Blog Tags GitHub

llm

6 posts tagged with "llm"

EfficientLLM: Efficiency in Large Language Models

首个全面评估 LLM 效率技术的大规模基准测试，涵盖架构预训练、微调和量化推理

benchmark efficiency llm quantization peft moe attention-mechanism

A Survey on Mixture of Experts in Large Language Models

MoE 在大语言模型中的全面综述，涵盖门控函数、专家网络、训练推理方案、系统设计和应用

survey mixture-of-experts llm sparse-activation conditional-computation gating-function load-balancing distributed-training

Tmax: A simple recipe for terminal agents

最强开源终端代理 RL 训练方案，通过 TMAX-15K 数据集和 DPPO 训练实现 Terminal-Bench 2.0 上 27% 的最优性能

llm reasoning reinforcement-learning agent terminal-agent software-engineering

Large Language Models for Generative Recommendation: A Survey and Visionary Discussions

LLM 生成式推荐综述，探讨如何将推荐系统从多阶段判别式流程转变为单阶段生成式流程

recommendation llm generative-model survey information-retrieval

Federation of Experts: Communication Efficient Distributed Inference for Large Language Models

通过将 MoE 架构重构为多个独立的专家集群，消除 all-to-all 通信瓶颈，实现高效的分布式推理

llm mixture-of-experts distributed-inference communication-efficiency expert-parallelism

Qwen3 Technical Report

Qwen3 系列大语言模型，集成思考模式和非思考模式，支持 0.6B 到 235B 参数规模

llm reasoning multimodal moe multilingual open-source