forked from phoenix-oss/llama-stack-mirror
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. |
||
---|---|---|
.. | ||
bedrock | ||
common | ||
datasetio | ||
inference | ||
kvstore | ||
memory | ||
scoring | ||
telemetry | ||
__init__.py |