sol-attn

Here are 4 public repositories matching this topic...

Language: All

Filter by language

Saganaki22 / ComfyUI-sol-attn

NVIDIA Sol-Attn for ComfyUI / Triton kernel on SM89 - SM121, with zero-copy MiniMax H3 nodes: memory-efficient attention, scheduled tau with graph preview, and feed-forward chunking. Measured ×ばつ vs SageAttention and −37% MLP peak VRAM on H3

triton attention video-generation memory-optimization diffusion-models blackwell memory-op sparse-attention comfyui sageattention comfyui-custom-nodes trito minimax-h3 sol-attn

Updated Aug 13, 2026
Python

aaalll12322 / ComfyUI-MiniMaxH3-SolAttn-V100

Star 16

Sol-Attn (arXiv 2607.24027) sparse acceleration for MiniMax H3 on V100 — single-node ComfyUI plugin (embedded FP16Safe + keep-or-drop kernel)

sla v100 comfyui minimax-h3 sol-attn

Updated Aug 29, 2026
C++

sumeetprashant / ComfyUI-SolAttn

Star 3

NVIDIA's Sol-Attn training-free sparse attention as an opt-in ComfyUI model patch - including consumer Blackwell (SM120 / RTX 50-series), which upstream gates off.

triton attention diffusion video-generation blackwell sparse-attention comfyui rtx-5090 minimax-h3 sol-attn

Updated Aug 13, 2026
Python

Beatau9610 / ComfyUI_sol-attn_Blackwell

Star 0

Accelerate MiniMax H3 video generation on RTX 5090 with Sol-Attn sparse attention, delivering up to 2x faster FlexAttention kernels.

triton attention diffusion video-generation blackwell sparse-attention comfyui rtx-5090 minimax-h3 sol-attn

Updated Sep 6, 2026
Python

Add this topic to your repo

To associate your repository with the sol-attn topic, visit your repo's landing page and select "manage topics."

Learn more