Ashwin Bharambe 928a39d17b feat(providers): Groq now uses LiteLLM openai-compat (#1303) ... Groq has never supported raw completions anyhow. So this makes it easier to switch it to LiteLLM. All our test suite passes. I also updated all the openai-compat providers so they work with api keys passed from headers. `provider_data` ## Test Plan ```bash LLAMA_STACK_CONFIG=groq \ pytest -s -v tests/client-sdk/inference/test_text_inference.py \ --inference-model=groq/llama-3.3-70b-versatile --vision-inference-model="" ``` Also tested (openai, anthropic, gemini) providers. No regressions.		2025-02-27 13:16:50 -08:00
..
building_applications	feat: allow specifying specific tool within toolgroup (#1239)	2025-02-26 14:07:05 -08:00
concepts	docs: Add vLLM to the list of inference providers in concepts and providers pages (#1227)	2025-02-23 20:16:30 -08:00
contributing	docs: Add note about distro_codegen.py and provider dependencies (#1175)	2025-02-20 09:23:46 -08:00
distributions	feat(providers): Groq now uses LiteLLM openai-compat (#1303)	2025-02-27 13:16:50 -08:00
getting_started	feat: allow specifying specific tool within toolgroup (#1239)	2025-02-26 14:07:05 -08:00
introduction	Update index.md (#888)	2025-01-28 04:55:41 -08:00
playground	fix!: update eval-tasks -> benchmarks (#1032)	2025-02-13 16:40:58 -08:00
providers	docs: Add vLLM to the list of inference providers in concepts and providers pages (#1227)	2025-02-23 20:16:30 -08:00
references	docs: Remove $ from client CLI ref to add valid copy and paste ability (#1260)	2025-02-25 13:50:00 -08:00
conf.py	feat: automatically update documentation version based on pyproject.toml source of truth	2025-02-26 13:42:12 -08:00
index.md	feat: automatically update documentation version based on pyproject.toml source of truth	2025-02-26 13:42:12 -08:00