Cluster 640334

9 repos

Python · 7

C++ · 1

TypeScript · 1

inference ·139,551

deep-learning ·139,551

data-parallelism ·128,189

pipeline-parallelism ·128,189

model-parallelism ·128,189

gpu ·106,457

machine-learning ·97,260

compression ·94,612

mixture-of-experts ·86,265

billion-parameters ·86,265

Related clusters

Cluster 63361831 PyTorch Deep Learning & NLP23 Cluster 63928813 Cluster 63682110 Cluster 63525931 Cluster 6531323

microsoft/DeepSpeed

DeepSpeed is a deep learning optimization library that makes distributed training and inference…

Python

43,132

3,180 commits

deepspeedai/DeepSpeed

DeepSpeed is a deep learning optimization library that makes distributed training and inference…

Python

43,133

3,160 commits

triton-inference-server/pytriton

PyTriton is a Flask/FastAPI-like interface that simplifies Triton's deployment in Python…

Python

850

322 commits

triton-inference-server/server

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

Python

10,995

2,784 commits

MrZoller/headroom

Work out which open-weight LLMs run on your hardware, and how comfortably — across discrete GPUs,…

TypeScript

134 commits

dylanyunlon/Neuron_SP

No description

Python

8,270 commits

hpcaitech/ColossalAI

Making large AI models cheaper, faster and more accessible

Python

41,441

3,890 commits

PaddlePaddle/PaddleFleetX

飞桨大模型开发套件，提供大语言模型、跨模态大模型、生物计算大模型等领域的全流程开发工具链。

Python

483

425 commits

zeux/meshoptimizer

Mesh optimization library that makes meshes smaller and faster to render

C++

8,347

4,157 commits