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

Fix the incorrect args in benchmark_and_profiling.md (#4542)

Browse Source 
Signed-off-by: Tianyu Zhou <albert.zty@antgroup.com>
This commit is contained in:
Albert
2025-03-18 15:07:06 +08:00
committed by GitHub
parent 804d250a0d
commit 2d0045125f
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
docs/references/benchmark_and_profiling.md
View File

@@ -35,7 +35,7 @@
python -m sglang.launch_server --model-path meta-llama/Llama-3.1-8B-Instruct
# send profiling request from client
python -m sglang.bench_serving --backend sglang --model-path meta-llama/Llama-3.1-8B-Instruct --num-prompts 10 --sharegpt-output-len 100 --profile
python -m sglang.bench_serving --backend sglang --model meta-llama/Llama-3.1-8B-Instruct --num-prompts 10 --sharegpt-output-len 100 --profile
```
Please make sure that the `SGLANG_TORCH_PROFILER_DIR` should be set at both server and client side, otherwise the trace file cannot be generated correctly . A secure way will be setting `SGLANG_TORCH_PROFILER_DIR` in the `.*rc` file of shell (e.g. `~/.bashrc` for bash shells).
@@ -59,7 +59,7 @@
For example, when profiling a server,
```bash
python -m sglang.bench_serving --backend sglang --model-path meta-llama/Llama-3.1-8B-Instruct --num-prompts 2 --sharegpt-output-len 100 --profile
python -m sglang.bench_serving --backend sglang --model meta-llama/Llama-3.1-8B-Instruct --num-prompts 2 --sharegpt-output-len 100 --profile
```
This command sets the number of prompts to 2 with `--num-prompts` argument and limits the length of output sequences to 100 with `--sharegpt-output-len` argument, which can generate a small trace file for browser to open smoothly.