Skip to content

Commit e6c0fc8

Browse files
authored
[bugfix] Fix compilation failure when compiling csrc/trtllm_moe_allreduce_fusion.cu (#1410)
[bugfix] Fix compilation failure when compiling csrc/trtllm_moe_allreduce_fusion.cu This file includes FP4QuantizationSFLayout from `flashinfer/comm/trtllm_moe_allreduce_fusion.cuh` which still uses the old format. <!-- .github/pull_request_template.md --> ## 📌 Description <!-- What does this PR do? Briefly describe the changes and why they’re needed. --> ## 🔍 Related Issues <!-- Link any related issues here --> ## 🚀 Pull Request Checklist Thank you for contributing to FlashInfer! Before we review your pull request, please make sure the following items are complete. ### ✅ Pre-commit Checks - [ ] I have installed `pre-commit` by running `pip install pre-commit` (or used your preferred method). - [ ] I have installed the hooks with `pre-commit install`. - [ ] I have run the hooks manually with `pre-commit run --all-files` and fixed any reported issues. > If you are unsure about how to set up `pre-commit`, see [the pre-commit documentation](https://pre-commit.com/). ## 🧪 Tests - [ ] Tests have been added or updated as needed. - [ ] All tests are passing (`unittest`, etc.). ## Reviewer Notes <!-- Optional: anything you'd like reviewers to focus on, concerns, etc. --> Signed-off-by: Po-Han Huang <[email protected]>
1 parent cf1b2d2 commit e6c0fc8

File tree

1 file changed

+1
-1
lines changed

1 file changed

+1
-1
lines changed

csrc/trtllm_moe_allreduce_fusion.cu

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -63,7 +63,7 @@ void trtllm_moe_allreduce_fusion(
6363
params.scale_factor = static_cast<float>(scale_factor);
6464
params.layout = layout_code.has_value()
6565
? static_cast<FP4QuantizationSFLayout>(layout_code.value())
66-
: FP4QuantizationSFLayout::SWIZZLED_128x4;
66+
: FP4QuantizationSFLayout::SWIZZLED;
6767
params.stream = stream;
6868

6969
params.moe_reduction_device_num_experts = moe_reduction_device_num_experts;

0 commit comments

Comments
 (0)