dylanyunlon 0154a3b297 fix(tuning_batched_topk): force bits=8, fix SMEM overflow ...

Previous version used base topk policy's bits (11 for key>=2B),
causing SMEM overflow: 512*4*key_size + 2048*4*batches > 49152.

Fix: force bits=8 (same as radix_sort decision for BI-V100).
SMEM: 512*4*key_size + 256*4*batches = manageable.
Also adds while-loop SMEM check on max_batches.

Detected by test_smem_safety.py: 3 overflows at key_size=2,4,8.

2026-08-01 12:36:57 +08:00

..

muh

fix(tuning_batched_topk): force bits=8, fix SMEM overflow

2026-08-01 12:36:57 +08:00

CMakeLists.txt

[MUH] Fix three-layer disconnect — C++ headers are now the single source of truth

2026-07-30 14:12:33 +00:00