Maciej Strzelczyk
@mestiv.dev
Running vLLM on Google Cloud TPUs? My latest post details critical strategies for optimizing inference performance. Discover how to get the most out of this powerful hardware and software combination. Read more: medium.com/google-cloud...
#vLLM #GoogleCloud #TPU #MachineLearning #LLMops #AI
#vLLM #GoogleCloud #TPU #MachineLearning #LLMops #AI
Optimizing vLLM inference on TPUs!
Learn how to push your TPUs to their limits with proper vLLM inference configuration options.
medium.com
September 19, 2025 at 12:59 PM
Running vLLM on Google Cloud TPUs? My latest post details critical strategies for optimizing inference performance. Discover how to get the most out of this powerful hardware and software combination. Read more: medium.com/google-cloud...
#vLLM #GoogleCloud #TPU #MachineLearning #LLMops #AI
#vLLM #GoogleCloud #TPU #MachineLearning #LLMops #AI
Do you want to try out Google Cloud TPUs, but don't know where to start? How about a simple Gemma 3 inference service on top of vLLM? It's easier than you probably think ;)
medium.com/google-cloud...
medium.com/google-cloud...
Serving Gemma 3 on TPU v5e and v6e using vLLM
Learn how to serve Gemma 3 27B on v5e and v6e TPU VMs!
medium.com
July 30, 2025 at 7:27 PM
Do you want to try out Google Cloud TPUs, but don't know where to start? How about a simple Gemma 3 inference service on top of vLLM? It's easier than you probably think ;)
medium.com/google-cloud...
medium.com/google-cloud...