sskj/README.md

64 lines
2.9 KiB
Markdown
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

# DSV4 / DeepSeek-V4-Flash 推理测速项目
> 记录 vllm-dspark、SGLang、vLLM 等后端在 DeepSeek-V4-Flash 上的 benchmark 脚本与最终结果。
## 目录说明
| 目录/文件 | 说明 |
|---|---|
| `scripts/` | 所有 benchmark 脚本、服务启动脚本、结果解析脚本 |
| `bench_results/` | 各次实验的最终产物:人可读 `.md` 报告 + 结构化 `results.json`(含原始数据与分位统计) |
| `BENCHMARK_WORKFLOW.md` | benchmark 目录与命名规范 |
| `scripts/SLO_STANDARDS.md` | 推理服务 SLO 标准TTFT/TPOT |
> 注:`.gitignore` 已排除 `envs/`、`deps/`、`tmp/`、`datasets/`、`logs/`、`*.zip`、原始 `raw_outputs/*.jsonl` 等大文件/中间文件。
## 实验索引
| 实验 | 脚本 | 最终报告 | 说明 |
|---|---|---|---|
| DSpark grid benchmark | `scripts/benchmark_dspark_0707/run_dspark_benchmark_grid.sh` | `bench_results/dspark_grid_20260707-132641/report.md` | P1/P2/P3 全量网格 |
| DSpark spec-tokens 对比 | `scripts/benchmark_dspark_0707/run_dspark_st_comparison.sh` | `bench_results/dspark_st_comparison_20260707-150649/comparison_report.md` | `--spec-tokens 3` vs `5` |
| SGLang EAGLE vs DSpark | `scripts/start_sglang_dsv4_8card.sh` + 对比解析脚本 | `bench_results/eagle_grid/dspark_vs_eagle_report.md` | EAGLE 投机解码对比 |
| SGLang vs vLLM 后端对比0707 | `scripts/benchmark_dsv4_backend_comparison.sh` | `bench_results/dsv4_backend_comparison_20260707/README.md` | 遗留 raw outputs 清单 |
| SGLang 8-card systematic | `scripts/run_sglang_benchmark.sh` | `bench_results/sglang_8card_systematic_20260704_120819/report.md` | 早期 SGLang 系统扫描 |
| SGLang 8-card max throughput | `scripts/run_sglang_max_throughput.sh` | `bench_results/sglang_8card_max_throughput_20260705_030839/summary.json` | 最大吞吐扫描 |
| vLLM-dspark Qwen3 | `scripts/bench_vllm_dspark_qwen3.py` | `bench_results/vllm_dspark_qwen3_20260705_121256/summary.json` | Qwen3 模型测速 |
| DSV4 后端对比0705 | `scripts/bench_dsv4_comparison.py` | `bench_results/dsv4_comparison_20260705_152221/summary.json` | 早期 DSpark 配置对比 |
## 快速复现
### DSpark grid
```bash
bash scripts/benchmark_dspark_0707/run_dspark_benchmark_grid.sh
```
### Spec-tokens 对比
```bash
bash scripts/benchmark_dspark_0707/run_dspark_st_comparison.sh
```
### 解析已有结果
```bash
/data/user1/yy/envs/sglang/bin/python scripts/benchmark_dspark_0707/parse_results.py \
/data/user1/yy/bench_results/dspark_grid_20260707-132641
```
## SLO 参考
详见 `scripts/SLO_STANDARDS.md`
主要关注指标:
- **TTFT P95**S2DeepSeek-V4-Flash 所在层)目标 `< 3s`
- **TPOT**S2 目标 `< 50ms`
## 环境要求
- Python env`/data/user1/yy/envs/vllm-dspark`(服务端)、`/data/user1/yy/envs/sglang`(压测客户端)
- 模型:`/data/models/DeepSeek-V4-Flash``/data/models/DeepSeek-V4-Flash-DSpark`
- 硬件8× H200当前配置