biondizzle 56dff8d185 fix: W_gate is (H, E) but F.linear expects (E, H), transpose before linear

2026-05-31 23:55:16 +00:00

..

__init__.py

Router: clean up dense_router_decode.py — realistic architecture, no fake code

2026-05-21 21:58:31 +00:00

_activation_topk.py

Router: full kernel stack — hash, topk, activation+topk, dense decode/prefill

2026-05-21 21:54:05 +00:00

dense_router_decode_kernel.py

fix: compute num_tma_load_bytes inside cute.compile context

2026-05-31 23:53:13 +00:00

dense_router_decode.py

fix: W_gate is (H, E) but F.linear expects (E, H), transpose before linear

2026-05-31 23:55:16 +00:00

dense_router_prefill.py

Router: clean up dense_router_decode.py — realistic architecture, no fake code

2026-05-21 21:58:31 +00:00