← back to Exo
disable tinygrad infernece engine test waiting Waiting on https://github.com/tinygrad/tinygrad/issues/5549
d2ed4c2a161289728e9bb7ad0c7af1cb15d83592 · 2024-07-20 12:13:14 -0700 · Alex Cheema
Files touched
M exo/inference/test_inference_engine.py
Diff
commit d2ed4c2a161289728e9bb7ad0c7af1cb15d83592
Author: Alex Cheema <alexcheema123@gmail.com>
Date: Sat Jul 20 12:13:14 2024 -0700
disable tinygrad infernece engine test waiting Waiting on https://github.com/tinygrad/tinygrad/issues/5549
---
exo/inference/test_inference_engine.py | 20 ++++++++++----------
1 file changed, 10 insertions(+), 10 deletions(-)
diff --git a/exo/inference/test_inference_engine.py b/exo/inference/test_inference_engine.py
index b4f898a9..2cdba8b6 100644
--- a/exo/inference/test_inference_engine.py
+++ b/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",
+# ))
← 115aab0d cache tinygrad models in github workflow
·
back to Exo
·
try with METAL_XCODE=1 for tinygrad metal 04f2aa2a →