay-das Apr 6, 2026
66d39a0
changed the file name for mla in yml file
pralay-das Apr 6, 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
1 change: 1 addition & 0 deletions .github/workflows/pr-test-xpu.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -60,6 +60,7 @@ jobs:
/miniforge3/envs/py3.10/bin/python3 -m pip install tabulate && \
cd /root/sglang/sgl-kernel-xpu/benchmark && \
python3 bench_flash_attn.py 2>&1 | tee flash.log && \
python3 bench_flash_mla_decode.py.py 2>&1 | tee mla.log && \
python3 bench_moe_topk_softmax.py 2>&1 | tee moe.log && \
python3 bench_fused_moe.py 2>&1 | tee fused_moe.log && \
python3 bench_moe_sum_reduce.py 2>&1 | tee moe_sum_reduce.log \
Expand Down
132 changes: 0 additions & 132 deletions benchmark/bench_cutlass_mla.py
View file
Open in desktop

This file was deleted.

Loading
Loading