summaryrefslogtreecommitdiff
path: root/candle-flash-attn/kernels/flash_fwd_hdim64_fp16_sm80.cu
Commit message (Collapse)AuthorAgeFilesLines
* Flash-Attn upgrade / SoftCap Candle-FlashAttn [1/n] (#2688)Michael Feil2024-12-311-1/+1
| | | | | | | | | * update flash-attn v1 * restore: hdim224 * add 224 flash_fwd_template * remove whitespace
* Update the flash attn kernels. (#2333)Laurent Mazare2024-07-151-2/+2
|
* chore: update flash attention kernels (#1518)OlivierDehaene2024-01-051-18/+2
| | | | | | | | | | | * chore: update flash attention kernels * fmt * remove unused kernels * force f32 * correct stride
* Again set a few extra params in flash-attn. (#245)Laurent Mazare2023-07-261-0/+26
* Again set a few extra params. * Use the appropriate kernel sizes. * Add all the kernel sizes. * Parallel compiling. * Reduce the amount of parallelism. * Add the missing kernel. * Fix a typo. * Remove bf16 support for now.