zhang-ge-hao

CEGIS

Counter-example guided inductive synthesis (CEGIS) implementation for the SMT solver Z3 by Microsoft Research

Qwen-TensorRT-LLM

GraphEval

Evaluating the Factuality of Large Language Models using Large-Scale Knowledge Graphs

pitest

State of the art mutation testing system for the JVM

LLM4Decompile

Reverse Engineering: Decompiling Binary Code with Large Language Models

mathematical_foundation

Mathematical Foundations for Deep Learning

minimal-light

A simple and elegant Jekyll theme for an academic personal homepage

repobench

✨ RepoBench: Benchmarking Repository-Level Code Auto-Completion Systems - ICLR 2024

rtp-llm

RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.

eeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeee

eeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeeee

TensorRT-LLM

TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.

MFTCoder

High Accuracy and efficiency multi-task fine-tuning framework for Code LLMs. This work has been accepted by KDD 2024.

EnergonAI

Large-scale model inference.

FasterTransformer4CodeFuse

High-performance LLM inference based on our optimized version of FastTransfomer

ByteTransformer

optimized BERT transformer inference on NVIDIA GPU. https://arxiv.org/abs/2210.03052

mac-precision-touchpad

Windows Precision Touchpad Driver Implementation for Apple MacBook / Magic Trackpad

LOFFER

博客主题 A Jekyll theme with Chinese UI and document

fastllm

纯c++的全平台llm加速库，支持python调用，chatglm-6B级模型单卡可达10000+token / s，支持glm, llama, moss基座，手机端流畅运行

BMInf

Efficient Inference for Big Models

NLPMetrics

Python code for various NLP metrics

picoGPT

An unnecessarily tiny implementation of GPT-2 in NumPy.

compose-spec

The Compose specification

demucs

Code for the paper Hybrid Spectrogram and Waveform Source Separation

music_source_separation

funcom

Funcom Source Code Summarization Tool - Public Release

Attn-to-FC

javalang

Pure Python Java parser and tools

aibolit

Static Analyzer for Java Code with Machine Learning in Mind

datasetforTBCCD

MSMARCO-Document-Ranking

MS MARCO(Microsoft Machine Reading Comprehension) is a large scale dataset focused on machine reading comprehension, question answering, and passage/document ranking