Skip to content

Commit

Permalink
feat: nvidia cuda
Browse files Browse the repository at this point in the history
  • Loading branch information
ryan4yin committed Nov 22, 2023
1 parent 7431762 commit 92d5102
Showing 1 changed file with 22 additions and 0 deletions.
22 changes: 22 additions & 0 deletions AI & Data-Science/Nvidia CUDA.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,22 @@
# Nvidia CUDA

## K8s 中的 GPU 监控

> https://github.com/NVIDIA/dcgm-exporter
## 利用 CUDA 加速计算

> https://developer.nvidia.cn/gpu-accelerated-libraries
### 1. TensorRT

> https://developer.nvidia.cn/tensorrt
如何使用 TensorRT 加速 pytorch 的推理?

参考:

1. https://pytorch.org/TensorRT/tutorials/notebooks.html
2. [Torch-TensorRT - Compile Stable Diffusion and Inference](https://pytorch.org/TensorRT/tutorials/_rendered_examples/dynamo/torch_compile_stable_diffusion.html)
3. [Compile a Torch Model(.pt) into Torch-TensorRT(xxx_trt.ts)](https://pytorch.org/TensorRT/cli/torchtrtc.html)

0 comments on commit 92d5102

Please sign in to comment.