Home Assistant Voice Pe – 25.12.3

🚀 Home Assistant Voice PE just dropped v25.12.3 — and it’s a quiet hero for ESPHome tinkerers!

Fixed that nasty `web_server` conflict where custom firmwares would crash when web UI and voice logic fought for resources. No more 502s. No more unresponsive dashboards.

If you’re running DIY voice control on ESP32/ESP8266 with Home Assistant — this patch is your new best friend.

Sponsored by the Open Home Foundation 🌱 (78 releases and counting!)

Upgrade now → 25.12.1…25.12.3

🔗 View Release

ComfyUI – v0.6.0

ComfyUI v0.6.0 just landed — and it’s like giving your AI workflow a turbo boost 🚀

• Native WebSockets → Real-time node updates & buttery-smooth previews (yes, even on mobile!)
• Custom Node Manager → Install & update nodes right in the UI. No more terminal chaos 🧩
• Memory Cleanup Overhaul → Big models? Longer sessions? Less crashes. Goodbye, OOM errors.
• Queue Inspector → See what’s running, pause or cancel jobs mid-process — total control.
• Dark Mode 2.0 → Sleeker, higher contrast, optional accent colors for your aesthetic 🖤
• Python 3.10+ only → Faster, leaner, modern under the hood
• Windows users: One-click installer is LIVE 🎉

Still 100% free. Still open-source. Still built by you.

Back up your workflows before upgrading — custom nodes are about to get a whole lot easier.

Grab it → https://www.comfy.org/

🔗 View Release

Home Assistant Voice Pe – 25.12.2

Big win for offline voice control! 🎤🏠

Home Assistant Voice PE just dropped v25.12.2 — and it’s got some serious upgrades.

🎧 Sendspin multi-room audio is now in public preview — sync your speakers across rooms without touching the cloud. Perfect if you’re already using Music Assistant.

🎉 Huge shoutout to @theHacker for their first-ever contribution — welcome to the crew!

Sponsored by the Open Home Foundation, with 78 releases under its belt — this thing is built to last.

More polish. Smoother sync. Zero internet needed.

Full details: [25.11.0…25.12.2]

🔗 View Release

Home Assistant Voice Pe – 25.12.1

Home Assistant Voice PE just dropped v25.12.1 🚀

Big win: Now sponsored by the Open Home Foundation—more power to offline voice control! 🏠🎙️

78 releases and counting, and this one’s smooth as butter.

New in 25.12.1:

• Full Sendspin multi-room audio protocol support (public preview)! Sync music across speakers like a pro—no cloud needed.
• Huge thanks to @theHacker for their first-ever contribution! 🙌

Perfect for tinkerers who want voice control without the internet. Upgrade, vibe out, and command your home like a wizard.

Changelog: [25.11.0…25.12.1]

🔗 View Release

Text Generation Webui – v3.22

🚀 text-generation-webui v3.22 is live!

llama.cpp just got a MASSIVE upgrade — now with portable, drop-and-run builds for EVERYONE:

• 🖥️ Windows/Linux:
• NVIDIA? `cuda12.4` = blistering speed
• AMD/Intel GPU? Grab the `vulkan` build — no CUDA required!
• Just CPU? Yep, `cpubuilds` work flawlessly.

• 🍎 Mac (Apple Silicon):
• `macos-arm64` = native performance, zero installs.

✨ Upgrade tip: Just unzip the new version → copy your old `user_data` folder over.

Your models, themes, settings — all preserved. No reconfiguring. No headaches.

Perfect for offline labs, travel, or when you just wanna run LLMs without installing 17 dependencies.

Go grab it — your local AI sandbox just got way more portable. 🎯

🔗 View Release

MLX-LM – v0.30.0

MLX LM v0.30.0 is live 🚀 — Apple Silicon LLMs just got a serious power-up!

• Server performance fixed: No more busy-waiting — idle polling is now lean, quiet, and efficient. 🛠️
• Transformers v5 fully supported: All the latest tokenizer tweaks, model updates, and Hugging Face magic? Covered. 🤖
• MIMO v2 Flash enabled: Multi-input models now fly with optimized attention — faster inference, less latency. ⚡
• Better error messages: Batching failed? Now you’ll know why — no more cryptic crashes. 📢
• Model parallel generation: Split massive models across GPUs like a pro. Scale your LLMs without rewriting code. 🧩
• Chat template fixes: `apply_chat_template` finally wraps correctly — no more dict chaos in your prompts. ✨

Thousands of Hugging Face models, quantized, fine-tuned, and served — all on your M-series chip. Time to upgrade and push your AI stack further. 🚀

🔗 View Release

Ollama – v0.13.5

🚀 Ollama v0.13.5 just dropped — and it’s a quiet game-changer for Gemma users!

Now you can use function calling with Gemma 2B locally — yes, really. Trigger webhooks, query databases, fetch weather, or call APIs directly from your tiny-but-mighty local Gemma model. No cloud needed.

💡 Why it’s cool:

• Function calling was already in Llama 3 & Mistral — now Gemma joins the party.
• Perfect for building private, lightweight AI agents that do stuff, not just chat.

Under the hood: parser fixes + smoother rendering = fewer hiccups, more flow.

Upgrade in one line:

“`bash

ollama pull gemma:2b

“`

Go build something that acts — not just responds. 🎯

🔗 View Release

Ollama – v0.13.5-rc1

🚀 Ollama v0.13.5-rc1 just dropped — and it’s a game-changer for Gemma users!

Now you can use function calling with Gemma 2B 🎯

Gemma can now dynamically invoke external tools and APIs — think real-time data lookup, code execution, or API calls — all triggered by natural language. No more clunky workarounds. Just define your tools, and let Gemma call them like a pro agent.

Plus:

• Smoother JSON parsing for tool definitions (no more malformed calls!)
• Minor performance boosts and bug fixes
• RC1 = stable enough for early adopters to test in real workflows

Grab it: `ollama pull gemma:2b` and start building smarter, reactive agents today.

Full release notes coming soon — but this feature? Totally worth the upgrade. 🛠️

🔗 View Release

ComfyUI – v0.5.1

ComfyUI v0.5.1 just dropped — and it’s a quiet hero 🛠️

Fixed critical crashes in custom nodes & image loading (no more mid-generate soul-crushes).

Memory management got a serious upgrade — smoother runs on weaker GPUs, even with massive workflows.

Error messages now actually tell you what went wrong… no more “something broke” mysteries.

UI feels slicker: cleaner node links, buttery drag-and-drop.

And hey — partial WebGPU support for Apple Silicon users is now live 🍎⚡ (Big things coming in v0.6!)

If you’ve been battling crashes or lag, this is your sign to update. Keep building! 🚀

🔗 View Release

Ollama – v0.13.5-rc0: GGML update to ec98e2002 (#13451)

Ollama v0.13.5-rc0 just dropped — and it’s all about speed under the hood! 🚀

The GGML inference engine got a major upgrade to commit `ec98e2002`, with smarter, leaner internals:

• ✅ MaskBatchPadding removed — Less padding = less overhead. KQ masking is now cleaner and faster.
• 🚫 NVIDIA Nemotron 3 Nano support paused — Temporarily pulled for stability. Coming back stronger soon!
• 🔧 Solar Pro tweaks — Under-the-hood adjustments, still being verified. If you’re using Solar, test your models!

No flashy UI — just a lighter, faster engine for local LLM inference. Think of it like swapping your car’s engine for a turbocharged version that runs cooler.

Pro tip: Custom models? Run sanity checks — GGML changes can ripple through quantization and attention layers.

Stay sharp, tinkerers. The local LLM revolution keeps accelerating. 🛠️

🔗 View Release