IMPORTANT: To view this page as Markdown, append `.md` to the URL (e.g. /get-started.md). For the complete documentation index, see llms.txt.
Skip to main content
For the complete documentation index, see llms.txt. Markdown versions of all pages are available by appending .md to any URL (e.g. /get-started.md).

Python module

max.pipelines.lora

LoRA adapter management for MAX pipelines.

Adapter management​

LoRAConfigConfiguration for LoRA (Low-Rank Adaptation) inference.
LoRAManagerV3Loads and routes ModuleV3 LoRA adapters (adapters-as-inputs).
LoRAModelManages LoRA weights and configuration for a single adapter.
LoRATargetModuleOne wrappable projection module and the PEFT projections it fuses.
get_lora_managerReturns the LoRA manager from the pipeline if LoRA is enabled.

LoRA types​

LoRAOperationEnum for different LoRA operations.
LoRARequestContainer for LoRA adapter requests.
LoRAResponseResponse from LoRA operations.
LoRAStatusEnum for LoRA operation status.
LoRATypeEnumeration for LoRA Types.
ADAPTER_CONFIG_FILEFile name of the LoRA adapter's config file inside the adapter's local directory, read when the adapter is loaded.
LORA_REQUEST_ENDPOINTName of the ZeroMQ endpoint the API server uses to push LoRA load and unload requests to workers.
LORA_RESPONSE_ENDPOINTName of the ZeroMQ endpoint workers use to return LoRA operation results to the API server.
NUM_ROUTING_INPUTSNumber of routing tensors in ModuleV3 LoRA batch info, matching max.nn.LoRA.set_lora_batch_info().