45 lines
1.1 KiB
Markdown
45 lines
1.1 KiB
Markdown
# AstrAI Promo — 动画渲染
|
||
|
||
Manim 驱动的技术动画，用于 AstrAI 宣传视频。
|
||
|
||
## 依赖
|
||
|
||
```bash
|
||
pip install manim
|
||
# 或: conda install -c conda-forge manim
|
||
```
|
||
|
||
## 渲染单个场景
|
||
|
||
```bash
|
||
# 1080p（推荐）
|
||
manim -qh promo/continuous_batching.py ContinuousBatching
|
||
|
||
# 480p 草稿
|
||
manim -ql promo/continuous_batching.py ContinuousBatching
|
||
|
||
# 4K
|
||
manim -4k promo/continuous_batching.py ContinuousBatching
|
||
```
|
||
|
||
## 渲染全部
|
||
|
||
```bash
|
||
python promo/render_all.py
|
||
```
|
||
|
||
输出到 `promo/output/videos/`。
|
||
|
||
## 场景清单
|
||
|
||
| 文件 | Scene class | 内容 | 建议时长 |
|
||
|------|-------------|------|---------|
|
||
| `transformer.py` | `Transformer` | GQA 注意力机制详解 (Q/K/V→RoPE→Attention→O) + 规格卡 | ~25s |
|
||
| `continuous_batching.py` | `ContinuousBatching` | 4 阶段流水线 + 吞吐对比 | ~30s |
|
||
| `paged_cache.py` | `PrefixCache` | 分页 KV 缓存：页表分配、按需扩容、回收 | ~30s |
|
||
| `architecture.py` | `Architecture` | 全栈架构逐层展开 | ~30s |
|
||
|
||
## 导入视频剪辑
|
||
|
||
输出的 `.mp4` 直接导入 DaVinci Resolve / Camtasia / Premiere Pro。
|