Claude 5cd2780320 fix(CRITICAL): CCCL overflow guard — clamp before cumsum + max-num-seqs=2
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.
2026-08-08 21:49:39 +00:00
2026-08-07 08:43:51 +00:00
2026-07-30 17:03:23 +08:00
2026-08-07 07:47:01 +00:00

project_6

Description
No description provided
Readme 427 MiB
Languages
C++ 41.8%
Cuda 31.6%
Python 22.2%
C 2.1%
CMake 1.1%
Other 1.1%