GitHub topics

metal

Mostly in LLM Infrastructure 20%, GUI 10%, Game Development 10%

Repositories

10

Total stars

2,247

Trending

vivaui

A Go-first, GPU-native desktop framework. No WebView, no bundled runtime.

Created Oct 2026

desktop direct3d framework golang gpu
Total 393
30 days +393
Dharshaneshwaran

Pools consumer laptops into one local runtime for Meta Llama models. Measures the free VRAM each machine reports, splits the model across CUDA and Metal devices through llama.cpp RPC, and rebuilds the pipeline when a worker drops out.

Created Oct 2026

cuda distributed-inference fault-tolerance gguf golang
Total 56
30 days +56
defilantech

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.

Created Nov 2025

ai apple-silicon autoscaling edge-computing gguf
Total 267
30 days +30
hybridgroup

Go with your own intelligence - Write Go applications that directly integrate llama.cpp for local inference using hardware acceleration on Linux, macOS, Windows, & WebAssembly.

Created Sep 2025

arduino-uno-q cuda gguf golang jetson-orin-nano
Total 676
30 days +20
gogpu

Pure Go WebGPU Implementation

Created Dec 2025

directx12 go golang gpu graphics
Total 202
30 days +13
go-webgpu

Zero-CGO WebGPU bindings for Go — GPU-accelerated graphics and compute in pure Go

Created Nov 2025

directx12 ffi gamedev go golang
Total 74
30 days +8
gogpu

Pure Go Shader Compiler — WGSL to SPIR-V, MSL, GLSL, HLSL, DXIL. Zero CGO.

Created Dec 2025

compiler directx dxil glsl go
Total 58
30 days +5
raketenkater

llama.cpp/ik_llama.cpp launcher: loads big MoE models across mismatched multi-GPU rigs by exact VRAM math.

Created Mar 2026

cuda gguf golang inference-server llama-cpp
Total 284
30 days +3

Top

hybridgroup

Go with your own intelligence - Write Go applications that directly integrate llama.cpp for local inference using hardware acceleration on Linux, macOS, Windows, & WebAssembly.

Created Sep 2025

arduino-uno-q cuda gguf golang jetson-orin-nano
Total 676
vivaui

A Go-first, GPU-native desktop framework. No WebView, no bundled runtime.

Created Oct 2026

desktop direct3d framework golang gpu
Total 393
raketenkater

llama.cpp/ik_llama.cpp launcher: loads big MoE models across mismatched multi-GPU rigs by exact VRAM math.

Created Mar 2026

cuda gguf golang inference-server llama-cpp
Total 284
defilantech

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.

Created Nov 2025

ai apple-silicon autoscaling edge-computing gguf
Total 267
gogpu

Pure Go WebGPU Implementation

Created Dec 2025

directx12 go golang gpu graphics
Total 202
rajveermalviya

Go bindings for WebGPU, a safe & cross-platform GPU abstraction

Created Jan 2022

directx12 go golang gpu metal
Total 164
go-webgpu

Zero-CGO WebGPU bindings for Go — GPU-accelerated graphics and compute in pure Go

Created Nov 2025

directx12 ffi gamedev go golang
Total 74
cyruzin

Clean architecture example in Golang.

Created May 2019

clean-architecture ddd-architecture go golang hexagonal-architecture
Total 73
gogpu

Pure Go Shader Compiler — WGSL to SPIR-V, MSL, GLSL, HLSL, DXIL. Zero CGO.

Created Dec 2025

compiler directx dxil glsl go
Total 58
Dharshaneshwaran

Pools consumer laptops into one local runtime for Meta Llama models. Measures the free VRAM each machine reports, splits the model across CUDA and Metal devices through llama.cpp RPC, and rebuilds the pipeline when a worker drops out.

Created Oct 2026

cuda distributed-inference fault-tolerance gguf golang
Total 56

Related

All topics →