Dezhao Song

Data processing for the MAN model

9

Hi Di, thanks a lot for sharing the code of this QA system. I have been trying to apply it to my own data. I skipped the pre-training and the...

[BUG] Qwen3: model loading failed when using meta device

19

**Describe the bug** I am running on a single node with 4 GPUs; each GPU has 24GB GPU memory. With Deepspeed-Inference, I was trying to load Qwen/Qwen3-4B using meta device....

[BUG] Deepspeed-Inference: support AutoTP for Llama-4 models

5

**Describe the bug** I was trying to run Deepspeed-Inference on Llama-4-Scout-Instruct for text generation purpose. The process failed when it started to load model. I am running on a single...