推理引擎VKAE实现23倍GPU加速，单卡B200跑出万级token吞吐，AI部署效率再突破。
VKAE: VIDRAFT's Inference Engine Hits 23× GPU Speedup and ~10K Tokens/sec on a Single Nvidia B200 TL;DR: VIDRAFT, a Korean Pre-AGI AI startup, has dev…
Fisher重加权剪枝，让大模型压缩更省能耗，部署更可持续。
arXiv:2608.00481v1 Announce Type: new Abstract: One-shot post-training pruning is the most energy-frugal compression strategy for largelanguage models…
8美元微控制器跑LLM：2890万参数模型在ESP32上运行，极限压缩实现边缘AI。
Article URL: https://github.com/slvDev/esp32-ai Comments URL: https://news.ycombinator.com/item?id=49050512 Points: 10 # Comments: 0
一行命令部署任何LLM，Flama让Gemma 4等模型在Apple Silicon上极速运行
Flama 2.0 brings first-class support for generative AI: downloading, packaging, and serving large language models (LLMs) is now as simple as running a…
面向空间NPU的端到端LLM部署，提出Agent技能系统实现从人工指导到自主运行，架构与机器学习协同创新。
arXiv:2606.07586v1 Announce Type: new Abstract: Spatial neural processing units (NPUs) provide an energy-efficient platform for edge LLM inference, bu…
新研究揭示AI模型在武装冲突地区部署时，可能因对齐失败而无意中激化矛盾，对AI安全与全球治理敲响警钟。
arXiv:2605.22720v1 Announce Type: new Abstract: AI models are already deployed in societies affected by armed conflict, and journalists, humanitarian …