Nodes/ComfyUI-NynxzH3/H3 Row Chunk
ComfyUI Node

H3 Row Chunk

Splits the attention qkv projection and the MLP into row chunks so their intermediates never exceed CUDA's int32 element limit. Fixes 'CUDA error: an illegal memory access was encountered' on sequences past ~75k rows, and lowers peak activation memory. These projections are row-wise, so this computes the same function — it is not an approximation and costs no quality.

By Nynxz·Created 14 days ago·Updated 5 days ago· 4
H3 Row Chunk
  • model
  • MODEL
  • report
chunk_rows0
CategoryNynxz/H3/Sampling

Inputs (2)

NameTypeDefaultDescription
modelMODELA MiniMax H3 model.
chunk_rowsINT00–1000000Rows per chunk. 0 picks a size from the sequence: small enough to stay under the int32 limit with margin AND to hold each widened intermediate near 1 GiB. Set a smaller number only if a run still faults — some kernels allocate workspace beyond their output.

Outputs (2)

NameTypeDescription
MODELMODEL
reportSTRINGWhere the int32 ceiling falls for this model, and what chunking does at a few clip lengths.