calculate dispatch normal input parameters using npu instead of cpu #177
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
calculate send_token_idx in layout kernel
calculate recv_count, recv_offset in notify dispatch kernel
change num_recv_tokens_per_expert_list from List to tensor
before
[tuning] Dispatch (BF16) 115.81 GB/s (HCCS), avg_t: 4036.01 us
[tuning] Combine 98.46 GB/s (HCCS), avg_t: 4747.07 us
after
[tuning] Dispatch (BF16) 133.23 GB/s (HCCS), avg_t: 3508.14 us
[tuning] Combine 101.20 GB/s (HCCS), avg_t: 4618.60 us