Update readme (#434)

2024-05-13 00:17:02 -07:00
parent 39191c8515
commit 455c9ccc4a
2 changed files with 7 additions and 4 deletions
--- a/benchmark/latency_throughput/test_latency.py
+++ b/benchmark/latency_throughput/test_latency.py
@@ -30,7 +30,8 @@ if __name__ == "__main__":
        response = requests.post(
            url + "/generate",
            json={
-                "input_ids": [[1,2,3], [1,2,3]],
+                "text": f"{a}, ",
+                #"input_ids": [[2] * 256] * 196,
                "sampling_params": {
                    "temperature": 0,
                    "max_new_tokens": max_new_tokens,