大模型量化与高性能推理优化实习生
北京
校招
实习
技术 - 基础架构
职位 ID：A227558
职位描述
职位要求
任职要求 1. 计算机、电子信息、人工智能、软件工程等相关专业，本科高年级或硕士在读。 2. 熟悉 Python 编程，了解 PyTorch，具备一定的代码开发和实验能力。 3. 了解计算机体系结构、计算机组成原理或并行计算的基本知识。 4. 了解深度学习基本原理，对神经网络模型有一定认识。 5. 了解 Transformer 基本结构，对大语言模型或多模态模型有兴趣。 6. 对模型量化、高性能计算或 AI 推理优化有兴趣，具备良好的学习能力和问题分析能力。 加分项 1. 有大语言模型或多模态模型相关实践经验。 2. 了解 GPTQ、AWQ、PTQ、QAT 等常见模型量化方法。 3. 了解 INT8、INT4 等低比特量化技术。 4. 了解 GPU、NPU 等 AI 加速硬件的基本原理，或具有相关开发经验。 5. 了解 CUDA、OpenCL、SIMD、OpenMP 等并行计算或高性能计算技术。 6. 对矩阵乘法、Attention 等核心算子的计算优化、访存优化有一定了解。 7. 有模型部署、推理性能分析或 C/C++ 开发经验。 8. 有论文阅读、技术复现或开源项目实践经历。 你将获得 1. 参与大语言模型及多模态模型量化技术的研发与实践。 2. 深入了解主流模型量化方法，接触低比特量化及前沿优化技术。 3. 参与实际模型的量化实验、精度分析与推理性能优化。 4. 接触 GPU/NPU 等异构计算平台，了解从模型算法、量化到高性能推理落地的完整技术链路。
投递
ModelBest established in August 2022, is an Artificial Intelligence technology company headquartered in Beijing, China. The company is deeply rooted in the field of general AI, with a focus on the innovation and application transformation of large-scale models. ModelBest boasts a prestigious founding R&D team from the Tsinghua in the AI field. Leveraging numerous cutting-edge technologies in natural language processing, the company is currently constructing a large-scale pre-trained model library and corresponding tools, aiming to standardize the technology and applications of large models.
Based on the capabilities of the CPM series of large models, ModelBest has successfully facilitated the intelligent upgrade and efficiency enhancement of various industries. Moreover, the company has released a multi-modal dialog assistant with hundreds of billions of parameters, “Luca", to the public. Adhering to the core philosophy of "intelligence encompassing all", we look forward to exploring and expanding unknown possibilities with global partners, aiming to ensure AI technology serves humanity for a better life in a safe and inclusive manner, laying a solid foundation for the advent of the AGI world.
OpenBMB (Open Lab for Big Model Base，https://github.com/OpenBMB), founded by ModelBest Inc & TsinghuaNLP, aims to build foundation models and systems towards AGI.
