[Der_Einzige]

Speculative decoding isn’t needed at all, right? Why include the final bits about it?

[latchkey]

https://docs.vllm.ai/projects/recipes/en/latest/GLM/GLM.html...

[foobar10000]

GLM 4.7 supports it - and in my experience for Claude code a 80 plus hit rate in speculative is reasonable. So it is a significant speed up.