adapt to sglang v0.5.2rc1 on dcu

python/sglang/README.md

+# Code Structures
+
+- `eval`: The evaluation utilities.
+- `lang`: The frontend language.
+- `srt`: The backend engine for running local models. (SRT = SGLang Runtime).
+- `test`: The test utilities.
+- `api.py`: The public APIs.
+- `bench_offline_throughput.py`: Benchmark the performance in the offline mode.
+- `bench_one_batch.py`: Benchmark the latency of running a single static batch without a server.
+- `bench_one_batch_server.py`: Benchmark the latency of running a single batch with a server.
+- `bench_serving.py`: Benchmark online serving with dynamic requests.
+- `check_env.py`: Check the environment variables and dependencies.
+- `global_config.py`: The global configs and constants.
+- `launch_server.py`: The entry point for launching the local server.
+- `utils.py`: Common utilities.
+- `version.py`: Version info.

python/sglang/__init__.py

+# SGLang public APIs
+
+# Frontend Language APIs
+from sglang.global_config import global_config
+from sglang.lang.api import (
+    Engine,
+    Runtime,
+    assistant,
+    assistant_begin,
+    assistant_end,
+    flush_cache,
+    function,
+    gen,
+    gen_int,
+    gen_string,
+    get_server_info,
+    image,
+    select,
+    separate_reasoning,
+    set_default_backend,
+    system,
+    system_begin,
+    system_end,
+    user,
+    user_begin,
+    user_end,
+    video,
+)
+from sglang.lang.backend.runtime_endpoint import RuntimeEndpoint
+from sglang.lang.choices import (
+    greedy_token_selection,
+    token_length_normalized,
+    unconditional_likelihood_normalized,
+)
+
+# Lazy import some libraries
+from sglang.utils import LazyImport
+from sglang.version import __version__
+
+Anthropic = LazyImport("sglang.lang.backend.anthropic", "Anthropic")
+LiteLLM = LazyImport("sglang.lang.backend.litellm", "LiteLLM")
+OpenAI = LazyImport("sglang.lang.backend.openai", "OpenAI")
+VertexAI = LazyImport("sglang.lang.backend.vertexai", "VertexAI")
+
+# Runtime Engine APIs
+ServerArgs = LazyImport("sglang.srt.server_args", "ServerArgs")
+Engine = LazyImport("sglang.srt.entrypoints.engine", "Engine")
+
+__all__ = [
+    "Engine",
+    "Runtime",
+    "assistant",
+    "assistant_begin",
+    "assistant_end",
+    "flush_cache",
+    "function",
+    "gen",
+    "gen_int",
+    "gen_string",
+    "get_server_info",
+    "image",
+    "select",
+    "separate_reasoning",
+    "set_default_backend",
+    "system",
+    "system_begin",
+    "system_end",
+    "user",
+    "user_begin",
+    "user_end",
+    "video",
+    "RuntimeEndpoint",
+    "greedy_token_selection",
+    "token_length_normalized",
+    "unconditional_likelihood_normalized",
+    "ServerArgs",
+    "Anthropic",
+    "LiteLLM",
+    "OpenAI",
+    "VertexAI",
+    "global_config",
+    "__version__",
+]