Smaller, faster, safer: running Kimi and GLM at scale

Smaller, faster, safer: running Kimi and GLM at scale(blog.cloudflare.com)

47 points by ascorbic 3 hours ago | 10 comments

scrlk 59 minutes ago |

Nice to see a provider being transparent about KV cache quantisation. I've been suspecting that some providers do this silently whilst heavily promoting their unquantised weights, even though KV quantisation can degrade quality more than weight quantisation.

However, I wish their testing were more detailed. Firstly, some model families are more sensitive to KV quantisation than others (only Kimi K2.6 was tested). Secondly, the evaluation suite they use to claim that FP8 KV quantisation is indistinguishable is noticeably lacking coding benchmarks; in long-running tasks, minor tool call errors compound over time.

syntaxing 17 minutes ago |

> View pricing in the Cloudflare dashboard ↗

Why… I wanted to see if it’s worth it to use cloudflare’s endpoint but I can’t even see the pricing

brokenodo 1 hour ago |

I was interested in reading this until my slop detector went off at the paragraph starting with “It's worth being precise about where the benefit comes from, because it isn't raw speed.”

I love AI, but I really hate reading it.

hankbond 1 hour ago | |

I have had to stop commenting this because it would end up on 50% of the posts here. I really wish we could flag prose as ai-generated on here and just filter it out.

trollbridge 29 minutes ago | | |

gr_norm 52 minutes ago | | |

LinkedIn (of all places!) announced a button for flagging this recently: https://www.linkedin.com/posts/hsrinivasan1_ai-slop-is-a-top...

How well it would work on this site, I'm not sure.

arjie 32 minutes ago | |

Cloudflare blogs are not meant to be human-read, AFAIK. They're raw material meant to be fed into an agent to be filtered down. I rarely read the contents because they are usually word-expanded to a greater degree than an article from The Atlantic.