feat(benchmarks): support HF model names in multi-turn benchmark (#27850)

2c0c7c39 · ai-jz · GitHub · e6751188 · 2c0c7c39
Unverified Commit 2c0c7c39 authored Nov 01, 2025 by ai-jz Committed by GitHub Nov 01, 2025
Show whitespace changes
Inline Side-by-side

Showing with 0 additions and 2 deletions

benchmarks/multi_turn/benchmark_serving_multi_turn.py benchmarks/multi_turn/benchmark_serving_multi_turn.py +0 -2

No files found.
--- a/benchmarks/multi_turn/benchmark_serving_multi_turn.py
+++ b/benchmarks/multi_turn/benchmark_serving_multi_turn.py
@@ -1429,8 +1429,6 @@ async def main() -> None:
    random.seed(args.seed)
    np.random.seed(args.seed)

-    if not os.path.exists(args.model):
-        raise OSError(f"Path does not exist: {args.model}")
    logger.info("Loading tokenizer")
    tokenizer = AutoTokenizer.from_pretrained(args.model)