面试题库

全部 Django Elasticsearch FastAPI Flask Function Call JVM Java IO Java 后端 Java 基础 Java 并发 Java 新特性 Java 集合 JavaWeb Kafka LLM LangChain LangGraph MongoDB MyBatis MySQL Netty Nginx Python RAG RabbitMQ Redis RocketMQ Spring Spring AI SpringBoot SpringCloud SpringMVC ZooKeeper 分布式 后端技术 大厂面经 大数据 微服务 提示词工程 操作系统 数据库 数据结构 智能体 海康威视2026秋季社招专项 消息队列 监控运维 算法 系统设计 缓存 计算机基础 计算机网络 设计模式 面试题 高可用 高并发
LLM 中等

When would you use QLoRA instead of standard LoRA?

作答 →
LLM 中等

What is QLoRA, and how does it differ from LoRA?

作答 →
LLM 中等

What are the challenges in LLM inference?

作答 →
LLM 中等

What are the different LLM inference engines available? Which one do you prefer?

作答 →
LLM 中等

How do you measure LLM inference performance?

作答 →
LLM 中等

Explain the greedy search decoding strategy and its main drawback

作答 →
LLM 中等

Explain the impact of the decoding strategy on LLM-generated output quality and latency

作答 →
LLM 中等

What are the different decoding strategies in LLMs?

作答 →
LLM 中等

Explain the purpose of ReAct prompting in AI Agents

作答 →
LLM 中等

How would you structure a prompt to ensure the LLM output is in a specific format, like JSON?

作答 →
LLM 中等

Describe a strategy for reducing hallucinations via prompt design

作答 →
LLM 中等

What is the purpose of masked self-attention in the Transformer decoder?

作答 →