Ollama – v0.15.5-rc3: qwen3next: fix issue in delta net (#14075)

Ollama v0.15.5‑rc3 – qwen3next: fix issue in delta net 🚀

A quick bug‑fix drop for anyone running Qwen 3 locally.

What’s new?

• Delta‑net axis fix: The `gDiffExp` tensor was being broadcast on the wrong dimension, causing gradient glitches during token prediction. The patch reshapes it to `[1, chunkSize, nChunks, …]`, restoring correct inference flow and eliminating spurious errors.
• Verified commit: `25579a` signed with GPG key B5690EEE… for reproducibility.

That’s the whole change—just a targeted stability tweak, but it means smoother Qwen 3 runs on macOS, Windows, or Linux. 🎯

Tip: After updating, run a quick test generation to confirm the error is gone before integrating into larger pipelines. Happy tinkering!

🔗 View Release

MLX-LM – v0.30.6

MLX‑LM v0.30.6 just dropped – fresh on Apple silicon! 🍏✨

What it does:

Generate text and fine‑tune massive LLMs right on your M‑series Mac using the MLX framework. Plug into Hugging Face, run quantized models, handle long prompts, and scale with distributed inference.

What’s new in this release:

• LongCat Flash parser & Lite – lightning‑fast token streaming (shoutout @kernelpool).
• Kimi‑K2.5 support – tool‑call handling fixed; Kimi models work out‑of‑the‑box.
• MLX bump – upgraded backend for smoother, faster Apple silicon performance.
• Nemotron H config fix – aligns with HuggingFace format → hassle‑free loading.
• MultiLinear quant bug – restored missing `mode` argument; no more crashes during quantization.
• CLI finally live – real command‑line interface (thanks @awniin) plus quick bug fixes.
• Distributed inference – server can now spread work across multiple nodes (big thanks @angeloskath).
• Custom model loading – drop any 🤖 model into the folder; the server auto‑detects it.
• BatchRotatingKVCache default – smarter cache handling in batch mode for faster generation.
• Step 3.5 Flash & conversion fix – new flash‑optimized step and corrected model conversion pipeline.
• Chat template kwargs + top_logprobs – richer chat templates supported; can return token‑level probabilities.
• Stability upgrades: GLM 4.7 fallback handling, Deepseek V3.2 tweaks, batch mamba & sliding‑window mask fixes.

🚀 New contributor alert: @jalehman landed the first PR—welcome aboard!

More speed, more flexibility, fewer crashes. Happy tinkering! 🎉

🔗 View Release

Ollama – v0.15.5-rc2

_New update detected._

🔗 View Release

ComfyUI – v0.12.2

_New update detected._

🔗 View Release

ComfyUI – v0.12.1

_New update detected._

🔗 View Release

ComfyUI – v0.12.0

_New update detected._

🔗 View Release

Ollama – v0.15.5-rc1

_New update detected._

🔗 View Release

Ollama – v0.15.5-rc0

_New update detected._

🔗 View Release

Ollama – v0.15.4: openclaw: run onboarding for fresh installs (#14006)

🚀 Ollama v0.15.4 just dropped — and it’s a game-changer for new users!

OpenClaw now auto-launches the onboarding wizard on fresh installs. No more fumbling with misconfigured gateways or confused “why isn’t this working?” moments. 🎯

✅ What’s new:

• Auto-onboarding: First-time users get a guided setup — gateway mode, token, auth? All pre-configured.
• Smart skip: `onboarded()` checks for a `wizard.lastRunAt` flag — no repeats if you’re already set up.
• Zero-config start: Fresh installs default to `–auth-choice skip –gateway-token ollama` — plug & play.

Already running Ollama? Nothing changes for you — just faster, smoother onboarding for the next dev joining the local LLM revolution.

Perfect if you’re just starting with Llama 3, Mistral, or GGUF models. No CLI headaches anymore. 🚀

🔗 View Release

Ollama – v0.15.3: cmd/config: rename integration to openclaw (#13979)

🚀 Ollama v0.15.3 just dropped — and it’s a quiet win for clarity!

The `integration` config option? Gone. In its place: `openclaw` 🐙

Cleaner name, less confusion — perfect as Ollama’s plugin ecosystem explodes.

If you’ve been tweaking `~/.ollama/config.json` or using env vars with `integration`, time to swap it out for `openclaw`. No new features, just smarter config vibes.

Pro tip: Run `ollama serve` after updating — your custom tools will thank you.

Keep local LLM-ing, one clean config at a time! 🤖

🔗 View Release