Skip to content

[FusedKernel]add layer norm quant fusion kernel #180

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
jikunshang wants to merge 4 commits into
base: main
Choose a base branch
from
+737 −0
Open

[FusedKernel]add layer norm quant fusion kernel #180

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
c6be8d9
add layer norm quant fusion kernel
jikunshang Mar 6, 2026
1ac3194
revert
jikunshang Mar 6, 2026
fc02361
add source file
jikunshang Mar 6, 2026
c56f169
Merge branch 'main' into kunshang/fuse_rms_norm_quant
jikunshang Mar 7, 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 CMakeLists.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -344,6 +344,7 @@ if(BASIC_KERNELS_ENABLED)
set(VLLM_EXT_SRC
"csrc/cache.cpp"
"csrc/layernorm.cpp"
"csrc/layernorm_quant.cpp"
Copy link

Copilot AI Mar 6, 2026

Choose a reason for hiding this comment

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

CMakeLists.txt adds csrc/layernorm_quant.cpp to VLLM_EXT_SRC, but that file does not exist in the repository (and rms_norm_static_fp8_quant / fused_add_rms_norm_static_fp8_quant have no definitions elsewhere under csrc/). This will break the build/link step; add the missing source file or remove the entry until the implementation is included.

Suggested change
"csrc/layernorm_quant.cpp"

Copilot uses AI. Check for mistakes.
"csrc/activation.cpp"
"csrc/pos_encoding_kernels.cpp"
"csrc/torch_bindings.cpp"
Expand Down
Loading