Inference Performance

22 posts · 6 sources

CoreweaveBlog2w

CoreWeave Mission Control | Operational Intelligence for AI

NVIDIABlog3w

Dense vs. MoE Models: Active Parameters, Throughput, and When to Choose Each

NVIDIABlog24 Aug

NVIDIA Vera Rubin and Blackwell Set a New Standard for Agentic AI Performance per Watt

CoreweaveBlog30 Jul

Introducing NVIDIA HGX B300 on the Essential Cloud for AI

NVIDIABlog2 Jul

Hardware-Rooted AI Security That Won’t Slow You Down

NVIDIABlog12 Jun

NVIDIA Achieves Leading Agentic Coding Performance on First Agentic AI Benchmark

BasetenBlog4 Jun

Introducing NVIDIA Nemotron 3 Ultra: The Nemotron 3.x family is here!

CoreweaveBlog20 May

BasetenBlog5 Feb

How to run LLM performance benchmarks (and why you should)

BasetenBlog15 Jan

The fastest Whisper — with streaming and diarization

ModalBlog18 Nov

Host overhead is killing your inference efficiency

BasetenBlog23 Oct

DeepSeek-OCR and the Unreasonable Usefulness of Compression

GoogleBlog20 May

LiteRT: Maximum performance, simplified- Google Developers Blog

ModalBlog24 Apr

How Lemon Slice built real-time generative video with Modal and Daily

BasetenBlog18 Apr

Accelerating inference with NVIDIA B200 GPUs

BasetenBlog4 Apr

The best open-source embedding models

ModalBlog19 Dec

Introducing: L40S GPUs on Modal

GoogleBlog14 May

AI Edge Torch: High Performance Inference of PyTorch Models on Mobile Devices- Google Developers Blog

BasetenBlog22 Feb

40% faster Stable Diffusion XL inference with NVIDIA TensorRT

BasetenBlog31 Jan

Introduction to quantizing ML models