flashinfer-ai/flashinfer v0.0.8
on GitHub

latest releases: nightly-v0.6.11-20260513, v0.6.11.post1, nightly-v0.6.11-20260511...

22 months ago

0.0.8 (2024-07-03)

Bugfix

fix prefill/append kernel behavior for empty kv-cache (#353) (7adc8c)
fix decode attention kernel with logits cap (#350) (f5f7a2)

Check out latest releases or
releases around flashinfer-ai/flashinfer v0.0.8

Don't miss a new flashinfer release

NewReleases is sending notifications on new releases.

Get notifications