1
Streaming Model Cascades for Semantic SQL
语义SQL遇性能瓶颈？流式级联让大模型按行推理成本骤降，数据查询提速新思路。
arXiv:2604.00660v2 Announce Type: replace-cross Abstract: Modern data warehouses extend SQL with semantic operators that invoke large language models …
2
Show HN: bote - A fast, modern and low-memory approach to processing a big JSON
快速处理大型JSON且占用极低内存，比同类库快数倍，适合大数据场景
Article URL: https://github.com/jankdc/bote Comments URL: https://news.ycombinator.com/item?id=48591141 Points: 3 # Comments: 1
3
ViCoStream: Streaming VideoLLMs Can Run Beyond 100 FPS with Stage-Wise Coordinated Inference
流式视频大模型推理飙至100+FPS，ViCoStream用阶段协调机制破解实时处理瓶颈，视频理解应用提速必读。
arXiv:2606.19849v1 Announce Type: new Abstract: Streaming VideoLLMs must continuously process incoming video while maintaining low query latency, maki…
4
Streaming Knowledge Compilation: Proactive Materiality-Scored Pinning for Time-Evolving LLM Wikis
LLM Wiki静态缓存假设不再适用，这篇论文提出了主动物性评分钉住方案，解决时变知识流式编译难题。
arXiv:2606.09877v1 Announce Type: new Abstract: LLM wiki systems compile knowledge into pre-filled KV caches for efficient inference, but assume a sta…
5
Learning, Experimenting - Concurrency in Go - Part 2
Go并发实战：分布式块文件存储中的流式处理与正确性保证，含基准测试优化经验。
Refresher - I'm building a distributed chunked filestore in Go, and I setup a post for Part 1 here . That part dealt with uploading a file - this post…
6
Show HN: Suture – a reverse proxy that repairs truncated JSON in LLM streams
面向 LLM 流式输出的反向代理，自动修复截断 JSON，保障下游解析稳定。
Article URL: https://github.com/tensorhq/suture-stream-repair Comments URL: https://news.ycombinator.com/item?id=48393431 Points: 1 # Comments: 0
7
Unlocking the Codex harness: how we built the App Server
OpenAI详解Codex App Server构建过程，双向JSON-RPC支持流式进度、工具调用与审批。
Learn how to embed the Codex agent using the Codex App Server, a bidirectional JSON-RPC API powering streaming progress, tool use, approvals, and diff…