You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
Repository navigation
Commit c5bf380
Browse filesBrowse the repository at this point in the historyBrowse files
Fix stale Int4Tensor assertions in gemma4_31b CUDA pipeline tests (pytorch#20230)
Packing converts Int4Tensor weights to CudaCoalescedInt4Tensor because
the CUDA int4 kernel is registered only on the coalesced type, which is
intentionally not a subclass of Int4Tensor. Update
test_int4_weights_preserved and test_load_converts_weights to assert
CudaCoalescedInt4Tensor.
0 commit comments