GraphCast-Lite: Running 0.25° (37 levels) FP32 model on 8GB VRAM consumer GPUs

Hi GraphCast Team,
Thank you for your groundbreaking work!
I'd like to share a community project, GraphCast-Lite, designed to run GraphCast inference on consumer hardware by heavily optimizing memory and speed.
Key Highlights:
8GB VRAM Support: Runs the high-resolution 0.25° model (37 levels) in full FP32 precision on consumer GPUs (e.g., RTX 2080 Ti) using a Static VRAM Pool and Dual-Chunking Engine.
High Performance: Forecasts 10 days (40 steps) in ~15s on RTX 4090 (BF16) and ~40s on RTX 2080 Ti (FP16) via TensorRT.
Lightweight: Replaces heavy dependencies with a pure PyTorch/TensorRT inference pipeline.
Repo: [](https://github.com/VectorElectron/graphcast-lite)
Hope this helps more researchers experiment with GraphCast without needing enterprise GPUs!
Best regards,

Review the linked VectorElectron/graphcast-lite repository and the issue's claims about PyTorch, TensorRT, VRAM usage, and forecast speed. The issue names no file, test, or requested change; completion would require clarifying whether the project should be integrated, documented, or merely acknowledged.

Written by the indexing model from the issue text.