ahxt

llm_factuality_tuning

FreeRTOS

'Classic' FreeRTOS distribution. Started as Git clone of FreeRTOS SourceForge SVN repo. Submodules the kernel.

triviaqa

Code for the TriviaQA reading comprehension dataset

krilla

A work-in-progress high-level PDF graphics library.

LCKV

Layer-Condensed KV cache w/ 10 times larger batch size, fewer params and less computation. Dramatic speed up with better task performance. Accepted to ACL 2024.

tinymist

Tinymist [ˈtaɪni mɪst] is an integrated language service for Typst [taɪpst].

LongRoPE

LongRoPE is a novel method that can extends the context window of pre-trained LLMs to an impressive 2048k tokens.

zotero

Zotero is a free, easy-to-use tool to help you collect, organize, annotate, cite, and share your research sources.

MindSearch

🔍 An LLM-based Multi-agent Framework of Web Search Engine (like Perplexity.ai Pro and SearchGPT)

flashattention2-custom-mask

Triton implementation of FlashAttention2 that adds Custom Masks.

CitationMap

A simple pip-installable Python tool to generate your own HTML citation world map from your Google Scholar ID.

gpu.cpp

A lightweight library for portable low-level GPU computation using WebGPU.

machine-learning-cheat-sheet

Classical equations and diagrams in machine learning

tensor

The Tensor (or Array)

volcano

A Cloud Native Batch System (Project under CNCF)

ngram

The n-gram Language Model

micrograd

The Autograd Engine

mlp

The Multilayer Perceptron Language Model

FLASHNN

FlagGems

FlagGems is an operator library for large language models implemented in Triton Language.

babilong

BABILong is a benchmark for LLM evaluation using the needle-in-a-haystack approach.

dattri

`dattri` is a PyTorch library for developing, benchmarking, and deploying efficient data attribution algorithms.

nvmath-python

NVIDIA Math Libraries for the Python Ecosystem

bpe.c

Simple Byte pair Encoding mechanism used for tokenization process . written purely in C

flash-attention-x

ScikitLearn.jl

Julia implementation of the scikit-learn API https://cstjean.github.io/ScikitLearn.jl/dev/

DeepSeek-Coder-V2

DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence

graphrag

A modular graph-based Retrieval-Augmented Generation (RAG) system

WinDiskWriter

🖥 Windows Bootable USB creator for macOS. 🛠 Patches Windows 11 to bypass TPM and Secure Boot requirements. 👾 UEFI & Legacy Support

Loong

[arxiv:2406.17419]Leave No Document Behind: Benchmarking Long-Context LLMs with Extended Multi-Doc QA