762 commits. 315 contributors. 104 first-timers. vLLM v0.30.0 is live. 🎉
This is a dev post classified by Jev as AI dev tools (a launch), kept by the Dev Radar because it carries real work, not commentary.
762 commits. 315 contributors. 104 first-timers. vLLM v0.30.0 is live. 🎉 Highlights: 🤖 Hybrid-attention hot paths: Kimi K3 streamlines KDA, AttnRes, and MLA; DeepSeek-V4.1-Flash adds MXFP8 KV and async Engram; Qwen3.8-Flash-Next fuses QSA/PLE and cuts sparse-GQA overhead 🗄️ HiSparse adds a host tier beneath sparse-MLA decode; under GPU pressure, only top-k misses return to a per-request hot buffer 🛠️ Model Runner V2 brings EAGLE3-style drafts to pipeline parallelism and extends adaptive verification to every draft-model speculator through online acceptance estimation (#50514, #52228) 🖋️ Dual
Posted by vLLM (49.9k followers) 2 h ago · 63 likes · 2.8k views · view the original post on X. Kept by the Dev Radar as AI dev tools.
More dev work like this
- Asked Claude Opus 5.5 to animate @PingRoomIO — @MahdiSPHP
- My ai-memory has more features than just sharing memory across agents. For example: it… — @AkitaOnRails
- Your coding agent can have a desktop sidekick — without a cloud account. — @DanKornas
- 🚨LATEST: OpenAI launches GPT-6 Sol and GPT-6 Luna with 50% lower API costs. — @coinbureau
- The news is out: DeepSeek-V4.1-Flash is free to use on WorkBuddy until October 9th! — @WorkBuddy_AI
- 斯坦福 2025 年秋季，开了一门 CS146S「现代软件开发者」，讲怎么跟编码 Agent 一起写软件，8 周作业全部公开在 GitHub 上。 — @GitHub_Daily
- @peterramsing @typesafeai Nice! I also built a Jev based ticket app. — @airesearch12
- in Executor v2, it's actually taking advantage of effect's error system now — @RhysSullivan
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 22k posts from 5k X accounts over the last 21 days, 2.5k tools, 12 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-23 04:56 UTC. Full method.