README: scope the download, fix the single-GPU vLLM-Omni command
#12
by saladday1 - opened
hf download MiniMaxAI/MiniMax-H3-Imagenow fetches about 204 GB, because the repository also holds the diffusers format (transformer_diffusers/,vae_diffusers/,text_encoder/). SGLang and vLLM-Omni only need the original checkpoint (68.7 GB) plus the MiniMax-H3 text encoder (66.7 GB). The new command downloads just those files. Checked with--dry-runon huggingface_hub 1.17.0 (30 files, 68.7 GB) and with a small real download on 0.35.3; both versions treat several positional names as patterns. Repeating--includeper pattern would work on 1.x but keep only the last pattern on 0.x.- The text encoder row said "Not in this repository", which is no longer true since the diffusers weights added
text_encoder/. - According to the vLLM-Omni recipe, keeping the whole model on one GPU needs about 135 GiB, so the plain single-GPU command fits B200/B300 but not H200 or H100. Added the recipe's one-H200 profile, which offloads the text encoder.
Closing this for now: I could not test the deployment changes end to end.
saladday1 changed pull request status to closed