.apply()
to apply any deployment configurations to Fireworks when using deployment_type="on-demand"
or deployment_type="on-demand-lora"
. This change ensures explicit control over when deployments are created and helps prevent accidental deployment creation.Key changes:.apply()
is now required for on-demand and on-demand-lora deployments.apply()
calls.apply()
, you are expected to set up the deployment through the deployment page at https://app.fireworks.ai/dashboard/deploymentsllm.apply()
after creating LLM instances with deployment_type="on-demand"
or deployment_type="on-demand-lora"
>=0.19.14
.LLM
Deployment Logic RefactorLLM
class deployment logic in the Build SDK to make it easier to understand.Key changes:id
parameter is now required when deployment_type
is "on-demand"
base_id
parameter is now required when deployment_type
is "on-demand-lora"
deployment_display_name
parameter is now optional and defaults to the filename where the LLM was instantiatedid
does not
exist. Otherwise, the existing deployment will be reused.firectl login
command.How it works:firectl login
command.#transform=inline
to document URLs.Migration recommendations:pyproject.toml
or requirements.txt
previous_response_id
parameter to maintain context without resending full historystore
parameter—choose whether responses are retrievable by ID or ephemeralfirectl create deployment "accounts/fireworks/models/<MODEL_ID of base model>" --enable-addons
firectl load-lora <MODEL_ID> --deployment <DEPLOYMENT_ID>