star7code/minimax-h3-chunk-star7

VRAM-efficient MiniMax H3 for ComfyUI: QKV/RoPE/MLP activation chunking, automatic OOM chunk reduction, and CK/SLA/Sol/Hybrid attention for SM75 and SM80+ GPUs.

语言：Python · GitHub 星标：97 · Fork：3

在 GitHub 上查看原仓库