crates.io
gfx-rs/wgpu
A cross-platform, safe, pure-Rust graphics API.
Apache-2.0Aug 28, 2026 · metrics 2.10.0
All tags
Catalogue tag
#metal
Every repository in the public record carrying this tag — from its GitHub topics or the keywords its package registries publish. Health is measured under the same versioned methodology as the rest of the record.
45 records
crates.io
tracel-ai/burn
Burn is a next generation tensor library and Deep Learning Framework that doesn't compromise on flexibility, efficiency and portability.
Apache-2.0Sep 16, 2026 · metrics 2.10.0
PyPI
tenstorrent/tt-metal
:metal: TT-NN operator library, and TT-Metalium low level kernel programming model.
Apache-2.0Sep 9, 2026 · metrics 2.10.0
crates.io
tracel-ai/cubecl
Multi-platform high-performance compute language extension for Rust.
Apache-2.0Sep 14, 2026 · metrics 2.10.0
Go
gogpu/wgpu
Pure Go WebGPU Implementation
MITSep 10, 2026 · metrics 2.10.0
PyPI
Genesis-Embodied-AI/quadrants
High-performance multi-platform compiler for physics simulation
Apache-2.0Oct 21, 2026 · metrics 2.10.0
Go
defilantech/LLMKube
Kubernetes operator for self-hosted LLM inference across a heterogeneous GPU fleet: NVIDIA CUDA, AMD Vulkan, and Apple Silicon Metal. Runtimes: llama.cpp, vLLM, TGI, mlx-server. Multi-GPU sharding, model caching, OpenAI-compatible endpoints. Apache-2.0, run across homelab and on-prem fleets, actively developed.
Apache-2.0Sep 5, 2026 · metrics 2.10.0
crates.io
rust-skia/rust-skia
Rust Bindings for the Skia Graphics Library
MITSep 7, 2026 · metrics 2.10.0
PyPI
pygfx/pygfx
Powerful and versatile visualization for Python.
BSD-2-ClauseOct 14, 2026 · metrics 2.10.0
PyPI · npm
rajveer43/VeloxQuant-MLX
Fast KV-cache quantization for Apple Silicon (MLX) — 43 research-adapted compression methods with Metal kernels
MITOct 21, 2026 · metrics 2.10.0
crates.io
raphamorim/rio
A hardware-accelerated GPU terminal emulator focusing to run in desktops and browsers.
MITAug 28, 2026 · metrics 2.10.0
npm
withcatai/node-llama-cpp
Run AI models locally on your machine with node.js bindings for llama.cpp. Enforce a JSON schema on the model output on the generation level
MITAug 27, 2026 · metrics 2.10.0
Go
metal-stack/metal-core
Middleware for pixiecore and switch access
AGPL-3.0Sep 13, 2026 · metrics 2.10.0
crates.io · npm · PyPI
ohdearquant/lattice
Run AI models on Apple Silicon and Raspberry Pi
Apache-2.0Oct 20, 2026 · metrics 2.10.0
PyPI · npm
ChanLumerico/lucid
Lumerico's Comprehensive Interface for Deep Learning
MITOct 3, 2026 · metrics 2.10.0
Go
gogpu/naga
Pure Go Shader Compiler — WGSL to SPIR-V, MSL, GLSL, HLSL, DXIL. Zero CGO.
MITSep 24, 2026 · metrics 2.10.0
npm
margelo/react-native-filament
🐧 A real-time physically based 3D rendering engine for React Native
MITOct 10, 2026 · metrics 2.10.0
PyPI · npm
youssofal/MTPLX
3x faster speeds on MLX | Qwen 3.8 27B | Native MTP Speculative Decoding On Apple Silicon With No External Drafter.
Apache-2.0Sep 15, 2026 · metrics 2.10.0
Go
go-webgpu/webgpu
Zero-CGO WebGPU bindings for Go — GPU-accelerated graphics and compute in pure Go
MITAug 27, 2026 · metrics 2.10.0
Go
gogpu/g3d
Pure Go 3D rendering library. Scene graph, PBR, GLTF. Zero CGO. Built on gogpu/wgpu.
MITSep 25, 2026 · metrics 2.10.0
npm · crates.io
mlx-node/mlx-node
No repository description published.
MITSep 16, 2026 · metrics 2.10.0
PyPI
ronaldoussoren/pyobjc
The Python <-> Objective-C Bridge with bindings for macOS frameworks
No licenseSep 10, 2026 · metrics 2.10.0
crates.io
frames-sg/j2k
Rust JPEG 2000 / HTJ2K codec with CUDA and Metal GPU paths.
Custom licenseSep 30, 2026 · metrics 2.10.0
Go
hybridgroup/yzma
Go with your own intelligence - Write Go applications that directly integrate llama.cpp for local inference using hardware acceleration on Linux, macOS, Windows, & WebAssembly.
Custom licenseSep 9, 2026 · metrics 2.10.0
Maven · npm
qxoticai/qxotic
AI sovereignty for the world's most trusted runtime.
Apache-2.0Oct 19, 2026 · metrics 2.10.0
NuGet
iyulab/lm-supply
.NET library for on-demand local AI model inference — zero bundled models, lazy loading, hardware-aware GPU/CPU selection, 10 task types including embeddings, generation, vision, and audio.
MITSep 10, 2026 · metrics 2.10.0
PyPI
tillahoffmann/jax-mps
A JAX backend for Apple Metal Performance Shaders (MPS), enabling GPU-accelerated JAX computations on Apple Silicon.
Apache-2.0Sep 10, 2026 · metrics 2.10.0
PyPI
ARahim3/mlx-dspark
Up to 4× faster LLM decoding on Apple Silicon, lossless. Native MLX port of DeepSeek's DSpark & z-lab's DFlash speculative decoding — Gemma-4, Qwen3.8, Muse-Glimmer, Nemotron, LFM2.5, Ornith-1.0, ternary Bonsai-27B.
MITOct 19, 2026 · metrics 2.10.0
PyPI
asher/mlx-kquant
Native K-quant support for MLX, with a quantization and fine-tuning toolchain for Apple Silicon
MITAug 23, 2026 · metrics 2.10.0
NuGet
ooples/AiDotNet.Tensors
The fastest .NET tensor library. Beats MathNet (6x), NumSharp (3200x), matches TorchSharp CPU - pure managed C# with hand-tuned AVX2/FMA SIMD kernels. Optional CUDA/OpenCL GPU acceleration.
Apache-2.0Sep 6, 2026 · metrics 2.10.0