Ollama – v0.12.10-rc1

🚀 Ollama v0.12.10-rc1 just dropped — and it’s all about trust, not flash!

🔒 Code signing is back on macOS & Windows — your downloads are now cryptographically verified, so you know it’s really Ollama, not a sneaky imposter.

Perfect for enterprises, devs in locked-down environments, or anyone who hates “this file is untrusted” warnings.

No new models. No UI tweaks. Just clean, quiet hardening — because security shouldn’t be an afterthought.

💡 Pro tip: If you script installs or deploy via CI/CD, your checksums and signature checks are back in action.

Keep it local. Keep it safe. 🛡️

🔗 View Release

Wyoming Openai – Maintenance release (0.3.9)

🚀 Wyoming OpenAI v0.3.9 is live — lean, mean, and ARM-ready!

🔧 CLI & Env Fixes: Now accepts real option names (no more internal ID confusion), and `STT_BACKEND`/`TTS_BACKEND` are case-insensitive. Typos? Clearer errors now!

🍎 ARM64 Support: Docker images built for Raspberry Pi, M1/M2 Macs — no more emulation. Just `docker pull` and go!

📦 Deps Upgraded: OpenAI v2.7.1, Ruff, pytest — faster, stabler, future-proofed.

⚙️ Build Pipeline Upgraded: GitHub Actions now use `build-push-action@v6` with QEMU + Buildx for seamless multi-arch builds.

📖 Docs updated to v0.3.9 — no more outdated examples!

7 files changed, +162/-17 lines. Zero fluff. Pure utility.

Install via `pip install wyoming-openai` or pull the new Docker image — your Pi (or M2 Mac) will thank you. 🐧🍎

🔗 View Release

ComfyUI – v0.3.68

ComfyUI v0.3.68 is live — quiet updates, massive stability wins! 🛠️✨

• Fixed a nasty crash when custom nodes had missing deps — no more sudden workflow deaths.
• Node loading now more resilient: one misbehaving node won’t bring down your whole pipeline.
• Smoother UI: tooltips landed in the right place, canvas renders faster even on massive setups.
• Under-the-hood dependency updates to squash security alerts — clean, quiet, and secure.

If you run custom nodes or heavy workflows? Update now. The best releases are the ones that just… work. 😌

🔗 View Release

Ollama – v0.12.9

💥 Ollama v0.12.9-rc0 just dropped — and it’s a GAME CHANGER for CPU-only users!

No more sluggish LLM inference on your old laptop or cloud instances. This update slays the performance regression that’s been holding back CPU-based runs.

✅ Snappier responses

✅ Smoother local workflows

✅ Full GGUF + Llama 3, DeepSeek-R1, Phi-4, Mistral support intact

Perfect for devs prototyping on bare metal or running lightweight models without a GPU. No flashy features — just pure, quiet speed gains. 🚀

Check the changelog — this one’s a hero update you’ll feel in every token.

🔗 View Release

Ollama – v0.12.9-rc0: ggml: Avoid cudaMemsetAsync during memory fitting

🚀 Ollama v0.12.9-rc0 just dropped — and it’s a quiet hero for GPU warriors!

The secret sauce? `ggml` now skips `cudaMemsetAsync` during memory fitting when it hits invalid pointers.

💡 Why it rocks:

• No more crashes when checking if your 70B model fits on a 24GB GPU
• Smoother `op_offload` workflows — no more CUDA tantrums during sizing checks
• Faster, more stable memory estimation under pressure

Think of it like silencing a false alarm before you pack your suitcase — no noise, just better packing.

Perfect for folks running Llama 3, DeepSeek-R1, or Mistral on edge GPUs. No reinstall needed — just update and let Ollama handle the heavy lifting. 🤖⚡

🔗 View Release

Ollama – v0.12.8: win: avoid ID mixups on refresh (#12869)

Ollama v0.12.8 just dropped—and Windows AMD GPU users, this is your win! 🎯

The fix? No more sneaky GPU ID mixups. On Windows, AMD’s device IDs would shuffle during refreshes, causing Ollama to accidentally pick your integrated iGPU instead of your powerful RX/RTX card. 😱

Now? Ollama respects GPU filters, ignores unsupported iGPUs entirely, and gives your discrete GPU the spotlight it deserves.

✅ No more misattributed VRAM

✅ Clean, accurate GPU detection on AMD Windows rigs

✅ Inference finally runs where it should—on your real GPU

Update now and stop letting your laptop’s integrated graphics do all the work. 🚀

🔗 View Release

Ollama – v0.12.8-rc0: win: avoid ID mixups on refresh (#12869)

🚀 Ollama v0.12.8-rc0 just dropped — and Windows AMD users, this one’s for YOU!

If you’ve been battling “out of memory” errors or weird VRAM stats after a driver update or display change, you’re not alone. Ollama now filters out integrated GPUs during device detection, so it stops misassigning your dGPU’s VRAM to your iGPU. 💥

✅ What’s new?

• Windows-only fix: Stops GPU ID shuffle chaos on AMD systems
• Ignores iGPUs — only your real Radeon/Ryzen GPU gets the workload
• No more mystery crashes. Just clean, stable LLM inference.

Perfect for Ryzen + Radeon folks running Llama 3 or DeepSeek-R1 locally. Upgrade now — your VRAM will thank you. 🛠️

🔗 View Release

Ollama – v0.12.7: int: harden server lifecycle (#12835)

🚀 Ollama v0.12.7 just dropped — and it’s the quiet hero your dev environment didn’t know it needed.

This patch (#12835) locks down the server lifecycle like a vault:

• 🚫 No more zombie `ollama` processes haunting your RAM after shutdowns
• 💥 Cleaner exits when the server crashes or gets killed
• 🧹 Smarter resource cleanup on Linux, macOS, and Windows

Perfect for CI/CD pipelines, automated tests, or anyone who’s ever stared at Task Manager wondering why Ollama won’t die.

No flashy new models… just rock-solid infrastructure that works when it matters most.

Your 2am deploy will thank you. 🛡️💻

🔗 View Release

Lemonade – v8.2.0

🚀 Lemonade v8.2.0 just dropped — and it’s a massive leap for local LLM lovers!

✅ Ryzen AI SW 1.6 support — Run Qwen3 with 4K prompts using hybrid NPU/GPU magic on AMD Ryzen. Faster inference, lower power, zero cloud dependency. 💥

📥 Load ANY model — Hugging Face? Local folder? Drag & drop it in. No more conversion headaches. Just point and run.

✨ UI got a glow-up:

• Upload models directly from the web interface — no CLI required!
• Smoother, smarter polling = fewer annoying refreshes
• Suggested=false models? Gone. Clean recommendations only.
• RAI/FLM models auto-hide on unsupported OSes — no more confusion
• Linux? Fallbacks now work even if FLM isn’t installed

🔧 Under the hood:

• macOS port conflicts? Fixed. 🍎
• CI/CD actually works now (no more silent crashes!)
• Docs updated with Dify & Copilot integrations 📚
• New Log Filter Extension for crystal-clear debugging 🔍

Big shoutout to first-time contributors @HyunhoAhn and @meghsat — welcome to the crew! 👏

Upgrade. Tinker. Crush your next local LLM benchmark.

🔗 Full changelog: v8.1.12…v8.2.0

🔗 View Release

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