feat(ops): add linear_gluact_linear cuTile kernel & other updates - #194

Open

hannahli-nv wants to merge 11 commits into

mainfrom

Commits on Aug 31, 2026

feat(ops): add linear_gluact_linear cuTile kernel

committed
152c784

Commits on Sep 2, 2026

Optimize cuTile modulated_rms_norm
xjmxyt
committed
637a3d0
tilecpp: perf fixes for the activations and moe_align_block
GordonWuCn
committed
30648e6

Commits on Sep 3, 2026

cuTile: add narrow-K skinny matmul autotune tiles for sm120
xjmxyt
committed
e7655e3
tests: default --arch to sm100 when no GPU is available
lirundong
committed
e821978
Expand SwiGLU test_perf coverage with prefill shapes
xjmxyt
committed
130e6cf