Skip to content

v0.1.3

Compare
Choose a tag to compare
@yzh119 yzh119 released this 31 Jul 10:47
· 170 commits to main since this release

0.1.3 (2024-07-31)

Bugfix

  • bugfix: Fix cudagraph mode of BatchPrefillWithRaggedKVCacheWrapper (#412) (9907bc)
  • fix cu118 cub usage for sampling kernels (#410) (58d359)

Misc

  • enhance allocator error info and add shape check for prefill begin forward functions (#413) (5e36c5)