drbh cbced7f0f9 feat: adjust attn weight loading logic (#1975) ... This PR updates `load_attention` to prefer loading specific attention based on the model type. Additionally there were two cases where `TensorParallelColumnLinear.load_multi` was called and this reduces it to a single path		2024-05-29 12:42:11 -04:00
..
layers	reenable xpu for tgi (#1939)	2024-05-23 14:11:08 +02:00
models	feat: adjust attn weight loading logic (#1975)	2024-05-29 12:42:11 -04:00
pb	chore: add pre-commit (#1569)	2024-02-16 11:58:58 +01:00
utils	reenable xpu for tgi (#1939)	2024-05-23 14:11:08 +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	Fixing the download strategy for ibm-fms (#1917)	2024-05-18 13:31:24 +02:00
interceptor.py	v2.0.0 (#1736)	2024-04-12 18:38:34 +02:00
server.py	Fixing some legacy behavior (big swapout of serverless on legacy stuff). (#1937)	2024-05-23 14:39:38 +02:00
tracing.py	feat(clients): Python client (#103)	2023-03-07 18:52:22 +01:00