Skip to content

GitLab

Commit 15a82b81 authored by Sijia Chen's avatar Sijia Chen Committed by Sijia Chen
Browse files

replace c10 optional with std optional

parent bcb90f2a
Hide whitespace changes
Inline Side-by-side
Showing with 1 addition and 1 deletion
csrc/flash_api.cpp
View file @ 15a82b81
...@@ -61,7 +61,7 @@ std::vector<at::Tensor> ...@@ -61,7 +61,7 @@ std::vector<at::Tensor>
mha_fwd_kvcache_mla( mha_fwd_kvcache_mla(
at::Tensor &q, // batch_size x seqlen_q x num_heads x head_size at::Tensor &q, // batch_size x seqlen_q x num_heads x head_size
const at::Tensor &kcache, // num_blocks x page_block_size x num_heads_k x head_size const at::Tensor &kcache, // num_blocks x page_block_size x num_heads_k x head_size
c10::optional<const at::Tensor> &vcache_, // num_blocks x page_block_size x num_heads_k x head_size_v std::optional<const at::Tensor> &vcache_, // num_blocks x page_block_size x num_heads_k x head_size_v
const int head_size_v, const int head_size_v,
const at::Tensor &seqlens_k, // batch_size const at::Tensor &seqlens_k, // batch_size
const at::Tensor &block_table, // batch_size x max_num_blocks_per_seq const at::Tensor &block_table, // batch_size x max_num_blocks_per_seq
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment