10 Commits

Author	SHA1	Message	Date
turboderp	91404f4e5f	MLP: Enable BC/graph path without fused up/gate proj (int8 mode)	2026-07-09 20:19:01 +02:00
turboderp	6e973a250a	Eval: Debug options	2026-05-29 16:23:37 +02:00
turboderp	30616a4b14	Update eval scripts	2026-05-19 00:36:54 +02:00
turboderp	8438123261	EXL3: Increase auto reconstruct threshold	2026-05-12 23:59:10 +02:00
turboderp	cb50b9fa6a	afmoe: Assert topk_groups=1 and use dots router	2026-04-23 21:05:21 +02:00
turboderp	0d3893face	Loader: Allow specifying max bsz for autosplit to better estimate recurrent state VRAM overhead	2026-04-18 14:12:29 +02:00
turboderp	7046a5c739	perf.py: Fix cache overflow	2026-04-06 01:58:27 +02:00
turboderp	85cb54c6f3	perf.py: Make sure test context is nontrivial to force more expert diversity	2026-03-07 01:18:27 +01:00
turboderp	b2b6f37e12	perf.py: Error out if test length > cache size	2026-02-17 20:04:13 +01:00
turboderp	428a082276	Add performance test	2026-01-22 23:28:53 +01:00