Simplify tokenizer manager (#2254)

2024-11-29 02:18:51 -08:00
parent 8b48496aaf
commit fe97a2d40f
7 changed files with 34 additions and 103 deletions
--- a/test/srt/test_srt_endpoint.py
+++ b/test/srt/test_srt_endpoint.py
@@ -220,9 +220,6 @@ class TestSRTEndpoint(unittest.TestCase):
        max_total_num_tokens = response_json["max_total_num_tokens"]
        self.assertIsInstance(max_total_num_tokens, int)

-        memory_pool_size = response_json["memory_pool_size"]
-        self.assertIsInstance(memory_pool_size, int)
-
        attention_backend = response_json["attention_backend"]
        self.assertIsInstance(attention_backend, str)