Add flash attention prefill shapes to benchmarks #330
+448
−0
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
FMarno
reviewed
Apr 25, 2025
| @@ -0,0 +1,448 @@ | |||
| PvcFMHABF16BF16FP32_RCR_h64_Causal_FixedLen --bm_name=bf16_bf16_fp32 --seq_len_qo=4096 --seq_len_kv=4096 --batch=1 --num_heads_q=8 --num_heads_kv=8 --head_size_qk=40 --head_size_vo=40 | |||
| #PvcFMHABF16BF16FP32_RCR_h64_Causal_FixedLen --bm_name=bf16_bf16_fp32 --seq_len_qo=4096 --seq_len_kv=77 --batch=1 --num_heads_q=8 --num_heads_kv=8 --head_size_qk=40 --head_size_vo=40 | |||
There was a problem hiding this comment.
Maybe add a TODO(codeplay) with a description of what is broken?
I guess it's the same for all the disabled benchmarks
There was a problem hiding this comment.
done, but not as a todo as we do not currently intend to fix that
There was a problem hiding this comment.
where is the requirement of 77 from?
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
Shapes with seq_len_kv == 77 are commented out as they are not supported by 2d block loads.