A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 14, 05:30 UTC
[Docs] Fix a tip indentation and typo (#24419)
Signed-off-by: windsonsea <haifeng.yao@daocloud.io>
Michael Yao committed
Sep 8, 2025 at 15:19 UTC
2f0b833a05190a71e837f0b6d3e2a01c25c86e73
1 file changed
+1
-1
docs/contributing/profiling.md
+1
-1
@@ -19,7 +19,7 @@ When using `vllm bench serve`, you can enable profiling by passing the `--profil
19
Traces can be visualized using <https://ui.perfetto.dev/>.
20
21
!!! tip
22
-You can directly call bench module without installing vllm using `python -m vllm.entrypoints.cli.main bench`.
22
+ You can directly call bench module without installing vLLM using `python -m vllm.entrypoints.cli.main bench`.
23
24
!!! tip
25
Only send a few requests through vLLM when profiling, as the traces can get quite large. Also, no need to untar the traces, they can be viewed directly.