Skip to content

Update kernel_wrapper.cpp #49

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
Bjorntday wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Update kernel_wrapper.cpp #49

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions src/ksana_llm/kernels/nvidia/kernel_wrapper.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1245,6 +1245,7 @@ void InvokePagedAttention(void* output_ptr, void* query_ptr, void** key_cache_pt
const_null_tensor, // rotary_cos_: seqlen_ro x (rotary_dim / 2)
const_null_tensor, // rotary_sin_: seqlen_ro x (rotary_dim / 2)
const_null_tensor, // cache_batch_idx_: indices to index into the KV cache
const_null_tensor, // indices that the KV cache starts. [batch_size,], nullptr, default 0
block_table_tensor, // batch_size x max_num_blocks_per_seq
alibi_slopes_tensor, // num_heads or batch_size x num_heads
out_tensor, // batch_size x seqlen_q x num_heads x head_size
Expand Down