[Feature]: Investigate the unstable perf of llama 3.1 8B fp8 in CI test_sanity_perf.py

### 🚀 The feature, motivation and pitch Investigate why llama 3.1 8B fp8 provides unstable results across CI runs and cannot be tested in CI. see: https://nvbugspro.nvidia.com/bug/6244474 This model is host bound (even in c=256) so the fluctuation is most likely related to cpu load. ### Alternatives _No response_ ### Additional context _No response_ ### Before submitting a new issue... - [x] Make sure you already searched for relevant issues, and checked the [documentation](https://nvidia.github.io/TensorRT-LLM/) and [examples](https://github.com/NVIDIA/TensorRT-LLM/tree/main/examples) for answers to frequently asked questions.