/images/logo-homepage.png
  • Core Compass
  • Core Platform
  • Core Community
  • About Us
  • Blog
  • Join Us
  • Contact Us

Jingkai He

Multi-Node LLM Serving Using sig LWS and vLLM

Posted on March 24, 2025 by Jingkai He

This article provides a guide on how to serve large language models on multiple nodes running on Kubernetes. Challenges Large Language Model (LLM) serving is a challenging task. Namely:

Serverless Exodus to GKE Autopilot

Posted on September 13, 2024 by Jingkai He

Over the last year CECG has been working on an engagement within a client’s Advertising Technology division to deliver an Ad decision server solution. It comes with the following requirements:

How to monitor an MVP Kubernetes-based Developer Platform with SLOs

Posted on June 13, 2023 by Jingkai He

For this engagement we built an MVP developer platform, based on Kubernetes, in a short timeframe (3 months) with 2 engineers. The goal was to get a small number of initial engineering teams’ application live.

authors

DEREK MORTIMER (5) NEOFYTOS ZACHARIA (4) CECG (3) JINGKAI HE (3) TIAGO ALVES (3) TOMASZ BARTOSIEWICZ (3) ANDREAS TTOFI (2) CHRISTOPHER BATEY (2) ILIA CHERNOV (2) SENNA SEMAKULA-BUUZA (2) SIMON AQUINO (1) ANDREAS TTOFI (1) CHRISTOPHER O’QUINN (1) GEOFF MACARTNEY (1) KORHAN OZTURK (1) MATT BURGESS (1) PHIVOS PHIVOU (1) ROBERT MOSS (1) SAVVAS MICHAEL (1) SEBASTIEN BONNET (1) SENNA SEMAKULA (1) SERGEI SIZOV (1) THOIBA THOUDAM (1)

Find Us:

info@cecg.io

London (HQ) | Nicosia

  • Home
  • About Us
  • Join Us
  • Privacy Policy
  • Cookie Settings
  • Core Compass
  • Core Platform
  • Core Community
  • Blog
Contact Us

© 2025 CECG All Rights Reserved