dgl-ascend
Deep Graph Library (DGL) with Ascend NPU support, developed by the BUPT-GAMMA group.
Installation
pip install dgl-ascend
Requirements: Ascend 910B NPU, CANN >= 8.5, aarch64 Linux, Python 3.11.
Quick Start
import torch
import torch_npu
import dgl
device = torch.device("npu:0")
g = dgl.graph(([0, 1, 2], [1, 2, 3])).to(device)
g.update_all(dgl.function.copy_u("x", "m"), dgl.function.sum("m", "h"))
License
Apache License 2.0.
1 maintainer
Metadata
1 maintainer
Release files for dgl-ascend 0.0.2
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Built distributions (wheels)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| dgl_ascend-0.0.2-cp311-cp311-manylinux_2_38_aarch64.whl | CPython 3.11 | CPython 3.11 | Linux glibc 2.38+ ARM64 | Details |
| dgl_ascend-0.0.2-cp311-cp311-manylinux_2_28_aarch64.whl | CPython 3.11 | CPython 3.11 | Linux glibc 2.28+ ARM64 | Details |
Total release size: 9.5 MB
Release files / dgl_ascend-0.0.2-cp311-cp311-manylinux_2_38_aarch64.whl
| Download URL | dgl_ascend-0.0.2-cp311-cp311-manylinux_2_38_aarch64.whl |
|---|---|
| Size | 4.7 MB |
| Tags | CPython 3.11 Linux glibc 2.38+ ARM64 |
|
SHA-256 checksum How to use checksums |
8506aac313481b91e17c312c3be39c74418e01b38d66b6dce6bf72770add0c02
|
|
BLAKE2b-256 checksum How to use checksums |
9c06d2a724e6bcdd3e4b5a922ce365a51c0eb6051bf480b8c3110e89c63e6e80
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.11.15
|
Release files / dgl_ascend-0.0.2-cp311-cp311-manylinux_2_28_aarch64.whl
| Download URL | dgl_ascend-0.0.2-cp311-cp311-manylinux_2_28_aarch64.whl |
|---|---|
| Size | 4.8 MB |
| Tags | CPython 3.11 Linux glibc 2.28+ ARM64 |
|
SHA-256 checksum How to use checksums |
a4ae478367dd615900414143fe86b946a1227c62037916610410d4e28062781f
|
|
BLAKE2b-256 checksum How to use checksums |
5f895bf6f2de0bbe2fed89dbd68563e0f0044a33b8bd9943a1d39d1611f6db32
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.11.14
|
