ai-and-i

See #363, which references a way to build it on linux using community-provided patches. I would love to see this integrated into the mainline!

I have the same issue when ssh-ing to an ubuntu 22.04 machine. I needed to reboot the machine to get it work. However, disabling the keyring fixed it for me...

Awesome, thanks for confirming! I tested llava-1.6 34B, and it's not working - looks like because of this issue: https://github.com/mlc-ai/mlc-llm/issues/1919 (llava-1.6-34b is based on yi-34b and I'm seeing exactly the...

The patch and build procedure from [this commit](https://github.com/meta-flutter/rive-common/tree/08cdd32c85b777b8ec6f8643cfab41446b180426) by @jwinarske actually works pretty well. I tested it on a bunch of rive files and interactions. The changes are also pretty...

I got success running riva on JP6 by upgrading ubuntu inside the riva-speech image. Something like this: ``` docker run --name riva_jp6 -ti nvcr.io/nvidia/riva/riva-speech:2.14.0-l4t-aarch64 bash # inside the docker container...

Great, thanks for confirming! We're still exploring, and will likely end up preferring low latency too. Unfortunately Llama-3-VILA1.5-8B didn't produce great results with our prompts, but llava-1.6 seems promising so...

Just in case it helps, the newer llama3-based lmms-lab/llama3-llava-next-8b (https://huggingface.co/lmms-lab/llama3-llava-next-8b) works out of the box — but you have to add `--chat-template=llama-3` (or set it programmatically; auto-detection doesn't work for...