Skip to content

[LLM Inference] Fix step.cu bug #8995

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

Merged
merged 1 commit into from
Aug 27, 2024
Merged

[LLM Inference] Fix step.cu bug #8995

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
2 changes: 1 addition & 1 deletion csrc/generation/step.cu
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -243,7 +243,7 @@ void StepPaddle(const paddle::Tensor& stop_flags,
const int length = input_ids.shape()[1];
const int pre_id_length = pre_ids.shape()[1];
constexpr int BlockSize = 512; // bsz < 256
const int max_decoder_block_num = pre_id_length / block_size - encoder_decoder_block_num;
const int max_decoder_block_num = length / block_size;
#ifdef DEBUG_STEP
printf("bsz: %d, block_num_per_seq: %d, length: %d, max_decoder_block_num: %d\n", bsz, block_num_per_seq, length, max_decoder_block_num);
#endif
Expand Down
Loading