langchain_nvidia_trt 0.0.1¶

langchain_nvidia_trt.llms¶

Classes¶

llms.StreamingResponseGenerator(llm, ...)

A Generator that provides the inference results from an LLM.

llms.TritonTensorRTError

Base exception for TritonTensorRT.

llms.TritonTensorRTLLM

TRTLLM triton models.

llms.TritonTensorRTRuntimeError

Runtime error for TritonTensorRT.