llama-stack/llama_stack/providers/inline/inference
Ashwin Bharambe cdcbeb005b
chore: remove llama_models.llama3.api imports from providers (#1107)
There should be a choke-point for llama3.api imports -- this is the
prompt adapter. Creating a ChatFormat() object on demand is inexpensive.
The underlying Tokenizer is a singleton anyway.
2025-02-19 19:01:29 -08:00
..
meta_reference chore: move all Llama Stack types from llama-models to llama-stack (#1098) 2025-02-14 09:10:59 -08:00
sentence_transformers build: format codebase imports using ruff linter (#1028) 2025-02-13 10:06:21 -08:00
vllm chore: remove llama_models.llama3.api imports from providers (#1107) 2025-02-19 19:01:29 -08:00
__init__.py precommit 2024-11-08 17:58:58 -08:00