radixark/miles

Reported Failure of Qwen3 14B

Open

#530 opened on Jan 29, 2026

View on GitHub
 (3 comments) (0 reactions) (1 assignee)Python (244 forks)github user discovery
bughelp wanted

Repository metrics

Stars
 (1,513 stars)
PR merge metrics
 (PR metrics pending)

Description

I highly think that Qwen3 235B should work, since we do a bunch of experiments on it. But, Qwen3 14B (I think it's a dense model), is also reported to not work.

https://huggingface.co/Qwen/Qwen3-14B

My suggestion is that, could try to install latest Miles docker and debug with it. May just need to use Megatron + SGLang.

Contributor guide