Merge branch 'main' into qwen-image-2.1

Signed-off-by: Isotr0py <Isotr0py@outlook.com>

examples/offline_inference/text_to_image/text_to_image.py

@@ -158,7 +158,11 @@ def parse_args() -> argparse.Namespace:
     parser.add_argument(
         "--enable-cache-dit-summary",
         action="store_true",
-        help="Enable cache-dit summary logging after diffusion forward passes.",
+        default=None,
+        help=(
+            "Enable cache-dit summary logging after diffusion forward passes. "
+            "Default: unset (defer to the deploy YAML's enable_cache_dit_summary)."
+        ),
     )
     parser.add_argument(
         "--ulysses-degree",

examples/offline_inference/text_to_speech/README.md

@@ -563,7 +563,7 @@ Single-stage native AR TTS at 48 kHz. Pipeline: `feat_encoder → MiniCPM4 → F
 ```bash
 pip install voxcpm
 # or, for a local source checkout:
-export VLLM_OMNI_VOXCPM_CODE_PATH=/path/to/voxcpm
+pip install -e /path/to/voxcpm
 ```
 
 ### Quick start

examples/offline_inference/text_to_speech/voxcpm2/end2end.py

@@ -1,7 +1,10 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM-Omni project
+
 """Offline VoxCPM2 inference example (native AR pipeline).
 
 Uses the single-stage native AR config (voxcpm2.yaml).
-Requires the `voxcpm` package or VLLM_OMNI_VOXCPM_CODE_PATH env var.
+Requires the `voxcpm` package (pip install voxcpm).
 """
 
 from __future__ import annotations