Jan Wassenberg 8e028632f7 0.98x prefill: refactor in prep for cache blocking. ... Slower because we now init tiles of C and accumulate into them. Also remove unused var in optimize_test and use BF16 typedef. PiperOrigin-RevId: 662115916		2024-08-12 09:26:29 -07:00
..
matmul-inl.h	0.98x prefill: refactor in prep for cache blocking.	2024-08-12 09:26:29 -07:00
matmul_test.cc	0.98x prefill: refactor in prep for cache blocking.	2024-08-12 09:26:29 -07:00
matvec-inl.h	Split matmul into matvec; add large matrix benchmark	2024-07-30 08:29:11 -07:00
matvec_test.cc	Split matmul into matvec; add large matrix benchmark	2024-07-30 08:29:11 -07:00
ops-inl.h	1.03-1.08x decode speedup: precompute Rope theta, fuse	2024-08-09 01:23:24 -07:00
ops_test.cc	Split up ops.h into ops/ops-inl and matmul-inl	2024-07-19 11:21:48 -07:00