Michael Dawson f316dffe80 feat: add cpu/cuda config for prompt guard ... Previously prompt guard was hard coded to require cuda which prevented it from being used on an instance without a cuda support. This PR allows prompt guard to be configured to use either cpu or cuda. Signed-off-by: Michael Dawson <mdawson@devrus.com>		2025-05-16 14:26:44 -04:00
..
agents	fix: Responses API: handle type=None in streaming tool calls (#2166)	2025-05-14 14:16:33 -07:00
datasetio	chore(refact): move paginate_records fn outside of datasetio (#2137)	2025-05-12 10:56:14 -07:00
eval	feat: implementation for agent/session list and describe (#1606)	2025-05-07 14:49:23 +02:00
inference	chore: enable pyupgrade fixes (#1806)	2025-05-01 14:23:50 -07:00
ios/inference	chore: removed executorch submodule (#1265)	2025-02-25 21:57:21 -08:00
post_training	fix: Don't require efficiency_config for torchtune (#2104)	2025-05-06 09:50:44 -07:00
safety	feat: add cpu/cuda config for prompt guard	2025-05-16 14:26:44 -04:00
scoring	chore: enable pyupgrade fixes (#1806)	2025-05-01 14:23:50 -07:00
telemetry	feat: add metrics query API (#1394)	2025-05-07 10:11:26 -07:00
tool_runtime	feat: Adding support for customizing chunk context in RAG insertion and querying (#2134)	2025-05-14 21:56:20 -04:00
vector_io	feat: implementation for agent/session list and describe (#1606)	2025-05-07 14:49:23 +02:00
__init__.py	impls -> inline, adapters -> remote (#381)	2024-11-06 14:54:05 -08:00