RamaLama v0.26.0 Released: TLS Support and GPU Detection Updates
containers/ramalama v0.26.0 is out, featuring TLS support for llama.cpp and vLLM, API key extensions, and GPU detecti ...
Magnitude v0.2.16 Released: Faster Parallel Requests and Docker
Magnitude v0.2.16 is out with major speedups for shared prompt prefixes, official Docker support, and new GGUF quanti ...
ComfyUI v0.44.0 Released with Expanded Partner Nodes
ComfyUI v0.44.0 is out, featuring expanded Partner Nodes for MiniMax, OpenAI, and Topaz, along with new video upscale ...
Unsloth v0.1.914-beta Released with Glass Theme and Speedups
Unsloth v0.1.914-beta is out, featuring a new Glass theme, faster Llama and Qwen3 generation on NVIDIA GPUs, and expa ...
Qwen 3.8 27B Can Interpret Model Weights Locally
Simon Willison reports that Qwen 3.8 27B running locally can interpret neural network weights, replicating capabiliti ...
Open WebUI v0.13.0 Released: Tabbed Workspaces & Security Fixes
Open WebUI v0.13.0 introduces tabbed workspaces, computer/browser use, security fixes, and multi-agent workflows. ...
Debate Erupts Over GPT-6 Astra’s Weight Manipulation Claims
The technical community discusses criticisms surrounding reports that GPT-6 Astra improved Qwen by reading and writin ...
SGLang v0.5.23 Released: Major Performance and Feature Updates
SGLang v0.5.23 is released with dramatic inference performance gains, Paged Experts, multi-platform support, and brea ...
InvokeAI v6.14.3 Released: Editable Vector Layers & More
InvokeAI v6.14.3 is now available, featuring editable vector layers for Canvas, download resumption fixes, and UI tra ...
vLLM v0.33.0 Released: CUDA 13.0, Speculative Decoding Upgrades
vLLM v0.33.0 is out, featuring PyTorch 2.14.0, CUDA 13.0 exclusive builds, enhanced speculative decoding, and support ...