The new GLM-5.3-Flash recipe on 2× DGX Spark — now with the cache fix.
This is a AI post classified by AGK Intelligence as AI infra & evals (a tool drop), kept by the AI Radar because it carries real work, not commentary.
The new GLM-5.3-Flash recipe on 2× DGX Spark — now with the cache fix. A 450k-token conversation used to re-prefill from zero: 292 s before its next turn. With CACHE_FIRST it resumes 99% cached in 5.1 s. Decode tok/s (thinking on) 1/2/4/8 streams: 41.8 / 60.2 / 80.3 / 104.9 Prefill ~1,770 tok/s · TTFT 0.2 s What I love about how @MiaAI_lab and @ashxhart work: they stay close to the community and ship fixes overnight — I sent logs, patch 0108 landed the next day, and it solves exactly my bottleneck. Even the tool-call guard came out of a user's agent report. This one's a keeper.
Posted by JCode (4k followers) 4 h ago · 8 likes · 1.7k views · view the original post on X. Kept by the AI Radar as AI infra & evals. Tools mentioned: glm-5.3-flash-dgx-sparks-1104.
More AI work like this
- websites bay area people use that normies have never heard of: — @chiefofautism
- Coding agents can ship an app in hours. — @DataChaz
- Introducing TRACE: Transparent Real-world Assessment of Content Extraction. — @getcontextdev
- We're sitting down with and @cjav_dev (@AnthropicAI) on Nov 17th at 10am PT to talk… — @sentry
- Introducing our next generation of model routers: — @OpenRouter
- a16z's Martin Casado: AI is the biggest rebuild of computer science since the internet.… — @guilleflorvs
- There are AI GPUs running in converted chicken coops. — @guilleflorvs
- Enterprise AI is only as useful as the data and business context behind it. — @databricks
Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 65.3k posts from 5k X accounts over the last 14 days, 10.4k tools, 19 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-06 17:44 UTC. Full method.