soon... 🤖🧠⚡️🚀🏙️🔥🏃‍♀️😱☠️🔚

I'm having a great time with GPT5.6 so far. I'm still not sure what it's for, but I feel very safe.

keepandroidopen.org/cta/ The *only* reason I have been using Android for the last 8 years is the fact that I have control of my device, I can hack on it and write software for it and sideload it without begging anyone for the privilege. As soon as Google's "Close Android" initiative goes into effect, I will buy an iPhone and I won't develop on Android again. @Google - Don't do this. Turn around. Cancel. Change your mind. Realize that you just made a stupid mistake after one too many beers, and you didn't actually mean it. And you are sorry for the confusion and chaos. Then this will just be a bad memory that fades away - instead of the permanent destruction you are about to inflict to your own platform, and millions of customers. And the major boon you are about to hand to Apple.

1/n I topped the HuggingFace Open LLM Leaderboard without changing a single weight. No training. No merging. No gradient descent. I duplicated 7 middle layers of Qwen2-72B and stitched it back together. This is the story of LLM Neuroanatomy 🧵

We just added Tensor Parallelism to TabbyAPI! Huge thanks to @turboderp_ and testers who made this possible. Now, enjoy the clip diving into the origins of Exllama. Wanna see TabbyAPI built live? Follow me on twitch: kingbri1st

1000 stars on tabbyAPI. Holy crap. Huge thanks to @turboderp and everyone who contributed!

TabbyAPI now supports ExllamaV3 with automatic backend detection! 🎉 Please note that exl3 is being actively worked on and mileage may vary compared to exl2 Thanks to @turboderp_ and all contributors for making this a reality.

I have decided to tweet today. So here is a visualization of how the paged cache works with continuous batching in ExLlamaV3. I think it's neat. #🐈

Seems to still be true that larger models are less sensitive to quantization. Here is Mistral-Large 123B at 1.4 bits per weight, running on one 24 GB GPU. #AI or something

\____

I made a thing. github.com/turboderp-org/exl…

CUDA builds character 😭

Supply chain alert! Don't use the comfyUI Impact pack! Its dependency ultralytics has been compromised on pypi. Thanks Shinon for letting me know in Discord. github.com/ultralytics/ultra…

Fun with grounding in Qwen2-VL. Finding the things. #wherearethethings #exllamav2 #cat

TabbyAPI now supports vision. Thanks to @turboderp_ for exllamav2's updates and DocShotgun for the initial work. Any Exl2 supported vision model works, but this release focuses on Pixtral from @MistralAI

1 year ago, I made TabbyAPI with @turboderp_ as a side project. Now, it's my most popular side project. I wanted to break away from the bloated nature of AIO local model backends and just run #exllama. Thanks to all the contributors and testers. github.com/theroyallab/tabby…

I performed a successful vocabulary transplant on Qwen2-0.5B and turned it into a useful draft model for Llama-3. What a time to be alive. #hashtag huggingface.co/turboderp/Qwa…