You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
petals/src/petals/client
Alexander Borzunov 6ba63c6cc8
Fix output shape when resuming generation (#211)
Before this PR, `model.generate()` returned one excess token when resuming generation with an existing (the last token of the previous session, `session.last_token_id`). This is an unexpected behavior not convenient for the downstream apps, so this PR changes it until it's too late.
1 year ago
..
routing Use length-weighted sampling in routing for inference (#204) 1 year ago
__init__.py Fix issues related to `petals` as a module (#159) 1 year ago
inference_session.py Use length-weighted sampling in routing for inference (#204) 1 year ago
remote_forward_backward.py Fix dtypes in backend schemas (#99) 1 year ago
remote_generation.py Fix output shape when resuming generation (#211) 1 year ago
remote_model.py Support libp2p relays for NAT traversal (#186) 1 year ago
remote_sequential.py Fix logging: do not duplicate lines, enable colors in Colab (#156) 1 year ago
sequential_autograd.py Use length-weighted sampling in routing for inference (#204) 1 year ago