• Home
  • Local LLM Deployment with vLLM

AI Vibe Coding for Javascript

Course Information

  • Sessions 1 day
  • Duration 7.5 hrs
  • Level Beginner
  • Assessment NA

Venue

12 Woodlands Square #07-85/86/87 Woods Square Tower 1, Singapore 737715. 5 mins walk from Woodlands (NS9) MRT station.

The venue is disabled-friendly.

Course Brochure

Download Course Brochure

Certification

  • Certificate of Achievement from Tertiary Infotech Academy Pte Ltd - Upon meeting at least 75% attendance and passing the assessment(s), participants will receive a Certificate of Achievement from Tertiary Infotech Academy Pte Ltd.

Local LLM Deployment with vLLM

Course Code: C136
AI Vibe Coding Series

37 Review(s) | Add Your Review

Share

What's This Course About

Sending every request to a commercial AI API means paying per token, waiting on someone else's latency, and shipping your data offsite. Running the model yourself removes all three — but a naive local deployment serves one request at a time and falls over the moment real traffic arrives. vLLM is the open source inference engine that closes that gap, using paged attention and continuous batching to serve open models at throughput that makes self-hosting genuinely practical.

In this hands-on 1-day course, you will stand up a local LLM deployment end to end: installing vLLM, loading models like Llama, Mistral and Qwen, and exposing them behind an OpenAI-compatible API so your existing code works unchanged. You will then make it perform — sizing GPU memory, applying quantisation to fit larger models on smaller cards, tuning batching and context length for your workload, and benchmarking honestly against what you are paying an API provider today.

You will leave with a running inference server, a tuned configuration and a clear cost-and-capacity picture for self-hosting — including where it genuinely wins and where a hosted API is still the better call. Ideal for developers, ML and platform engineers, and technical leads evaluating private or on-premise AI deployment.

Funding Options

No funding is available for this course

For WSQ funding, please checkout the details at WSQ - Generative AI Model Development and Fine Tuning

Course Fee

$350.00 (GST-exclusive)
$381.50 (GST-inclusive)

Course Date

* Required Fields

Additional Note

Please bring your own laptop for hands-on training. If you don't have laptop, we can provide spare laptop for training use.

Post-Course Support

  • We provide free consultation related to the subject matter after the course.
  • Please email your queries to enquiry@tertiaryinfotech.com and we will forward your queries to the subject matter experts.

Cancellation & Reschedule Policy

  • You can register your interest without upfront payment. There is no penalty for withdrawal of the course before the class commences.
  • We reserve the right to cancel or re-schedule the course due to unforeseen circumstances. If the course is cancelled, we will refund 100% for any paid amount.
  • Note the venue of the training is subject to changes due to availability of the classroom.

Course Details

Course Details

What You'll Learn

Topic 1 Why Self-Host an LLM

  • Cost, latency and data privacy trade-offs
  • Hosted API vs local deployment: when each wins
  • Hardware and GPU requirements
  • How vLLM differs from a naive local setup

Topic 2 Getting Started with vLLM

  • Installing and configuring vLLM
  • Loading open models: Llama, Mistral, Qwen
  • Serving an OpenAI-compatible API
  • Connecting existing applications with no code changes

Topic 3 Performance and Memory

  • Paged attention and continuous batching explained
  • Sizing GPU memory for your model
  • Quantisation to fit larger models on smaller cards
  • Tuning batching, context length and throughput

Topic 4 Running It in Production

  • Benchmarking against a hosted API
  • Monitoring, logging and health checks
  • Scaling, concurrency and failure handling
  • Cost modelling and ongoing maintenance

Course Info

Promotion Code

Your will get 10% discount voucher for 2nd course onwards if you write us a Google review.

Minimum Entry Requirement

Knowledge and Skills

  • Able to operate using computer functions
  • Minimum 3 GCE ‘O’ Levels Passes including English or WPL Level 5 (Average of Reading, Listening, Speaking & Writing Scores)

Attitude

  • Positive Learning Attitude
  • Enthusiastic Learner

Experience

  • Minimum of 1 year of working experience.

Target Age Group: 21-65 years old

Minimum Software/Hardware Requirement

Software:

You can download and install the following software:

Hardware: Windows and Mac Laptops

Job Roles

Job Roles

  • Web Developer
  • Front-End Developer
  • UI/UX Designer
  • Full-Stack Developer (Beginner)
  • Web Designer
  • Mobile App Developer (using frameworks like React Native)
  • CMS Developer (e.g., WordPress, Joomla)
  • E-commerce Platform Developer
  • Software Engineer (looking to expand skill set)
  • Game Developer (for web-based games)
  • IT Specialist (wanting to learn web development)
  • Product Manager (wishing to understand technical aspects)
  • Digital Marketer (with a tech inclination)
  • Tech Start-up Founder
  • Website Maintenance Specialist.

Trainers

Trainers

Shahul Maricar is a certified trainer. Shahul H. Maricar has been a content developer and webmaster, building educational websites and applications with HTML, CSS and JavaScript. He then served as an IT analyst, writing programs for automating custom workflows as well as data extraction and analysis in the healthcare field.
He is currently a freelance educator and is actively involved with development projects in game programming, computer-aided design and computer graphics.

Fritz is ACTA-certified, as well as a registered MOE instructor, and a graduate of the 2018 ConsenSys Blockchain Developer Program, with a Bachelor in Electrical and Electronic Engineering (Computer Specialisation) from Nanyang Technological University.
With more than 10 years of experience teaching at a local polytechnic, Fritz is passionate about imparting knowledge to teens, adults, and children. He believes that an education in technology and in how things work is essential for everyone, so that they can harness and invent the technologies of the future. He is excited about exploring anything related to computers and IT, with a keen interest in electronics and native cross-platform mobile app development so that our ubiquitous mobile phones can be conveniently used to control and interact with devices wirelessly and over the Internet. 

Mohamed Afiq is a ACTA certifed trainer. Mohamed Afiq startup CTO for 3 years building proprietary delivery system from scratch and then managing a team of 20 developers. He builted multiple web apps using MEAN or similar stacks. He is also a founder and sole developer for PlayTours: https://playtours.app/ . He leads instructor at CodeNinja, teaching coding to kids 9-16 years old and teach adults front-end and back-end for web development.

Review

Customer Reviews (37)

Might Recommend Review by Course Participant/Trainee
1. Do you find the course meet your expectation?
2. Do you find the trainer knowledgeable in this subject?
3. How do you find the training environment
More codes on DOM and JSON (Posted on 3/26/2018)
Will Recommend Review by Course Participant/Trainee
1. Do you find the course meet your expectation?
2. Do you find the trainer knowledgeable in this subject?
3. How do you find the training environment
more exercises for each topic and longer time-frame (Posted on 2/27/2018)
Will Recommend Review by Course Participant/Trainee
1. Do you find the course meet your expectation?
2. Do you find the trainer knowledgeable in this subject?
3. How do you find the training environment
Nil (Posted on 2/26/2018)
Will Recommend Review by Course Participant/Trainee
1. Do you find the course meet your expectation?
2. Do you find the trainer knowledgeable in this subject?
3. How do you find the training environment
Less emphasize on the basics/fundamentals and more coverage of the DOM and website creation (Posted on 2/12/2018)
Might Recommend Review by Course Participant/Trainee
1. Do you find the course meet your expectation?
2. Do you find the trainer knowledgeable in this subject?
3. How do you find the training environment
Nil (Posted on 1/29/2018)

Items 31 to 35 of 37 total

per page
Page:
  1. 1
  2. ...
  3. 4
  4. 5
  5. 6
  6. 7
  7. 8

Write Your Own Review

You're reviewing: Local LLM Deployment with vLLM

How do you rate this product? *

  1 star 2 stars 3 stars 4 stars 5 stars
1. Do you find the course meet your expectation?
2. Do you find the trainer knowledgeable in this subject?
3. How do you find the training environment