Dify: v1.7.1
Dify 1.7.1. Source highlight: 🎉 Dify v1.7.1 Release Notes 🎉
1172 tracked entries. Older history is imported progressively; see source coverage.
Dify 1.7.1. Source highlight: 🎉 Dify v1.7.1 Release Notes 🎉
LocalAI v3.2.3. Source highlight: fix(cuda): be consistent with image tag naming
LocalAI v3.2.2. Source highlight: fix(backends gallery): trim string when reading cap from file
Hugging Face Transformers v4.54.0. Source highlight: In order to become the source of truth, we recognize that we need to address two common and long-heard critiques about `transformers`:
LocalAI v3.2.1. Source highlight: fix(install.sh): update to use the new binary naming
vLLM v0.10.0. Source highlight: v0.10.0 release includes 308 commits, 168 contributors (62 new!).
LocalAI v3.2.0. Source highlight: Welcome to LocalAI 3.2.0! This is a release that refactors our architecture to be more flexible and lightweight.
Dify 1.7.0. Source highlight: 🌟 What’s New in v1.7.0? 🌟
Hugging Face Transformers v4.53.3. Source highlight: Small path release 4.53.3!
Open WebUI v0.6.18. Source highlight: [0.6.18] - 2025-07-19
Open WebUI v0.6.17. Source highlight: [0.6.17] - 2025-07-19
Ollama v0.10.0. Source highlight: Ollama's new app is available for macOS and Windows: Download Ollama
Open WebUI v0.6.16. Source highlight: [0.6.16] - 2025-07-14
Hugging Face Transformers v4.53.2. Source highlight: This patch contains the following bug fixes:
Dify 1.6.0. Source highlight: 🌟 What’s New in v1.6.0? 🌟
Ollama v0.9.6. Source highlight: Fixed styling issue in launch screen
vLLM v0.9.2. Source highlight: This release contains 452 commits from 167 contributors (31 new!)
Hugging Face Transformers v4.53.1. Source highlight: This patch contains several bug fixes. The following commits are included:
Ollama v0.9.5. Source highlight: Updates to Ollama for macOS and Windows
Dify 1.5.1. Source highlight: 🎉 What’s New in v1.5.1? 🎉
LocalAI v3.1.1. Source highlight: fix(backends gallery): correctly identify gpu vendor
Ollama v0.9.4. Source highlight: Updates to Ollama for macOS and Windows
LocalAI v3.1.0. Source highlight: Support for Gemma 3n!
Hugging Face Transformers v4.53.0. Source highlight: Gemma 3n models are designed for efficient execution on low-resource devices. They are capable of multimodal input, handling text, image, video, and audio input, and generating text outputs, with open weights for pre-trained and instruction-tuned variants. These models were trained with data in over
Ollama v0.9.3. Source highlight: 
Dify 1.5.0. Source highlight: 🚀 What's New in v1.5.0?
LocalAI v3.0.0. Source highlight: 🚀 LocalAI 3.0 – A New Era Begins
Ollama v0.9.2. Source highlight: Fixed issue where tool calls without parameters would not be returned correctly
Open WebUI v0.6.15. Source highlight: [0.6.15] - 2025-06-16
Dify 1.4.3. Source highlight: 🚀 What’s New in v1.4.3? 🚀
Dify 1.4.2. Source highlight: 🚀 What's New in v1.4.2?
vLLM v0.9.1. Source highlight: Progress in large scale serving
Open WebUI v0.6.14. Source highlight: [0.6.14] - 2025-06-10
Ollama v0.9.1. Source highlight: Tool calling improvements
vLLM v0.9.0.1. Source highlight: This patch release contains important bugfix for DeepSeek family of models on NVIDIA Ampere and below (#18807)
Hugging Face Transformers v4.52.4. Source highlight: The following commits are included in that patch release:
Open WebUI v0.6.13. Source highlight: [0.6.13] - 2025-05-30
Ollama v0.9.0. Source highlight: DeepSeek-R1-2508: DeepSeek-R1 has received a minor version upgrade to DeepSeek-R1-0528 for the 8 billion parameter distilled model and the full 671 billion parameter model. In this update, DeepSeek R1 has significantly improved its reasoning and inference capabilities.
Open WebUI v0.6.12. Source highlight: [0.6.12] - 2025-05-29
Ollama v0.8.0. Source highlight: Ollama will now stream responses with tool calls blog post
Dify 1.4.1. Source highlight: 🚀 What’s New in v1.4.1? 🚀
Open WebUI v0.6.11. Source highlight: [0.6.11] - 2025-05-27
Hugging Face Transformers v4.52.3. Source highlight: Patch release v4.52.3
Ollama v0.7.1. Source highlight: Improved model memory management to allocate sufficient memory to prevent crashes when running multimodal models in certain situations
Hugging Face Transformers v4.52.2. Source highlight: Patch release v4.52.2
Hugging Face Transformers v4.52.1. Source highlight: The Qwen2.5-Omni model is a unified multiple modalities model proposed in Qwen2.5-Omni Technical Report from Qwen team, Alibaba Group.
Open WebUI v0.6.10. Source highlight: [0.6.10] - 2025-05-19
Dify 1.4.0. Source highlight: 🌟 What's New in v1.4.0? 🌟
vLLM v0.9.0. Source highlight: vLLM has upgraded to PyTorch 2.7! (#16859) This is a breaking change for environment dependency.
Ollama v0.7.0. Source highlight: Ollama now supports multimodal models via Ollama’s new engine, starting with new vision multimodal models: