PyTorch implementation of FlashMLA.
FlashMLA is an efficient MLA decoding kernel for Hopper GPUs, optimized for variable-length sequences serving. Currently released: BF16; Paged kvcache with block size of 64.
-
Notifications
You must be signed in to change notification settings - Fork 2
PyTorch implementation of FlashMLA.
License
Yuan-ManX/FlashMLA-PyTorch
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
PyTorch implementation of FlashMLA.
Resources
License
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published