ᕈablo ᑕarrera (パブロ)

🐧 🦀🐍

[ᕈablo ᑕarrera (パブロ) @prce__]

@ggerganov You made possible

[ᕈablo ᑕarrera (パブロ) @prce__]

@adaption_ai @sarahookr 🫶

[ᕈablo ᑕarrera (パブロ) @prce__]

@sarahookr Me please

[Sara Hooker @sarahookr]

You get a gpu. And….. You get a gpu.

One of the biggest barriers to frontier AI is compute and know-how.

This month we remove both as obstacles. Computes on us. AutoScientist is on your side.

Join our beta program now.

[Georgi Gerganov @ggerganov]

llama.cpp now has an official website: https://t.co/vztdUpdBWL

Our goal is to make local AI accessible to everyone, and improving the user experience is a big part of that. On the new landing page you’ll find a single-line cross-platform installer. The installation provides a single unified `llama` entrypoint which you can use to run/serve models and interface with 3rd-party agentic applications.

While oriented towards simplified user experience, the new `llama` application also provides all the advanced functionality of the existing llama.cpp tooling with which experienced users are already familiar. Also note that all GGUF models that you might have already downloaded with llama.cpp in the past will be automatically available to use without downloading again (they are stored in the common HF cache on your machine).

We have many improvements in the pipeline both at the UX and at the engine level and we plan to iteratively ship new things over the coming months. One of the main focuses will be seamless integration with local-friendly 3rd-party agents (such as Pi). In the meantime, we’ll continue to listen for feedback from the community and adjust accordingly, so keep letting us know what you think and need.

[ᕈablo ᑕarrera (パブロ) @prce__]

@mirrash7 @typesfast If this is posible I want to be in the whitelist even is not open source. What amazing job sir

[mirrash.eth 🦇🔊 @mirrash7]

Adapted my tennis AI pipeline for pickleball 🎾

-Audio based shot detection
-Top down court visualization
-Shot attribution
-Ball + player + pose tracking (RF-DETR + ViTPose)

[ᕈablo ᑕarrera (パブロ) @prce__]

@ggerganov Huge

[Georgi Gerganov @ggerganov]

llama.cpp adds MTP for the Qwen3.6 family

This is a significant milestone for the local AI ecosystem. The performance jump with these changes is massive and elevates local inference on commodity hardware further.

Special thanks to Aman Gupta for leading this development!

https://t.co/vjaMwEpIaR

[ᕈablo ᑕarrera (パブロ) @prce__]

@sarahookr Ricky Martin was the real deal!

[ᕈablo ᑕarrera (パブロ) @prce__]

@ClementDelangue Great article! I need to buy 4090 or 3090

[ᕈablo ᑕarrera (パブロ) @prce__]

@Newegg When the machine get heat the experience got frozen

[ᕈablo ᑕarrera (パブロ) @prce__]

@ngxson @huggingface @ggml_org @julien_c I want this friends!

[ᕈablo ᑕarrera (パブロ) @prce__]

Ha sido un día agitado me estoy muriendo de sed.
En la esquina vagancia tiene algo para beber.
Me dice que está mezcladito, agua de coco será?
Pero me pegó tan duro, debe tener algo más.

[ᕈablo ᑕarrera (パブロ) @prce__]

@letsgetrusty Good topic this look like Linux distros you have your own favorite no complains on the drama around

[ᕈablo ᑕarrera (パブロ) @prce__]

@sinovoip This look awesome are we talking 10gb of bandwidth on this Ethernet and fiber ports for q home firewall ?

[ᕈablo ᑕarrera (パブロ) @prce__]

@rustjobs_dev Me I’m from Ecuador can I apply?

[ᕈablo ᑕarrera (パブロ) @prce__]

@skdh Red and pretty

[ᕈablo ᑕarrera (パブロ) @prce__]

@soumithchintala Selfhost forgejo for the home bois. I need a better cpu for my actions workload but tomato potato

[ᕈablo ᑕarrera (パブロ) @prce__]

@ThePrimeagen Ma homie