jianyuheng

提取候选框算法

1

想请教一下改进selectivesearch提取候选框的思路？

Why is my experimental cifar10 result far worse than your paper shows?

1

Hi, Sir! Thanks for your excellent idea! I download your code and plan to recreate your experiment results. But when i set the parameters with `'sh scripts/cifar10_svdd.sh gpu cifar 0...

Thanks for your outstanding work. After reading your paper, I carefully analyze your code. I found out that you used pytorch api function `prob = F.softmax(pred, dim=1)`. Based on my...

How to pruning LLMs with Multi Query Attention?

Activation quantization of Stable Diffusion.

1

The weight quantization of sd does not have any loss of precision (W8A16), but even if the activation value uses dynamic quantization (W8A8), it will have a huge impact on...

awqlora

1

Excited for your great research. Can we combine qlora and awq, like [gptqlora](https://github.com/qwopqwop200/gptqlora)? if it's possible, would you consider releasing a version of awqlora? Best regards.

Question about inference speed

3

I'm trying compare the inference performance of gptq (reorder) and awq on A100-40G. The table below is the result of preliminary tests. | LLaMA-13B | best(t/s) | worse(t/s) | |...

When I manually set StoppingCriteria， Lookahead can only generate one token.