Pinned Repositories
llama3-s
Llama3.1 learns to Listen
cortex
Drop-in, local AI alternative to the OpenAI stack. Multi-engine (llama.cpp, TensorRT-LLM, ONNX). Powers 👋 Jan
batdongsan_crawl
chatroom
Small chatroom for people to use for fun
cli_tools
cloudflare-serverless-telegram-bot
hive-metastore-alan
Apache Hive Metastore as a Standalone server in Docker
portfolio
rm_docker_desktop
No more docker desktop
trino-segment-connector
tikikun's Repositories
tikikun/trino-segment-connector
tikikun/cli_tools
tikikun/batdongsan_crawl
tikikun/cloudflare-serverless-telegram-bot
tikikun/hive-metastore-alan
Apache Hive Metastore as a Standalone server in Docker
tikikun/portfolio
tikikun/rm_docker_desktop
No more docker desktop
tikikun/ai-group-tabs
A Chrome extension helps you group your tabs with AI.
tikikun/architecture
tikikun/bdsCrawler
tikikun/chat-ui
Open source codebase powering the HuggingChat app
tikikun/ChatGPT.nvim
ChatGPT Neovim Plugin: Effortless Natural Language Generation with OpenAI's ChatGPT API
tikikun/dominic_backend
Home server backend of mine
tikikun/dominic_dpp
tikikun/frontend
tikikun/hugo-theme-mini
A fast, minimalist and responsive hugo theme for bloggers.
tikikun/layersfusion
tikikun/llama-cuda-graph-example
Example of applying CUDA graphs to LLaMA-v2
tikikun/llama.cpp-avx-vnni
Port of Facebook's LLaMA model in C/C++
tikikun/llama2.cpp
Inference Llama 2 in one file of pure C++
tikikun/llama_server
tikikun/multitent_cube_example
tikikun/my_container
The container that I use
tikikun/nitro
A fast, lightweight, embeddable inference engine to supercharge your apps with local AI. OpenAI-compatible API
tikikun/nitro-tensorrt-llm-personal-mirror
Nitro is an C++ inference server on top of TensorRT-LLM. OpenAI-compatible API. Run blazing fast inference on Nvidia GPUs. Used in Jan
tikikun/sentencepiece
Unsupervised text tokenizer for Neural Network-based text generation.
tikikun/tabbyAPI-personal-fork
An OAI compatible exllamav2 API that's both lightweight and fast
tikikun/tikikun.github.io
tikikun/torchtune
A Native-PyTorch Library for LLM Fine-tuning
tikikun/vim_setup
A launch point for your personal nvim configuration