Repository navigation
Add 2 hard inference challenges: FP8 Block-Scaled GEMM (140), Flash Decoding Attention (141) - #350
Merged
Merged
Conversation
…ecoding Attention (141) Free, hard LLM-inference kernels. FP8 block-scaled GEMM is the DeepSeek-V3 / DeepGEMM E4M3 x E4M3 matmul with 1x128 float32 scales. Flash decoding attention is long-context single-token (T << S) multi-head decode. References accumulate in float64. Leaves Interview Track #349 (134-139) untouched.
kunal-mansukhani
requested review from
ishaan-arya and
shxjames
as code owners
October 15, 2026 16:30
![github-actions[bot]](https://avatars.githubusercontent.com/in/15368?s=60&v=4){kind=small}
github-actions
Bot
added
the
needs-human-review
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Two new free, hard LLM-inference challenges (numbers continue after Interview Track's reserved 134–139; #349 left untouched):
Skipped the CEO examples that already exist: MLA Decode (114), Grouped GEMM (99), NVFP4 (89).
Details
access_tier = free, difficulty hardmax.gpu/std.memory)validate_challenges.py: 0 errors; black / isort / flake8 / clang-format clean locallyTest plan
python scripts/validate_challenges.py→ 0 errorsapi.leetgpu.com/api/v1/challenges