Crash reporter for ML inference on edge devices: silent failures, latency collapse, OOM traces. In development.
Project description
crashframe
Crash reporter for ML inference on edge devices.
One line of code wraps your ONNX Runtime session; crashframe logs runtime errors, NaN and degenerate outputs, latency collapse, silent CPU fallback and OOM traces to a local file, with a built-in web report for headless devices. No cloud, no telemetry, numpy is the only dependency.
Status: in development. This release reserves the package name. Watch the repo for v0.1.
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 crashframe-0.0.1.tar.gz.
File metadata
- Download URL: crashframe-0.0.1.tar.gz
- Upload date:
- Size: 2.0 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.11.9
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
b535c657acda5e64363366a3be914b3fa2890c722aeaa8f8e924f16de46fa9dd
|
|
| MD5 |
e2bedecd14dc256517d8fbe9beeb2caf
|
|
| BLAKE2b-256 |
0967451b8dfacf33a0e1d57530f148704b34f226f76c59467dbc31048048ba7f
|
File details
Details for the file crashframe-0.0.1-py3-none-any.whl.
File metadata
- Download URL: crashframe-0.0.1-py3-none-any.whl
- Upload date:
- Size: 1.7 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.11.9
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
18924a1e7909ff23681c0d3faddc5b23087008541c82f17aaa542c318deef09f
|
|
| MD5 |
f369cdc1473a70d3d5184f1d4088a794
|
|
| BLAKE2b-256 |
5aafb2492fab8784fec3e18945921e06e2065a488afaf71a42b141743a5dea79
|
