Nodes/ComfyUI-SolAttn_triton/MiniMax H3 Long-Sequence Attention (Experimental)
ComfyUI Node

MiniMax H3 Long-Sequence Attention (Experimental)

H3-only Sol-Attn candidate from 12K tokens. Builds an explicit accepted-block mask with 90% estimated mass coverage and a 50% exact floor, then uses the stable grouped INT8 QK/PV kernel. Conditioning query/KV rows and sensitive transformer blocks stay dense.

By DrBearJew·Created 11 days ago·Updated 11 days ago· 0
MiniMax H3 Long-Sequence Attention (Experimental)
  • model
  • MODEL
enabledfalse
verbosefalse
Categorysol_attn/minimax_h3

Inputs (3)

NameTypeDefaultDescription
modelMODEL
enabledBOOLEANfalseExplicit opt-in; disabled preserves dense attention.
verboseBOOLEANfalse

Outputs (1)

NameTypeDescription
MODELMODEL