Computable GPU Index (CGI): an open, verifiable price index for GPU compute, in USD per GPU-hour. Reproduce any published value from the public record.
-
Updated
Sep 24, 2026 - Python
#
gpu-compute
Here are 75 public repositories matching this topic...
Revives the last functional CUDA deep-learning stack on macOS High Sierra. NVIDIA CUDA 10.2 + cuDNN 7.6.5 + PyTorch 1.7.0 fully working on GTX Pascal GPUs — a discontinued ecosystem resurrected.
deep-learning reverse-engineering cuda pytorch nvidia hackintosh cudnn nvidia-web-driver macos-high-sierra gpu-compute gtx10-series pascal-gpu pytorch-build legacy-macos macos-deep-learning cuda-revival cuda-10-2 cudnn-7-6-5 pytorch-1-7 macos-nvidia
-
Updated
Nov 14, 2025 - Python
Experimental open-source compatibility research for running DLSS Neural Rendering workloads on AMD RDNA2/gfx1030. Includes ISA translation, host emulation, proof-oriented validation, and bounded hardware testing. Early development: no end-to-end game frame yet.
open-source research compiler amd gpu reverse-engineering shader isa hip amdgpu rocm directx12 dlss neural-rendering gpu-compute navi21 rdna2 gfx1030 rx-6000
-
Updated
Oct 4, 2026 - Python
REST API wrapper around Google Colab CLI that enables remote execution of Python code on Colab VMs with GPU support. Features session management, real-time streaming, and automatic keep-alive.
nodejs python express rest-api session-management code-execution google-colab render-hosting gpu-compute python-remote-development colabbridge colab-api colab-cli colab-vm gpu-t4
-
Updated
Jul 4, 2026 - JavaScript
A pseudo operating system for local and cloud compute (Opensourcing on 5000th star)
cloud self-hosted artificial-intelligence operating-system cloud-computing remote-desktop webos gpu-computing remote-access web-os browseros browser-os remote-terminal pseudo-operating-system pseudo-desktop gpu-compute
-
Updated
Apr 18, 2024
A cross-platform C++ GPU compute microbenchmark supporting Vulkan, DX12, DX11, OpenGL, and Metal. Features hardware timestamp profiling and deep cross-architecture analysis.
benchmark opengl metal vulkan cpp17 profiling compute-shader renderdoc directx-11 directx-12 gpu-compute
-
Updated
Jul 31, 2026 - C++
GPU Implementation of Mandelbrot Fractal Generator with Benchmarking
-
Updated
Aug 30, 2026 - HIP
Real-Time AI Frame Interpolation for AMD GPUs
-
Updated
Jun 27, 2026 - Python
Experimental tensor compiler with a Python frontend, typed SSA IR, semantics preservation tests, and Metal lowering.
-
Updated
Sep 24, 2026 - Python
Experimental host-side Metal compute API prototype with a Vulkan executor and offline parity research.
-
Updated
Sep 22, 2026 - Rust
Production-ready engineering references for high-performance spatial visualization pipelines with WebGPU — GPU compute, WGSL shaders, deck.gl, Cesium, and Python backend integration.
webgl geospatial gis data-visualization cesium webgpu compute-shaders deckgl eleventy wgsl spatial-visualization gpu-compute
-
Updated
Aug 11, 2026 - CSS
AtlasCTF: from-scratch CTF math, symbolic solving, and hardware-accelerated search platform
-
Updated
Jul 28, 2026 - Rust
GPU Implementation of Newton Fractal Generator with Benchmarking
-
Updated
Aug 30, 2026 - HIP
MCP server for Gate402: pay-per-call agent APIs over x402. Open-model LLM inference, Base trading data, SEC filings and web scraping. 20 tools, free tier, no signup.
mcp web-scraping micropayments cursor base cline ai-agents claude defi usdc onchain trading-agent gpu-compute llm-inference agent-tools model-context-protocol http-402 mcp-server x402 agent-payments
-
Updated
Sep 19, 2026 - TypeScript
Instant USDC payouts for GPU operators. Connect your RTX 4090/5090 to Spraay and get paid in USDC on Base every time a job completes. No 2-week wait. No PayPal. No platform fees. Supports vLLM, Ollama, ComfyUI. Batch split payouts to multiple wallets.
gpu batch base batch-payments gpu-mining instant-payouts usdc gpu-operator ai-inference gpu-compute vllm rtx-5090 x402 gpu-rental rtx-4090 ai-compute usdc-payments
-
Updated
Jun 26, 2026 - TypeScript
基于 UE5.4 / Lyra / Chaos 的五个 SIGGRAPH 物理研究复现作品：GPU 布料、软体、Flow Map、反向设计与物理驱动角色。
-
Updated
Aug 30, 2026 - C++
Voxlang - Systems Language
programming-language rust compiler cuda developer-tools zero-dependency hip bare-metal systems-programming memory-safe gpu-compute
-
Updated
Jun 30, 2026 - Rust
Small-scale SIMD OS for many-agent systems
rust kernel gpu scheduling actor-model simd operating-system systems-programming continuations gpu-compute
-
Updated
Aug 9, 2026 - Rust
USDG bonding and metered GPU lease contracts for Prism Network.
-
Updated
Sep 2, 2026 - Solidity
Voxel engine from scratch in Swift + Metal for Apple Silicon
-
Updated
Apr 1, 2026 - Swift
Add this topic to your repo
To associate your repository with the gpu-compute topic, visit your repo's landing page and select "manage topics."