l4rz / building-a-poor-mans-supercomputerLinks
I've built a 4x V100 box for less than $5,500.
☆141Updated 3 years ago
Alternatives and similar repositories for building-a-poor-mans-supercomputer
Users that are interested in building-a-poor-mans-supercomputer are comparing it to the libraries listed below
Sorting:
- Inference code for LLaMA models☆188Updated 2 years ago
- Framework agnostic python runtime for RWKV models☆147Updated last year
- A library for incremental loading of large PyTorch checkpoints☆56Updated 2 years ago
- OpenAI API webserver☆188Updated 3 years ago
- SoTA Transformers with C-backend for fast inference on your CPU.☆309Updated last year
- ☆56Updated 2 years ago
- A ready-to-deploy container for implementing an easy to use REST API to access Language Models.☆65Updated 2 years ago
- Lightweight machine learning library based on OpenCL 1.2☆74Updated 4 years ago
- Use Datasette to explore LAION improved_aesthetics_6plus training data used by Stable DIffusion☆58Updated last year
- Quantized inference code for LLaMA models☆13Updated 2 years ago
- Voice swapping with VQ-VAE and diffusion models☆67Updated 3 years ago
- Drop in replacement for OpenAI, but with Open models.☆152Updated 2 years ago
- Python bindings for llama.cpp☆197Updated 2 years ago
- GPT Takes the Bar Exam☆142Updated 2 years ago
- Training a model similar to OpenAI DALL-E with volunteers from all over the Internet using hivemind and dalle-pytorch (NeurIPS 2021 demo)☆27Updated 2 years ago
- ☆252Updated 2 years ago
- Thispersondoesnotexist went down, so this time, while building it back up, I am going to open source all of it.☆90Updated last year
- A colab notebook that combines Stable Diffusion + DALL-E Mini (Craiyon)☆125Updated 2 years ago
- Inference on CPU code for LLaMA models☆137Updated 2 years ago
- Inference code for LLaMA models☆46Updated 2 years ago
- Prepare for DeekSeek R1 inference: Benchmark CPU, DRAM, SSD, iGPU, GPU, ... with efficient code.☆72Updated 5 months ago
- Scripts for converting Keras CV Stable Diffusion to tflite☆31Updated last year
- Running SXM2/SXM3/SXM4 NVidia data center GPUs in consumer PCs☆115Updated 2 years ago
- ☆130Updated 3 years ago
- Port of Microsoft's BioGPT in C/C++ using ggml☆87Updated last year
- A JAX implementation of the continuous time formulation of Consistency Models☆85Updated 2 years ago
- Simple Annotated implementation of GPT-NeoX in PyTorch☆110Updated 2 years ago
- The GeoV model is a large langauge model designed by Georges Harik and uses Rotary Positional Embeddings with Relative distances (RoPER).…☆121Updated 2 years ago
- ☆90Updated 2 years ago
- Backend for the diffusion-ui frontend☆25Updated last year