github flashinfer-ai/flashinfer v0.1.3

latest releases: nightly-v0.6.12-20260524, nightly-v0.6.12-20260523, v0.6.12rc1...
22 months ago

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)

Don't miss a new flashinfer release

NewReleases is sending notifications on new releases.