amperecomputingai Goto Github PK

ai-hackathon-2022

Public AI Hackathon content

ai-poc-benchmarks

aio-examples

ampere-ai-ref-apps

ampere-ai-serge-chat

ampere_model_library

AML's goal is to make benchmarking of various AI architectures on Ampere CPUs a pleasurable experience :)

arm_compute_library

Fork of ARM Compute Library

autogptq

An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.

benchmark

TorchBench is a collection of open source benchmarks used to evaluate PyTorch performance.

cloud-ai-sdk

Qualcomm Cloud AI SDK (Platform and Apps) enable high performance deep learning inference on Qualcomm Cloud AI platforms delivering high throughput and low latency across Computer Vision, Object Detection, Natural Language Processing and Generative AI models.

denoising-diffusion-pytorch

Implementation of Denoising Diffusion Probabilistic Model in Pytorch

dlrm

An implementation of a deep learning recommendation model (DLRM)

fastt5

⚡ boost inference speed of T5 models by 5x & reduce the model size by 3x.

images

inference_results_v2.0

llama-cpp-python

llama_index

LlamaIndex is a data framework for your LLM applications

minitrace

Simple C/C++ library for producing JSON traces suitable for Chrome's built-in trace viewer (about:tracing).

mldemos

Scripts used for various types of external demos

onednn

Fork of oneDNN

opennmt-py

Open Source Neural Machine Translation in PyTorch

opennmt-tf

Neural machine translation and sequence learning using TensorFlow

paddle

Fork of PaddlePaddle framework

releases_meta

server

The Triton Inference Server provides an optimized cloud and edge inferencing solution.

stable-diffusion-webui

Stable Diffusion web UI

stablediffusion

High-Resolution Image Synthesis with Latent Diffusion Models

tensorflow-serving

Fork of tensorflow serving for ARM64 build

tensorflow_serving_client

tensorrt_backend

The Triton backend for TensorRT.