-
sf3d-webgpu Public
Stable Fast 3D (SF3D) single-image 3D mesh generation running entirely in WebGPU compute shaders
-
kaminos Public
Kaminos (κάμινος) — hallucinated world kiln. WebGPU/Three.js workbench for meeting, creating and exploring locally generated virtual worlds.
JavaScript UpdatedOct 12, 2026 -
trellis2mlx Public
MLX-native TRELLIS.2 inference for Apple Silicon — generate 3D meshes from images on > 16GB Macs
-
gpu-greenroom Public
Filesystem-backed GPU job queue with cooperative leases: one worker, one flock, a receipt for everything. Lets a fleet of agents share one Apple Silicon GPU.
Python MIT License UpdatedOct 12, 2026 -
-
spoke Public
Voice-first macOS control surface for dictation, assistant workflows, and hands-free control.
Python UpdatedOct 12, 2026 -
mlx-audio Public
Forked from Blaizzy/mlx-audioA text-to-speech (TTS), speech-to-text (STT) and speech-to-speech (STS) library built on Apple's MLX framework, providing efficient speech analysis on Apple Silicon.
Python MIT License UpdatedOct 9, 2026 -
moge-webgpu Public
Single-image depth and surface normal estimation running entirely in the browser via WebGPU compute shaders. Port of MoGe-2 (ViT-Large + ConvStack) from PyTorch.
-
Anytop Public
Forked from Anytop2025/AnytopCharacter Animation Diffusion with Any Topology
-
webgpu-samples Public
Forked from webgpu/webgpu-samplesWebGPU Samples
TypeScript BSD 3-Clause "New" or "Revised" License UpdatedSep 24, 2026 -
-
sharp-webgpu Public
Apple SHARP single-image 3D Gaussian Splat generation in WebGPU compute shaders
-
wilor-mlx Public
WiLoR hand pose estimation for Apple Silicon — rebuilt end-to-end in MLX for real-time use
-
-
lyonsno Public
GPU and ML systems for Apple Silicon and the browser, with public upstream work and research projects.
UpdatedAug 26, 2026 -
mlx-ideogram4 Public
Ideogram4 9.3B text-to-image on Apple Silicon via NF4 Metal kernels. 11.5 GB peak memory.
-
mlx-nf4 Public
NF4 / NormalFloat4 quantization kernels for MLX
Python MIT License UpdatedAug 25, 2026 -
mlx Public
Forked from ml-explore/mlxMLX: An array framework for Apple silicon
C++ MIT License UpdatedAug 12, 2026 -
mlx-whisper-patched Public
mlx-whisper with decode timeout + sync barrier (pending upstream PR to ml-explore/mlx-examples)
Python UpdatedJul 28, 2026 -
Unified deferred WebGPU renderer for Gaussian splats + triangle meshes with PBR relighting. SAM3 material segmentation, VLM-guided inverse tone mapping, SH-based GI, confidence-weighted G-buffer vo…
-
pixal3d-mlx Public
MLX-native Pixal3D (SIGGRAPH 2026) image-to-3D inference for Apple Silicon. Pure MLX, no PyTorch.
-
moge-mlx Public
MLX-native MoGe-2 monocular geometry estimation for Apple Silicon. Pure MLX, no PyTorch.
Python UpdatedJul 1, 2026 -
webgpu-vit-attention Public
Vision Transformer (DeiT-Tiny) inference in WebGPU compute shaders with interactive attention map visualization
-
motion-diffusion-model Public
Forked from GuyTevet/motion-diffusion-modelThe official PyTorch implementation of the paper "Human Motion Diffusion Model"
-
cosmos3-mlx Public
NVIDIA Cosmos 3 Nano (16B) on Apple Silicon via MLX — text/image-to-video generation for physical AI (robotics, driving, industrial)
-
mlx-examples Public
Forked from ml-explore/mlx-examplesExamples in the MLX framework
Python MIT License UpdatedJun 20, 2026 -
vllm-mlx Public
Forked from waybarrios/vllm-mlxOpenAI and Anthropic compatible server for Apple Silicon. Run LLMs and vision-language models (Llama, Qwen-VL, LLaVA) with continuous batching, MCP tool calling, and multimodal support. Native MLX …
Python UpdatedJun 16, 2026 -
mlx-vlm Public
Forked from Blaizzy/mlx-vlmMLX-VLM is a package for inference and fine-tuning of Vision Language Models (VLMs) on your Mac using MLX.
Python MIT License UpdatedJun 15, 2026 -
three.js Public
Forked from gonnavis/three.jsJavaScript 3D library.
JavaScript MIT License UpdatedJun 12, 2026 -
pytorch Public
Forked from pytorch/pytorchTensors and Dynamic neural networks in Python with strong GPU acceleration
Python Other UpdatedJun 7, 2026
{{ message }}