Generating High-Performance Schedules in MLIR
https://mp.weixin.qq.com/s/8THJfcLNy8dx19QtOC5EIA
https://github.com/NVIDIA/TensorRT-LLM/blob/main/docs/source/blogs/tech_blog/blog9_Deploying_GPT_OSS_on_TRTLLM.md
https://mp.weixin.qq.com/s/mbpQSU3mH_71KUb9_qbDKg