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
Alexander Borzunov 26ebbfe8f0
Support macOS (#477)
This PR makes both clients and servers work on macOS. Specifically, it:

- Follows https://github.com/learning-at-home/hivemind/pull/586 to run a macOS-compatible `p2pd` binary (both x86-64 and ARM64 are supported)
- Fixes forking issues and tests on macOS, Python 3.10+
- Introduces basic support for serving model blocks on Apple M1/M2 GPUs (torch.mps)
- Increases max number of open files by default (it's not enough on Linux and is really small on macOS)
9 months ago
..
__init__.py Make Petals a pip-installable package (attempt 2) (#102) 2 years ago
backend.py Rewrite MemoryCache alloc_timeout logic (#434) 9 months ago
block_functions.py Make client compatible with transformers' GenerationMixin (#464) 10 months ago
block_selection.py Use get_logger(__name__) instead of get_logger(__file__) (#265) 1 year ago
block_utils.py Rewrite MemoryCache alloc_timeout logic (#434) 9 months ago
from_pretrained.py Hide excess key message (#476) 9 months ago
handler.py Rewrite MemoryCache alloc_timeout logic (#434) 9 months ago
memory_cache.py Rewrite MemoryCache alloc_timeout logic (#434) 9 months ago
reachability.py Support macOS (#477) 9 months ago
server.py Support macOS (#477) 9 months ago
task_pool.py Use get_logger(__name__) instead of get_logger(__file__) (#265) 1 year ago
task_prioritizer.py Make client compatible with transformers' GenerationMixin (#464) 10 months ago
throughput.py Support macOS (#477) 9 months ago