Hot Reload For Development Deployments

Hot reload for development deployments Announcing our Series F . Learn more

changelog / post

Hot reload for development deployments

Mar 27, 2026 Go back

truss watch and truss push --watch now support hot-reloading model code changes with the --hot-reload and --watch-hot-reload flags. Instead of restarting the inference server, hot reload swaps your model class in-process: keeping weights and caches loaded for near-instant iteration on predict() logic.

For more information, see Deploy and iterate .

Explore Baseten today Start deploying Talk to an engineer

Popular models GLM 5.2

Kimi K2.7 Code

DeepSeek V4

GPT OSS 120B

Whisper Large V3

NVIDIA Nemotron 3 Ultra

Explore all

Popular models GLM 5.2

Kimi K2.7 Code

DeepSeek V4

GPT OSS 120B

Whisper Large V3

NVIDIA Nemotron 3 Ultra

Explore all