Skip to content
Validate Gradle Wrapper

max sequence length for memory efficient attention #22163

Sign in to view logs

max sequence length for memory efficient attention

max sequence length for memory efficient attention #22163

Triggered via push October 27, 2023 19:45
@aciddelgadoaciddelgado
pushed e7a50ee
aciddelgado/gqa_memeff_v2
Status Success
Total duration 34s
Artifacts –
This run and associated checks have been archived and are scheduled for deletion. Learn more about checks retention

gradle-wrapper-validation.yml

on: push
Validation
24s
Validation
Fit to window
Zoom out
Zoom in

Annotations

14 warnings and 1 notice
[cpplint] onnxruntime/contrib_ops/cuda/bert/group_query_attention.cc#L60: onnxruntime/contrib_ops/cuda/bert/group_query_attention.cc#L60
Lines should be <= 120 characters long [whitespace/line_length] [2]
[cpplint] onnxruntime/contrib_ops/cuda/bert/group_query_attention.cc#L160: onnxruntime/contrib_ops/cuda/bert/group_query_attention.cc#L160
Lines should be <= 120 characters long [whitespace/line_length] [2]
[cpplint] onnxruntime/contrib_ops/cuda/bert/group_query_attention.cc#L163: onnxruntime/contrib_ops/cuda/bert/group_query_attention.cc#L163
Lines should be <= 120 characters long [whitespace/line_length] [2]
[cpplint] onnxruntime/contrib_ops/cuda/bert/group_query_attention.cc#L164: onnxruntime/contrib_ops/cuda/bert/group_query_attention.cc#L164
Lines should be <= 120 characters long [whitespace/line_length] [2]
[cpplint] onnxruntime/contrib_ops/cuda/bert/group_query_attention.cc#L176: onnxruntime/contrib_ops/cuda/bert/group_query_attention.cc#L176
Add #include <vector> for vector<> [build/include_what_you_use] [4]
[cpplint] onnxruntime/contrib_ops/cuda/bert/group_query_attention_helper.h#L156: onnxruntime/contrib_ops/cuda/bert/group_query_attention_helper.h#L156
Lines should be <= 120 characters long [whitespace/line_length] [2]
[cpplint] onnxruntime/contrib_ops/cuda/bert/group_query_attention_impl.cu#L157: onnxruntime/contrib_ops/cuda/bert/group_query_attention_impl.cu#L157
At least two spaces is best between code and comments [whitespace/comments] [2]
[cpplint] onnxruntime/contrib_ops/cuda/bert/group_query_attention_impl.cu#L287: onnxruntime/contrib_ops/cuda/bert/group_query_attention_impl.cu#L287
Using deprecated casting style. Use static_cast<int>(...) instead [readability/casting] [4]
[cpplint] onnxruntime/contrib_ops/cuda/bert/group_query_attention_impl.cu#L399: onnxruntime/contrib_ops/cuda/bert/group_query_attention_impl.cu#L399
Using deprecated casting style. Use static_cast<int>(...) instead [readability/casting] [4]
[cpplint] onnxruntime/contrib_ops/cuda/bert/group_query_attention_impl.cu#L453: onnxruntime/contrib_ops/cuda/bert/group_query_attention_impl.cu#L453
Using deprecated casting style. Use static_cast<float>(...) instead [readability/casting] [4]
[cpplint] onnxruntime/contrib_ops/cuda/bert/group_query_attention_impl.cu#L458: onnxruntime/contrib_ops/cuda/bert/group_query_attention_impl.cu#L458
Lines should be <= 120 characters long [whitespace/line_length] [2]
[cpplint] onnxruntime/contrib_ops/cuda/bert/group_query_attention_impl.cu#L528: onnxruntime/contrib_ops/cuda/bert/group_query_attention_impl.cu#L528
Lines should be <= 120 characters long [whitespace/line_length] [2]
[cpplint] onnxruntime/contrib_ops/cuda/bert/group_query_attention_impl.cu#L559: onnxruntime/contrib_ops/cuda/bert/group_query_attention_impl.cu#L559
Lines should be <= 120 characters long [whitespace/line_length] [2]
[cpplint] onnxruntime/contrib_ops/cuda/bert/group_query_attention_impl.cu#L597: onnxruntime/contrib_ops/cuda/bert/group_query_attention_impl.cu#L597
Lines should be <= 120 characters long [whitespace/line_length] [2]
[misspell] onnxruntime/test/python/transformers/test_flash_attn.py#L1266: onnxruntime/test/python/transformers/test_flash_attn.py#L1266
"EFFICEINT" is a misspelling of "EFFICIENT"