From eac35143755ffef400b0fb99b6c267dc547d8536 Mon Sep 17 00:00:00 2001 From: wangli Date: Wed, 26 Feb 2025 16:40:43 +0800 Subject: [PATCH] fix doc Signed-off-by: wangli --- docs/source/tutorials.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/source/tutorials.md b/docs/source/tutorials.md index 4e94a10a..82bddbac 100644 --- a/docs/source/tutorials.md +++ b/docs/source/tutorials.md @@ -342,7 +342,7 @@ Benchmark vllm-ascend's performance under various workload, for **developers** t ### Quick Use #### Prerequisites - Please make sure that you have vllm and vllm-ascned installed and npu environment，cause these scripts are specially prepared for npu devices -- To speed up the script， you can cache the models and datasets locally in advance and change the path in the json file in the [benchmarks](../../benchmarks/scripts/tests/) folder +- To speed up the script， you can cache the models and datasets locally in advance and change the path in the json file in the [benchmarks](../benchmarks/scripts/tests/) folder #### Run benchmarks these scripts can automatically conduct performance testing of serving, through and latency, run the following command: