ehhuang 0b695538af fix: chat completion with more than one choice (#2288) ... # What does this PR do? Fix a bug in openai_compat where choices are not indexed correctly. ## Test Plan Added a new test. Rerun the failed inference_store tests: llama stack run fireworks --image-type conda pytest -s -v tests/integration/ --stack-config http://localhost:8321 -k 'test_inference_store' --text-model meta-llama/Llama-3.3-70B-Instruct --count 10		2025-05-27 15:39:15 -07:00
..
apis	feat(responses): add output_text delta events to responses (#2265)	2025-05-27 13:07:14 -07:00
cli	fix: handle None external_providers_dir in build with run arg (#2269)	2025-05-27 09:41:12 +02:00
distribution	fix: index non-MCP toolgroups at registration time (#2272)	2025-05-26 20:33:36 -07:00
models	chore: make cprint write to stderr (#2250)	2025-05-24 23:39:57 -07:00
providers	fix: chat completion with more than one choice (#2288)	2025-05-27 15:39:15 -07:00
strong_typing	chore: enable pyupgrade fixes (#1806)	2025-05-01 14:23:50 -07:00
templates	chore: remove dependencies.json (#2281)	2025-05-27 10:26:57 -07:00
ui	build: Bump version to 0.2.8	2025-05-27 20:28:29 +00:00
__init__.py	export LibraryClient	2024-12-13 12:08:00 -08:00
env.py	refactor(test): move tools, evals, datasetio, scoring and post training tests (#1401)	2025-03-04 14:53:47 -08:00
log.py	chore: make cprint write to stderr (#2250)	2025-05-24 23:39:57 -07:00
schema_utils.py	chore: enable pyupgrade fixes (#1806)	2025-05-01 14:23:50 -07:00