Ashwin Bharambe 9fa69b0337 feat(distro): no huggingface provider for starter (#3258) ... The `trl` dependency brings in `accelerate` which brings in nvidia dependencies for torch. We cannot have that in the starter distro. As such, no CPU-only post-training for the huggingface provider.		2025-08-26 14:06:36 -07:00
..
__init__.py	API Updates (#73)	2024-09-17 19:51:35 -07:00
agents.py	fix: only load mcp when enabled in tool_group (#2621)	2025-07-04 20:27:05 +05:30
batches.py	feat: add batches API with OpenAI compatibility (with inference replay) (#3162)	2025-08-15 15:34:15 -07:00
datasetio.py	docs: auto generated documentation for providers (#2543)	2025-06-30 15:13:20 +02:00
eval.py	docs: auto generated documentation for providers (#2543)	2025-06-30 15:13:20 +02:00
files.py	feat: Add S3 Files Provider (#3202)	2025-08-22 10:38:59 -04:00
inference.py	feat(distro): no huggingface provider for starter (#3258)	2025-08-26 14:06:36 -07:00
post_training.py	feat(distro): no huggingface provider for starter (#3258)	2025-08-26 14:06:36 -07:00
safety.py	docs: auto generated documentation for providers (#2543)	2025-06-30 15:13:20 +02:00
scoring.py	docs: auto generated documentation for providers (#2543)	2025-06-30 15:13:20 +02:00
telemetry.py	docs: auto generated documentation for providers (#2543)	2025-06-30 15:13:20 +02:00
tool_runtime.py	fix: only load mcp when enabled in tool_group (#2621)	2025-07-04 20:27:05 +05:30
vector_io.py	chore(tests): fix responses and vector_io tests (#3119)	2025-08-12 16:15:53 -07:00