chore: import upstream snapshot with attribution

examples/app/base_url/demo.py

@@ -0,0 +1,14 @@
+# Copyright (c) ModelScope Contributors. All rights reserved.
+import os
+
+os.environ['CUDA_VISIBLE_DEVICES'] = '0'
+
+if __name__ == '__main__':
+    from swift import AppArguments, DeployArguments, app_main, run_deploy
+
+    # Here's a runnable demo provided.
+    # In a real scenario, you can simply remove the deployed context.
+    with run_deploy(
+            DeployArguments(model='Qwen/Qwen2.5-1.5B-Instruct', verbose=False, log_interval=-1, infer_backend='vllm'),
+            return_url=True) as url:
+        app_main(AppArguments(model='Qwen2.5-1.5B-Instruct', base_url=url, stream=True, max_new_tokens=2048))

examples/app/base_url/demo.sh

@@ -0,0 +1,7 @@
+# You need to have a deployed model or api service first
+CUDA_VISIBLE_DEVICES=0 swift app \
+    --model '<model_name>' \
+    --base_url http://127.0.0.1:8000/v1 \
+    --stream true \
+    --max_new_tokens 2048 \
+    --lang zh

examples/app/llm/sglang.sh

@@ -0,0 +1,7 @@
+# test_env: pip install "sglang[all]==0.4.6.*" -U
+CUDA_VISIBLE_DEVICES=0 swift app \
+    --model Qwen/Qwen2.5-7B-Instruct \
+    --stream true \
+    --infer_backend sglang \
+    --max_new_tokens 2048 \
+    --lang zh

examples/app/llm/vllm.sh

@@ -0,0 +1,8 @@
+CUDA_VISIBLE_DEVICES=0 swift app \
+    --model Qwen/Qwen2.5-7B-Instruct \
+    --stream true \
+    --infer_backend vllm \
+    --max_new_tokens 2048 \
+    --vllm_gpu_memory_utilization 0.9 \
+    --vllm_max_model_len 8192 \
+    --lang zh

examples/app/mllm.sh

@@ -0,0 +1,13 @@
+CUDA_VISIBLE_DEVICES=0 \
+MAX_PIXELS=1003520 \
+VIDEO_MAX_PIXELS=50176 \
+FPS_MAX_FRAMES=12 \
+swift app \
+    --model Qwen/Qwen2.5-VL-7B-Instruct \
+    --stream true \
+    --infer_backend vllm \
+    --vllm_gpu_memory_utilization 0.9 \
+    --vllm_max_model_len 8192 \
+    --max_new_tokens 2048 \
+    --vllm_limit_mm_per_prompt '{"image": 5, "video": 2}' \
+    --lang zh