From 4d635c035a0bf13b2486ffbf7e633e39bdb9a994 Mon Sep 17 00:00:00 2001 From: Adrian Tobiszewski Date: Fri, 31 Oct 2025 14:17:56 +0100 Subject: [PATCH 1/2] Update README.md --- demos/continuous_batching/agentic_ai/README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/demos/continuous_batching/agentic_ai/README.md b/demos/continuous_batching/agentic_ai/README.md index 82a60c09d1..00a9c4a9e0 100644 --- a/demos/continuous_batching/agentic_ai/README.md +++ b/demos/continuous_batching/agentic_ai/README.md @@ -489,7 +489,7 @@ Using LLM models with AI agents has a unique load characteristics with multi-tur To simulate such type of load, we should use a dedicated tool [multi_turn benchmark](https://github.com/vllm-project/vllm/tree/main/benchmarks/multi_turn). ```bash git clone -b v0.10.2 https://github.com/vllm-project/vllm -cd vllm/benchmarking/multi-turn +cd vllm/benchmarks/multi-turn pip install -r requirements.txt sed -i -e 's/if not os.path.exists(args.model)/if 1 == 0/g' benchmark_serving_multi_turn.py # Testing single client scenario, for example with GPU execution From 34e765b99277f26b628cd7205a725a8047e6304e Mon Sep 17 00:00:00 2001 From: Adrian Tobiszewski Date: Fri, 31 Oct 2025 15:15:26 +0100 Subject: [PATCH 2/2] Update demos/continuous_batching/agentic_ai/README.md --- demos/continuous_batching/agentic_ai/README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/demos/continuous_batching/agentic_ai/README.md b/demos/continuous_batching/agentic_ai/README.md index 00a9c4a9e0..55414c08c1 100644 --- a/demos/continuous_batching/agentic_ai/README.md +++ b/demos/continuous_batching/agentic_ai/README.md @@ -489,7 +489,7 @@ Using LLM models with AI agents has a unique load characteristics with multi-tur To simulate such type of load, we should use a dedicated tool [multi_turn benchmark](https://github.com/vllm-project/vllm/tree/main/benchmarks/multi_turn). ```bash git clone -b v0.10.2 https://github.com/vllm-project/vllm -cd vllm/benchmarks/multi-turn +cd vllm/benchmarks/multi_turn pip install -r requirements.txt sed -i -e 's/if not os.path.exists(args.model)/if 1 == 0/g' benchmark_serving_multi_turn.py # Testing single client scenario, for example with GPU execution