Skip to content

Fp8 lora dense kernel #35242

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
yugong333 wants to merge 9 commits into
base: main
Choose a base branch
from
+1,515 −1
Open

Fp8 lora dense kernel #35242

Show file tree
Hide file tree
Changes from 5 commits
Commits
Show all changes
9 commits
Select commit Hold shift + click to select a range
4984290
Regular FP8 LoRA kernels
yugong333 Feb 6, 2026
45cfe2a
fix bugs
yugong333 Feb 9, 2026
1f570d3
Fix type annotation error
yugong333 Feb 13, 2026
a5775c3
Fix type annotation error
yugong333 Feb 14, 2026
3bd85c1
Adding annotation
yugong333 Feb 22, 2026
df14451
Renaming get_lora_scale_ptr
yugong333 Feb 24, 2026
cfeda7f
Refactor fp8_mmk to remove duplication
yugong333 Feb 24, 2026
28afaf3
Revert file
yugong333 Feb 24, 2026
257aa9b
Fixing bugs
yugong333 Feb 25, 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
4 changes: 4 additions & 0 deletions vllm/lora/ops/triton_ops/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,13 +12,17 @@
fused_moe_lora_expand,
fused_moe_lora_shrink,
)
from vllm.lora.ops.triton_ops.lora_expand_fp8_op import lora_expand_fp8
from vllm.lora.ops.triton_ops.lora_expand_op import lora_expand
from vllm.lora.ops.triton_ops.lora_kernel_metadata import LoRAKernelMeta
from vllm.lora.ops.triton_ops.lora_shrink_fp8_op import lora_shrink_fp8
from vllm.lora.ops.triton_ops.lora_shrink_op import lora_shrink

__all__ = [
"lora_expand",
"lora_expand_fp8",
"lora_shrink",
"lora_shrink_fp8",
"LoRAKernelMeta",
"fused_moe_lora",
"fused_moe_lora_shrink",
Expand Down
Loading