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.

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
..
__init__.py	Move SequenceManagerConfig -> ClientConfig, petals.dht_utils -> petals.utils.dht (#463)	9 months ago
asyncio.py	Shield alloc & free from cancellation (#163)	1 year ago
auto_config.py	Add Falcon support (#499)	9 months ago
convert_block.py	Support Llama 2 (#379)	10 months ago
dht.py	Store (start_block, end_block) in each DHT record for reliability (#510)	8 months ago
disk_cache.py	Allow free_disk_space_for() remove arbitrary files from Petals cache (#339)	11 months ago
hf_auth.py	Support Llama 2 (#379)	10 months ago
logging.py	Remove unused imports and attributes (#324)	11 months ago
misc.py	Rewrite MemoryCache alloc_timeout logic (#434)	9 months ago
packaging.py	Add customizable input tensors (#445)	9 months ago
peft.py	Rewrite MemoryCache alloc_timeout logic (#434)	9 months ago
ping.py	Fix petals.utils.ping for servers with client-mode DHT (#430)	10 months ago
random.py	Implement shortest-path routing for inference (#362)	10 months ago
version.py	Add LLaMA support (#323)	11 months ago