v0.6.8 GPT-4o is available now in Dify
Dify 0.6.8. Source highlight: ✨ What’s New in v0.6.8? ✨
1172 tracked entries. Older history is imported progressively; see source coverage.
Dify 0.6.8. Source highlight: ✨ What’s New in v0.6.8? ✨
Ollama v0.1.37. Source highlight: Fixed issue where models with uppercase characters in the name would not show with `ollama list`
Ollama v0.1.36. Source highlight: Fixed `exit status 0xc0000005` error with AMD graphics cards on Windows
Ollama v0.1.35. Source highlight: Llama 3 ChatQA: A model from NVIDIA based on Llama 3 that excels at conversational question answering (QA) and retrieval-augmented generation (RAG).
LocalAI v2.15.0. Source highlight: 🎉 LocalAI v2.15.0! 🚀
Dify 0.6.7. Source highlight: ✨ What’s New in v0.6.7? ✨
Open WebUI v0.1.124. Source highlight: [0.1.124] - 2024-05-08
Ollama v0.1.34. Source highlight: Llava Llama 3: A new high-performing LLaVA model fine-tuned from Llama 3 Instruct.
Hugging Face Transformers v4.40.2. Source highlight: Fix torch fx for LLama model
vLLM v0.4.2. Source highlight: Chunked prefill is ready for testing! It improves inter-token latency in high load scenario by chunking the prompt processing and priortizes decode (#4580)
LocalAI v2.14.0. Source highlight: 🚀 AIO Image Update: llama3 has landed!
Open WebUI v0.1.123. Source highlight: [0.1.123] - 2024-05-02
Dify 0.6.6. Source highlight: ✨ What’s New in v0.6.6? ✨
Ollama v0.1.33. Source highlight: Llama 3: a new model by Meta, and the most capable openly available LLM to date
Open WebUI v0.1.122. Source highlight: [0.1.122] - 2024-04-27
LocalAI v2.13.0. Source highlight: Hello folks, Ettore here - I'm happy to announce the v2.13.0 LocalAI release is out, with many features!
Dify 0.6.5. Source highlight: ✨ What’s New in v0.6.5? ✨
Open WebUI v0.1.121. Source highlight: [0.1.121] - 2024-04-24
vLLM v0.4.1. Source highlight: Support and enhance CommandR+ (#3829), minicpm (#3893), Meta Llama 3 (#4175, #4182), Mixtral 8x22b (#4073, #4002)
Hugging Face Transformers v4.40.1. Source highlight: Kudos to @pcuenca for the prompt fix in:
Dify 0.6.4. Source highlight: ✨ Spotlight on Dify v0.6 ✨
Open WebUI v0.1.120. Source highlight: [0.1.120] - 2024-04-20
Hugging Face Transformers v4.40.0. Source highlight: Llama 3 is supported in this release through the Llama 2 architecture and some fixes in the `tokenizers` library.
Open WebUI v0.1.119. Source highlight: [0.1.119] - 2024-04-16
Dify 0.6.3. Source highlight: ✨ Spotlight on Dify v0.6 ✨
Dify 0.6.2. Source highlight: PLEASE UPGRADE to `v0.6.2` AS SOON AS POSSIBLE TO PREVENT DATA LEAKAGE.
LocalAI v2.12.4 is published, but the available notes are too limited to assess upgrade impact. Review the official source before upgrading.
Ollama v0.1.32. Source highlight: WizardLM 2: State of the art large language model from Microsoft AI with improved performance on complex chat, multilingual, reasoning and agent use cases.
Open WebUI v0.1.118. Source highlight: [0.1.118] - 2024-04-10
LocalAI v2.12.3. Source highlight: I'm happy to announce the v2.12.3 LocalAI release is out!
Dify 0.6.1. Source highlight: ✨ Spotlight on Dify v0.6.0 ✨
LocalAI v2.12.1. Source highlight: I'm happy to announce the v2.12.1 LocalAI release is out!
LocalAI v2.12.0. Source highlight: I'm happy to announce the v2.12.0 LocalAI release is out!
Dify 0.6.0-fix1. Source highlight: **EMERGENCY FIX:** `ADD FEATURE` dialog of Agent application that incorrectly used the Text Generator App dialog content.
Dify 0.6.0. Source highlight: Introducing Dify Workflow! 🎉
Ollama v0.1.31. Source highlight: 
Open WebUI v0.1.117. Source highlight: [0.1.117] - 2024-04-03
vLLM v0.4.0.post1. Source highlight: v0.4.0 lacks support for sm70/75 support. We did a hotfix for it.
Hugging Face Transformers v4.39.3. Source highlight: The `AWQ` issue persisted, and there was a regression reported with beam search and input embeddings.
Dify 0.5.11-fix1. Source highlight: Fixed critical issue
Open WebUI v0.1.116. Source highlight: [0.1.116] - 2024-03-31
vLLM v0.4.0. Source highlight: New models: Command+R(#3433), Qwen2 MoE(#3346), DBRX(#3660), XVerse (#3610), Jais (#3183).
Dify 0.5.11. Source highlight: Add azure blob storage support by @JohnJyong in #2919
Hugging Face Transformers v4.39.2. Source highlight: Series of fixes for backwards compatibility (AutoAWQ and other quantization libraries, imports from `trainer_pt_utils`) and functionality (LLaMA tokenizer conversion)
Ollama v0.1.30. Source highlight: Command R: a Large Language Model optimized for conversational interaction and long context tasks.
LocalAI v2.11.0. Source highlight: Introducing LocalAI v2.11.0: All-in-One Images!
Open WebUI v0.1.115. Source highlight: [0.1.115] - 2024-03-24
Hugging Face Transformers v4.39.1. Source highlight: Patch release to fix some breaking changes to LLaVA model, fixes/cleanup for Cohere & Gemma and broken doctest
Open WebUI v0.1.114. Source highlight: [0.1.114] - 2024-03-20
Hugging Face Transformers v4.39.0. Source highlight: 🚨 VRAM consumption 🚨