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

Jump to bottom

[pytorch] Upgrade pytorch 1.13.0 documents #2158

Merged
merged 1 commit into from
Nov 17, 2022
Merged

[pytorch] Upgrade pytorch 1.13.0 documents #2158

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
13 changes: 8 additions & 5 deletions docs/development/dependency_management.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -61,19 +61,22 @@ See [How to use DJL's BOM](../../bom/README.md#how-to-use-djls-bom) for detail.
| | [pytorch-native-cpu(osx-aarch64)](../../engines/pytorch/pytorch-engine/README.md#macos-m1) | Contains PyTorch native library for macOS M1 |
| | [pytorch-native-cpu(win-x86_64)](../../engines/pytorch/pytorch-engine/README.md#windows-cpu) | Contains PyTorch native library for Windows |
| | [pytorch-native-cpu(linux-x86_64)](../../engines/pytorch/pytorch-engine/README.md#linux-cpu) | Contains PyTorch native library for Linux |
| | [pytorch-native-cu116(linux-x86_64)](../../engines/pytorch/pytorch-engine/README.md#linux-gpu) | Contains PyTorch native library for Linux with CUDA 11.6 |
| | [pytorch-native-cu116(win-x86_64)](../../engines/pytorch/pytorch-engine/README.md#windows-gpu) | Contains PyTorch native library for Windows with CUDA 11.6 |
| | [pytorch-native-cu102(linux-x86_64)](../../engines/pytorch/pytorch-engine/README.md#linux-gpu) | Contains PyTorch native library for Linux with CUDA 10.2 |
| | [pytorch-native-cu102(win-x86_64)](../../engines/pytorch/pytorch-engine/README.md#windows-gpu) | Contains PyTorch native library for Windows with CUDA 10.2 |
| | [pytorch-native-cu116-precxx11(linux-x86_64)](../../engines/pytorch/pytorch-engine/README.md#for-pre-cxx11-build) | Contains PyTorch native library for Linux with CUDA 11.6 |
| | [pytorch-native-cu117(linux-x86_64)](../../engines/pytorch/pytorch-engine/README.md#linux-gpu) | Contains PyTorch native library for Linux with CUDA 11.7 |
| | [pytorch-native-cu117(win-x86_64)](../../engines/pytorch/pytorch-engine/README.md#windows-gpu) | Contains PyTorch native library for Windows with CUDA 11.7 |
| | [pytorch-native-cu117-precxx11(linux-x86_64)](../../engines/pytorch/pytorch-engine/README.md#for-pre-cxx11-build) | Contains PyTorch native library for Linux with CUDA 11.7 |
| | [pytorch-native-cpu-precxx11(linux-x86_64)](../../engines/pytorch/pytorch-engine/README.md#for-pre-cxx11-build) | Contains PyTorch native library for centOS 7 and Ubuntu 14.04 |
| | [pytorch-native-cpu-precxx11(linux-aarch64)](../../engines/pytorch/pytorch-engine/README.md#for-aarch64-build) | Contains PyTorch native library for Linux ARM |
| | [pytorch-jni](../../engines/pytorch/pytorch-engine/README.md) | Contains PyTorch JNI native library |
| | pytorch-native-auto (deprecated) | No longer needed since DJL 0.15.0 |
| | pytorch-native-cu116(linux-x86_64) (deprecated) | Contains PyTorch native library for Linux with CUDA 11.6 |
| | pytorch-native-cu116(win-x86_64) (deprecated) | Contains PyTorch native library for Windows with CUDA 11.6 |
| | pytorch-native-cu116-precxx11(linux-x86_64) (deprecated) | Contains PyTorch native library for Linux with CUDA 11.6 |
| | pytorch-native-cu113(linux-x86_64) (deprecated) | Contains PyTorch native library for Linux with CUDA 11.3 |
| | pytorch-native-cu113(win-x86_64) (deprecated) | Contains PyTorch native library for Windows with CUDA 11.3 |
| | pytorch-native-cu111(linux-x86_64) (deprecated) | Contains PyTorch native library for Linux with CUDA 11.1 |
| | pytorch-native-cu111(win-x86_64) (deprecated) | Contains PyTorch native library for Windows with CUDA 11.1 |
| | pytorch-native-cu102(linux-x86_64) (deprecated) | Contains PyTorch native library for Linux with CUDA 10.2 |
| | pytorch-native-cu102(win-x86_64) (deprecated) | Contains PyTorch native library for Windows with CUDA 10.2 |
| | pytorch-native-cu101(linux-x86_64) (deprecated) | Contains PyTorch native library <= 1.7.1 for Linux with CUDA 10.1 |
| | pytorch-native-cu101(win-x86_64) (deprecated) | Contains PyTorch native library <= 1.7.1 for Windows with CUDA 10.1 |
| | pytorch-native-cu92(linux-x86_64) (deprecated) | Contains PyTorch native library <= 1.6.0 for Linux with CUDA 9.2 |
Expand Down
94 changes: 39 additions & 55 deletions engines/pytorch/pytorch-engine/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -45,6 +45,7 @@ The following table illustrates which pytorch version that DJL supports:

| PyTorch engine version | PyTorch native library version |
|------------------------|-------------------------------------------|
| pytorch-engine:0.20.0 | 1.11.0, 1.12.1, 1.13.0 |
| pytorch-engine:0.19.0 | 1.10.0, 1.11.0, 1.12.1 |
| pytorch-engine:0.18.0 | 1.9.1, 1.10.0, 1.11.0 |
| pytorch-engine:0.17.0 | 1.9.1, 1.10.0, 1.11.0 |
Expand Down Expand Up @@ -80,43 +81,43 @@ to avoid downloading the native libraries at runtime.
### macOS
For macOS, you can use the following library:

- ai.djl.pytorch:pytorch-jni:1.12.1-0.19.0
- ai.djl.pytorch:pytorch-native-cpu:1.12.1:osx-x86_64
- ai.djl.pytorch:pytorch-jni:1.13.0-0.20.0
- ai.djl.pytorch:pytorch-native-cpu:1.13.0:osx-x86_64

```xml
<dependency>
<groupId>ai.djl.pytorch</groupId>
<artifactId>pytorch-native-cpu</artifactId>
<classifier>osx-x86_64</classifier>
<version>1.12.1</version>
<version>1.13.0</version>
<scope>runtime</scope>
</dependency>
<dependency>
<groupId>ai.djl.pytorch</groupId>
<artifactId>pytorch-jni</artifactId>
<version>1.12.1-0.19.0</version>
<version>1.13.0-0.20.0</version>
<scope>runtime</scope>
</dependency>
```

### macOS M1
For macOS M1, you can use the following library:

- ai.djl.pytorch:pytorch-jni:1.12.1-0.19.0
- ai.djl.pytorch:pytorch-native-cpu:1.12.1:osx-aarch64
- ai.djl.pytorch:pytorch-jni:1.13.0-0.20.0
- ai.djl.pytorch:pytorch-native-cpu:1.13.0:osx-aarch64

```xml
<dependency>
<groupId>ai.djl.pytorch</groupId>
<artifactId>pytorch-native-cpu</artifactId>
<classifier>osx-aarch64</classifier>
<version>1.12.1</version>
<version>1.13.0</version>
<scope>runtime</scope>
</dependency>
<dependency>
<groupId>ai.djl.pytorch</groupId>
<artifactId>pytorch-jni</artifactId>
<version>1.12.1-0.19.0</version>
<version>1.13.0-0.20.0</version>
<scope>runtime</scope>
</dependency>
```
Expand All @@ -127,80 +128,63 @@ installed on your GPU machine, you can use one of the following library:

#### Linux GPU

- ai.djl.pytorch:pytorch-jni:1.12.1-0.19.0
- ai.djl.pytorch:pytorch-native-cu116:1.12.1:linux-x86_64 - CUDA 11.6
- ai.djl.pytorch:pytorch-native-cu102:1.12.1:linux-x86_64 - CUDA 10.2
- ai.djl.pytorch:pytorch-jni:1.13.0-0.20.0
- ai.djl.pytorch:pytorch-native-cu117:1.13.0:linux-x86_64 - CUDA 11.7

```xml
<dependency>
<groupId>ai.djl.pytorch</groupId>
<artifactId>pytorch-native-cu116</artifactId>
<artifactId>pytorch-native-cu117</artifactId>
<classifier>linux-x86_64</classifier>
<version>1.12.1</version>
<version>1.13.0</version>
<scope>runtime</scope>
</dependency>
<dependency>
<groupId>ai.djl.pytorch</groupId>
<artifactId>pytorch-jni</artifactId>
<version>1.12.1-0.19.0</version>
<scope>runtime</scope>
</dependency>
```

```xml
<dependency>
<groupId>ai.djl.pytorch</groupId>
<artifactId>pytorch-native-cu102</artifactId>
<classifier>linux-x86_64</classifier>
<version>1.12.1</version>
<scope>runtime</scope>
</dependency>
<dependency>
<groupId>ai.djl.pytorch</groupId>
<artifactId>pytorch-jni</artifactId>
<version>1.12.1-0.19.0</version>
<version>1.13.0-0.20.0</version>
<scope>runtime</scope>
</dependency>
```

### Linux CPU

- ai.djl.pytorch:pytorch-jni:1.12.1-0.19.0
- ai.djl.pytorch:pytorch-native-cpu:1.12.1:linux-x86_64
- ai.djl.pytorch:pytorch-jni:1.13.0-0.20.0
- ai.djl.pytorch:pytorch-native-cpu:1.13.0:linux-x86_64

```xml
<dependency>
<groupId>ai.djl.pytorch</groupId>
<artifactId>pytorch-native-cpu</artifactId>
<classifier>linux-x86_64</classifier>
<scope>runtime</scope>
<version>1.12.1</version>
<version>1.13.0</version>
</dependency>
<dependency>
<groupId>ai.djl.pytorch</groupId>
<artifactId>pytorch-jni</artifactId>
<version>1.12.1-0.19.0</version>
<version>1.13.0-0.20.0</version>
<scope>runtime</scope>
</dependency>
```

### For aarch64 build

- ai.djl.pytorch:pytorch-jni:1.12.1-0.19.0
- ai.djl.pytorch:pytorch-native-cpu-precxx11:1.12.1:linux-aarch64
- ai.djl.pytorch:pytorch-jni:1.13.0-0.20.0
- ai.djl.pytorch:pytorch-native-cpu-precxx11:1.13.0:linux-aarch64

```xml
<dependency>
<groupId>ai.djl.pytorch</groupId>
<artifactId>pytorch-native-cpu-precxx11</artifactId>
<classifier>linux-aarch64</classifier>
<scope>runtime</scope>
<version>1.12.1</version>
<version>1.13.0</version>
</dependency>
<dependency>
<groupId>ai.djl.pytorch</groupId>
<artifactId>pytorch-jni</artifactId>
<version>1.12.1-0.19.0</version>
<version>1.13.0-0.20.0</version>
<scope>runtime</scope>
</dependency>
```
Expand All @@ -210,22 +194,22 @@ 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:1.12.1-0.19.0
- ai.djl.pytorch:pytorch-native-cu116-precxx11:1.12.1:linux-x86_64 - CUDA 11.6
- ai.djl.pytorch:pytorch-native-cpu-precxx11:1.12.1:linux-x86_64 - CPU
- ai.djl.pytorch:pytorch-jni:1.13.0-0.20.0
- ai.djl.pytorch:pytorch-native-cu117-precxx11:1.13.0:linux-x86_64 - CUDA 11.7
- ai.djl.pytorch:pytorch-native-cpu-precxx11:1.13.0:linux-x86_64 - CPU

```xml
<dependency>
<groupId>ai.djl.pytorch</groupId>
<artifactId>pytorch-native-cu116-precxx11</artifactId>
<artifactId>pytorch-native-cu117-precxx11</artifactId>
<classifier>linux-x86_64</classifier>
<version>1.12.1</version>
<version>1.13.0</version>
<scope>runtime</scope>
</dependency>
<dependency>
<groupId>ai.djl.pytorch</groupId>
<artifactId>pytorch-jni</artifactId>
<version>1.12.1-0.19.0</version>
<version>1.13.0-0.20.0</version>
<scope>runtime</scope>
</dependency>
```
Expand All @@ -235,13 +219,13 @@ 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>1.12.1</version>
<version>1.13.0</version>
<scope>runtime</scope>
</dependency>
<dependency>
<groupId>ai.djl.pytorch</groupId>
<artifactId>pytorch-jni</artifactId>
<version>1.12.1-0.19.0</version>
<version>1.13.0-0.20.0</version>
<scope>runtime</scope>
</dependency>
```
Expand All @@ -256,42 +240,42 @@ For the Windows platform, you can choose between CPU and GPU.

#### Windows GPU

- ai.djl.pytorch:pytorch-jni:1.12.1-0.19.0
- ai.djl.pytorch:pytorch-native-cu116:1.12.1:win-x86_64
- ai.djl.pytorch:pytorch-jni:1.13.0-0.20.0
- ai.djl.pytorch:pytorch-native-cu117:1.13.0:win-x86_64 - CUDA 11.7

```xml
<dependency>
<groupId>ai.djl.pytorch</groupId>
<artifactId>pytorch-native-cu116</artifactId>
<artifactId>pytorch-native-cu117</artifactId>
<classifier>win-x86_64</classifier>
<version>1.12.1</version>
<version>1.13.0</version>
<scope>runtime</scope>
</dependency>
<dependency>
<groupId>ai.djl.pytorch</groupId>
<artifactId>pytorch-jni</artifactId>
<version>1.12.1-0.19.0</version>
<version>1.13.0-0.20.0</version>
<scope>runtime</scope>
</dependency>
```

### Windows CPU

- ai.djl.pytorch:pytorch-jni:1.12.1-0.19.0
- ai.djl.pytorch:pytorch-native-cpu:1.12.1:win-x86_64
- ai.djl.pytorch:pytorch-jni:1.13.0-0.20.0
- ai.djl.pytorch:pytorch-native-cpu:1.13.0:win-x86_64

```xml
<dependency>
<groupId>ai.djl.pytorch</groupId>
<artifactId>pytorch-native-cpu</artifactId>
<classifier>win-x86_64</classifier>
<scope>runtime</scope>
<version>1.12.1</version>
<version>1.13.0</version>
</dependency>
<dependency>
<groupId>ai.djl.pytorch</groupId>
<artifactId>pytorch-jni</artifactId>
<version>1.12.1-0.19.0</version>
<version>1.13.0-0.20.0</version>
<scope>runtime</scope>
</dependency>
```