6 Commits

Author	SHA1	Message	Date
Antoni Baum	a10d3056da	[Core] Set linear_weights directly on the layer (#3977)	2024-04-11 16:35:51 -04:00
SangBin Cho	01bfb22b41	[CI] Try introducing isort. (#3495)	2024-03-25 07:59:47 -07:00
Nick Hill	41deac4a3d	[BugFix] 1D query fix for MoE models (#3597)	2024-03-24 16:00:16 -07:00
Zhuohan Li	2f8844ba08	Re-enable the 80 char line width limit (#3305)	2024-03-10 19:49:14 -07:00
Woosuk Kwon	f0d4e14557	Add fused top-K softmax kernel for MoE (#2769)	2024-02-05 17:38:02 -08:00
Philipp Moritz	d0d93b92b1	Add unit test for Mixtral MoE layer (#2677)	2024-01-31 14:34:17 -08:00