소스 검색

disable tinygrad infernece engine test waiting Waiting on https://github.com/tinygrad/tinygrad/issues/5549

Alex Cheema 1 년 전
부모
커밋
d2ed4c2a16
1개의 변경된 파일10개의 추가작업 그리고 10개의 파일을 삭제
  1. 10 10
      exo/inference/test_inference_engine.py

+ 10 - 10
exo/inference/test_inference_engine.py

@@ -24,15 +24,15 @@ async def test_inference_engine(inference_engine_1: InferenceEngine, inference_e
     assert np.array_equal(resp_full, resp2)
     assert np.array_equal(next_resp_full, resp4)
 
-# asyncio.run(test_inference_engine(
-#     MLXDynamicShardInferenceEngine(),
-#     MLXDynamicShardInferenceEngine(),
-#     "mlx-community/Meta-Llama-3-8B-Instruct-4bit",
-# ))
-
-# TODO: Waiting on https://github.com/tinygrad/tinygrad/issues/5549
 asyncio.run(test_inference_engine(
-    TinygradDynamicShardInferenceEngine(),
-    TinygradDynamicShardInferenceEngine(),
-    "llama3-8b-sfr",
+    MLXDynamicShardInferenceEngine(),
+    MLXDynamicShardInferenceEngine(),
+    "mlx-community/Meta-Llama-3-8B-Instruct-4bit",
 ))
+
+# TODO: Waiting on https://github.com/tinygrad/tinygrad/issues/5549
+# asyncio.run(test_inference_engine(
+#     TinygradDynamicShardInferenceEngine(),
+#     TinygradDynamicShardInferenceEngine(),
+#     "llama3-8b-sfr",
+# ))