FlashInfer's silu_and_mul_scaled_nvfp4_experts_quantize and
scaled_fp4_grouped_quantize kernels corrupt real token scales when
padding rows (beyond masked_m) contain NaN or garbage data.
This affects the FlashInferCuteDSLBatchedExperts MoE path used with
NVFP4 weights (e.g. nvidia/DeepSeek-R1-0528-NVFP4-v2 with DeepEP LL).
The corruption produces wrong finite values (silent accuracy
degradation) that compound across layers.
Fix: zero-fill padding rows in flashinfer_cutedsl_moe_masked before
calling the FlashInfer quantization kernels.
Tests:
- test_silu_quant_cross_row_corruption: direct kernel test (xfail,
proving the underlying FlashInfer kernel bug exists)
- test_grouped_quant_cross_row_corruption: direct kernel test (xfail)
- test_cutedsl_wrapper_nan_padding: wrapper test (PASSES with fix)
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Signed-off-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
