Releasesby Glyphtruss 0.18.39
- test: expect 401 for a wrong performance-client API key Add Hugging Face OIDC authentication to weights config Update development Python version to 3.13.17 Release 0.18.39
Also shipped Nov 9, 2026Baseten in November 2026 →
The following AlloyDB AI features and improvements are generally available ( GA ): - Smart batching for AI...
The following AlloyDB AI features and improvements are generally available ( GA ): Smart batching for AI functions: AI function acceleration is generally available for ai.if , ai.rank , ai.analyze_sentiment , ai.summarize , ai.extract , ai.classify , and ai.generate on AlloyDB clusters running PostgreSQL 17 and later.
To support your FinOps practices, you can now opt in to compute cost attribution in BigQuery editions
To support your FinOps practices, you can now opt in to compute cost attribution in BigQuery editions. This feature attributes billed compute charges directly to the query projects that use your administration project's reservation capacity.
Query performance troubleshooting and job and system performance comparison in the BigQuery jobs explorer are...
Query performance troubleshooting and job and system performance comparison in the BigQuery jobs explorer are generally available (GA). For more information, see Troubleshoot job performance and Diagnose performance regressions by comparing jobs and systems .
When you create or schedule a pipeline, you can specify the maximum number of concurrently executed pipeline...
When you create or schedule a pipeline, you can specify the maximum number of concurrently executed pipeline tasks. This feature is generally available (GA).
You can use compression functions in GoogleSQL to compress or decompress bytes or string values by using the...
You can use compression functions in GoogleSQL to compress or decompress bytes or string values by using the Zstandard (Zstd) lossless data compression algorithm. The following functions are supported: ZSTD_COMPRESS ZSTD_DECOMPRESS_TO_BYTES ZSTD_DECOMPRESS_TO_STRING These functions are in Preview .
Fast mode for Anthropic Claude models is generally available
Fast mode for supported Anthropic Claude models, starting with Claude Fable 5.2 ( claude-fable-5-2 ), is available in General Availability (GA) . You can set "speed": "fast" in online pay-as-you-go prediction requests to accelerate output token generation for latency-sensitive agentic workflows.
More from trussEvery truss release →
truss 0.18.37
Truss 0.18.37 adds support for list-form configuration secrets and routes base image builds through the build platform.
truss 0.18.36
- Fix Chains reference generation and refresh curated output feat(performance-client): add batch System One API feat(train): resolve train init --examples through ml-cookbook's examples index feat(cli/train): show pending job messages on push and add --availability-model to train update Add periodic banner recommending the Baseten CLI fix: return 503 for...
truss 0.18.35
- feat: set the sampler replica count in truss loops push feat: Label model server startup logs until readiness (DI-2301) Widen fastapi constraint to <0.137.0 :boom: fix(server): register model module in sys.modules before exec_module Release 0.18.35
truss 0.18.34
- Add include and exclude filters to BDN mount configuration feat: Forward egress_restrictions for BIS and warn about missing hosts Release 0.18.34
truss 0.18.33
- feat(performance-client): NET-1589 Explicit trace context and opt-in OTLP export fix(performance-client): stop hedge and retry budgets from wrapping past zero Add --spot to truss train workstation fix(chains): consolidate push logging and stop duplicate status header Add an SSH opt-out for loops exec Keep inference working when performance client tracing...
truss 0.18.32
- Bump control server truss pin to fix dev deployments on newer GPUs Set control server websocket limit to 100MiB (NET-1566) Fix two integration test failures on main Allow data-parallel BEI encoder deployments Release 0.18.32
truss 0.18.31
- Truss: support updated training auth config (OIDC, AssumeRole) Remove transfer command from BEI startup trt config: Honor configured BEI max token limit Add fp8_mlp_only quantization type fix(config): preserve YAML merge keys during duplicate checks Honor global --non-interactive in child commands Update the base_image examples in the config schema Add...