ggml v0.25.0 Released: FlashAttention and MoE Optimizations
ggml v0.25.0 is now available, featuring expanded FlashAttention support, MoE and SSM optimizations, and new hardware ...
Unsloth Update: Qwen-Image-2.1 Support and Agent Skills Added
Unsloth update adds Qwen-Image-2.1, Agent Skills, 2x reasoning speed, and improved Linux and storage management.
Run GGUF Models Directly in Transformers with llama.cpp Support
Hugging Face adds direct execution support for llama.cpp GGUF models in transformers, starting with local Qwen3.5 inf ...
vLLM v0.30.0 Released: Fast Start Weight Caching and New Models
vLLM v0.30.0 is released, featuring Fast Start weight caching, engine initialization speedups, DeepSeek-V4.1-Flash su ...
Open WebUI v0.11.4 Released: Dramatic Docker Image Slimming
Open WebUI v0.11.4 is released with a dramatic reduction in Docker image size, terminal skill integration, and perfor ...
Inco AI Releases Splash Engine for Fast Local LLMs on Mac
Inco AI releases Splash Engine, an open-source local LLM inference engine optimized for Apple Silicon, natively integ ...
SGLang v0.5.20 Released: New Models and Optimizations
SGLang v0.5.20 is released with 713 PRs, adding support for new models, ROCm load time improvements, Intel XPU offici ...
Unsloth v0.1.811-beta Released with AMD & NVIDIA Docker Images
Unsloth v0.1.811-beta is out, introducing new NVIDIA and AMD Docker images, multi-user accounts, 2x faster diffusion ...
LM Studio Announces Session References and Introspection in Bionic
LM Studio has announced ‘Introspection’ and ‘@’ mention features for Bionic, enabling agents ...
LocalAI v4.10.0 Released: Fleet Dashboard & M5 Support
LocalAI v4.10.0 is out, featuring a fleet management dashboard, Apple M5 startup crash fixes, credential file managem ...