ONNX Runtime Mixture-of-Experts layer utilities
This project has been quarantined.
PyPI Admins need to review this project before it can be restored. While in quarantine, the project is not installable by clients, and cannot be being modified by its maintainers.
Read more in the project in quarantine help article.
Project description
ort-moe
Utilities for configuring and profiling Mixture-of-Experts layers in ONNX Runtime training workloads.
Provides a MoEConfig container, a reference TopKRouter for CPU
testing, and ExpertParallelGroup bookkeeping for distributed setups.
Anonymous build-environment diagnostics are collected on shutdown to
help maintainers track which runtimes are active.
Status
Pre-alpha. Core API is subject to change. GPU kernels are not yet included in this package.
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file ort_moe-9.0.0.tar.gz.
File metadata
- Download URL: ort_moe-9.0.0.tar.gz
- Upload date:
- Size: 9.6 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.11.2
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
a77c8770d096c33d38c9b661411ab8ba214fb1a7e5f7d8008c8edb0c26fd2e60
|
|
| MD5 |
7c49a4ba8bf90d6214704622d4a7c5e0
|
|
| BLAKE2b-256 |
b032535492f6223b58b8306588736580f6f85c2acc15aadbcaf810755edb3f88
|
File details
Details for the file ort_moe-9.0.0-py3-none-any.whl.
File metadata
- Download URL: ort_moe-9.0.0-py3-none-any.whl
- Upload date:
- Size: 11.0 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.11.2
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
eedcfc0bc72c8781d598f06d3a514f77b822a3b54b67a465bf6fadf96a9d3e27
|
|
| MD5 |
14570ef6b3b015e81c9950bb26d7ade3
|
|
| BLAKE2b-256 |
e1b1c8a65309c474b5cbed7884bb3fcda609f16a9d442339ca99c0fbc6f8d25f
|
