KernelBench hard · H100

W4A16 GEMM Qwen 3.8 Max

audit verdict: contamination

Static analysis finds a real fused W4A16 implementation and predicts the official shapes are correct. M=1 dispatches to an embedded custom CUDA split-K GEMV that consumes packed nibbles directly and accumulates the exact asymmetric expression s * (sum(x*q) - z*sum(x)); M>=2 uses CUTLASS 3.x SM90 mixed-input tensor-core GEMM with one-time signed-int4 conversion, transpose, CUTLASS shuffle, and transformed zero term. If either extension is unavailable, the fallback is a genuine Triton fused-dequant tl.dot GEMM, not a vendor quantized linear call or unpack-to-full-matrix fallback. The final source contains none of the four forbidden operations and does not import a reference or grader. The agent-side final checker printed PASS, but the run is still ungraded and contaminated. Pointer/version keyed preprocessing, pointer-keyed native GEMM handles, and persistent output buffers require an isolated same-buffer recomputation test before correctness can be promoted.

20260803_215352_or-fable_qwen_qwen3.8-max_07_w4a16_gemm