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 536b985
Browse filesBrowse the repository at this point in the historyBrowse files
Arm backend: Refine DeepSeek-Qwen model tests (pytorch#21733)
Refine the DeepSeek-R1-Distill-Qwen-1.5B model tests to follow the final
layer-test split more closely.
The reduced-config model cases remain the normal CI coverage, while the
checkpoint-sized 1.5B BF16 paths stay isolated in slow xlarge tests.
This keeps the large embedding table and checkpoint-sized activations
out of the normal shard.
The patch also removes the defensive qwen2 importorskip guard so the
test depends on the normal CI environment in the same way as the layer
tests.
cc @digantdesai@freddan80@per@zingo@oscarandersson8218@mansnils@Sebastian-Larsson@robell@rascani
0 commit comments