Code for the NeurIPS 2022 paper "Optimal Brain Compression: A Framework for Accurate Post-Training Quantization and Pruning".
active 2023-12-06 → 2026-02-22 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 810 days from 2023-12-06 to 2026-02-22. Pushes: 0 total, peak 0 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 3 total, peak 1 in a day. Comments: 3 total, peak 1 in a day. Stars: 31 total, peak 2 in a day.
- Pushes
- Pull requests
- Issues
- Comments
- Stars
Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.
Top contributors
Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity
| Contributor | Contributions | Pushes | PRs | Comments |
|---|---|---|---|---|
| vinsis | 2 | 0 | 0 | 1 |
| mj0219 | 1 | 0 | 0 | 0 |
| FangyanXiao | 1 | 0 | 0 | 0 |
| frankinwi | 1 | 0 | 0 | 1 |
| andyhahaha | 1 | 0 | 0 | 1 |
Recent activity
Latest issues, pull requests and releases
- Issue#9mj02192024-04-07 12:32Can I experiment with other models and datasets, such as MobileNetV2, VGG11, GoogleNet, etc. Thank you very much!
- Issue#5FangyanXiao2024-01-12 07:35About pruning in Mobilenet_v2
- Issue comment#5andyhahaha2024-01-12 07:27About pruning in Mobilenet_v2
- Issue comment#8vinsis2023-12-16 06:46`TrueOBS.quantize` could be made faster by calculating the inverse Hessian per row only once
- Issue#8vinsis2023-12-16 06:46`TrueOBS.quantize` could be made faster by calculating the inverse Hessian per row only once
- Issue comment#7frankinwi2023-12-07 09:02IndexError: index -10219 is out of bounds for axis 0 with size 10001 when running spdy.py for mixed quantization 2:4
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 31 stars here means stars gained during the window, not the repo's star count.