Files
rocm_vllm_nightly/app/start_openai.py
T
2026-04-05 02:08:49 +08:00

94 lines
3.1 KiB
Python

import json
import os
import subprocess
import sys
from app.model_catalog import load_catalog, resolve_model_profile, resolve_runtime_settings
def build_command() -> list[str]:
config_file = "config.json"
catalog = load_catalog(config_file)
runtime = resolve_runtime_settings(catalog)
_, updates, env_vars = resolve_model_profile(
content=catalog,
requested_model=runtime["model_key"],
requested_tp=runtime["tensor_parallel_size"],
)
for key, value in env_vars.items():
os.environ[key] = value
host = str(runtime["openai_host"])
port = str(runtime["openai_port"])
public_model_name = str(runtime["public_model_name"]).strip()
default_enable_thinking = bool(runtime["default_enable_thinking"])
reasoning_enabled = bool(runtime["reasoning_enabled"])
api_key = runtime["api_key"] or ""
dtype = str(updates["dtype"] or runtime["dtype"])
quantization = str(updates["quantization"] or "").strip()
model_impl = str(updates["model_impl"] or "").strip()
reasoning_parser = str(updates["reasoning_parser"] or "").strip()
revision = runtime["revision"] or ""
cmd = [
sys.executable,
"-m",
"vllm.entrypoints.openai.api_server",
"--host",
host,
"--port",
port,
"--model",
str(updates["model_name"]),
"--served-model-name",
public_model_name or str(updates["served_model_name"]),
"--tensor-parallel-size",
str(updates["tensor_parallel_size"]),
"--max-model-len",
str(updates["max_model_len"]),
"--gpu-memory-utilization",
str(updates["gpu_memory_utilization"]),
"--max-num-seqs",
str(updates["max_num_seqs"]),
"--dtype",
dtype,
]
if updates["trust_remote_code"]:
cmd.append("--trust-remote-code")
if updates["enforce_eager"]:
cmd.append("--enforce-eager")
if updates["enable_auto_tool_choice"]:
cmd.append("--enable-auto-tool-choice")
if updates["tool_call_parser"]:
cmd.extend(["--tool-call-parser", str(updates["tool_call_parser"])])
cmd.extend(
[
"--default-chat-template-kwargs",
json.dumps({"enable_thinking": default_enable_thinking}),
]
)
if reasoning_enabled and reasoning_parser:
cmd.extend(["--reasoning-parser", reasoning_parser])
if quantization:
cmd.extend(["--quantization", quantization])
if model_impl:
cmd.extend(["--model-impl", model_impl])
if revision:
cmd.extend(["--revision", revision])
if api_key:
cmd.extend(["--api-key", api_key])
if updates.get("kv_cache_dtype"):
cmd.extend(["--kv-cache-dtype", str(updates["kv_cache_dtype"])])
if updates.get("enable_prefix_caching"):
cmd.append("--enable-prefix-caching")
if updates.get("max_num_batched_tokens", 0) > 0:
cmd.extend(["--max-num-batched-tokens", str(updates["max_num_batched_tokens"])])
return cmd
def main() -> None:
command = build_command()
raise SystemExit(subprocess.call(command))
if __name__ == "__main__":
main()