From bf8a85cc6c9966301e69ff79636c5ce3939abae9 Mon Sep 17 00:00:00 2001 From: Hyunjae Woo Date: Tue, 3 Oct 2023 16:54:51 -0700 Subject: [PATCH] Remove note about 23.09 release --- src/c++/perf_analyzer/docs/llm.md | 9 --------- 1 file changed, 9 deletions(-) diff --git a/src/c++/perf_analyzer/docs/llm.md b/src/c++/perf_analyzer/docs/llm.md index dc9302310..b4102952e 100644 --- a/src/c++/perf_analyzer/docs/llm.md +++ b/src/c++/perf_analyzer/docs/llm.md @@ -28,15 +28,6 @@ OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. # Benchmarking LLM -> **Note** -> -> These benchmarks currently only work with Perf Analyzer built from the latest -> `main` branch. See -> [build from source instructions](install.md#build-from-source). If you are using -> Perf Analyzer from the Triton SDK container (e.g. -> `nvcr.io/nvidia/tritonserver:-py3-sdk`), you **will need to wait until the -> `23.09` container is released to perform the steps in this guide**. - The following guide shows the reader how to use Triton [Perf Analyzer](https://github.com/triton-inference-server/client/tree/main/src/c%2B%2B/perf_analyzer) to measure and characterize the performance behaviors of Large Language Models