Baseten Blog | Page 2


FP8: Efficient model inference with 8-bit floating point numbers

The FP8 data format has an expanded dynamic range versus INT8 which allows for quantizing weights and activations for more LLMs without loss of output quality.


Announcing our Series B

We’ve spent the last four and a half years building Baseten to be the most performant, scalable, and reliable way to run your machine learning workloads.


The benefits of globally distributed infrastructure for model serving

Multi-cloud and multi-region infrastructure for model serving provides availability, redundancy, lower latency, cost savings, and data residency compliance.


New in February 2024

3x throughput with H100 GPUs, 40% lower SDXL latency with TensorRT, and multimodal open source models.

Model performance

40% faster Stable Diffusion XL inference with NVIDIA TensorRT

Using NVIDIA TensorRT to optimize each component of the SDXL pipeline, we improved SDXL inference latency by 40% and throughput by 70% on NVIDIA H100 GPUs.


Why GPU utilization matters for model inference

Save money on high-traffic model inference workloads by increasing GPU utilization to maximize performance per dollar for LLMs, SDXL, Whisper, and more.

ML models

The best open source large language model

Explore the best open source large language models for 2024 for any budget, license, and use case.

Model performance

Unlocking the full power of NVIDIA H100 GPUs for ML inference with TensorRT

Double or triple throughput at same-or-better latencies by switching to H100 GPUs from A100s for model inference with TensorRT/TensorRT-LLM.


New in January 2024

A library for open source models, general availability for L4 GPUs, and performance benchmarking for ML inference