Lightnews — Scholar-powered news

Reposted by deadprogram

The Hybrid Group

@hybridgroup.com

yzma 1.0 beta 3 is out!

Write Go applications that directly integrate llama.cpp for hardware accelerated local inference.

- new installation CLI
- Jinja chat templates
- new llama.cpp download binary formats
- more benchmarks

Go get it right now!

github.com/hybridgroup/...

#golang #llama

Release 1.0.0-beta.3 · hybridgroup/yzma

What's Changed feature: use runtime.GOARCH for download to support arm64 on Linux/Windows by @deadprogram in #111 feature: add download location for llama.cpp prebuilt binaries for Linux arm64 Vul...

github.com

December 2, 2025 at 2:30 PM

Reposted by deadprogram

Philippe Charrière 💜

@k33gorg.bsky.social

🚀 Just published: Getting started with Kronk
Updated with Kronk v0.25.0
new URL:
k33g.hashnode.dev/baby-steps-w...

December 1, 2025 at 6:29 AM

Reposted by deadprogram

Philippe Charrière 💜

@k33gorg.bsky.social

🚀 New blog post: Baby steps with Kronk!

Kronk (created by @goinggo.net ) provides a high-level API on top of Yzma (by @deadprogram.com) to build GenAI applications in Go with local model inference - no external dependencies needed.

Read more: k33g.hashnode.dev/baby-steps-w...

#Golang #AI #GenAI

k33g.hashnode.dev

November 30, 2025 at 7:25 AM

Reposted by deadprogram

TinyGo

@tinygo.org

Thinking about @fosdem.org in Jan/Feb in Brussels? Do it!
Visit the TinyGo stand & go give a TinyGo talk:
github.com/go-devroom/cfp
lists.fosdem.org/pipermail/fo...
robotics-devroom.github.io/cfp/fosdem26
discourse.llvm.org/t/cfp-fosdem...
lists.fosdem.org/pipermail/fo...
Deadline tomorrow!

GitHub - go-devroom/cfp: Go Devroom CfP — FOSDEM 2026

Go Devroom CfP — FOSDEM 2026. Contribute to go-devroom/cfp development by creating an account on GitHub.

github.com

November 29, 2025 at 12:30 PM

Reposted by deadprogram

Philippe Charrière 💜

@k33gorg.bsky.social

🎉 Yzma now works on NVIDIA Jetson Orin Nano!

Today, thanks to Ron Evans (@deadprogram.com), I'm running local LLM models with hardware acceleration directly on the Jetson!

Your first Yzma program on Jetson: k33g.hashnode.dev/installing-a...

My weekend is going to be busy 🤓

k33g.hashnode.dev

November 28, 2025 at 8:48 AM

Reposted by deadprogram

Go Devroom @ FOSDEM

@godevroom.fosstodon.org.ap.brid.gy

You like Gophers? They might be your front row audience for your Go talk this February!?

Just don’t miss our CfP deadline which is this Sunday! https://github.com/go-devroom/cfp

Have a Go topic to talk about? Yea? Apply! No? :boost_requested:

November 24, 2025 at 8:29 PM

Reposted by deadprogram

The Hybrid Group

@hybridgroup.com

We're moving at the speed of thought, so yzma v1.0 beta2 is out!

Better, faster, and more benchmarks to show it too.

Run local models using Go with your CPU, CUDA, or Vulkan.

You know what to do!

github.com/hybridgroup/...

#golang #llama #llamacpp

GitHub - hybridgroup/yzma: Go for hardware accelerated local inference with llama.cpp directly integrated into your applications

Go for hardware accelerated local inference with llama.cpp directly integrated into your applications - hybridgroup/yzma

github.com

November 24, 2025 at 2:51 PM

Reposted by deadprogram

The Hybrid Group

@hybridgroup.com

yzma 1.0 beta1 is out!

Use Go for hardware accelerated local inference with llama.cpp directly integrated into your applications. No external model servers or CGo.

Go get it right now!

github.com/hybridgroup/...

#golang #llama #vlm #llm #local #gpu

GitHub - hybridgroup/yzma: Go for hardware accelerated local inference with llama.cpp directly integrated into your applications

Go for hardware accelerated local inference with llama.cpp directly integrated into your applications - hybridgroup/yzma

github.com

November 20, 2025 at 9:14 PM

Reposted by deadprogram

Chewxy

@bsky.chewxy.com

In tonight's #golangsyd, we have @intermer.net on Sense and Sensibility Writing a Hardware Sensor Driver in #tinygo #golang

November 20, 2025 at 7:54 AM

Reposted by deadprogram

William (Bill) Kennedy

@goinggo.net

Thanks to @deadprogram.com and his Yzma project, you don't need to deploy model servers anymore, you can run GGUF models directly in your #golang code.

I have cool examples, including a full RAG app using DuckDB. I will have more complex examples soon.

github.com/ardanlabs/ai...

ai-training/cmd/examples/example13 at main · ardanlabs/ai-training

Provide examples for Go developers to use AI in their products - ardanlabs/ai-training

github.com

November 16, 2025 at 3:36 PM

Reposted by deadprogram

takasago

@sago35tk.bsky.social

TinyGo Keeb Tour 2026 in Toyama を公開しました！
2026 年の初回は 2026/01/09 に開催します。今回は BuriKaigi 内で開催となっていて、富山国際会議場というすごい場所ではんだ付けを行います。是非遊びに来てください。
tinygo-keeb.connpass.com/event/375651/
#tinygo_keeb

TinyGo Keeb Tour 2026 in Toyama (2026/01/09 13:00〜)

## イベント申込み方法このイベントは BuriKaigi の connpass ページで参加募集する予定です。 (まだ募集墓石されていません) ## イベントの説明 TinyGo と自作キーボードをかけ合わせた楽しいハンズオン全国ツアーを開催しています。...

tinygo-keeb.connpass.com

November 15, 2025 at 8:54 AM

Reposted by deadprogram

Hourly Cosmos

@hourlycosmos.bsky.social

Hubble Checks out a Home for Old Stars - From Goddard Space Flight Center - https://flic.kr/p/BQwDW2

This image, taken with the Wide Field Planetary Camera 2 on board the NASA/ESA Hubble Space Telescope, shows the globular cluster Terzan 1. Lying around 20,000 light-years from us in the constellation of Scorpius (The Scorpion), it is one of about 150 globular clusters belonging to our galaxy, the Milky Way.

Typical globular clusters are collections of around a hundred thousand stars, held together by their mutual gravitational attraction in a spherical shape a few hundred light-years across. It is thought that every galaxy has a population of globular clusters. Some, like the Milky Way, have a few hundred, while giant elliptical galaxies can have several thousand.

They contain some of the oldest stars in a galaxy, hence the reddish colors of the stars in this image — the bright blue ones are foreground stars, not part of the cluster. The ages of the stars in the globular cluster tell us that they were formed during the early stages of galaxy formation! Studying them can also help us to understand how galaxies formed.

Terzan 1, like many globular clusters, is a source of X-rays. It is likely that these X-rays come from binary star systems that contain a dense neutron star and a normal star. The neutron star drags material from the companion star, causing a burst of X-ray emission. The system then enters a quiescent phase in which the neutron star cools, giving off X-ray emission with different characteristics, before enough material from the companion builds up to trigg...

November 14, 2025 at 11:00 AM

Reposted by deadprogram

takasago

@sago35tk.bsky.social

#BuriKaigi 2026 内で開催する TinyGo Keeb Tour (はんだ付け + ソフトなワークショップ) で使う zero-kb02 を準備していってる。みんな、はんだ付けしにきてね！今は TinyGo のファームウェアしかないけど、 Vial とか zmk とか prk でファームウェア書いてくれる人も募集中です。
#tinygo_keeb

November 14, 2025 at 12:21 AM

Reposted by deadprogram

takasago

@sago35tk.bsky.social

新刊 TinyGo Keebook vol.2 も準備できました。私も技術書典19オフライン会場にて売り子していますので、ぜひ握手しに来てください。
#技術書典 #技術書典19 #tinygo_keeb
techbookfest.org/product/cXBQ...

TinyGo Keebook vol.2 - TinyGo x 自作キーボード応用ガイド：TinyGo Keeb

本書「TinyGo Keebook vol.2」は、自作キーボード(Keeb) とTinyGo を組み合わせたイベント「TinyGo Keeb Tour」から生まれました。「TinyGo Keeb Tour」は、はんだ付けとTinyGo によるファームウェア開発という組み合わせで行われています。 TinyGo は、小型マイコンに向けて最適化されたGo の実装です。これにより、従来C…

techbookfest.org

November 13, 2025 at 12:40 AM

deadprogram

@deadprogram.com

"Captions With Attitude" in your browser from your webcam generated by a Vision Language Model (VLM) from a Go program running entirely on your local machine using llama.cpp!

github.com/hybridgroup/...

#golang #vlm #openCV #llama #yzma

November 11, 2025 at 8:24 PM

Reposted by deadprogram

takasago

@sago35tk.bsky.social

2025/10/12 TinyGo Conference 2025 in JAPAN
#tinygo_conf
Hardware fun with Tinygo: Games & Toys by Daniel Esteban
youtu.be/vKVtYqJq34A

Hardware fun with Tinygo: Games & Toys (Daniel Esteban) - 2025/10/12 TinyGo Conference 2025 in JAPAN

https://conf.tinygo-keeb.org/2025/ 資料 https://talks.madriguera.me/2025/tinygoconf.slide

youtu.be

November 9, 2025 at 10:39 AM

Reposted by deadprogram

takasago

@sago35tk.bsky.social

2025/10/12 TinyGo Conference 2025 in JAPAN
#tinygo_conf
TinyGo でも GraphQL サーバをビルドしたい！ by N9tE9
youtu.be/PV3LzbbYW_Y

TinyGo でも GraphQL サーバをビルドしたい！ (N9tE9) - 2025/10/12 TinyGo Conference 2025 in JAPAN

https://conf.tinygo-keeb.org/2025/ 資料 https://docs.google.com/presentation/d/1dFw3XIImpGvtz1dywpIDixxnlCRx6Zr9_-_IkzX2GFs/edit?usp=sharing

youtu.be

November 8, 2025 at 11:06 AM

Reposted by deadprogram

The Hybrid Group

@hybridgroup.com

Life's comes at you fast, and so do new releases of yzma!

Use pure Go for hardware accelerated local inference on Vision Language Models & Tiny Language Models.

0.9.0 out now with API improvements, model downloading, & more.

github.com/hybridgroup/...

#golang #llama #vlm #tlm

GitHub - hybridgroup/yzma: yzma lets you use Go for local inference+embedding with Vision Language Models (VLMs) and Large Language Models (LLMs) using llama.cpp without CGo.

yzma lets you use Go for local inference+embedding with Vision Language Models (VLMs) and Large Language Models (LLMs) using llama.cpp without CGo. - hybridgroup/yzma

github.com

November 7, 2025 at 4:59 PM

Reposted by deadprogram

takasago

@sago35tk.bsky.social

2025/10/12 TinyGo Conference 2025 in JAPAN
#tinygo_conf
TinyGo & TinyGo Keeb & … by @sago35tk.bsky.social
youtu.be/KOsydL4aMYA

TinyGo & TinyGo Keeb & … - 2025/10/12 TinyGo Conference 2025 in JAPAN

https://conf.tinygo-keeb.org/2025/ 資料 https://docs.google.com/presentation/d/11-TDgra3NH-n2KYYAgSYV87ANywnY1lcGacZvMSIjGc/edit?usp=sharing

youtu.be

November 6, 2025 at 1:45 PM

Reposted by deadprogram

squillace

@squillace.bsky.social

if you are into #webassembly in the EU, there is an embarrassment of riches, but @wasm.io just announced the CFP for this spring!!!!

www.papercall.io/wasmio26

PaperCall.io - Wasm I/O 2026

Wasm I/O 2026 brings together the global WebAssembly community for two inspiring days in Barcelona, Spain on March 19–20. Join us to explore the future of WebAssembly, share ideas, and help grow a wel...

www.papercall.io

November 6, 2025 at 3:31 PM

Reposted by deadprogram

Ardan Labs

@ardanlabs.com

Gophers, 1-hour countdown for stream #60! 😎
Join @goinggo.net & @kenriquezcodes.bsky.social with special guest @deadprogram.com as they go live at 11 am EST!

📽️ Today's stream link: youtube.com/live/eiI9yiY...

#golang #Livestream #SoftwareDesign

Ultimate Go Software Design LIVE: Ron Evans Ep.60

YouTube video by Ardan Labs

youtube.com

November 4, 2025 at 3:00 PM

Reposted by deadprogram

Ardan Labs

@ardanlabs.com

Ult. Software Design LIVE Schedule

Join @goinggo.net & @kenriquezcodes.bsky.social in this week's streams:
Tue. 11/4 & Thu.11/6 from 11am - 1pm EST

Tomorrow we'll have a special guest: @deadprogram.com

Stay tuned 1hr before the LIVE show for the stream link!😎
📽️Last episodes here: bit.ly/3CShDOS

November 3, 2025 at 8:31 PM

Reposted by deadprogram

The Hybrid Group

@hybridgroup.com

yzma 0.8.0 is out, now with over 87% coverage of the llama.cpp API from pure Go! More robust, more examples.

Go get it right now!

github.com/hybridgroup/...

#golang #llamacpp #vlm #slm #tlm

GitHub - hybridgroup/yzma: yzma lets you use Go for local inference+embedding with Vision Language Models (VLMs) and Large Language Models (LLMs) using llama.cpp without CGo.

yzma lets you use Go for local inference+embedding with Vision Language Models (VLMs) and Large Language Models (LLMs) using llama.cpp without CGo. - hybridgroup/yzma

github.com

November 3, 2025 at 10:38 AM

Reposted by deadprogram

Go Devroom @ FOSDEM

@godevroom.fosstodon.org.ap.brid.gy

Hello Gophers!

You might have seen it :gopher:
You might see just it now :ac_amazed:

Our CFP for FOSDEM 2026 is now OPEN

https://github.com/go-devroom/cfp

Want to help us out? Send in a talk :masto_wink: Want to help us out even more? :boost_requested: