1
GitHub availability report: June 2026
了解GitHub 2026年6月服务可用性报告，六起事件导致性能降级，官方故障复盘值得关注。
In June, we experienced six incidents that resulted in degraded performance across GitHub services. The post GitHub availability report: June 2026 app…
2
Characterizing Software Aging in GPU-Based LLM Serving Systems
揭秘GPU上LLM服务系统的软件老化特征，为提升系统长期稳定性提供关键洞察。
arXiv:2606.11916v1 Announce Type: cross Abstract: This paper proposes an empirical methodology to study software aging in GPU-based LLM serving system…
3
Stop Listening to Me! How Multi-turn Conversations Can Degrade LLM Reliability
多轮对话让LLM可靠性下降？研究揭示在医疗等高风险场景中静态评测与真实使用的巨大鸿沟。
arXiv:2603.11394v3 Announce Type: replace-cross Abstract: Large language models (LLMs) excel on static benchmarks, but their performance across multi-…
4
Fitting Is Not Enough: Smoothness in Extremely Quantized LLMs
LLM极端量化中平滑性比数值拟合更重要，揭示性能下降新成因。
arXiv:2605.08894v2 Announce Type: replace-cross Abstract: Large language models (LLMs) achieve strong performance but incur high deployment costs, mot…