Transformers Release v5.13.0

UpdateJul 3, 2026VerifiedAdded Sep 22, 2026

Release v5.13.0 New Model additions KimiK 2.5, 2.6, and 2.7 This release includes the architecture for Kimi 2.5 which is used by 2.5-2.7: Kimi K2.5 is an open-source, native multimodal agentic model that advances practical capabilities in long-horizon coding, coding-driven design, proactive autonomous execution, and swarm-based task orchestration.

AI agents Performance

Read Hugging Face's release notes

https://github.com/huggingface/transformers/releases/tag/v5.13.0

Summaries of vendors' own notes. Product names and logos belong to their owners; logos via logo.dev.

More Transformers releases

TransformersJul 11, 2026

Transformers Patch release v5.13.1

Patch release v5.13.1 This patch is focused on enabling transformers for the latest release of vllm! Be more defensive with remap_legacy_layer_types for custom models ( #47245 ) from @hmellor Fix custom code which doesn't know about the new linear layer type names ( #47174 ) from @hmellor Fix case where _LazyAutoMapping.register is passed a str key ( #47148...

UpdateSource

TransformersJul 15, 2026

Transformers Release v5.14.0

Release v5.14.0 New Model additions Inkling (fresh from Thinking Machines): 975B total, 41B active Add Inkling model #47347 by @molbap @Cyrilvallez @eustlb and @zucchini-nlp Inkling is a general-purpose multimodal model that accepts text, image and audio inputs and generates text outputs.

UpdateAI agentsVector searchStreamingSource

TransformersJul 16, 2026

Transformers Patch release: v5.14.1

Patch release v5.14.1 This patch solves a few issues which appeared when integrating Inkling model, most notably an issue affecting models using EncoderDecoderCache during assisted generation. It also fixes an issue that could appear during prefill with StaticCache and sdpa without padding for Inkling which uses a position_bias.

UpdateSource

TransformersAug 10, 2026

Transformers Release: v5.15.0

Release v5.15.0 New Model additions Meta Muse Glimmer Muse Glimmer, released today, is Meta’s new multimodal model, especially designed for agentic use cases. Distilled from Muse to 30B parameters, and released under the Apache 2.0 license, it can be deployed to local setups for privacy-aware applications such as coding, document analysis, personal...

UpdateAI agentsObservabilityDeveloper toolsSource

TransformersAug 19, 2026

Transformers Patch release: v5.15.1

Patch release v5.15.1 This patch most notably solves a few issues with DFlash and MTP candidate generators, as well as an issue where images could sometimes not be processed on accelerator if using Lanczos filter.

UpdateSource

TransformersAug 26, 2026

Transformers Release v5.16.1

Release v5.16.1 This is a special release as we include GLM! (and a few small fixes) GLM-5.3-Flash GLM-5.3-Flash, the first natively multimodal model in the GLM-5 series.

UpdateAI agentsLLMsSecuritySource

TransformersAug 26, 2026

Transformers Release: v5.16.0

Release v5.16.0 New Model additions Qwen4-Exp Qwen4-Exp builds on Qwen3.5's hybrid text and multimodal architecture with three key components: GatedResidual (GR), Qwen Sparse Attention (QSA), and Per-Layer Embedding (PLE). GR is a Qwen-developed residual architecture that combines Hyper-Connection with GatedNorm.

UpdateVector searchSQLStreamingSource

TransformersSep 10, 2026

Transformers Release 5.17.0

Release v5.17.0 New Model additions HYV4 Hy4-Preview is a 780B-parameter mixture-of-experts language model that activates 49B parameters per token. Each MoE layer holds 256 routed experts plus one always-active shared expert and routes every token to 8 of them. The context window is 1M tokens.

PreviewSQLStreamingSource

Also shipped on Jul 3, 2026

Databricks Databricks Data Intelligence PlatformJul 3, 2026

Okta support for automatic identity management is now generally available

Okta support for automatic identity management is now generally available. Automatic identity management lets you sync users and groups from Okta into Databricks without SCIM provisioning.

GASecuritySource

Snowflake Snowflake Cortex AIJul 3, 2026

Resource budgets for Cortex Search

Snowflake now supports resource budgets to control credit spending for Cortex Search services. Resource budgets let you define a monthly spending limit and take automated actions, such as revoking access or suspending the service, when spending exceeds your limits. For more information, see Resource budgets for Cortex Search .

UpdatePricingSource

Vercel AI SDK and AI GatewayJul 3, 2026

Vercel Sandbox now supports FUSE-based filesystems

Vercel Sandbox now supports FUSE, letting you mount remote storage and custom filesystems inside a running Sandbox. Use it to attach S3 buckets, network filesystems, or any other FUSE-compatible driver as a regular path.

UpdateStreamingDeveloper toolsSource

Vercel Vercel platformJul 3, 2026

Manage Vercel Flags segments with Vercel CLI

Vercel Flags segments can now be managed from the Vercel CLI with the new vercel flags segments command. A segment is the targeting primitive a flag uses to decide who sees what. Membership composes from three repeatable tokens: include: , exclude: , and rule: . Pass them to --add or --remove for incremental edits.

UpdateAI agentsData integrationDeveloper toolsSource

Vercel AI SDK and AI GatewayJul 3, 2026

Agent Runs now available in the Vercel MCP and CLI

Your agent can now inspect Agent Runs via the Vercel MCP and CLI for eve , the open-source agent framework. eve traces are automatically ingested when deployed to Vercel and available as Agent Runs.

UpdateAI agentsMCPData integrationSource

ClickHouse ClickHouseJul 3, 2026

ClickHouse Release 26.6

ClickHouse 26.6 is here! In this release, we have hypothetical skip indexes, cascading refreshable materialized views, experimental support for continuous queries, and more!

UpdateSource