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 5ce4f1a159
Store (start_block, end_block) in each DHT record for reliability (#510)
This PR fixes gaps in the DHT server info caused by unavailable DHT keys. Now, one DHT key is enough to get info about all blocks hosted by a server - so we'll see info until all keys are unavailable.

Also, this PR refactors `petals.client.routing` and `petals.server.block_selection` modules to use the common `compute_spans()` function (defined in `petals.utils.dht`) and `RemoteSpanInfo` class (defined in `petals.data_structures`).
8 months ago
..
routing Store (start_block, end_block) in each DHT record for reliability (#510) 8 months ago
__init__.py Move SequenceManagerConfig -> ClientConfig, petals.dht_utils -> petals.utils.dht (#463) 9 months ago
config.py Move SequenceManagerConfig -> ClientConfig, petals.dht_utils -> petals.utils.dht (#463) 9 months ago
from_pretrained.py Make client compatible with transformers' GenerationMixin (#464) 9 months ago
inference_session.py Create model index in DHT (#491) 9 months ago
lm_head.py Make client compatible with transformers' GenerationMixin (#464) 9 months ago
ptune.py Make client compatible with transformers' GenerationMixin (#464) 9 months ago
remote_forward_backward.py Move SequenceManagerConfig -> ClientConfig, petals.dht_utils -> petals.utils.dht (#463) 9 months ago
remote_generation.py Fix prompt tuning after #464 (#501) 9 months ago
remote_sequential.py Make client compatible with transformers' GenerationMixin (#464) 9 months ago
sequential_autograd.py Make client compatible with transformers' GenerationMixin (#464) 9 months ago