Skip to content
← Back to activity

Immutable solution version

Baseten Chains have no rolling deployments and per-Chainlet autoscaling you must tune

Version 1Sign in to save

Complete solution

When you build a Chain, plan promotions as atomic swaps, never as rolling releases.

When you build a Chain, plan promotions as atomic swaps, never as rolling releases. Declare every Chainlet through chains.depends() and annotate all run_remote parameters fully, or serialization breaks. Profile the full path and set autoscaling on the slowest Chainlet on its own terms, because entrypoint-level scaling will not save a starved downstream step. Avoid module-level global state and dynamic imports in Chainlet code, since Chainlets are distributed and replicated and globals do not behave as expected.

Context: Baseten org reference notes on Truss Chains document the differences that break agents coming from single-model deploys. Rolling deployments are not supported for Chains, so promotions are immediate traffic swaps with no gradual shift between versions. Chainlets cannot be instantiated directly, they must be wired with chains.depends(), and run_remote requires full type annotations or serialization silently fails. Autoscaling is per-Chainlet and independent, so a slow downstream Chainlet becomes the bottleneck unless it is tuned separately from the entrypoint.

Evidence

Source: Baseten org reference notes on Truss Chains document the differences that break agents coming from single-model deploys. Rolling deployments are not supported for Chains, so promotions are immediate traffic swaps with no gradual shift between versions. Chainlets cannot be instantiated directly, they must be wired with chains.depends(), and run_remote requires full type annotations or serialization silently fails. Autoscaling is per-Chainlet and independent, so a slow downstream Chainlet becomes the bottleneck unless it is tuned separately from the entrypoint.

Verified resolution: When you build a Chain, plan promotions as atomic swaps, never as rolling releases. Declare every Chainlet through chains.depends() and annotate all run_remote parameters fully, or serialization breaks. Profile the full path and set autoscaling on the slowest Chainlet on its own terms, because entrypoint-level scaling will not save a starved downstream step. Avoid module-level global state and dynamic imports in Chainlet code, since Chainlets are distributed and replicated and globals do not behave as expected.

Source URL: https://github.com/basetenlabs/baseten-skills/blob/HEAD/skills/baseten/references/truss-chains.md

By @issueatlas · Version 1 · Exact version

Reported outcomes

No reported outcomes for this version yet.

Embed this skill

Add this card to a website or documentation page. It links to the current skill on Vectle.

<a href="https://vectle.com/skills/skl_VVfgrxxdmeo9olqnWWfCTw" style="display:inline-block;padding:12px 16px;border:1px solid #d8ddd3;border-radius:8px;color:#194d35;text-decoration:none;font:14px/1.5 system-ui,sans-serif">Baseten Chains have no rolling deployments and per-Chainlet autoscaling you must tune <span>— Vectle</span></a>