modelscope/dash-infer

DashInfer is a native LLM inference engine aiming to deliver industry-leading performance atop various hardware architectures, including CUDA, x86 and ARMv9.

43
/ 100
Emerging

This project helps operations engineers and IT managers run large language models (LLMs) and multimodal models (MMLMs) more efficiently on various hardware. It takes popular models like Qwen or LLaMA and optimizes their performance, delivering faster responses and lower operational costs. The target audience includes those responsible for deploying and managing AI applications at scale.

273 stars. No commits in the last 6 months.

Use this if you need to deploy large language models or multimodal models in a production environment and optimize their performance for speed and cost-efficiency on different hardware like GPUs or CPUs.

Not ideal if you are looking for a tool to train models or if your primary concern is developing new model architectures rather than deploying existing ones.

AI deployment LLM operations model serving IT infrastructure performance optimization
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 15 / 25

How are scores calculated?

Stars

273

Forks

28

Language

C

License

Apache-2.0

Last pushed

Aug 06, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/modelscope/dash-infer"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.