Engines and Tools

ExLlamaV3 v1.4.9 Released: New Models & CPU Offload

ExLlamaV3 v1.4.9 is released with faster CPU offloading, Intel AVX512BW support, and new model architectures.

Engines and Tools

ComfyUI v0.35.0 Released: New Models and Memory Improvements

ComfyUI v0.35.0 is out, featuring Comfy Compiler, container memory management improvements, new model support, and AM ...

Engines and Tools

Unsloth v0.1.808-beta Released with Speedups for Diffusion

Unsloth v0.1.808-beta brings significant performance gains for diffusion models, AMD GPUs, and Apple Silicon, alongsi ...

Engines and Tools

vLLM v0.29.0 Released: Model Runner V2 Now Default

vLLM v0.29.0 is released with Model Runner V2 as default, FlashInfer all-reduce, new admission control flags, and sup ...

Engines and Tools

Unsloth v0.1.807-beta Released with Major Performance Boost

Unsloth v0.1.807-beta is out, bringing major performance boosts for AMD and Apple Silicon, Vulkan defaults, and Windo ...

Engines and Tools

ExLlamaV3 1.4.8 Released: VRAM Opt & FA-2 Removal

ExLlamaV3 1.4.8 is released. Key updates include VRAM allocation optimization and the complete removal of Flash Atten ...

Engines and Tools

InvokeAI v6.14.1 Released with Memory and Krea-2 Support

InvokeAI v6.14.1 is released, featuring Krea-2 LoRA support, memory management optimization, and UI enhancements for ...