Initial vLLM agent strategy

scripts/smoke_check.py

@@ -0,0 +1,42 @@
+from __future__ import annotations
+
+import argparse
+import json
+
+from app.clients.modelhub import ModelHubClient
+from app.domain.gpu import expand_gpu_aliases
+from app.domain.vllm_configs import gen_vllm_config
+from app.settings import load_settings
+
+
+def redact(payload: dict) -> dict:
+    clone = dict(payload)
+    if "contestApiToken" in clone:
+        clone["contestApiToken"] = "***"
+    return clone
+
+
+def main():
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--no-submit", action="store_true", help="Only print a redacted payload")
+    parser.add_argument("--model-id", default="Qwen/Qwen2.5-0.5B-Instruct")
+    parser.add_argument("--gpu-alias", default="k100")
+    args = parser.parse_args()
+
+    settings = load_settings(require_secrets=not args.no_submit)
+    client = ModelHubClient(settings)
+    pairs = expand_gpu_aliases([args.gpu_alias])
+    if not pairs:
+        raise SystemExit(f"unsupported gpu alias for vLLM: {args.gpu_alias}")
+    _, gpu_type = pairs[0]
+    config = gen_vllm_config(gpu_type, args.model_id, settings.default_max_model_len)
+    payload = client.build_contest_payload(args.model_id, gpu_type, config)
+    print(json.dumps(redact(payload), ensure_ascii=False, indent=2))
+    if args.no_submit:
+        return
+    result = client.create_contest_task(args.model_id, gpu_type, config)
+    print(result)
+
+
+if __name__ == "__main__":
+    main()