22 Jan
2026
22 Jan
'26
1:26 p.m.
Following a hint found on Twitter [1], a little patch on VLLM allowed me to increase the context length on the GLM 4.7-Flash models from 8000 to 200000 (!) tokens. Now, those models get good rankings, but they REALLY overthink. The good thing is that if this patch works with other models, I can run the big GLM 4.7 on bigger nodes! Let’s bark! [1] https://x.com/TheAhmadOsman/status/2013881920099062163