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.

Sign up for GitHub

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

docs: add disk usage / memory usage benchmark table #751

Merged
merged 17 commits into from
Jun 15, 2022
Merged

docs: add disk usage / memory usage benchmark table #751

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
17 commits
Select commit Hold shift + click to select a range
12cc4c7
docs: add disk usage and peak memory usage to benchmark table
ZiniuYu Jun 7, 2022
01f1445
docs: add disk usage
ZiniuYu Jun 12, 2022
789fa73
docs: benchmark_table
ZiniuYu Jun 13, 2022
7747a23
docs: benchmark_table
ZiniuYu Jun 13, 2022
f30ce8e
docs: disk usage
ZiniuYu Jun 13, 2022
418111d
docs: peak memory usage
ZiniuYu Jun 13, 2022
1e66ad2
docs: peak memory usage
ZiniuYu Jun 13, 2022
fe9ff41
docs: peak memory usage
ZiniuYu Jun 13, 2022
b03f47b
docs: peak memory usage
ZiniuYu Jun 13, 2022
c79ac3b
docs: benchmark table
ZiniuYu Jun 13, 2022
b77fae2
docs: add RAM usage
ZiniuYu Jun 13, 2022
7789ae3
docs: add RAM usage
ZiniuYu Jun 13, 2022
61db23c
docs: update RAM usage
ZiniuYu Jun 14, 2022
c687fe3
docs: update RAM usage
ZiniuYu Jun 14, 2022
882cad0
docs: update narrative
ZiniuYu Jun 14, 2022
5946c75
docs: use default config in benchmark
ZiniuYu Jun 15, 2022
d2d7be2
docs: correct link
ZiniuYu Jun 15, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
26 changes: 13 additions & 13 deletions docs/user-guides/server.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -60,19 +60,19 @@ The procedure and UI of ONNX and TensorRT runtime would look the same as Pytorch

## Model support

Open AI has released 9 models so far. `ViT-B/32` is used as default model in all runtimes. Due to the limitation of some runtime, not every runtime supports all nine models. Please also note that different model give different size of output dimensions. This will affect your downstream applications. For example, switching the model from one to another make your embedding incomparable, which breaks the downstream applications. Here is a list of supported models of each runtime and its corresponding size:

| Model | PyTorch | ONNX | TensorRT | Output dimension |
| --- |---------| ---- | --- |--- |
| RN50 | ✅ |✅ | ✅| 1024 |
| RN101 | ✅ |✅ | ✅| 512 |
| RN50x4 | ✅ |✅ | ✅| 640 |
| RN50x16 | ✅ |✅ | ❌| 768 |
| RN50x64 | ✅ |✅ | ❌| 1024 |
| ViT-B/32 | ✅ |✅ | ✅| 512 |
| ViT-B/16 | ✅ |✅ | ✅| 512 |
| ViT-L/14 | ✅ |✅ | ✅| 768 |
| ViT-L/14-336px | ✅ |✅ | ❌| 768 |
Open AI has released 9 models so far. `ViT-B/32` is used as default model in all runtimes. Due to the limitation of some runtime, not every runtime supports all nine models. Please also note that different model give different size of output dimensions. This will affect your downstream applications. For example, switching the model from one to another make your embedding incomparable, which breaks the downstream applications. Below is a list of supported models of each runtime and its corresponding size. We include the disk usage (in delta) and the peak RAM and VRAM usage (in delta) when running on a single Nvidia TITAN RTX GPU (24GB VRAM) using a default `minibatch_size=32` in server and a default `batch_size=8` in client.

| Model | PyTorch | ONNX | TensorRT | Output Dimension | Disk Usage (MB) | Peak RAM Usage (GB) | Peak VRAM Usage (GB) |
|----------------|---------|------|----------|------------------|-----------------|---------------------|----------------------|
| RN50 | ✅ | ✅ | ✅ | 1024 | 256 | 2.99 | 1.36 |
| RN101 | ✅ | ✅ | ✅ | 512 | 292 | 3.51 | 1.40 |
| RN50x4 | ✅ | ✅ | ✅ | 640 | 422 | 3.23 | 1.63 |
| RN50x16 | ✅ | ✅ | ❌ | 768 | 661 | 3.63 | 2.02 |
| RN50x64 | ✅ | ✅ | ❌ | 1024 | 1382 | 4.08 | 2.98 |
| ViT-B/32 | ✅ | ✅ | ✅ | 512 | 351 | 3.20 | 1.40 |
| ViT-B/16 | ✅ | ✅ | ✅ | 512 | 354 | 3.20 | 1.44 |
| ViT-L/14 | ✅ | ✅ | ✅ | 768 | 933 | 3.66 | 2.04 |
| ViT-L/14-336px | ✅ | ✅ | ❌ | 768 | 934 | 3.74 | 2.23 |


## YAML config
Expand Down
2 changes: 1 addition & 1 deletion scripts/benchmark.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -79,7 +79,7 @@ def run(self):
time_costs = []
for _ in range(self.num_iter):
start = time.perf_counter()
r = client.encode(batch)
r = client.encode(batch, batch_size=self.batch_size)
time_costs.append(time.perf_counter() - start)
self.avg_time = np.mean(time_costs[2:])

Expand Down