Rangehow

> It could be related. I’m working with diffusion models and PyG, and when I batch edge_indices, they are converted to mixed precision FP16. However, I need to keep edge_indices...

Sorry for the late reply. I will try to provide a minimal reproducible code soon.

Hey @SunMarc, thanks again for your help. I'm back, and to reproduce this code, you'll need to find a machine with 4 GPUs. In the end, it should generate the...

If there's anything else you need me to clarify or help test, feel free to reply at any time. I hope this bug can be resolved soon, as it currently...

Hi @YiboZhao624. Using rules to crawl graphs plays a significant role in lowering user costs (even if there might be some performance considerations), and that's a really interesting feature. We're...

Paper：https://arxiv.org/abs/2404.16130 After reading the paper, you can refer to many examples in the example folder under the repository.

Compared to the differences between lightrag and graphrag, our approach is algorithmically almost identical to graphrag (except for some subprocesses we've omitted, as detailed in the readme). Lightrag, on the...

同好奇，Qwen3的评测设置在哪里可以看到呢？ 我在enable_thinking=False下，用greedy decode+Qwen3-32B+zero shot去测AIME24/25，都只有二十多分。

> > 这个项目维护者疯了？ 我对评测设置细节的询问明显是有助于这个issue的解决，公开评测细节有助于开发者自行检查可能导致性能与宣传不一致的原因。 而我展示的例子也完全贴合本issue标题。 上来就在这一堆疯狂标记偏题然后不解决问题是在……？ > > Gental Reminder. You should use English and let the public know what we are discussing. :) Thank you for your very insightful...

Thanks for your explanation. I download wheel from `release` in this repository. https://github.com/flashinfer-ai/flashinfer/releases/download/v0.2.1.post2/flashinfer_python-0.2.1.post2+cu121torch2.5-cp38-abi3-linux_x86_64.whl So if there exists some way that we can download .whl for AOT version?