Submissions by xmo

vLLM V1: A Major Upgrade to vLLM's Core Architecture

vLLM v0.6.0: 2.7x Throughput Improvement and 5x Latency Reduction

ML Serving Is Broken

Products Are Functions

Governments vs. Big Tech: Resolving Differences in Contact Tracing

Evolving the Databricks Brand

Scaling Python Asyncio with Ray

Preventing the Death of the Dataframe

YouTube algorithm recommend everyone les miserable video

Demo of OpenAI's (Smaller) GPT2 Model

Looking Back at Postgres

Faster pandas, even on your laptop

Modin: Speed up your pandas by changing one line of code

Architecting Applications for Kubernetes

Pandas on Ray – Early Lessons from Parallelizing Pandas

A Short History of Prediction-Serving Systems