radixark/miles

Reported Failure of Qwen3 14B

Open

#530 ouverte le 29 janv. 2026

Voir sur GitHub
 (3 commentaires) (0 réactions) (1 assigné)Python (244 forks)github user discovery
bughelp wanted

Métriques du dépôt

Stars
 (1 513 stars)
Métriques de merge PR
 (Merge moyen 9j 17h) (200 PRs mergées en 30 j)

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.

Guide contributeur