beng

dspy

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

Megatron-LM

Ongoing research training transformer models at scale

litellm

Call all LLM APIs using the OpenAI format. Use Bedrock, Azure, OpenAI, Cohere, Anthropic, Ollama, Sagemaker, HuggingFace, Replicate (100+ LLMs)

txtai

💡 All-in-one open-source embeddings database for semantic search, LLM orchestration and language model workflows

PentestGPT

A GPT-empowered penetration testing tool

streaming-llm

[ICLR 2024] Efficient Streaming Language Models with Attention Sinks

Time-Series-Library

A Library for Advanced Deep Time Series Models.

phoenix

AI Observability & Evaluation

vimGPT

Browse the web with GPT-4V and Vimium

Video-LLaVA

Video-LLaVA: Learning United Visual Representation by Alignment Before Projection

CoreFreq

CoreFreq is a CPU monitoring and tuning software designed for 64-bit processors.

speakeasy

Windows kernel and user mode emulation.

lm-sensors

lm-sensors repository

aiconfig

AIConfig is a config-based framework to build generative AI applications.

mvts_transformer

Multivariate Time Series Transformer, public version

BakLLaVA

OhmGraphite

Expose hardware sensor data to Graphite / InfluxDB / Prometheus / Postgres / Timescaledb

amdgpu-clocks

Simple script to control power states of amdgpu driven GPUs

NeurIPS2023-One-Fits-All

The official code for "One Fits All: Power General Time Series Analysis by Pretrained LM (NeurIPS 2023 Spotlight)"

Flowformer

About Code release for "Flowformer: Linearizing Transformers with Conservation Flows" (ICML 2022), https://arxiv.org/pdf/2202.06258.pdf

a5k

Another World on a chip

ICML2022-FEDformer

Source code of ICML'22 paper: FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting

clx

A collection of RAPIDS examples for security analysts, data scientists, and engineers to quickly get started applying RAPIDS and GPU acceleration to real-world cybersecurity use cases.

DeepLog

PyTorch implementation of Deeplog: Anomaly detection and diagnosis from system logs through deep learning

wmi

domino

User friendly and open source platform for workflow creation and monitoring

gpumgr

gpumgr is a GPU manager for Linux allowing easy command line/web interface management of GPU power limits, clocks, fan speeds and more. gpumgr is multi-gpultural spiritual successor of amdpwrman.

pyperfmon

Python Module for reading perfmon stats from local and remote windows machines

odvii

odvii - command line tool for windows AMD ADL.

Powershell-MAHM

Submit system performance data from MSI Afterburner Remote Server to InfluxDB