设备端AI推理新突破：自动云回退、4-bit无损量化、PyTorch模型一键转换。
Hi HN, Roman and Henry here from Cactus ( https://github.com/cactus-compute/cactus ). We just shipped the biggest upgrade to our on-device inference p…
PyTorch原生打造的大规模LLM强化学习后训练框架，高效协调样本生成与策略更新。
Article URL: https://pytorch.org/blog/miles-a-pytorch-native-stack-for-large-scale-llm-rl-post-training/ Comments URL: https://news.ycombinator.com/it…
用大模型学bug上下文，精准提升PyTorch到JAX代码翻译的鲁棒性。
arXiv:2510.09898v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have shown strong performance on code translation between widel…
PyTorch官方2026年AI编程实战手册，核心策略与最佳实践一网打尽
Article URL: https://docs.pytorch.org/devlogs/ai-agents/2026-05-30-ai-coding-playbook/ Comments URL: https://news.ycombinator.com/item?id=48361727 Poi…
PyTorch神经网络权重与偏置初始化实战，手把手教你正确设置初始参数提升模型性能。
In the previous article , we got started with expressing a neural network in the form of Python code. In this article, we will continue building on th…
PyTorch编译器扩展Flashlight，高效加速各类注意力变体，助力大模型推理与训练
arXiv:2511.02043v4 Announce Type: replace Abstract: Attention is a fundamental building block of large language models (LLMs), so there have been many…
PyTorch官方推出的后训练微调库torchtune，原生集成LoRA、QLoRA等高效技术，简化大模型适配流程。
arXiv:2605.21442v1 Announce Type: new Abstract: Modern LLMs typically require multistage training pipelines to achieve strong downstream performance, …
从零复现GPT核心机制，基于PyTorch实现简洁自回归语言模型，AI学习者必读的底层论文教程。
arXiv:2605.17398v1 Announce Type: cross Abstract: This paper presents MiniGPT, a compact from-scratch implementation of GPT-style autoregressive langu…
PyTorch生成建模工具包，简化VAE、GAN、扩散模型等实现与实验。
arXiv:2605.17605v1 Announce Type: new Abstract: Modern generative modeling has grown into a broad collection of related but often separately implement…
两阶段RAG管道防止LLM幻觉导致测试错误，开源PyTorch工具直击内存bug。
Article URL: https://github.com/msunda17/impactarbiter-cli Comments URL: https://news.ycombinator.com/item?id=48181654 Points: 1 # Comments: 0