Search Results for "light"

TokenSpeed is an LLM inference engine designed for high-performance production agent workloads. It aims to combine TensorRT-LLM-level speed with vLLM-level usability, making it relevant for teams that need fast generation without sacrificing developer ergonomics. The project is focused on the specific needs of agentic systems, where latency, throughput, and efficient scheduling matter across many short or tool-heavy requests. It builds on ideas and components from the broader open-source...

...It also brings advanced perception capabilities, including spatial grounding, object recognition, OCR across 32 languages, and robust handling of challenging inputs like low-light or distorted text.

Our light reimplementation of bert for keras. A cleaner, lighter version of bert for keras. This is the keras version of the transformer model library re-implemented by the author and is committed to combining transformer and keras with as clean code as possible. The original intention of this project is for the convenience of modification and customization, so it may be updated frequently.