Skip to content

[LoRA][II] Add fused MOE LoRA Triton kernel and tests #19711

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
Fridge003 merged 6 commits into from
Mar 19, 2026
Merged

[LoRA][II] Add fused MOE LoRA Triton kernel and tests #19711

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
7337647
Add fused MOE LoRA Triton kernel and tests
yushengsu-thu Mar 2, 2026
56877bf
update
yushengsu-thu Mar 2, 2026
f1c4f55
Merge branch 'main' into moe-lora-triton-kernel
yushengsu-thu Mar 12, 2026
347c3ef
Merge branch 'main' into moe-lora-triton-kernel
yushengsu-thu Mar 14, 2026
df5d4c5
Merge branch 'main' from upstream into moe-lora-triton-kernel
yushengsu-thu Mar 17, 2026
f829663
fix lint
yushengsu-thu Mar 17, 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: 2 additions & 0 deletions python/sglang/srt/lora/triton_ops/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,6 +2,7 @@
from .chunked_sgmv_expand import chunked_sgmv_lora_expand_forward
from .chunked_sgmv_shrink import chunked_sgmv_lora_shrink_forward
from .embedding_lora_a import embedding_lora_a_fwd
from .fused_moe_lora_kernel import fused_moe_lora
from .gate_up_lora_b import gate_up_lora_b_fwd
from .qkv_lora_b import qkv_lora_b_fwd
from .sgemm_lora_a import sgemm_lora_a_fwd
Expand All @@ -14,6 +15,7 @@
"sgemm_lora_b_fwd",
"chunked_sgmv_lora_shrink_forward",
"chunked_sgmv_lora_expand_forward",
"fused_moe_lora",
"chunked_embedding_lora_a_forward",
"embedding_lora_a_fwd",
]
Loading
Loading