Official Inference Code of EAGLE-4
- eagle
- gpu
- llm-inference
- sglang
Repository Index
47,133 repositories indexed
145–168 of 345 · Most stars
Fast Clojure Matrix Library
TranslatedUsing dense-compute cards to accelerate sparse, large-VRAM hosts, where the hosts include AI Max+ 395, M3 512G, DGX Spark, and others.
- llama-cpp
- pipeline-parallelism
- prefill-decode
- rtx-3060
Robotics with GPU computing
GPU Trace Visualizer
Drop-in FSR 3.1 upscaler for Direct3D 12 that runs DLSS's network (Model E) on AMD GPUs
id Software's Quake 2 v3.21 with mission packs and Vulkan support (Windows, Linux, macOS, FreeBSD, Raspberry Pi 4)
- vulkan
- vulkan-api
- quake
- quake2
Real-time WebGPU ocean renderer written from scratch, no engine. FFT waves, whitecaps, sun glitter, physically based sunset sky with clouds, free camera. Built with Claude Code (Opus 5.5). Opens from a single 61 KB HTML file in Chrome.
BitCracker is the first open source password cracking tool for memory units encrypted with BitLocker
- bitlocker
- password-cracker
- cuda
- cryptography
Agent-first reverse engineering for macOS, Windows and Linux: any ACP agent reads, renames and patches binaries, Android apps and GPU kernels next to you.
Nornicdb is a distributed low-latency, Graph+Vector, Temporal MVCC with all sub-ms HNSW search, graph traversal, and writes. Using Neo4j Bolt/Cypher and qdrant's gRPC means you can switch with no changes while adding intelligent features like schemas, managed embeddings, reranking+llm, GPU accel, Auto-TLP, Policy-based Memory Decay, and MCP server.
- bolt
- cypher
- database
- enterprise-solutions
VUDA is a header-only library based on Vulkan that provides a CUDA Runtime API interface for writing GPU-accelerated applications.
CPU and GPU-accelerated Machine Learning Library
Thin, unified, C++-flavored wrappers for the CUDA APIs
- api-wrapper
- cuda
- cuda-runtime-api
- modern-cpp
The repository host gives no description.
C++ library for solving large sparse linear systems with algebraic multigrid method
- amg
- c-plus-plus
- sparse-linear-systems
- opencl
Show an agent a problem: mark up, record, send
AMDNR Neural Rendering on AMD GPUs, built into OptiScaler: model interleave, residual composition, XeSS frame generation up to 6X, FSR Ray Regeneration. Discord: https://discord.gg/AMDNR · Ko-fi: https://ko-fi.com/3zinr
⚡ Datoviz: high-performance GPU rendering for scientific data visualization
- visualization
- graphics
- data-visualization
- scientific-visualization
Vulkan 2D graphics library
vibe coded supermimic within 1h, LAFAN passed within 1.5 gpuh training
Desktop apps in Zig, with native UI drawn on the GPU or a web frontend
DNABERT: pre-trained Bidirectional Encoder Representations from Transformers model for DNA-language in genome
- kmer
- dnabert-model
- kmer-format
- gpu
A GUI app for Omarchy Linux.