Author: Tater Totterson

Ollama – v0.12.7-rc1

Hey AI tinkerers! 🚀

Ollama just dropped v0.12.7-rc1 — quiet release, big impact.

✅ Fixed `conv2d` bias calculation (PR #12834)

If you’re running vision models like LLaVA, Phi-Vision, YOLO, or ResNet locally — this patch ensures your convolutional layers calculate biases correctly. No more subtle accuracy drifts in image outputs.

No flashy new models or UI tweaks this time — just clean, reliable math under the hood. Perfect for devs who need stable inference with image-capable LLMs.

Pro tip: If you’re fine-tuning or deploying vision models via Ollama, upgrade now. Precision matters. 📸🧠

🔗 View Release

Ollama – v0.12.7-rc0

🚀 Ollama v0.12.7-rc0 just landed — and it’s a game-changer for local multimodal AI!

Say hello to Qwen3-VL — Alibaba’s powerful new vision-language model, now fully supported in Ollama. Run image + text understanding locally: analyze photos, scan docs, or ask “what’s in this picture?” — zero cloud required. 📸🧠

✨ Also new:

• Faster model loads on ARM64 (M-series Macs, Raspberry Pi 5)
• Smarter GPU memory — fewer OOM crashes with multi-image prompts
• CLI fixes on Windows: `ollama run` is now more stable

Grab it with:

`ollama run qwen3vl`

Still in RC — stable drop coming soon. Time to go offline with vision? ✅

🔗 View Release

ComfyUI – v0.3.67

🚀 ComfyUI v0.3.67 just dropped — and it’s a quiet powerhouse!

• New `LatentUpscale` node → Fine-tune upscaling with interpolation & sharpening controls. Say goodbye to bloated memory usage in high-res workflows.
• Negative prompt bleed FIXED → Finally, clean conditioning. No more sneaky negative prompts muddying your positives.
• WebUI snappier than ever → Dragging nodes in massive workflows? Smooth as butter now.
• SD3.5 Turbo support → Early access for custom node devs — ComfyUI’s ahead of the curve again.
• macOS PNG fix → No more corrupted metadata. Your exports are safe now. 🎉
• UI polish → Better labels, smarter tooltips, and a new `Ctrl+Shift+S` for Quick Save.

If you’re running SDXL or prepping for SD3 — this update is your new secret weapon. Update now and feel the difference! 🛠️✨

🔗 View Release

Tater – Tater v37

Tater v37 just turned your MiSTer into a voice-activated retro arcade 🎮✨

Say “play Super Mario 3 on SNES” — and Tater handles the rest:

• 🕹️ Finds your game (even with typos!) using fuzzy matching
• 🔍 Auto-detects the right MiSTer core from your setup
• 🚀 Launches it via MiSTer Remote (thanks, wizzomafizzo!)
• 📸 Captures clean screenshots + auto-formats captions for Discord, HA, IRC, WebUI — no junk, just perfect shares

New magic:

• 🎙️ Say “now_playing” → Tater cheers you on with the current game
• 🏠 “go_to_menu” → One command to return to MiSTer’s main menu
• 🧠 Smarter game indexing with synonyms — “Zelda” = “Legend of Zelda,” no stress

Setup? Drop `remote.sh` in `/media/fat/Scripts/`, set `MISTER_HOST:PORT`, and run the index script.

One voice command. A whole retro library awakened.

Go play something wonderful. 🕹️💛

🔗 View Release

Tater – Tater v36

Tater v36 just dropped—and it’s spud-tier genius 🥔🚀

Matrix support is LIVE: encrypted, federated, and fully synced with Element, Cinny & FluffyChat. E2EE? Check. Auto-avatar updates via Redis? Double check. Typing indicators, smart mentions, and perfect Markdown rendering (emojis included!)—all working flawlessly.

Plugins? Updated & unified: ComfyUI, web summaries, YouTube digests, SFTP monitors—they now run identically across Discord, IRC, WebUI, and Matrix. No more platform lock-in.

Logs are cleaner, SDK noise is gone, and your WebUI avatar auto-syncs to Matrix in real time.

TL;DR: Tater’s now the Swiss Army knife of the fediverse—private, powerful, and proudly decentralized.

Redis. Coffee. AI magic. 🤖☕

🔗 View Release

Perplexica – v1.11.2

Perplexica v1.11.2 just dropped—and it’s a bug-slaying masterpiece! 🎯

Transformer models? Now loading properly—no more cryptic “why isn’t this working?” panic.

Model selection? Actually updates the state now (goodbye, ghost selections 🕶️).

Empty messages? Eradicated. No more accidental blank sends derailing your flow.

Small patch, huge win for folks who just want AI search to work.

Built on SearxNG, supports Qwen, DeepSeek, Llama, Mistral—local or cloud.

Docker or direct install. API ready.

Your AI zen is restored. 🧠✨

Full changelog: [v1.11.1…v1.11.2]

🔗 View Release

Deep-Live-Cam – Version 2.3b now released

🚨 Deep-Live-Cam v2.3b just dropped—and it’s smooth as silk now!

🔥 New & Fixed:

• LogsFace — No more false positives. Clean, accurate face detection.
• Mouth Mask — Precision tracking that actually sticks to your lips, no more ghosting.
• FPS Counter — Real-time performance stats, now stable and useful (no more spikes or crashes).

⚡ Runs faster on CUDA, CoreML, DirectML & OpenVINO.

📦 Just run `deep-live-cam.bat`—no more setup headaches.

✨ Only available via QuickStart right now. Grab it before the link expires—this version is too good to wait. 🎥💥

🔗 View Release

Perplexica – v1.11.1

Perplexica v1.11.1 just dropped 🚀 — your open-source Perplexity alternative just got way smoother!

• No more hanging searches — SearxNG timeouts? Fixed. Queries now actually finish instead of ghosting you.
• Your go-to LLM (Qwen, DeepSeek, Llama, Mistral) remembers your pick — stored in localStorage. No more dropdown roulette on reload.
• Run commands? Your data now persists via volumes. Say hello to saved outputs, goodbye to “oh no, I lost my last run.”

Tiny release. Huge quality-of-life wins. Perfect for devs who just wanna search, not reconfigure. 🛠️✨

🔗 View Release

Text Generation Webui – v3.16

🚀 Text Generation WebUI v3.16 just dropped—and it’s a game-changer for local LLM folks!

New portable build via symlink? Yes, please. Devs juggling multiple setups can now switch models and configs without reinstalling. Big shoutout to @reksar! 🙌

macOS Apple Silicon users—your day is saved. Python deps now work flawlessly on Tahoe (thanks @drieschel)! 🍎

Backend upgrades? Oh yeah:

• llama.cpp updated to latest GGML fork → now supports Llama-Mini-2.0 and Ring-Mini-2.0! Tiny but mighty models, unlocked.
• ExLlamaV3 v0.0.11 = faster inference, smoother text flow.
• Triton-Windows updated to 3.5.0.post21 → better CUDA perf on Windows rigs.

Portable builds are now even easier:

📥 Download → 📦 Unzip → 💾 Copy your old `user_data` folder in → ✅ All models, themes, and settings preserved. No pip. No venvs. Just AI magic.

Pick your build:

• NVIDIA? → `cuda12.4` (new) or `cuda11.7` (legacy)
• AMD/Intel? → Use `vulkan`
• CPU-only? → `cpu` build
• Mac? → `macos-arm64` (M-series) or `macos-x86_64`

No install. No fuss. Just drop-in, run, and chat with your LLMs like never before. 🚀

🔗 View Release

Wyoming Openai – Streaming hotfix and Chatterbox TTS release (0.3.8)

🎙️ Wyoming OpenAI 0.3.8 is live—and TTS streaming just got a serious upgrade!

Say goodbye to stilted audio pauses. The new smart TTS streaming uses pySBD to chunk text at sentence boundaries, then prefetches the next line while playing the current one—so even if OpenAI stumbles, your voice assistant keeps flowing.

🚀 Highlights:

• 🚀 Parallel prefetching: Up to 3 TTS requests running at once, sequenced perfectly.
• 🐳 Chatterbox TTS support: Drop-in Docker compose for self-hosted neural voices—with voice cloning!
• 🛡️ Robust error handling: New `TtsStreamError` + `_abort_synthesis` to kill broken streams and stop audio doubles.
• 📦 Install via `pip install wyoming-openai`—no git needed.
• 🔧 Updated deps: `openai==2.3.0`, `wyoming==1.8.0` for full compatibility.

Perfect for Home Assistant users who want smooth, low-latency voice—whether on cloud APIs or local models like Piper, Kokoro, or Edge TTS.

No more buffering. Just natural, uninterrupted speech. 🎧✨

Check the docs and start streaming!

🔗 View Release