Add SGLang inference benchmark doc w/ initial support for DeepSeek-R1-Distill-Qwen-32B (#4870)

This commit is contained in:
yugang-amd
2025-07-25 12:42:40 -04:00
committed by GitHub
parent 2c9c3d0ba1
commit cc5bc5a882
6 changed files with 328 additions and 0 deletions

View File

@@ -82,6 +82,8 @@ subtrees:
title: vLLM inference performance testing
- file: how-to/rocm-for-ai/inference/benchmark-docker/pytorch-inference.rst
title: PyTorch inference performance testing
- file: how-to/rocm-for-ai/inference/benchmark-docker/sglang.rst
title: SGLang inference performance testing
- file: how-to/rocm-for-ai/inference/deploy-your-model.rst
title: Deploy your model