EngineX-Hygon/sglang
5
0
Fork 0
Code Issues Pull Requests Actions 7 Projects Releases Wiki Activity

Super tiny fix typo (#5559)

Browse Source
This commit is contained in:
fzyzcjy
2025-04-21 05:21:18 +08:00
committed by GitHub
parent fa2f677e18
commit 9c43477710
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/references/deepseek.md
View File

@@ -152,7 +152,7 @@ Add arguments `--speculative-algorithm`, `--speculative-draft-model-path`,
python3 -m sglang.launch_server --model-path deepseek-ai/DeepSeek-V3-0324 --speculative-algorithm EAGLE --speculative-draft-model-path lmsys/DeepSeek-V3-0324-NextN --speculative-num-steps 1 --speculative-eagle-topk 1 --speculative-num-draft-tokens 2 --trust-remote-code --tp 8
```
- The draft model are available at huggingface: [lmsys/DeepSeek-V3-0324-NextN](https://huggingface.co/lmsys/DeepSeek-V3-0324-NextN), [lmsys/DeepSeek-R1-NextN](https://huggingface.co/lmsys/DeepSeek-R1-NextN). It can also be exported from original DeepSeek-V3/R1 model with [export_deepseek_nextn.py](https://github.com/sgl-project/sglang/blob/main/scripts/export_deepseek_nextn.py) script.
- The best configuratin for `--speculative-num-steps`, `--speculative-eagle-topk` and `--speculative-num-draft-tokens` can be searched with [bench_speculative.py](https://github.com/sgl-project/sglang/blob/main/scripts/playground/bench_speculative.py) script for given batch size. The minimum configuration is `--speculative-num-steps 1 --speculative-eagle-topk 1 --speculative-num-draft-tokens 2`, which can achieve speedup for larger batch sizes.
- The best configuration for `--speculative-num-steps`, `--speculative-eagle-topk` and `--speculative-num-draft-tokens` can be searched with [bench_speculative.py](https://github.com/sgl-project/sglang/blob/main/scripts/playground/bench_speculative.py) script for given batch size. The minimum configuration is `--speculative-num-steps 1 --speculative-eagle-topk 1 --speculative-num-draft-tokens 2`, which can achieve speedup for larger batch sizes.
When using FlashInfer MLA wrapper (`--attention-backend flashinfer`) with speculative decoding, set the `--speculative-eagle-topk` parameter to `1`. The FlashAttention 3 backend also only supports `--speculative-eagle-topk 1`.
- To enable DeepSeek MTP for large batch sizes (>32), there are some parameters should be changed (Reference [this discussion](https://github.com/sgl-project/sglang/issues/4543#issuecomment-2737413756)):
- Adjust `--max-running-requests` to a larger number. The default value is `32` for MTP. For larger batch sizes, you should increase this value beyond the default value.