1
Frontier-class LLM inference on a laptop CPU
笔记本CPU也能跑前沿LLM？这个开源项目性能直逼甚至超越llama.cpp，技术细节曝光效率提升关键。
Article URL: https://github.com/arizqi/cpubrrr Comments URL: https://news.ycombinator.com/item?id=49026595 Points: 1 # Comments: 0
2
AdaptiveSD A Stability-Aware, Runtime-Adaptive Speculative Decoding Framework with Multi-Policy Orchestration for CPU-Constrained LLM Inference
面向CPU受限场景的自适应投机解码框架，多策略编排让LLM推理更高效。
arXiv:2607.03876v1 Announce Type: new Abstract: With the rise of small quantized GGUF-based language models and their increasing use for on-device inf…
3
Epic 虚幻引擎 6 公开，游戏《火箭联盟》确认搭载
Epic 虚幻引擎 6 公开，实时渲染画面惊艳，CPU 性能提升 40%，《火箭联盟》率先搭载，游戏开发新标杆。
IT之家 5 月 25 日消息，据 IGN 今日报道，Epic Games 旗下开发商 Psyonix 发布了运行于虚幻引擎 6（Unreal Engine 6）的《火箭联盟》（Rocket League）更新版本的预览，并首次展示了其全新 Logo。 Epic 与 Psyonix 尚未解释虚幻引擎…
4
AI agent harnesses like OpenClaw are changing LLMs, inference, and CPUs
OpenClaw等AI代理工具正在重塑LLM推理与CPU效率，一文看懂技术新趋势。
Article URL: https://www.theregister.com/ai-ml/2026/05/17/how-ai-agent-harnesses-like-openclaw-are-changing-llms-inference-and-cpus/5241530 Comments U…