The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
Updated 2026-06-21 02:28:09 +00:00
Official front-end implementation of ComfyUI
Updated 2026-06-21 02:01:04 +00:00
MSCCL++: A GPU-driven communication stack for scalable AI applications
Updated 2026-06-21 01:40:22 +00:00
Updated 2026-06-20 22:44:12 +00:00
CUDA Templates and Python DSLs for High-Performance Linear Algebra
Updated 2026-06-20 13:42:52 +00:00
[DEPRECATED] Moved to ROCm/rocm-libraries repo. NOTE: develop branch is maintained as a read-only mirror
Updated 2026-06-20 12:21:35 +00:00
Updated 2026-06-19 20:42:53 +00:00
llama.cpp fork with additional SOTA quants and improved performance
Updated 2026-06-19 16:17:13 +00:00
The ultimate training toolkit for finetuning diffusion models
Updated 2026-06-19 14:00:40 +00:00
Your self hosted YouTube media server
Updated 2026-06-19 10:55:22 +00:00
Updated 2026-06-19 06:09:02 +00:00
Updated 2026-06-18 12:04:39 +00:00
A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations
Updated 2026-06-18 09:35:31 +00:00
Updated 2026-06-18 09:28:51 +00:00
Updated 2026-06-17 22:38:58 +00:00
NVIDIA Linux open GPU kernel module source
Updated 2026-06-17 19:58:23 +00:00
Updated 2026-06-17 16:35:43 +00:00