[ICLR2025]: OSTQuant: Refining Large Language Model Quantization with Orthogonal and Scaling Transformations for Better Distribution Fitting
active 2024-10-17 → 2026-05-27 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 588 days from 2024-10-17 to 2026-05-27. Pushes: 4 total, peak 2 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 17 total, peak 2 in a day. Comments: 13 total, peak 4 in a day. Stars: 68 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 |
|---|---|---|---|---|
| BrotherHappy | 11 | 3 | 0 | 6 |
| Wangguanru1 | 3 | 0 | 0 | 1 |
| thuiaaa | 2 | 0 | 0 | 2 |
| lidh15 | 2 | 0 | 0 | 2 |
| RanchiZhao | 2 | 0 | 0 | 0 |
| lzd19981105 | 2 | 0 | 0 | 0 |
| wowhao32 | 1 | 0 | 0 | 0 |
| grandxin | 1 | 0 | 0 | 0 |
| thu-mzy | 1 | 0 | 0 | 0 |
| JustQJ | 1 | 0 | 0 | 0 |
| ywlq | 1 | 0 | 0 | 1 |
| Coco58323 | 1 | 0 | 0 | 0 |
| StiphyJay | 1 | 1 | 0 | 0 |
| fxmarty-amd | 1 | 0 | 0 | 1 |
| songsm921 | 1 | 0 | 0 | 0 |
| LauraKrone24 | 1 | 0 | 0 | 0 |
| zhanglei1172 | 1 | 0 | 0 | 0 |
| xixi1998xixi | 1 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue#16thu-mzy2025-09-28 03:19可以提供一份详细的运行指南吗
- Issue comment#10Wangguanru12025-09-18 12:09Does jointly optimizing a rotation matrix with a scaling matrix have the same effect as optimizing only a rotation matrix?
- Issue comment#10fxmarty-amd2025-09-18 12:03Does jointly optimizing a rotation matrix with a scaling matrix have the same effect as optimizing only a rotation matrix?
- Issue#11BrotherHappy2025-09-04 13:10Please Support for Mamba
- Issue#13BrotherHappy2025-09-04 13:10脚本参数问题
- Issue comment#4lidh152025-09-02 02:12How to Calculate QSUR in practice？
- Issue comment#2BrotherHappy2025-09-02 02:07Comparison with FlatQuant
- Issue comment#8BrotherHappy2025-09-02 02:03How to save real quantized model to reproduce inference speedup and memory saving?
- Issue comment#13BrotherHappy2025-09-02 01:58脚本参数问题
- Issue#14zhanglei11722025-08-18 04:42好奇学习率是用什么方法搜出来的
- Issue#13JustQJ2025-06-24 07:48脚本参数问题
- Issue comment#4thuiaaa2025-06-04 04:11How to Calculate QSUR in practice？
- Issue comment#4thuiaaa2025-06-03 12:05How to Calculate QSUR in practice？
- Issue comment#4lidh152025-05-21 03:18How to Calculate QSUR in practice？
- Issue comment#6ywlq2025-05-11 06:23llama3和qwen系列的支持
- Issue#10Wangguanru12025-05-05 14:18Does jointly optimizing a rotation matrix with a scaling matrix have the same effect as optimizing only a rotation matrix?
- Issue#10Wangguanru12025-05-05 14:14Does jointly optimizing a rotation matrix with a scaling matrix have the same effect as optimizing only a rotation matrix?
- Issue#9wowhao322025-04-23 11:21Why Norm Weight is before R_res.T?
- Issue#8LauraKrone242025-04-11 08:23How to save real quantized model to reproduce inference speedup and memory saving?
- Issue comment#4BrotherHappy2025-04-09 02:03How to Calculate QSUR in practice？
- Issue#7lzd199811052025-04-02 06:52图5流程
- Issue#7lzd199811052025-04-02 06:41图5流程
- Issue comment#6BrotherHappy2025-03-10 02:35llama3和qwen系列的支持
- Issue#6grandxin2025-03-05 01:58llama3和qwen系列的支持
- Issue#5xixi1998xixi2025-02-21 09:03s_k^i
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 68 stars here means stars gained during the window, not the repo's star count.