joennlae

tensorli

Absolute minimalistic implementation of a GPT-like transformer using only numpy (<650 lines).

halutmatmul

Hashed Lookup Table based Matrix Multiplication (halutmatmul) - Stella Nera accelerator

halutmatmul-openroad-reports

llm-bandwidth

camelot

A Python library to extract tabular data from PDFs

containers

stuff to build runpod containers

continuous-eval

Open-Source Evaluation for GenAI Application Pipelines

dokku

A docker-powered PaaS that helps you build and manage the lifecycle of applications

dokku-pages

Simple static sites on Dokku!

dspy

DSPy: The framework for programming—not prompting—foundation models

gradio

Build and share delightful machine learning apps, all in Python. 🌟 Star to support our work!

llama.cpp

Port of Facebook's LLaMA model in C/C++

llama_index

LlamaIndex (formerly GPT Index) is a data framework for your LLM applications

llm-course

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

llmsherpa

Developer APIs to Accelerate LLM Projects

LLMTest_NeedleInAHaystack

Doing simple retrieval from LLM models at various context lengths to measure accuracy

llvm-project

The LLVM Project is a collection of modular and reusable compiler and toolchain technologies. Note: the repository does not accept github pull requests at this moment. Please submit your patches at http://reviews.llvm.org.

medplum

Medplum is a healthcare platform that helps you quickly develop high-quality compliant applications.

mimic-fhir

A version of MIMIC-IV in FHIR

mistral-src

Reference implementation of Mistral AI 7B v0.1 model.

nlm-ingestor

This repo provides the server side code for llmsherpa API to connect. It includes parsers for various file formats.

nlm-utils

Common utilities used by all nlm-* libraries.

ruby-lsp

An opinionated language server for Ruby

runpod-python

🐍 | Python library for RunPod API and serverless worker SDK.

text-generation-inference

Large Language Model Text Generation Inference

TinyLlama

The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.

unstructured

Open source libraries and APIs to build custom preprocessing pipelines for labeling, training, or production machine learning pipelines.

vllm

A high-throughput and memory-efficient inference and serving engine for LLMs

worker-vllm

The RunPod worker template for serving our large language model endpoints. Powered by vLLM.

xuantie-gnu-toolchain

GNU toolchain for Xuantie RISC-V CPU, including GCC and Binutils ……