Alex Chen

ML engineer focused on cost-efficient AI infrastructure. I benchmark GPU clouds and share practical guides for running LLMs in production. 📬 Telegram: https://t.me/qisuancloud

Joined on Oct 6, 2026 https://qisuanai.com

Alex Chen

Oct 23

SGLang vs vLLM: Your Agent Is Slow Because You Picked the Wrong Cache

#llm #opensource #benchmarking #machinelearning

5 min read

Want to connect with Alex Chen?

Create an account to connect with Alex Chen. You can also sign in below to proceed if you already have an account.

Create Account

Already have an account? Sign in

Alex Chen

Oct 19

Your 128K Context Fits on a 4090 — If You Quantize the KV Cache

#gpu #llm #vllm #ai

3 min read

Alex Chen

Oct 16

Stop Overpaying for GPUs: Spot vs On-Demand for LLM Inference (With Real Numbers)

#gpu #llm #cloud #machinelearning

3 min read

Alex Chen

Oct 11

Your 7B Model Fits on a 4090 — Until You Open a 128K Context Window

#ai #llm #gpu #tutorial

3 min read

Alex Chen

Oct 9

Your 7B Model Doesn't Need an H100: A Practical GPU Sizing Guide for LLM Inference

#llm #gpu #ai #tutorial

2 min read

Alex Chen

Oct 6

I Compared 5 GPU Clouds for LLM Inference in 2026 — Here's What I Found

#ai #gpu #llm #cloud

2 min read

DEV Community

Alex Chen

Badges

1 Week Community Wellness Streak

Writing Debut

SGLang vs vLLM: Your Agent Is Slow Because You Picked the Wrong Cache

Want to connect with Alex Chen?

Your 128K Context Fits on a 4090 — If You Quantize the KV Cache

Stop Overpaying for GPUs: Spot vs On-Demand for LLM Inference (With Real Numbers)

Your 7B Model Fits on a 4090 — Until You Open a 128K Context Window

Your 7B Model Doesn't Need an H100: A Practical GPU Sizing Guide for LLM Inference

I Compared 5 GPU Clouds for LLM Inference in 2026 — Here's What I Found