Nicolas Patry 799a193b10 Fixing Phi3.		2024-06-01 08:47:00 +00:00
..
layers	Fixing exl2 scratch buffer. (#1990)	2024-05-31 18:01:43 +02:00
models	Fixing Phi3.	2024-06-01 08:47:00 +00:00
pb	chore: add pre-commit (#1569)	2024-02-16 11:58:58 +01:00
utils	Purely refactors paged/attention into `layers/attention` and make hardware differences more obvious with 1 file per hardware. (#1986)	2024-05-31 17:57:01 +02:00
__init__.py	feat(clients): Python client (#103)	2023-03-07 18:52:22 +01:00
cache.py	fix(server): decrease memory fragmentation (#557)	2023-07-06 14:28:33 +02:00
cli.py	Add support for exl2 quantization	2024-05-30 11:28:05 +02:00
interceptor.py	v2.0.0 (#1736)	2024-04-12 18:38:34 +02:00
server.py	Add support for exl2 quantization	2024-05-30 11:28:05 +02:00
tracing.py	feat(clients): Python client (#103)	2023-03-07 18:52:22 +01:00