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

How do Transformer model address the vanishing gradient problem?

作答 →

LLM 中等

What is the computational complexity of self-attention in the Transformer model?

作答 →

LLM 中等

Can you briefly explain the difference between LLM training and LLM inference?

作答 →

LLM 中等

What is the purpose of the position-wise feed-forward sublayer in the Transformer model?

作答 →

LLM 中等

How does Transformer model address the vanishing gradient problem?

作答 →

LLM 中等

Explain how KV Cache accelerates LLM inference

作答 →

LLM 中等

Tell me the basic steps involved in running an inference query on an LLM

作答 →

LLM 中等

CNNs and RNNs don’t use positional embeddings. Why do transformers use positional embeddings?

作答 →

LLM 中等

What role does instruction tuning play in improving an LLM’s usability?

作答 →

LLM 中等

What are the different types of LLM fine-tuning?

作答 →

LLM 中等

What are the different phases in LLM development?

作答 →

LLM 中等

How does batching generally help with LLM inference efficiency?

作答 →