一种针对自注意力头激活的量化策略，该策略考虑到自注意力头中激活的异质分布特征，能够有效捕获量化参数以最小化多头自注意力层中的近似误差，同时通过运行时估计来降低量化参数存储成本，在保证模型性能的前提下将模型量化为8比特。在此基础上，结合针对输入维度的模型剪枝算法，本文还进一步提出了一种视觉Transformer的量化剪枝联合优化算法，通过评估线性层�
active 2025-02-09 → 2025-02-09 (UTC)
Activity over time
Daily event counts in the loaded window
Line chart, 1 days from 2025-02-09 to 2025-02-09. Pushes: 0 total, peak 0 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 0 total, peak 0 in a day. Comments: 0 total, peak 0 in a day. Stars: 0 total, peak 0 in a day.
- Pushes
- Pull requests
- Issues
- Comments
- Stars
Top contributors
Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity
Nobody pushed, opened or commented here in the loaded window — this repo's activity is stars and forks only.
Recent activity
Latest issues, pull requests and releases
No issue or PR events — this repo's activity is pushes only.
Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 0 stars here means stars gained during the window, not the repo's star count.