Skip to content

[WS2][CUDA][MiniMax-H3] tp_adaln_3mod: column-parallel AdaLN projection, byte-equal to WS1 (RFC #420 stack 8/10) - #493

Open
fusheng-ji wants to merge 135 commits into
RL-Align:test-h3from
fusheng-ji:feat/h3-tp-adaln-3mod
Open

fusheng-ji wants to merge 135 commits into
RL-Align:test-h3from
fusheng-ji:feat/h3-tp-adaln-3mod

fix(h3): skip the weight and bias gradients of a frozen tensor-parall…

7b85941
Select commit
Loading
Failed to load commit list.
Sign in for the full log view

Annotations

2 warnings and 1 notice
review
succeeded Oct 29, 2026 in 1m 16s