An algorithm for weight-activation quantization (W4A4, W4A8) of LLMs, supporting both static and dynamic quantization
active 2024-10-08 → 2025-12-08 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 427 days from 2024-10-08 to 2025-12-08. Pushes: 7 total, peak 2 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 39 total, peak 5 in a day. Comments: 56 total, peak 5 in a day. Stars: 144 total, peak 11 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 |
|---|---|---|---|---|
| ChenMnZ | 43 | 7 | 0 | 28 |
| brisker | 6 | 0 | 0 | 5 |
| lonleyodd | 4 | 0 | 0 | 2 |
| jameshensman | 3 | 0 | 0 | 1 |
| Dianaia | 3 | 0 | 0 | 1 |
| yoghur | 3 | 0 | 0 | 1 |
| sasha-hailo | 3 | 0 | 0 | 2 |
| songh11 | 3 | 0 | 0 | 1 |
| fpcsong | 3 | 0 | 0 | 1 |
| L1aoXingyu | 3 | 0 | 0 | 2 |
| laomao0 | 2 | 0 | 0 | 1 |
| geqian-9192 | 2 | 0 | 0 | 1 |
| github-yizhang | 2 | 0 | 0 | 0 |
| ponytaill | 2 | 0 | 0 | 1 |
| yyfcc17 | 2 | 0 | 0 | 1 |
| ostix360 | 2 | 0 | 0 | 1 |
| z18256199275 | 2 | 0 | 0 | 1 |
| JustVelkhana | 1 | 0 | 0 | 0 |
| 01000-you | 1 | 0 | 0 | 1 |
| lsjlsj5846 | 1 | 0 | 0 | 0 |
Recent activity
Latest issues, pull requests and releases
- Issue#31MAI7162025-11-26 06:23Bug in get_wikitext2 validation loader in utils/data_utils.py
- Issue comment#23sasha-hailo2025-10-06 20:24Possible PrefixQuant issues on Smaller LLMs?
- Issue comment#23a192842025-10-06 13:04Possible PrefixQuant issues on Smaller LLMs?
- Issue comment#2454limiao2025-07-18 03:09qwen2.5支持吗
- Issue#27JustVelkhana2025-06-21 05:40Can't run evaluate for piqa datasets? May it because there's no lm_eval?
- Issue comment#25ChenMnZ2025-02-07 12:32Question about speedup
- Issue#25SemyonBevzuk2025-02-07 10:36Question about speedup
- Issue comment#11QingshuiL2025-01-24 02:34AttributeError: 'WrappedPrefixCausalLM' object has no attribute 'generate'
- Issue#24aqe6702025-01-23 11:26qwen2.5支持吗
- Issue comment#23ChenMnZ2025-01-16 02:46Possible PrefixQuant issues on Smaller LLMs?
- Issue comment#19ChenMnZ2025-01-15 02:37Not quant Q layer?
- Issue comment#23ChenMnZ2025-01-15 02:35Possible PrefixQuant issues on Smaller LLMs?
- Issue comment#23sasha-hailo2025-01-14 11:15Possible PrefixQuant issues on Smaller LLMs?
- Issue#23sasha-hailo2025-01-13 11:58Possible PrefixQuant issues on Smaller LLMs?
- Issue comment#22fpcsong2024-12-26 12:22Question about rotated model
- Issue#22fpcsong2024-12-26 12:22Question about rotated model
- Issue#22fpcsong2024-12-26 11:49Question about rotated model
- Issue comment#21laomao02024-12-20 07:07Question about Preventing Outlier Tokens during Inference
- Issue comment#20z182561992752024-12-16 03:08How to test chat model
- Issue comment#20yoghur2024-12-16 02:58How to test chat model
- Issue#20yoghur2024-12-16 02:57How to test chat model
- Issue#20yoghur2024-12-13 10:58How to test chat model
- Issue#19laomao02024-12-13 02:42Not quant Q layer?
- Issue#18z182561992752024-12-12 08:52evaluate error
- Issue#17lsjlsj58462024-12-12 02:29Why does finer granularity in quantization result in more overhead?
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 144 stars here means stars gained during the window, not the repo's star count.