update readme and test

cli99 · Jan 3, 2024 · 9932ff4 · 9932ff4
1 parent f5acbde
commit 9932ff4
Showing 1 changed file with 1 addition and 2 deletions.
diff --git a/tests/test_inference.py b/tests/test_inference.py
@@ -75,5 +75,4 @@ def test_llama2_70b():
         num_tokens_to_generate=512,
     )
 
-    assert within_range(summary_dict["total_decode_latency"], 180.06,
-                        TOLERANCE)
+    assert within_range(summary_dict["total_decode_latency"], 18.06, TOLERANCE)