https://waqasm86.github.io/Mohammad Waqas — AI Inference & GPU SystemsTechnical research notes, reproducible benchmarks and engineering articles on vLLM, CUDA, NVIDIA GPUs, distributed inference, Kubernetes and AI infrastructure by Mohammad Waqas. 2026-09-25T09:58:30+05:00 Mohammad Waqas https://waqasm86.github.io/ Jekyll © 2026 Mohammad Waqas /assets/img/favicons/favicon.ico /assets/img/favicons/favicon-96x96.png Why I Built kaggle-vllm: Reproducible vLLM Inference on Dual NVIDIA T4 GPUs2026-09-24T09:00:00+05:00 2026-09-24T09:00:00+05:00 https://waqasm86.github.io/posts/why-i-built-kaggle-vllm/ Mohammad Waqas An evidence-first introduction to the compatibility, provenance, and experiment design behind running upstream vLLM in a managed dual-T4 notebook environment.