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

[Doc] fix wrong flag in deepseek documentation (#4427)

Browse Source
This commit is contained in:
Zhan Lu
2025-03-14 18:30:55 +00:00
committed by GitHub
parent 642ab418f3
commit 660305c38a
2 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
benchmark/deepseek_v3/README.md
View File

@@ -197,11 +197,11 @@ Assuming that master node IP is `MASTER_IP`, checkpoint path is `/path/to/DeepSe
#master
python3 -m sglang.launch_server \
--model meituan/DeepSeek-R1-Block-INT8 --tp 16 --dist-init-addr \
MASTER_IP:5000 --nnodes 2 --node-rank 0 --trust-remote --enable-torch-compile --torch-compile-max-bs 8
MASTER_IP:5000 --nnodes 2 --node-rank 0 --trust-remote-code --enable-torch-compile --torch-compile-max-bs 8
#cluster
python3 -m sglang.launch_server \
--model meituan/DeepSeek-R1-Block-INT8 --tp 16 --dist-init-addr \
MASTER_IP:5000 --nnodes 2 --node-rank 1 --trust-remote --enable-torch-compile --torch-compile-max-bs 8
MASTER_IP:5000 --nnodes 2 --node-rank 1 --trust-remote-code --enable-torch-compile --torch-compile-max-bs 8
```
> **Note that the launch command here enables `torch.compile` Optimization**. For optimal performance, please refer to the command options in [Performance Optimization Options](#option_args).

2
docs/references/deepseek.md
View File

@@ -141,7 +141,7 @@ With data parallelism attention enabled, we have achieved up to **1.9x** decodin
Add arguments `--speculative-algorithm`, `--speculative-draft-model-path`,
`--speculative-num-steps`, `--speculative-eagle-topk` and `--speculative-num-draft-tokens` to enable this feature. For example:
```
python3 -m sglang.launch_server --model-path deepseek-ai/DeepSeek-V3 --speculative-algorithm EAGLE --speculative-draft-model-path lmsys/DeepSeek-V3-NextN --speculative-num-steps 1 --speculative-eagle-topk 1 --speculative-num-draft-tokens 2 --trust-remote --tp 8
python3 -m sglang.launch_server --model-path deepseek-ai/DeepSeek-V3 --speculative-algorithm EAGLE --speculative-draft-model-path lmsys/DeepSeek-V3-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-NextN](https://huggingface.co/lmsys/DeepSeek-V3-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.