Skip to content

Commit

Permalink
[docs] Updates README for pytorch 2.0.1
Browse files Browse the repository at this point in the history
  • Loading branch information
@frankfliu
frankfliu committed Jul 13, 2023
1 parent 8dea610 commit f1e71b2
Show file tree
Hide file tree
Showing 2 changed files with 37 additions and 35 deletions.
1 change: 1 addition & 0 deletions README.md
View file
Original file line number Diff line number Diff line change
Expand Up @@ -85,6 +85,7 @@ The following pseudocode demonstrates running training:

## Release Notes

* [0.23.0](https://github.com/deepjavalibrary/djl/releases/tag/v0.23.0) ([Code](https://github.com/deepjavalibrary/djl/tree/v0.23.0))
* [0.22.1](https://github.com/deepjavalibrary/djl/releases/tag/v0.22.1) ([Code](https://github.com/deepjavalibrary/djl/tree/v0.22.1))
* [0.21.0](https://github.com/deepjavalibrary/djl/releases/tag/v0.21.0) ([Code](https://github.com/deepjavalibrary/djl/tree/v0.21.0))
* [0.20.0](https://github.com/deepjavalibrary/djl/releases/tag/v0.20.0) ([Code](https://github.com/deepjavalibrary/djl/tree/v0.20.0))
Expand Down
71 changes: 36 additions & 35 deletions engines/pytorch/pytorch-engine/README.md
View file
Original file line number Diff line number Diff line change
Expand Up @@ -46,6 +46,7 @@ The following table illustrates which pytorch version that DJL supports:

| PyTorch engine version | PyTorch native library version |
|------------------------|-------------------------------------------|
| pytorch-engine:0.23.0 | 1.11.0, 1.12.1, **1.13.1**, 2.0.1 |
| pytorch-engine:0.22.1 | 1.11.0, 1.12.1, **1.13.1**, 2.0.0 |
| pytorch-engine:0.21.0 | 1.11.0, 1.12.1, **1.13.1** |
| pytorch-engine:0.20.0 | 1.11.0, 1.12.1, **1.13.0** |
Expand Down Expand Up @@ -109,21 +110,21 @@ export PYTORCH_FLAVOR=cpu
### macOS
For macOS, you can use the following library:

- ai.djl.pytorch:pytorch-jni:2.0.0-0.22.1
- ai.djl.pytorch:pytorch-native-cpu:2.0.0:osx-x86_64
- ai.djl.pytorch:pytorch-jni:2.0.1-0.23.0
- ai.djl.pytorch:pytorch-native-cpu:2.0.1:osx-x86_64

```xml
<dependency>
<groupId>ai.djl.pytorch</groupId>
<artifactId>pytorch-native-cpu</artifactId>
<classifier>osx-x86_64</classifier>
<version>2.0.0</version>
<version>2.0.1</version>
<scope>runtime</scope>
</dependency>
<dependency>
<groupId>ai.djl.pytorch</groupId>
<artifactId>pytorch-jni</artifactId>
<version>2.0.0-0.22.1</version>
<version>2.0.1-0.23.0</version>
<scope>runtime</scope>
</dependency>
```
Expand All @@ -133,21 +134,21 @@ For macOS, you can use the following library:
### macOS M1
For macOS M1, you can use the following library:

- ai.djl.pytorch:pytorch-jni:2.0.0-0.22.1
- ai.djl.pytorch:pytorch-native-cpu:2.0.0:osx-aarch64
- ai.djl.pytorch:pytorch-jni:2.0.1-0.23.0
- ai.djl.pytorch:pytorch-native-cpu:2.0.1:osx-aarch64

```xml
<dependency>
<groupId>ai.djl.pytorch</groupId>
<artifactId>pytorch-native-cpu</artifactId>
<classifier>osx-aarch64</classifier>
<version>2.0.0</version>
<version>2.0.1</version>
<scope>runtime</scope>
</dependency>
<dependency>
<groupId>ai.djl.pytorch</groupId>
<artifactId>pytorch-jni</artifactId>
<version>2.0.0-0.22.1</version>
<version>2.0.1-0.23.0</version>
<scope>runtime</scope>
</dependency>
```
Expand All @@ -158,63 +159,63 @@ installed on your GPU machine, you can use one of the following library:

#### Linux GPU

- ai.djl.pytorch:pytorch-jni:2.0.0-0.22.1
- ai.djl.pytorch:pytorch-native-cu118:2.0.0:linux-x86_64 - CUDA 11.8
- ai.djl.pytorch:pytorch-jni:2.0.1-0.23.0
- ai.djl.pytorch:pytorch-native-cu118:2.0.1:linux-x86_64 - CUDA 11.8

```xml
<dependency>
<groupId>ai.djl.pytorch</groupId>
<artifactId>pytorch-native-cu118</artifactId>
<classifier>linux-x86_64</classifier>
<version>2.0.0</version>
<version>2.0.1</version>
<scope>runtime</scope>
</dependency>
<dependency>
<groupId>ai.djl.pytorch</groupId>
<artifactId>pytorch-jni</artifactId>
<version>2.0.0-0.22.1</version>
<version>2.0.1-0.23.0</version>
<scope>runtime</scope>
</dependency>
```

### Linux CPU

- ai.djl.pytorch:pytorch-jni:2.0.0-0.22.1
- ai.djl.pytorch:pytorch-native-cpu:2.0.0:linux-x86_64
- ai.djl.pytorch:pytorch-jni:2.0.1-0.23.0
- ai.djl.pytorch:pytorch-native-cpu:2.0.1:linux-x86_64

```xml
<dependency>
<groupId>ai.djl.pytorch</groupId>
<artifactId>pytorch-native-cpu</artifactId>
<classifier>linux-x86_64</classifier>
<scope>runtime</scope>
<version>2.0.0</version>
<version>2.0.1</version>
</dependency>
<dependency>
<groupId>ai.djl.pytorch</groupId>
<artifactId>pytorch-jni</artifactId>
<version>2.0.0-0.22.1</version>
<version>2.0.1-0.23.0</version>
<scope>runtime</scope>
</dependency>
```

### For aarch64 build

- ai.djl.pytorch:pytorch-jni:2.0.0-0.22.1
- ai.djl.pytorch:pytorch-native-cpu-precxx11:2.0.0:linux-aarch64
- ai.djl.pytorch:pytorch-jni:2.0.1-0.23.0
- ai.djl.pytorch:pytorch-native-cpu-precxx11:2.0.1:linux-aarch64

```xml
<dependency>
<groupId>ai.djl.pytorch</groupId>
<artifactId>pytorch-native-cpu-precxx11</artifactId>
<classifier>linux-aarch64</classifier>
<scope>runtime</scope>
<version>2.0.0</version>
<version>2.0.1</version>
</dependency>
<dependency>
<groupId>ai.djl.pytorch</groupId>
<artifactId>pytorch-jni</artifactId>
<version>2.0.0-0.22.1</version>
<version>2.0.1-0.23.0</version>
<scope>runtime</scope>
</dependency>
```
Expand All @@ -224,22 +225,22 @@ installed on your GPU machine, you can use one of the following library:
We also provide packages for the system like CentOS 7/Ubuntu 14.04 with GLIBC >= 2.17.
All the package were built with GCC 7, we provided a newer `libstdc++.so.6.24` in the package that contains `CXXABI_1.3.9` to use the package successfully.

- ai.djl.pytorch:pytorch-jni:2.0.0-0.22.1
- ai.djl.pytorch:pytorch-native-cu118-precxx11:2.0.0:linux-x86_64 - CUDA 11.8
- ai.djl.pytorch:pytorch-native-cpu-precxx11:2.0.0:linux-x86_64 - CPU
- ai.djl.pytorch:pytorch-jni:2.0.1-0.23.0
- ai.djl.pytorch:pytorch-native-cu118-precxx11:2.0.1:linux-x86_64 - CUDA 11.8
- ai.djl.pytorch:pytorch-native-cpu-precxx11:2.0.1:linux-x86_64 - CPU

```xml
<dependency>
<groupId>ai.djl.pytorch</groupId>
<artifactId>pytorch-native-cu118-precxx11</artifactId>
<classifier>linux-x86_64</classifier>
<version>2.0.0</version>
<version>2.0.1</version>
<scope>runtime</scope>
</dependency>
<dependency>
<groupId>ai.djl.pytorch</groupId>
<artifactId>pytorch-jni</artifactId>
<version>2.0.0-0.22.1</version>
<version>2.0.1-0.23.0</version>
<scope>runtime</scope>
</dependency>
```
Expand All @@ -249,13 +250,13 @@ All the package were built with GCC 7, we provided a newer `libstdc++.so.6.24` i
<groupId>ai.djl.pytorch</groupId>
<artifactId>pytorch-native-cpu-precxx11</artifactId>
<classifier>linux-x86_64</classifier>
<version>2.0.0</version>
<version>2.0.1</version>
<scope>runtime</scope>
</dependency>
<dependency>
<groupId>ai.djl.pytorch</groupId>
<artifactId>pytorch-jni</artifactId>
<version>2.0.0-0.22.1</version>
<version>2.0.1-0.23.0</version>
<scope>runtime</scope>
</dependency>
```
Expand All @@ -270,42 +271,42 @@ For the Windows platform, you can choose between CPU and GPU.

#### Windows GPU

- ai.djl.pytorch:pytorch-jni:2.0.0-0.22.1
- ai.djl.pytorch:pytorch-native-cu118:2.0.0:win-x86_64 - CUDA 11.8
- ai.djl.pytorch:pytorch-jni:2.0.1-0.23.0
- ai.djl.pytorch:pytorch-native-cu118:2.0.1:win-x86_64 - CUDA 11.8

```xml
<dependency>
<groupId>ai.djl.pytorch</groupId>
<artifactId>pytorch-native-cu118</artifactId>
<classifier>win-x86_64</classifier>
<version>2.0.0</version>
<version>2.0.1</version>
<scope>runtime</scope>
</dependency>
<dependency>
<groupId>ai.djl.pytorch</groupId>
<artifactId>pytorch-jni</artifactId>
<version>2.0.0-0.22.1</version>
<version>2.0.1-0.23.0</version>
<scope>runtime</scope>
</dependency>
```

### Windows CPU

- ai.djl.pytorch:pytorch-jni:2.0.0-0.22.1
- ai.djl.pytorch:pytorch-native-cpu:2.0.0:win-x86_64
- ai.djl.pytorch:pytorch-jni:2.0.1-0.23.0
- ai.djl.pytorch:pytorch-native-cpu:2.0.1:win-x86_64

```xml
<dependency>
<groupId>ai.djl.pytorch</groupId>
<artifactId>pytorch-native-cpu</artifactId>
<classifier>win-x86_64</classifier>
<scope>runtime</scope>
<version>2.0.0</version>
<version>2.0.1</version>
</dependency>
<dependency>
<groupId>ai.djl.pytorch</groupId>
<artifactId>pytorch-jni</artifactId>
<version>2.0.0-0.22.1</version>
<version>2.0.1-0.23.0</version>
<scope>runtime</scope>
</dependency>
```

0 comments on commit f1e71b2

Please sign in to comment.