AmpereComputingAI/ampere_model_library
AML's goal is to make benchmarking of various AI architectures on Ampere CPUs a pleasurable experience :)
This helps AI/ML engineers quickly evaluate how well various AI models perform on Ampere CPUs. You input your desired AI model (like ResNet-50 or Whisper) and it outputs clear performance metrics. This is designed for AI practitioners and hardware evaluators who need to understand AI model efficiency on Ampere server architectures.
Use this if you are developing or deploying AI applications and need to benchmark the performance of popular AI models on Ampere computing systems.
Not ideal if you are looking to train or fine-tune models, or if you are not working with Ampere CPUs.
Stars
23
Forks
8
Language
Python
License
Apache-2.0
Category
Last pushed
Feb 26, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/AmpereComputingAI/ampere_model_library"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
PaddlePaddle/FastDeploy
High-performance Inference and Deployment Toolkit for LLMs and VLMs based on PaddlePaddle
mlc-ai/mlc-llm
Universal LLM Deployment Engine with ML Compilation
skyzh/tiny-llm
A course of learning LLM inference serving on Apple Silicon for systems engineers: build a tiny...
ServerlessLLM/ServerlessLLM
Serverless LLM Serving for Everyone.
AXERA-TECH/ax-llm
Explore LLM model deployment based on AXera's AI chips