Skip to content
Build and test

Fix a bug in flash attention where kv_seq_len should divide block_k_major. #10961

Sign in to view logs

Fix a bug in flash attention where kv_seq_len should divide block_k_major.

Fix a bug in flash attention where kv_seq_len should divide block_k_major. #10961

Run time

Learn about OS pricing on GitHub Actions
Job Run time
get-torch-commit
2s
Build PyTorch/XLA / build
1h 11m 31s
TPU tests / tpu-test
1h 14m 2s
Build docs / build-docs
1m 44s
CPU tests / test (benchmark_tests)
8m 55s
CPU tests / test (python_tests, xla_op1)
18m 15s
CPU tests / test (python_tests, xla_op2)
5m 49s
CPU tests / test (python_tests, xla_op3)
11m 16s
CPU tests / test (python_tests, torch_mp_op)
12m 47s
CPU tests / test (cpp_tests, cpp_tests1)
5m 42s
CPU tests / test (cpp_tests, cpp_tests2)
6m 6s
3h 36m 9s