Commit Graph

661 Commits

Author SHA1 Message Date
laurent 934655a60d Add squeeze/unsqueeze/stack. 2023-06-27 19:32:00 +01:00
laurent 1d504cc6b3 Rework the debug trait. 2023-06-27 19:10:30 +01:00
laurent 684f66326d Add the get method. 2023-06-27 17:39:58 +01:00
laurent c44e5346f4 Add some helper functions. 2023-06-27 17:37:09 +01:00
laurent dbe3e4e7c0 Add some test utils module. 2023-06-27 16:20:28 +01:00
laurent e221d38819 Factor the slicing code in cuda. 2023-06-27 15:45:59 +01:00
laurent 07a682c2ff Run the tensor tests for the cuda backend too. 2023-06-27 15:37:01 +01:00
laurent ca6aa8ff12 Use num-cpus to enable parallelism. 2023-06-27 14:42:26 +01:00
laurent 318503cd38 Cache the causal mask in llama. 2023-06-27 12:21:08 +01:00
laurent 380d61e990 Fix two cuda bugs (matmul and where_cond). 2023-06-27 11:31:04 +01:00
Nicolas Patry d7f729fb8f Refactor the hierarchy. 2023-06-27 11:57:27 +02:00