deepseek-ai / deepseek-ai/FlashMLA
Request for Ampere GPU Support in FlashMLA
Open
- Dominant language
- C++
- Stars
- 12.9k
- Forks
- 1.2k
- Avg merge
- 4h 20m
- Merged PRs (30d)
- 2
Description
I would like to request support for NVIDIA Ampere architecture GPUs in FlashMLA. I understand that many of the current optimizations are specific to Hopper GPUs, but having a "lite" version compatible with Ampere would be highly beneficial.
Extending compatibility to Ampere GPUs would allow a broader range of users to utilize FlashMLA, especially those without access to Hopper GPUs.
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.