HNHacker News
TopNewBestAskShowJobs

xmo

95 karma · joined April 19, 2018

submissionscomments

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

blog.vllm.ai·5 pts·xmo·
0

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

blog.vllm.ai·3 pts·xmo·
0

ML Serving Is Broken

medium.com·2 pts·xmo·
0

Products Are Functions

feltpresence.com·1 pts·xmo·
0

Governments vs. Big Tech: Resolving Differences in Contact Tracing

medium.com·1 pts·xmo·
1

Evolving the Databricks Brand

databricks.com·2 pts·xmo·
0

Scaling Python Asyncio with Ray

medium.com·2 pts·xmo·
0

Preventing the Death of the Dataframe

towardsdatascience.com·3 pts·xmo·
0

YouTube algorithm recommend everyone les miserable video

youtu.be·1 pts·xmo·
0

Demo of OpenAI's (Smaller) GPT2 Model

text-gen.simon-mo.com·1 pts·xmo·
0

Looking Back at Postgres

arxiv-vanity.com·1 pts·xmo·
0

Faster pandas, even on your laptop

hackernoon.com·1 pts·xmo·
0

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

rise.cs.berkeley.edu·7 pts·xmo·
0

Architecting Applications for Kubernetes

digitalocean.com·1 pts·xmo·
0

Pandas on Ray – Early Lessons from Parallelizing Pandas

rise.cs.berkeley.edu·84 pts·xmo·
19

A Short History of Prediction-Serving Systems

rise.cs.berkeley.edu·26 pts·xmo·
0