Dify: v0.5.10
Dify 0.5.10. Source highlight: Added Anthripic `claude-3-haiku-20240307` by @lroolle #2825
AI Models & LLM Frameworks archive — Page 18
1172 tracked entries. Older history is imported progressively; see source coverage.
LocalAI v2.10.1 — Release Notes & Engineering Impact
LocalAI v2.10.1. Source highlight: fix(llama.cpp): fix eos without cache
Open WebUI v0.1.113 — Release Notes & Engineering Impact
Open WebUI v0.1.113. Source highlight: [0.1.113] - 2024-03-18
LocalAI v2.10.0 — Release Notes & Engineering Impact
LocalAI v2.10.0. Source highlight: LocalAI v2.10.0 Release Notes
Open WebUI v0.1.112 — Release Notes & Engineering Impact
Open WebUI v0.1.112. Source highlight: [0.1.112] - 2024-03-15
Dify: v0.5.9
Dify 0.5.9. Source highlight: Supported Groq LLM by @Yeuoly #2733
Open WebUI v0.1.111 — Release Notes & Engineering Impact
Open WebUI v0.1.111. Source highlight: [0.1.111] - 2024-03-10
Ollama v0.1.29 — Release Notes & Engineering Impact
Ollama v0.1.29. Source highlight: Ollama now supports AMD graphics cards in preview on Windows and Linux. All the features are now accelerated by AMD graphics cards, and support is included by default in Ollama for Linux, Windows and Docker.
Open WebUI v0.1.110 — Release Notes & Engineering Impact
Open WebUI v0.1.110 is published, but the available notes are too limited to assess upgrade impact. Review the official source before upgrading.
Open WebUI v0.1.109 — Release Notes & Engineering Impact
Open WebUI v0.1.109. Source highlight: [0.1.109] - 2024-03-06
Dify: v0.5.8
Dify 0.5.8. Source highlight: Added Anthropic `claude-3` LLM with Vision #2684
Open WebUI v0.1.108 — Release Notes & Engineering Impact
Open WebUI v0.1.108. Source highlight: Automatically created new release
Open WebUI v0.1.107 — Release Notes & Engineering Impact
Open WebUI v0.1.107. Source highlight: Automatically created new release
vLLM v0.3.3 — Release Notes & Engineering Impact
vLLM v0.3.3. Source highlight: Performance optimization and LoRA support for Gemma
Ollama v0.1.28 — Release Notes & Engineering Impact
Ollama v0.1.28. Source highlight: StarCoder2: the next generation of transparently trained open code LLMs that comes in three sizes: 3B, 7B and 15B parameters.
Hugging Face Transformers v4.38.2 — Release Notes & Engineering Impact
Hugging Face Transformers v4.38.2. Source highlight: Fix backward compatibility issues with Llama and Gemma:
Dify: v0.5.7
Dify 0.5.7. Source highlight: Added `Mistral AI` model provider. #2594
Open WebUI v0.1.106 — Release Notes & Engineering Impact
Open WebUI v0.1.106. Source highlight: @eltociear made their first contribution in https://github.com/open-webui/open-webui/pull/924
Open WebUI v0.1.105 — Release Notes & Engineering Impact
Open WebUI v0.1.105. Source highlight: @buroa made their first contribution in https://github.com/open-webui/open-webui/pull/914
Open WebUI v0.1.104 — Release Notes & Engineering Impact
Open WebUI v0.1.104. Source highlight: Automatically created new release
Open WebUI v0.1.103 — Release Notes & Engineering Impact
Open WebUI v0.1.103. Source highlight: Automatically created new release
LocalAI v2.9.0 — Release Notes & Engineering Impact
LocalAI v2.9.0. Source highlight: This release brings many enhancements, fixes, and a special thanks to the community for the amazing work and contributions!
Open WebUI v0.1.102 — Release Notes & Engineering Impact
Open WebUI v0.1.102. Source highlight: Automatically created new release
Ollama v0.1.27 — Release Notes & Engineering Impact
Ollama v0.1.27. Source highlight: 
Hugging Face Transformers v4.38.1 — Release Notes & Engineering Impact
Hugging Face Transformers v4.38.1. Source highlight: Fix eager attention in Gemma!
vLLM v0.3.2 — Release Notes & Engineering Impact
vLLM v0.3.2. Source highlight: This version adds support for the OLMo and Gemma Model, as well as `seed` parameter.
Hugging Face Transformers: v4.38: Gemma, Depth Anything, Stable LM; Static Cache, HF Quantizer, AQLM
Hugging Face Transformers v4.38.0. Source highlight: Gemma is a new opensource Language Model series from Google AI that comes with a 2B and 7B variant. The release comes with the pre-trained and instruction fine-tuned versions and you can use them via `AutoModelForCausalLM`, `GemmaForCausalLM` or `pipeline` interface!
Ollama v0.1.26 — Release Notes & Engineering Impact
Ollama v0.1.26. Source highlight: Support for `bert` and `nomic-bert` embedding models
Dify: v0.5.6
Dify 0.5.6. Source highlight: Added voice choose for TTS in App. Thanks @charli117!
vLLM v0.3.1 — Release Notes & Engineering Impact
vLLM v0.3.1. Source highlight: This version fixes the following major bugs:
LocalAI v2.8.2 — Release Notes & Engineering Impact
LocalAI v2.8.2. Source highlight: fix(tts): fix regression when supplying backend from requests
LocalAI v2.8.1 — Release Notes & Engineering Impact
LocalAI v2.8.1. Source highlight: This is a patch release, mostly containing minor patches and bugfixes from 2.8.0.
Ollama v0.1.25 — Release Notes & Engineering Impact
Ollama v0.1.25. Source highlight: 
Dify: v0.5.5
Dify 0.5.5. Source highlight: Adding SMTP method for sending emails. Thanks @jonahcui!
LocalAI v2.8.0 — Release Notes & Engineering Impact
LocalAI v2.8.0. Source highlight: This release adds support for Intel GPUs, and it deprecates old ggml-based backends which are by now superseded by llama.cpp (that now supports more architectures out-of-the-box). See also https://github.com/mudler/LocalAI/issues/1651.
Ollama v0.1.24 — Release Notes & Engineering Impact
Ollama v0.1.24. Source highlight: OpenAI Compatibility
Dify: v0.5.4
Dify 0.5.4. Source highlight: GPT-3.5-Turbo-0125 Integration
Ollama v0.1.23 — Release Notes & Engineering Impact
Ollama v0.1.23. Source highlight: The LLaVA model family on Ollama has been updated to version 1.6, and now includes a new `34b` version:
Dify: v0.5.3
Dify 0.5.3. Source highlight: Support function calling for more models (Azure OpenAI, xinference, ZhipuAI, Minimax)
vLLM v0.3.0 — Release Notes & Engineering Impact
vLLM v0.3.0. Source highlight: Experimental multi-lora support
Hugging Face Transformers: Patch release v4.37.2
Hugging Face Transformers v4.37.2. Source highlight: Protecting the imports for SigLIP's tokenizer if sentencepiece isn't installed
LocalAI v2.7.0 — Release Notes & Engineering Impact
LocalAI v2.7.0. Source highlight: This release adds support to the transformer backend for LLM as well!
Ollama v0.1.22 — Release Notes & Engineering Impact
Ollama v0.1.22. Source highlight: Stable LM 2: A state-of-the-art 1.6B small language model.
Dify: v0.5.2
Dify 0.5.2. Source highlight: Add OpenAI `gpt-4-turbo-preview`, `gpt-4-0125-preview`, `text-embedding-3-large`, `text-embedding-3-small` Models
Dify: v0.5.1
Dify 0.5.1. Source highlight: add multiple LLM debug mode ⚔️
Hugging Face Transformers: Patch release: v4.37.1
Hugging Face Transformers v4.37.1. Source highlight: A patch release to resolve import errors from removed custom types in generation utils
Dify: v0.5.0
Dify 0.5.0. Source highlight: 🎉🎉 **Dify Version 0.5 Release Notes**
LocalAI v2.6.1 — Release Notes & Engineering Impact
LocalAI v2.6.1. Source highlight: This is a patch release containing bug-fixes around parallel request support with llama.cpp models.
Hugging Face Transformers: v4.37 Qwen2, Phi-2, SigLIP, ViP-LLaVA, Fast2SpeechConformer, 4-bit serialization, Whisper longform generation
Hugging Face Transformers v4.37.0. Source highlight: Qwen2 is the new model series of large language models from the Qwen team. Previously, the Qwen series was released, including Qwen-72B, Qwen-1.8B, Qwen-VL, Qwen-Audio, etc.
LocalAI v2.6.0 — Release Notes & Engineering Impact
LocalAI v2.6.0. Source highlight: move BUILD_GRPC_FOR_BACKEND_LLAMA logic to makefile: errors in this section now immediately fail the build