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
Sharding detection (TP, EP, BMM) should create a "sharding config", instead of directly modifying the compute graph, they should parse the graph read-only.
The config should be then processed by a separate pattern executor that apply graph transformations provided.
This way, the autosharding logic could be bypassed/overwritten by manually specifying the sharding config.