tests: keep tests/ aligned with upstream; move SM120 decode coverage to sgl_deep_gemm/tests - #65
Merged
Merged
Conversation
The valid-rows comparison for m-grouped contiguous (padding rows are unspecified after the decode optimizations) belongs in sglang's own test copy, which already has it (sgl_deep_gemm/tests/test_fp8_fp4.py). Requested in deepseek-ai#59 review.
The contiguous test always selected the maximum alignment (128), so the decode layouts (alignment 32, BLOCK_M=32) were never exercised. Pass the per-group expected m like the masked test does and add a (num_groups=128, expected_m_per_group=2) decode case. Covers FP8, w4a4 and mixed FP4 quant configs at the minimum alignment; existing cases keep selecting 128.
Fridge003
approved these changes
Jul 21, 2026
Fridge003
pushed a commit
that referenced
this pull request
Jul 23, 2026
…to sgl_deep_gemm/tests (#65)
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Follow-up to the #59 review (@Fridge003).
Changes
Revert
tests/test_fp8_fp4.pyto itspre-#59state. Move tests tosgl_deep_gemm/tests/test_fp8_fp4.pyAdd MoE-decode coverage to
sgl_deep_gemm/tests/.