Ben Browning 8a1c0a1008 Improve groq OpenAI API compatibility ... This doesn't get Groq to 100% on the OpenAI API verification tests, but it does get it to 88.2% when Llama Stack is in the middle, compared to the 61.8% results for using an OpenAI client against Groq directly. The groq provider doesn't use litellm under the covers in its openai_chat_completion endpoint, and instead directly uses an AsyncOpenAI client with some special handling to improve conformance of responses for response_format usage and tool calling. Signed-off-by: Ben Browning <bbrownin@redhat.com>		2025-04-13 13:41:52 -04:00
..
bedrock	chore: Revert "chore(telemetry): remove service_name entirely" (#1785)	2025-03-25 14:42:05 -07:00
cerebras	chore: Revert "chore(telemetry): remove service_name entirely" (#1785)	2025-03-25 14:42:05 -07:00
ci-tests	test: verification on provider's OAI endpoints (#1893)	2025-04-07 23:06:28 -07:00
dell	chore: Revert "chore(telemetry): remove service_name entirely" (#1785)	2025-03-25 14:42:05 -07:00
dev	Improve groq OpenAI API compatibility	2025-04-13 13:41:52 -04:00
experimental-post-training	fix: fix experimental-post-training template (#1740)	2025-03-20 23:07:19 -07:00
fireworks	test: verification on provider's OAI endpoints (#1893)	2025-04-07 23:06:28 -07:00
groq	Improve groq OpenAI API compatibility	2025-04-13 13:41:52 -04:00
hf-endpoint	chore: Revert "chore(telemetry): remove service_name entirely" (#1785)	2025-03-25 14:42:05 -07:00
hf-serverless	chore: Revert "chore(telemetry): remove service_name entirely" (#1785)	2025-03-25 14:42:05 -07:00
meta-reference-gpu	feat: add batch inference API to llama stack inference (#1945)	2025-04-12 11:41:12 -07:00
nvidia	chore: Revert "chore(telemetry): remove service_name entirely" (#1785)	2025-03-25 14:42:05 -07:00
ollama	chore: Revert "chore(telemetry): remove service_name entirely" (#1785)	2025-03-25 14:42:05 -07:00
open-benchmark	chore: Revert "chore(telemetry): remove service_name entirely" (#1785)	2025-03-25 14:42:05 -07:00
passthrough	chore: Revert "chore(telemetry): remove service_name entirely" (#1785)	2025-03-25 14:42:05 -07:00
remote-vllm	docs: Redirect instructions for additional hardware accelerators for remote vLLM provider (#1923)	2025-04-10 10:04:17 +02:00
sambanova	test: verification on provider's OAI endpoints (#1893)	2025-04-07 23:06:28 -07:00
tgi	chore: Revert "chore(telemetry): remove service_name entirely" (#1785)	2025-03-25 14:42:05 -07:00
together	test: verification on provider's OAI endpoints (#1893)	2025-04-07 23:06:28 -07:00
verification	Improve groq OpenAI API compatibility	2025-04-13 13:41:52 -04:00
vllm-gpu	chore: Revert "chore(telemetry): remove service_name entirely" (#1785)	2025-03-25 14:42:05 -07:00
__init__.py	Auto-generate distro yamls + docs (#468)	2024-11-18 14:57:06 -08:00
dependencies.json	fix: use torchao 0.8.0 for inference (#1925)	2025-04-10 13:39:20 -07:00
template.py	feat(api): (1/n) datasets api clean up (#1573)	2025-03-17 16:55:45 -07:00