Skip to content

Releases: CentML/flashinfer

Release candidate #2 for MLPerf Inference v6.0

10 Feb 08:30
a649449

Choose a tag to compare

What's Changed

  • Pulled the fp8 attention support & minor fix for compatibility by @zhandaz in #2

New Contributors

Full Changelog: mlperf-inf-mm-q3vl-v6.0-rc1...mlperf-inf-mm-q3vl-v6.0-rc2

Release candidate #1 for MLPerf Inference v6.0

06 Feb 23:41
4f66641

Choose a tag to compare

What's Changed

  • Update cudnn prefill to use correct sequence strides by @maxyanghu in #1

New Contributors

Full Changelog: https://github.com/CentML/flashinfer/commits/mlperf-inf-mm-q3vl-v6.0-rc1