5cd2780320864ca4cf77d81d354d76059135a439
Three fixes derived from CCCL source code patterns: 1. CCCL accumulator_t pattern (dispatch_segmented_scan.cuh): - Clamp g to [-5, 2] BEFORE cumsum (was: no pre-clamp, post-clamp ±80) - Tighten post-cumsum clamp to ±20 (was ±80) - Clamp A_log to [-8, 4] before exp() (was: unclamped) - Clamp softplus output to max=10 (was: unclamped) - Clamp g before exp_() in decode path (was: NO clamp at all) 2. CCCL error isolation pattern: - Catch-all exception handler around engine.generate() - max-num-seqs 1→2 to prevent t2_n_2 crash cascade 3. Reduce _DNN_CHUNK 4096→2048 (fewer cumsum steps = less overflow) Root cause: Sub508/509 scored 0 because t2_n_2 killed engine process. NaN (99.98-100% per GatedDeltaNet layer) from unclamped cumsum→exp overflow.
project_6
Description
Languages
C++
41.8%
Cuda
31.6%
Python
22.2%
C
2.1%
CMake
1.1%
Other
1.1%