From eb768189eeb18e2f33518f45a7fd0b5e3b57c122 Mon Sep 17 00:00:00 2001 From: Mick Date: Sat, 17 Jan 2026 12:24:59 +0800 Subject: [PATCH] [diffusion] doc: add instruction for adding performance baseline of new model (#17249) --- python/sglang/multimodal_gen/docs/contributing.md | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/python/sglang/multimodal_gen/docs/contributing.md b/python/sglang/multimodal_gen/docs/contributing.md index 33a4699b8..78330c2ba 100644 --- a/python/sglang/multimodal_gen/docs/contributing.md +++ b/python/sglang/multimodal_gen/docs/contributing.md @@ -49,8 +49,11 @@ For PRs that impact **latency**, **throughput**, or **memory usage**, you **shou Consider adding tests to the `pr-test` or `nightly-test` suites to safeguard your changes, especially for PRs that: -1. support a new model -2. support or fix important features -3. significantly improve performance +- support a new model + - add a testcase for this new model to `testcase_configs.py` +- support or fix important features +- significantly improve performance + +Please run the according testcase, then update/add the baseline to `perf_baselines.json` by following the instruction in console if applicable. See [test](https://github.com/sgl-project/sglang/tree/main/python/sglang/multimodal_gen/test) for examples