Releasesby GlyphvLLM 0.29.0
v0.29.0 Highlights This release features 594 commits from 277 contributors (91 new)! Model Runner V2 is now the default for all models ( #53183 ), completing the rollout that began with pooling models ( #48290 ).
Also shipped Sep 10, 2026vLLM in September 2026 →
BigQuery conversational analytics adds ML.CORRELATION in preview
Conversational analytics can now use ML.CORRELATION to calculate statistical correlations between a target column and one or more metric columns in a table.
BigQuery ML.METRICS evaluates predictions without a stored model
The preview ML.METRICS function computes classification or regression evaluation metrics on any table or query with actual and predicted values, with no need to create or reference a stored model.
You can use the AI.CAUSAL_EFFECT function to quantify the impact of specific interventions on time series data
You can use the AI.CAUSAL_EFFECT function to quantify the impact of specific interventions on time series data. This feature is in Preview .
BigQuery Data Engineering Agent integrates with BigQuery Graph
The Data Engineering Agent now uses BigQuery Graph for extra context between source and destination schemas, improving schema mapping accuracy in data engineering pipelines. It is generally available.
Using dbt artifacts for Slim CI and defer to production in dbt Projects on Snowflake (General availability)
Slim CI, defer to production, failed-execution recovery, and concurrent execution are now generally available for dbt Projects on Snowflake. Reuse dbt artifacts from recent production executions to accelerate development, streamline CI/CD workflows, and recover from failed production runs without maintaining a separate artifact store.
External secret providers (Preview)
External secret providers are now in preview. If your organization already keeps API keys, database passwords, and similar values in AWS Secrets Manager, Azure Key Vault, or Google Cloud Secret Manager, Snowflake can read those values when a query needs them, so you don't have to maintain a second copy in a Snowflake secret .
More from vLLMEvery vLLM release →
vLLM 0.30.0
v0.30.0 Highlights This release features 762 commits from 315 contributors (104 new)! New models : DeepSeek-V4.1-Flash ( #56214 , #56228 , #56208 ) with the whole KV stored in MXFP8 through the FlashMLA V4.1 record on SM100 ( #56893 ), DeepGEMM Mega-mHC ( #56962 ), and async Engram prefetch with Engram DP sharding ( #56512 ); DeepSeek-V4-Flash-Vision-Exp (...
vLLM 0.31.0
v0.31.0 Highlights This release features 717 commits from 307 contributors (96 new)! - DeepSeek-V4.1-Flash performance: FlashMLA mega attention with the V4.1 NVFP4 compressed KV cache is now the SM100 default ; DeepGEMM sparse MQA logits for the indexer and Mega-Gate fusing the gate GEMM with expert selection ; decoder boundaries fuse the TP all-reduce, mHC...
vLLM 0.32.0
v0.32.0 Highlights This release features 814 commits from 363 contributors (121 new)! - Structured decisions and generic parsers: the new POST /v1/systemone endpoint answers choice, noul and score questions over a structured state , is served by default (#60677, #60696), and also runs on Cloudflare/clef-omni , LiquidAI/d1-3B and DiffusionGemma .