pottokao/MiniMax-H3-FL2VA-turbo-4step-v1.2-768p-NVFP4-SVDQuant-vLLM-Omni

Add pre-built vLLM-Omni SM120 docker image (docker load)

Patch/README: add SM121 (GB10) alongside SM120

README: pre-built image via docker/ tarball + docker load

Document SM120 vLLM-Omni patch (3 files) + build/run; placeholder for pre-built image

Turbo 4-step v1.2 768p NVFP4 SVDQuant (rank-32) for vLLM-Omni

Add model card

initial commit