用最优传输理论动态放置专家副本，从拓扑感知角度根治MoE训练负载失衡，值得算法工程师细读。
Article URL: https://arxiv.org/abs/2608.03676 Comments URL: https://news.ycombinator.com/item?id=49330030 Points: 1 # Comments: 0
应对突发推理负载，改进WAIT调度算法，提升LLM服务稳定性与吞吐量。
arXiv:2608.06135v1 Announce Type: new Abstract: Large Language Models (LLMs) such as ChatGPT and Claude are widely used for information retrieval and …
用在线线性规划算法优化LLM服务的多目标路由，兼顾效率与资源均衡
arXiv:2607.03948v1 Announce Type: new Abstract: We study the online routing problem in large language model serving, where requests arrive sequentiall…
为Claude账户打造智能负载均衡，预测性调度提升API调用效率，开源方案值得尝试。
Article URL: https://github.com/yasyf/cc-pool Comments URL: https://news.ycombinator.com/item?id=48515767 Points: 1 # Comments: 0
为HAProxy和Stunnel打造的超轻量级开源GUI，让配置管理更直观高效。
Article URL: https://chrissiefken.github.io/osbal/ Comments URL: https://news.ycombinator.com/item?id=48495069 Points: 2 # Comments: 0
创新性负载均衡与通信优化，FlashCP打破LLM长上下文训练效率瓶颈。
arXiv:2606.08476v1 Announce Type: cross Abstract: Context parallelism (CP) is essential for training large-scale, long-context language models, as it …
开源LLM网关ToTra，集成PII扫描、语义缓存和负载均衡，确保GDPR与EU AI Act合规。
Article URL: https://github.com/SugaC-275/ToTra Comments URL: https://news.ycombinator.com/item?id=48420028 Points: 2 # Comments: 0
将你的Google账户变成免费、负载均衡的LLM API网关，整合多个来源降低成本。
Article URL: https://github.com/arifozgun/OpenGem Comments URL: https://news.ycombinator.com/item?id=48296259 Points: 4 # Comments: 4
新框架直接优化群体级专家平衡，解决MoE训练中负载均衡偏差问题。
arXiv:2605.15403v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) models rely on balanced expert utilization to fully realize their scalability…