f15edbb6ef
* Add tests for openai api_server coverage * update * Update tests for openai api_server * fix bugs * test: disable some api_server lifespan/controller tests for local env * Format test_api_server with black * update * update * test: narrow envs patch in api_server tests to avoid side effects * fix: separate MagicMock creation to avoid missing req argument * fix: patch TRACES_ENABLE env var in api_server tests * fix: use os.environ patch for TRACES_ENABLE * test: use fake fastdeploy.envs in api_server tests * test: pass fake Request into chat/completion routes * test: increase coverage for tracing and scheduler control * fix: set dynamic_load_weight in tracing headers test * ci: add retry and validation for FastDeploy.tar.gz download * ci: fix indentation in _base_test.yml * refactor: simplify test_api_server.py (807->480 lines, ~40% reduction) * fix: restore missing args attributes (revision, etc.) in _build_args * fix: patch sys.argv to prevent SystemExit: 2 in api_server tests * improve coverage * Remove docstring from test_api_server.py Removed unnecessary docstring from test_api_server.py --------- Co-authored-by: CSWYF3634076 <wangyafeng@baidu.com>
English | 简体中文
Installation
|
Quick Start
|
Supported Models
FastDeploy : Inference and Deployment Toolkit for LLMs and VLMs based on PaddlePaddle
News
[2025-11] FastDeploy v2.3 is newly released! It adds deployment support for two major models, ERNIE-4.5-VL-28B-A3B-Thinking and PaddleOCR-VL-0.9B, across multiple hardware platforms. It further optimizes comprehensive inference performance and brings more deployment features and usability enhancements. For all the upgrade details, refer to the v2.3 Release Note.
[2025-09] FastDeploy v2.2: It now offers compatibility with models in the HuggingFace ecosystem, has further optimized performance, and newly adds support for baidu/ERNIE-21B-A3B-Thinking!
About
FastDeploy is an inference and deployment toolkit for large language models and visual language models based on PaddlePaddle. It delivers production-ready, out-of-the-box deployment solutions with core acceleration technologies:
- 🚀 Load-Balanced PD Disaggregation: Industrial-grade solution featuring context caching and dynamic instance role switching. Optimizes resource utilization while balancing SLO compliance and throughput.
- 🔄 Unified KV Cache Transmission: Lightweight high-performance transport library with intelligent NVLink/RDMA selection.
- 🤝 OpenAI API Server and vLLM Compatible: One-command deployment with vLLM interface compatibility.
- 🧮 Comprehensive Quantization Format Support: W8A16, W8A8, W4A16, W4A8, W2A16, FP8, and more.
- ⏩ Advanced Acceleration Techniques: Speculative decoding, Multi-Token Prediction (MTP) and Chunked Prefill.
- 🖥️ Multi-Hardware Support: NVIDIA GPU, Kunlunxin XPU, Hygon DCU, Iluvatar GPU, Enflame GCU, MetaX GPU, Intel Gaudi etc.
Requirements
- OS: Linux
- Python: 3.10 ~ 3.12
Installation
FastDeploy supports inference deployment on NVIDIA GPUs, Kunlunxin XPUs, Iluvatar GPUs, Enflame GCUs, Hygon DCUs and other hardware. For detailed installation instructions:
Get Started
Learn how to use FastDeploy through our documentation:
- 10-Minutes Quick Deployment
- ERNIE-4.5 Large Language Model Deployment
- ERNIE-4.5-VL Multimodal Model Deployment
- Offline Inference Development
- Online Service Deployment
- Best Practices
Supported Models
Learn how to download models, enable using the torch format, and more:
Advanced Usage
Acknowledgement
FastDeploy is licensed under the Apache-2.0 open-source license. During development, portions of vLLM code were referenced and incorporated to maintain interface compatibility, for which we express our gratitude.