Home
last modified time | relevance | path

Searched defs:max_smem_per_block (Results 1 – 2 of 2) sorted by relevance

/external/pytorch/aten/src/ATen/native/transformers/cuda/flash_attn/
Dflash_bwd_launch_template.h141 int max_smem_per_block; in run_mha_bwd_hdim32() local
165 int max_smem_per_block; in run_mha_bwd_hdim64() local
210 int max_smem_per_block; in run_mha_bwd_hdim96() local
236 int max_smem_per_block; in run_mha_bwd_hdim128() local
270 int max_smem_per_block; in run_mha_bwd_hdim160() local
290 int max_smem_per_block; in run_mha_bwd_hdim192() local
318 int max_smem_per_block; in run_mha_bwd_hdim256() local
Dflash_fwd_launch_template.h323 int max_smem_per_block; in run_mha_fwd_hdim224() local
352 int max_smem_per_sm, max_smem_per_block; in run_mha_fwd_hdim256() local