# Baidu — FastDeploy 2.0: A Large-Scale Model Inference and Deployment Toolkit with Native Support for ERNIE 4.5

- Company: Baidu (baidu.com)
- Announced: 2025-08-14T00:00:00+00:00
- Category: developer-tool-release
- Subject: ERNIE
- Models affected: ERNIE 4.5, ERNIE-4.5-300B-A47B, Qwen3, DeepSeek
- Source: https://ernie.baidu.com/blog/posts/fastdeploy2.0/
- Record: https://forck.live/items/4654-fastdeploy-2-0-a-large-scale-model-inference-and-deployment-toolkit-with

Baidu announced FastDeploy 2.0, an end-to-end toolkit for efficient deployment and high-performance inference of large models, with native support for the ERNIE 4.5 family. It features high-throughput inference using Expert Parallel and Prefill-Decode Disaggregation, near-lossless 2-bit quantization enabling trillion-parameter models on a single GPU, and optimizations for heterogeneous hardware. Benchmark results show significant throughput gains over vLLM for ERNIE and other models.

## Evidence

Verbatim from https://ernie.baidu.com/blog/posts/fastdeploy2.0/:

> FastDeploy 2.0, built on the PaddlePaddle framework , addresses this demand by offering an end-to-end toolkit for efficient deployment and high-performance inference of large models.

---

Record: https://forck.live/items/4654-fastdeploy-2-0-a-large-scale-model-inference-and-deployment-toolkit-with
Catalogue: https://forck.live/llms.txt
Feed: https://forck.live/feed.md