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
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
..
bloom Disable chunked_forward() on AVX512 CPUs (#179) 1 year ago
cli Report server version and dht.client_mode in rpc_info(), check for updates on startup (#209) 1 year ago
client Fix output shape when resuming generation (#211) 1 year ago
server Fix output shape when resuming generation (#211) 1 year ago
utils Report server version and dht.client_mode in rpc_info(), check for updates on startup (#209) 1 year ago
__init__.py Bump version to 1.1.0 (#190) 1 year ago
constants.py Add service checking direct reachability from peers (#195) 1 year ago
data_structures.py Add local tensor-parallel fwd/bwd (#143) 1 year ago
dht_utils.py Fix logging: do not duplicate lines, enable colors in Colab (#156) 1 year ago