apache / tvm

Open deep learning compiler stack for cpu, gpu and specialized accelerators
https://tvm.apache.org/
Apache License 2.0
11.76k stars 3.47k forks source link

[3rdparty] Bump FlashInfer #17143

Closed MasterJH5574 closed 2 months ago

MasterJH5574 commented 3 months ago

This PR bumps FlashInfer and updates PagedKVCache accordingly for performance improvement.

MasterJH5574 commented 3 months ago

Not yet ready for review.