This website requires JavaScript.
Explore
Help
Register
Sign In
Serendipity
/
CTI-Inference-Opt
Watch
1
Star
1
Fork
0
You've already forked CTI-Inference-Opt
Code
Issues
Pull Requests
Actions
Packages
Projects
Releases
Wiki
Activity
Files
69a0ad367ebc86dcee77f9c82b3e10da432d9ea3
CTI-Inference-Opt
/
代码
/
code
T
History
Serendipity
1cf1024368
revert: 移除 torch.compile(default 模式也因动态 batch 形状导致编译开销 > 收益)
...
保留 inference_mode + FP16 + Flash Attention(当前最优 56.98 分)
2026-06-13 12:07:28 +08:00
..
build_env.sh
fix: build_env.sh 简化为纯净版本(避免 CUDA 预热导致异常)
2026-06-12 21:55:09 +08:00
infer.py
revert: 移除 torch.compile(default 模式也因动态 batch 形状导致编译开销 > 收益)
2026-06-13 12:07:28 +08:00
requirements.txt
revert: requirements.txt 还原为原始完整依赖列表
2026-06-12 21:24:22 +08:00