chenwanqq

Results 16 comments of chenwanqq

> Hello! Any plans for adding multimodal (e.g. llava) and embedding models? I'm working on it now.[chenwanqq/candle-llava](https://github.com/chenwanqq/candle-llava) It's not easy dude, tons of image preprocess and tensor concat.

> > I'm working on it now.[chenwanqq/candle-llava](https://github.com/chenwanqq/candle-llava) > > It's not easy dude, tons of image preprocess and tensor concat. > > Yes! Would you be willing to contribute your...

I also have the same question, for llava reasons😉

I have implemented LLaVA at [candle-llava](https://github.com/chenwanqq/candle-llava). Will contribute to this project soon.

> @chenwanqq can you say more about llama.cpp? Sorry, I deleted my post before because when I replied, I just did not really understand what a dev container is. Of...

Hi, please see this issue. It's so important...

that is a serious problem. I try to write a demo to train resnet but it can't work because of this error.

> @chenwanqq I just merged GPTQ support! Sorry, I have intensive job interviews these days, so the progress is kind of slow. I will pick up this part very soon!

> @chenwanqq I cannot measure any T/s speedup. I think that because we are using a GPU and the commands are async, the Rust drop code runs quickly enough that...