Chenggang Zhao 7ffb118e54 Support multicasting on B

2025-03-25 14:56:42 +08:00

..

include/deep_gemm

Support multicasting on B

2025-03-25 14:56:42 +08:00

jit

Support multicasting on B

2025-03-25 14:56:42 +08:00

jit_kernels

Support multicasting on B

2025-03-25 14:56:42 +08:00

__init__.py

fix typo

2025-02-26 18:37:22 +08:00

utils.py

Correctly flush L2, as reconstructing the tensors on every iteration effectively put them in the L2, and gave the GPU enough idle time to avoid thermal throttling in a potentially unrealistic way.

2025-03-15 20:46:24 +00:00