diff --git a/python/pyproject.toml b/python/pyproject.toml
index 016be10c0..6ec25a0d2 100755
--- a/python/pyproject.toml
+++ b/python/pyproject.toml
@@ -93,7 +93,6 @@ diffusion = [
   "remote-pdb",
   "st_attn ==0.0.7",
   "vsa==0.0.4",
-  "yunchang==0.6.3.post1",
   "runai_model_streamer",
   "cache-dit==1.1.8"
 ]
diff --git a/python/sglang/multimodal_gen/runtime/distributed/parallel_state.py b/python/sglang/multimodal_gen/runtime/distributed/parallel_state.py
index adbabaec9..367b9ccb3 100644
--- a/python/sglang/multimodal_gen/runtime/distributed/parallel_state.py
+++ b/python/sglang/multimodal_gen/runtime/distributed/parallel_state.py
@@ -418,7 +418,7 @@ def initialize_model_parallel(
 
         PROCESS_GROUP = _DummyProcessGroup()
     else:
-        # Build yunchang SP sub-groups based on the true SP groups. This is
+        # Build SGLang Diffusion SP sub-groups based on the true SP groups. This is
         # critical when TP>1, because SP groups may be strided in global ranks
         # (e.g., tp-sp order).
         sp_groups = rank_generator.get_ranks("sp")