For the complete documentation index, see llms.txt. Markdown versions of all pages are available by appending .md to any URL (e.g. /max/get-started.md).
Python module
max.pipelines.weights
Weight loading utilities for MAX pipelines.
HuggingFace integration
HuggingFaceRepo | Handle for interacting with a Hugging Face repository (remote or local). |
|---|
download_weight_files | Downloads weight files for a Hugging Face model and returns local paths. |
|---|---|
generate_local_model_path | Generates the local filesystem path where a Hugging Face model repo is cached. |
is_diffusion_pipeline | Check if a Hugging Face repository is a diffusion pipeline. |
try_to_load_from_cache | Wrapper around huggingface_hub.try_to_load_from_cache; validates repo exists. |
validate_hf_repo_access | Validates repository access and raises clear, user-friendly errors. |
Weight loading
WeightPathParser | Parses and validates weight paths for model configuration. |
|---|
auto_cast_weights_from_env | Returns the pipeline default for Module auto-cast, read from env. |
|---|---|
parse_quant_config | Parses scaled quantization config from HuggingFace config and state dict. |
AUTO_CAST_ENV_VAR | str(object='') -> str str(bytes_or_buffer[, encoding[, errors]]) -> str |
|---|
Was this page helpful?
Thank you! We'll create more content like this.
Thank you for helping us improve!