105 Commits

Author	SHA1	Message	Date
laurent	c1bbbf94f6	Start refactoring the stride.	2023-06-28 12:57:30 +01:00
laurent	19183b8e4f	Factor out the gemm bits.	2023-06-28 08:51:13 +01:00
laurent	0417d9cec8	Add more cuda testing again.	2023-06-28 08:33:43 +01:00
laurent	ca6aa8ff12	Use num-cpus to enable parallelism.	2023-06-27 14:42:26 +01:00
Nicolas Patry	d7f729fb8f	Refactor the hierarchy.	2023-06-27 11:57:27 +02:00