GLM Built Its Own Inference Infrastructure

We built a complete production-grade inference service from scratch on a cluster of more than 100,000 Chinese-made AI accelerators. All production inference for GLM-5.3-Flash runs on this system.

Interesting that the tone of announcements between US and Chinese providers is converging.

GLM has in the past been more technical rather than speculation about future development on RSI etc.

Also curious whether those 100k accelerators are entirely locally made. If that's genuinely end to end on all components including lithography, memory, design etc then that is quite a feat.

I was gonna ask how people found their coding plans, and realized, have they massively ramped up the prices? Seems the middle plan is ~$80/month now, didn't that used to be like $20/month? Cheapest plan is ~$20/month currently.

They must have hit really hard scaling limits if the prices were hiked so much so quickly.

> Today, GLM-5.3 has become an indispensable daily coding partner for everyone on the team, and it is moving steadily toward replacing us. If this trend continues, given enough compute and enough time, its endpoint is a system that can design and train its own successor entirely autonomously. This is known as Recursive Self-Improvement, or RSI.

Statements dreamed up by the utterly deranged.

Different angle on the same model: the full GLM-5.3 (744B MoE, 4-bit experts, 434 GB on disk) runs on a single MacBook Pro M5 Max with 128 GB by streaming the experts from NVMe SSDs instead of keeping them in memory.

One drive gives about 2 tok/s; striped across four drives it reaches 3.5 tok/s with byte-identical output, and our best internal build with a not-yet-published patch does 4.2.

Method and numbers: https://github.com/argonautlabsai/argodrive (built on antirez/ds4).

[dead]

Well, other than the infrastructure they got from illegally routing millions of paying customers' requests through Anthropic's Opus 4.8 in a distillation attack...

This article left me with one immediate question: "WTF is GLM?".

Honestly, I have no idea what z.ai is either (I'm aware of an AI-enabled editor called Zed, but that's under zed.dev), so it's a bit presumptuous from them to assume that everyone is familiar with their product...