Alex Cheema 490fa102a4 tinygrad inference engine преди 1 година
..
mlx ca6095c04d a generic test for every inference engine преди 1 година
tinygrad 490fa102a4 tinygrad inference engine преди 1 година
__init__.py 850b72d3ea make StatefulShardedModel callable, add some tests for mlx sharded inference преди 1 година
inference_engine.py b01f69bb6b add support for multiple concurrent requests with request ids преди 1 година
shard.py 563dcb56b0 mlx sharded implementation with example of distributed inference преди 1 година
test_inference_engine.py 490fa102a4 tinygrad inference engine преди 1 година