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/server
Artem Chumachenko 30f522d1a0
Fix dummy cache allocation (#574)
* Fix dummy cache allocation

* Try mps device selecting

* Rechain reloc
2 weeks ago
..
__init__.py Make Petals a pip-installable package (attempt 2) (#102) 1 year ago
backend.py Add Mixtral models (#553) 4 weeks ago
block_functions.py Fix p2p pushing in rpc_inference (by @miaoqijun ) , support transformers 4.38.2 (#563) 1 month ago
block_selection.py Store (start_block, end_block) in each DHT record for reliability (#510) 8 months ago
block_utils.py Fix Mixtral-related issues (#570) 3 weeks ago
from_pretrained.py Fix Mixtral-related issues (#570) 3 weeks ago
handler.py Fix p2p pushing in rpc_inference (by @miaoqijun ) , support transformers 4.38.2 (#563) 1 month ago
memory_cache.py Fix race condition in MemoryCache (#487) 8 months ago
reachability.py Support macOS (#477) 8 months ago
server.py Improve default arguments for clients and servers (#530) 6 months ago
task_pool.py Remove no-op process in PrioritizedTaskPool (#484) 8 months ago
task_prioritizer.py Make client compatible with transformers' GenerationMixin (#464) 8 months ago
throughput.py Fix dummy cache allocation (#574) 2 weeks ago