Changelog
🎯 Build SDK: Reward-kit integration for evaluator development
The Build SDK now natively integrates with reward-kit to simplify evaluator development for Reinforcement Fine-Tuning (RFT). You can now create custom evaluators in Python with automatic dependency management and seamless deployment to Fireworks infrastructure.
Key features:
- Native reward-kit integration for evaluator development
- Automatic packaging of dependencies from
pyproject.toml
orrequirements.txt
- Local testing capabilities before deployment
- Direct integration with Fireworks datasets and evaluation jobs
- Support for third-party libraries and complex evaluation logic
See our Developing Evaluators guide to get started with your first evaluator in minutes.
Added new Responses API for advanced conversational workflows and integrations:
- Continue conversations across multiple turns using the
previous_response_id
parameter to maintain context without resending full history. - Stream responses in real time as they are generated for responsive applications.
- Control response storage with the
store
parameter—choose whether responses are retrievable by ID or ephemeral.
See the Response API guide for usage examples and details.
What’s new
🚀 Easier & faster LoRA fine-tune deployments on Fireworks
You can now deploy a LoRA fine-tune with a single command and get speeds that approximately match the base model:
Earlier, this involved two distinct steps, and the resultant deployment was slower than the base model:
- Create a deployment using
firectl create deployment "accounts/fireworks/models/<MODEL_ID of base model>" --enable-addons
- Then deploy the addon to the deployment:
firectl load-lora <MODEL_ID> --deployment <DEPLOYMENT_ID>
Docs: https://docs.fireworks.ai/models/deploying#deploying-to-on-demand
This change is for dedicated deployments with a single LoRA. You can still deploy multiple LoRAs on a deployment or deploy LoRA(s) on some Serverless models as described in the docs.