Add more testing for chunked prefill (#27506)

2026-06-09 20:19:30 +08:00
parent 609f5f549c
commit 1368717248
42 changed files with 7929 additions and 22 deletions
@@ -0,0 +1,26 @@
+import unittest
+
+from sglang.test.chunked_prefill_test_utils import ChunkedTestBase
+
+
+class TestChunkedFeatureLoRAOverlap(ChunkedTestBase):
+    __test__ = True
+    model = "meta-llama/Llama-3.2-1B-Instruct"
+    gsm8k_threshold = 0.20
+    feature_args = [
+        "--enable-lora",
+        "--enable-lora-overlap-loading",
+        "--lora-paths",
+        "nicoboss/Llama-3.2-1B-Instruct-Uncensored-Lora",
+        "codelion/Llama-3.2-1B-Instruct-tool-calling-lora",
+        "--max-loras-per-batch",
+        "2",
+        "--max-loaded-loras",
+        "4",
+        "--mem-fraction-static",
+        "0.75",
+    ]
+
+
+if __name__ == "__main__":
+    unittest.main()