July 10, 2025 · Fireworks AI
Build SDK LLM class requires id for on-demand and base_id for on-demand-lora
Based on early feedback from users and internal testing, we've refactored the LLM class deployment logic in the Build SDK to make it easier to understand.
Key changes:
- The
idparameter is now required whendeployment_typeis"on-demand" - The
base_idparameter is now required whendeployment_typeis"on-demand-lora" - The
deployment_display_nameparameter is now optional and defaults to the filename where the LLM was instantiated
A new deployment will be created if a deployment with the same id does not exist. Otherwise, the existing deployment will be reused.
Latest Fireworks AI platform changes
Public cookbook moves to fw-ai-external/cookbook, fireworks-training-cookbook on PyPI
Ultra-fast Serverless mode in Preview, with DeepSeek V4.1 Flash 1017 at 6-8x speed
DeepSeek V4 Flash (0731) removed from the shared Serverless Training pool
Rune 26B-A4B available on Serverless, returning probabilities for up to 256 questions
fireworks-ai 1.2.30 replaces TITO sidecar 502 errors with source-specific error codes