Tracked topic
… The effect is largest at low concurrency, where per-request latency matters most: Concurrent requests GLM FP8 tok/s GLM INT4 tok/s INT4 gain 1 60 92 +55% 8 425 513 +21% 16 683 825 +21% 32 994 1,267 +27% 64 1,672 1,933 +16% Prefill behaves differently. …
…和 JavaScript 跨语言调用 Python 和 JavaScript Workers 现在可以直接互相通信，使混合语言项目开发更轻松。 更小、更快、更安全：大规模运行 Kimi 和 GLM 探索如何在不牺牲质量、可靠性和安全性的情况下，更高效地提供大型模型。 推出 Billable Usage API：Cloudflare 的程序化成本可见性 一种更简单的方式，跟踪我们的自助产品的使用情况和成本。 Cloudflare Workers 和容器现已支持入站 TCP 连接和…
… AI } "@cf/zai-org/glm-5.2" ; } override getSystemPrompt { return You are a bug triage agent. …
… AI } "@cf/zai-org/glm-5.2" ; } override getSystemPrompt { return You are a bug triage agent. …
… AI } "@cf/zai-org/glm-5.2" ; } override getSystemPrompt { return You are a bug triage agent. …
… Smaller, faster, safer: running Kimi and GLM at scale Exploring how we serve large models more efficiently, without sacrificing quality, reliability, or safety. …
… Kleiner, schneller, sicherer: Kimi und GLM im großen Maßstab betreiben Erkunden, wie wir große Modelle effizienter bedienen, ohne Qualität, Zuverlässigkeit oder Sicherheit zu beeinträchtigen. …
… AI } "@cf/zai-org/glm-5.2" ; } override getSystemPrompt { return You are a bug triage agent. …
… Identifiers for the agent class, conversation, and Durable Object are attached so you can correlate across traces. invoke agent itinerary builder : The subagent, nested under the parent, taking 1.83 minutes of that time. chat @cf/zai-org/glm-4.7-flash : Model calls at each level, with duration and … …
To show you the most relevant results, we’ve omitted some entries very similar to those already shown. Repeat the search with the omitted results included.