DeepSpeed
8d376ada - Use ops directly, stop using builder.load to use ops

Commit
1 year ago
Use ops directly, stop using builder.load to use ops This PR mainly handles all places where InferenceBuilder is used to access any op or a specific implementation for an op. Instead an op is defined, and its proper implementation is picked inside and the usage will be transparent to the user. What was done in the PR: 1) Added missing ops (added a py file with fallback mechanism) 2) Added missing fallback implementations for existing ops 3) removed all usages for builder.load and replaced them with ops instead. 4) a small change to softmax_context signature to fit the fallback signature.
Author
Committer
Parents
Loading