server : adjust spec tests to generate up to 16 tokens (#19093)

diff --git a/tools/server/tests/unit/test_speculative.py b/tools/server/tests/unit/test_speculative.py
index d2f3fba5fe7a921baad8815406d8635cc13caf35..eebd3cc8fa2a361444ee03937cb1a99158a7afea 100644 (file)
--- a/tools/server/tests/unit/test_speculative.py
+++ b/tools/server/tests/unit/test_speculative.py
@@ -30,6 +30,7 @@ def test_with_and_without_draft():
         "prompt": "I believe the meaning of life is",
         "temperature": 0.0,
         "top_k": 1,
+        "n_predict": 16,
     })
     assert res.status_code == 200
     content_no_draft = res.body["content"]
@@ -42,6 +43,7 @@ def test_with_and_without_draft():
         "prompt": "I believe the meaning of life is",
         "temperature": 0.0,
         "top_k": 1,
+        "n_predict": 16,
     })
     assert res.status_code == 200
     content_draft = res.body["content"]
@@ -68,6 +70,7 @@ def test_different_draft_min_draft_max():
             "prompt": "I believe the meaning of life is",
             "temperature": 0.0,
             "top_k": 1,
+            "n_predict": 16,
         })
         assert res.status_code == 200
         if last_content is not None: