DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm
Repository Index
47,133 repositories indexed
1–13 of 13 · Most stars
Burn is a next generation tensor library and Deep Learning Framework that doesn't compromise on flexibility, efficiency and portability.
- autodiff
- deep-learning
- machine-learning
- rust
Open Machine Learning Compiler Framework
- compiler
- tensor
- deep-learning
- gpu
NumPy & SciPy for GPU
- cuda
- cudnn
- cublas
- cusolver
LMCache: Supercharge Your LLM with the Fastest KV Cache Layer
Pyro is an experienced and powerful Laravel PHP CMS.
- cms
- framework
- cmf
- pyrocms
Project Maya - run GLM-5.3-Flash (321B MoE), DeepSeek-V4.1-Flash-1017 (748B MoE) and MiniMax-M3.1-Flash (428B MoE) privately on your own GPU(s), from one card to 16, NVIDIA or AMD, Linux or Windows. Engine, server, dashboard, OpenAI- and Anthropic-compatible API, quant tools.
stdgpu: Efficient STL-like Data Structures on the GPU
- gpu
- gpu-computing
- gpu-acceleration
- gpgpu
TensorFlow ROCm port
Exascale multiphase flow solver — 2025 Gordon Bell Prize Finalist | 200T grid points on 43K+ GPUs
- gpu
- exascale
- cfd
- fortran
Low-latency local speech-to-speech voice assistant with Ming-3.0-audio-tiny on AMD and Nvidia GPUs. Easy setup on Windows and Linux
- amd
- local-llm
- radeon
- realtime
SuperMimic-UniLab: An Independent reproduction of SuperMimic on UniLab for whole-body humanoid motion tracking.
- amd
- motrixsim
- mujoco
- rocm
detects nested contexts in loops or function literals
- context
- go
- golang
- linter