Zerogpu And Publishing

references/zerogpu-and-publishing.mdMarkdown14 KBView on GitHub

ZeroGPU is the default hardware target. It’s a shared serverless GPU pool: GPU is allocated on each request, held for the duration of a @spaces.GPU function call, and released. The key implications for the demo’s code shape:

ZeroGPU rules

Models go on at module level, not lazy-loaded inside the GPU function.

Zerogpu And Publishing · Huggingface Lora Space Builder · huggingface/skills · Skills Docs

cuda

import torch
import spaces
from diffusers import QwenImagePipeline

pipe = QwenImagePipeline.from_pretrained("Qwen/Qwen-Image", torch_dtype=torch.bfloat16)
pipe.to("cuda")
pipe.load_lora_weights("user/my-lora")

@spaces.GPU(duration=60)
def generate(prompt):
    return pipe(prompt).images[0]

from huggingface_hub import HfApi, get_token

def resolve_auth():
    """Returns (token, username) or (None, None) if no usable auth."""
    cached = get_token()  # picks up HF_TOKEN env var or cached CLI login
    if not cached:
        return None, None
    try:
        info = HfApi().whoami(token=cached)
        return cached, info["name"]
    except Exception:
        return None, None  # token exists but is invalid/expired

from huggingface_hub import HfApi, ModelCard

api = HfApi(token=hf_token)  # token may be None for public repos

try:
    info = api.repo_info(repo_id)  # 401/403 → private/gated; need token
except Exception as e:
    # Handle private/gated repo case
    ...

files = api.list_repo_files(repo_id)
card = ModelCard.load(repo_id, token=hf_token)
base_model = card.data.get("base_model")
pipeline_tag = card.data.get("pipeline_tag")
readme_text = card.text

from huggingface_hub import HfApi, SpaceHardware

api = HfApi(token=hf_token)
username = api.whoami()["name"]
repo_id = f"{username}/{space_name}"

api.create_repo(
    repo_id=repo_id,
    repo_type="space",
    space_sdk="gradio",
    space_hardware=SpaceHardware.ZERO_A10G,
    private=True,
    exist_ok=True,
)

# Set HF token as a Space secret if the LoRA or base model is private/gated
api.add_space_secret(repo_id=repo_id, key="HF_TOKEN", value=hf_token)

# Upload files
for path in ["app.py", "requirements.txt", "README.md"]:
    api.upload_file(
        path_or_fileobj=path,
        path_in_repo=path,
        repo_id=repo_id,
        repo_type="space",
    )

Zerogpu And Publishing

ZeroGPU rules

Zerogpu And Publishing

ZeroGPU rules

HF Hub patterns

Authentication — check first, ask only if needed

Reading the LoRA repo

Picking the LoRA weights file

Loading a private LoRA in `app.py`

Creating and publishing the Space

`SpaceHardware.ZERO_A10G`

Updating an existing Space

After publishing

Publish-time failures (before the build starts)

Common build failures