Abu Qader

Software Engineer

Model performance

How we run GPT OSS 120B at 500+ tokens per second on NVIDIA GPUs

Amir Haghighat
4 others
GPT OSS 120B
News

Introducing our Speculative Decoding Engine Builder integration for ultra-low-latency LLM inference

Justin Yi
3 others
Speculative Decoding in Engine Builder
Model performance

How to double tokens per second for Llama 3 with Medusa

Abu Qader
1 other
Double Llama TPS with Medusa
News

Introducing automatic LLM optimization with TensorRT-LLM Engine Builder

Abu Qader
1 other
TensorRT-LLM Engine Creation
Model performance

Benchmarking fast Mistral 7B inference

Abu Qader
3 others
Mistral 7B
Model performance

Introduction to quantizing ML models

Abu Qader
1 other
Quantization

Explore Baseten today

Start deploying
Talk to an engineer