Skip to main content

Notes

Compiling Neuron model

·1310 words· loading · loading
This post is a step-by-step tutorial on compiling PyTorch models for AWS Neuron (Inf2) chips, focusing on BlipForQuestionAnswering. It covers model wrapping, tracing, inference, and practical code examples for deployment.

WebSocket

·611 words· loading · loading
This post explains the differences between HTTP-based APIs (REST, polling, streaming, SSE) and WebSocket APIs, using analogies and code samples to illustrate communication models and protocol upgrades.