We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent e051869 commit 1214f99Copy full SHA for 1214f99
tests/unittest/_torch/speculative/test_eagle3.py
@@ -2,6 +2,7 @@
2
import os
3
import sys
4
import tempfile
5
+import unittest
6
from pathlib import Path
7
from unittest.mock import patch
8
@@ -374,7 +375,6 @@ def test_multi_eagle3(use_one_model: bool):
374
375
pass
376
377
-<<<<<<< HEAD
378
@pytest.mark.parametrize("disable_overlap_scheduler", [True, False])
379
def test_eagle3_cuda_graph_padding(disable_overlap_scheduler: bool):
380
"""Test CUDA graph padding with 3 requests and max_batch_size=4.
0 commit comments