Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Update the ViT model's README #293

Merged
merged 10 commits into from
Oct 25, 2023
20 changes: 19 additions & 1 deletion inference/benchmarks/vit_l_16/README.md
Original file line number Diff line number Diff line change
Expand Up @@ -60,6 +60,24 @@ find ./val -name "*JPEG" | wc -l
- TensorRT 8.5.1.7
- torch_tensorrt 1.3.0

#### 2.2 昆仑芯R200

- ##### 硬件环境
- 机器、加速卡型号: R200

- ##### 软件环境
- OS版本:Ubuntu 20.04
- OS kernel版本: 5.15.0-56-generic
- 加速卡驱动版本:4.0
- Docker 版本:20.10.21
- 依赖软件版本:
- pytorch: 1.13.0+cpu
- onnx: 1.14.0

- 推理工具包

- XTCL 2.1

### 3. 运行情况

* 指标列表
Expand All @@ -83,5 +101,5 @@ find ./val -name "*JPEG" | wc -l
| ----------- | --------- | ---- | ---- | -------- | ----------- | ---------- | ------------- | ------------ | ----------- | ----------- |
| tensorrt | fp16 | 64 |1009.7 | 777.8 | 796.7 | 825.8 | 1329.2 | 26.2% | 79.0/79.3 | 35.0/40.0 |
| tensorrt | fp32 | 32 | 1275.9 | 482.4 | 491.1 | 555.5 | 590.5 | 23.3% | 79.3/79.3 | 35.0/40.0 |
| kunlunxin_xtcl | W32A16 | 32 | 2118.307 | / | / | 130.006 | 144.914 | 27.9% | 79.3/79.3 | / |
| kunlunxin_xtcl | W32A16 | 32 | / | / | / | / | / | 27.9% | 79.3/79.3 | / |