ggerganov / stable-diffusion.cpp
Stable Diffusion in pure C/C++
☆56Updated last year
Related projects: ⓘ
- Port of Suno AI's Bark in C/C++ for fast inference☆50Updated 5 months ago
- Python bindings for ggml☆125Updated 2 weeks ago
- Inference of Mamba models in pure C☆176Updated 6 months ago
- Inference Vision Transformer (ViT) in plain C/C++ with ggml☆215Updated 5 months ago
- LLaVA server (llama.cpp).☆173Updated 10 months ago
- Port of Meta's Encodec in C/C++☆187Updated last month
- Port of Microsoft's BioGPT in C/C++ using ggml☆87Updated 6 months ago
- Tiny Dream - An embedded, Header Only, Stable Diffusion C++ implementation☆248Updated 10 months ago
- Inference Vision Transformer (ViT) in plain C/C++ with ggml☆31Updated 9 months ago
- Inference of Large Multimodal Models in C/C++. LLaVA and others☆46Updated 11 months ago
- asynchronous/distributed speculative evaluation for llama3☆36Updated last month
- A ggml (C++) re-implementation of tortoise-tts☆147Updated 3 weeks ago
- GGML implementation of BERT model with Python bindings and quantization.☆25Updated 7 months ago
- llama.cpp clone with additional SOTA quants and improved CPU performance☆57Updated this week
- Experiments with BitNet inference on CPU☆46Updated 5 months ago
- WebGPU LLM inference tuned by hand☆145Updated last year
- Local ML voice chat using high-end models.☆138Updated last week
- GGML implementation of BERT model with Python bindings and quantization.☆51Updated 7 months ago
- GGUF implementation in C as a library and a tools CLI program☆238Updated 2 months ago
- LLM-based code completion engine☆172Updated last year
- Web browser version of StarCoder.cpp☆43Updated last year
- CLIP inference in plain C/C++ with no extra dependencies☆433Updated last month
- tinygrad port of the RWKV large language model.☆43Updated 3 months ago
- Course Project for COMP4471 on RWKV☆16Updated 7 months ago
- Download full or partial git-lfs repos without temporarily using 2x disk space☆30Updated 11 months ago
- General purpose GPU compute framework built on Vulkan to support 1000s of cross vendor graphics cards (AMD, Qualcomm, NVIDIA & friends). …☆35Updated last week
- iterate quickly with llama.cpp hot reloading. use the llama.cpp bindings with bun.sh☆45Updated 10 months ago
- ☆55Updated last month
- Fork of llama.cpp, extended for GPT-NeoX, RWKV-v4, and Falcon models☆28Updated last year
- example of using CoreML from c++☆21Updated last year