shhn1

Results 5 comments of shhn1

hi ，when the ZeroQuant inference will be released?

Any updates on this? Thanks @yaozhewei

Out of memory

Hi, I also encountered a similar problem, did you solve it? If it is solved, could you please tell me how to fix it? Thank you so much!

[Bug] Could not build wheels for mmcv, which is required to install pyproject.toml-based projects

> > I am also facing the same issue, not able to build from source also and I am using torch version-1.11.0, even then I am facing this issue. This...

Training on Chinese dataset does not work

> I also trained qwen3-8b eagle3 using SpecForge on a Chinese dataset(Chinese-DeepSeek-R1-Distill-data-110k)(generated answer using Qwen3-8B), but after 10 epoch only got (Position 0) train acc 0.7. and test using vllm...

[Bug] [OOM issue] How to use 16K or 32k ctx on llama3.1-70b or llama3.1-8b

I have the same problem. When I try to train the qwen3 32b model with 32k data, the OOM problem occurs after 2000 steps. How can I solve it? I...