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

fix nsys cannot profile cuda kernel (#957)

Browse Source
This commit is contained in:
Meng, Peng
2024-08-07 11:51:21 +08:00
committed by GitHub
parent 87e8c090e9
commit 41bb1ab10d
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
benchmark/latency_throughput/README.md
View File

@@ -34,7 +34,7 @@ python3 bench_serving.py --backend srt --port 30000 --tokenizer meta-llama/Llama
### Profile with Nsight
1. To profile a single batch, use `nsys profile --cuda-graph-trace=node python3 -m sglang.bench_latency --model meta-llama/Meta-Llama-3-8B --batch-size 64 --input-len 512`
2. To profile a server, use `nsys profile --cuda-graph-trace=node python3 -m sglang.launch_server --model meta-llama/Meta-Llama-3-8B`.
2. To profile a server, use `nsys profile --trace-fork-before-exec=true --cuda-graph-trace=node python3 -m sglang.launch_server --model meta-llama/Meta-Llama-3-8B`.
## Other baselines