Open WebUI v0.5.0 — Release Notes & Engineering Impact
Open WebUI v0.5.0. Source highlight: [0.5.0] - 2024-12-25
1172 tracked entries. Older history is imported progressively; see source coverage.
Open WebUI v0.5.0. Source highlight: [0.5.0] - 2024-12-25
Dify 0.14.2. Source highlight: ✨ What’s New in v0.14.2? ✨
Dify 0.14.1. Source highlight: ✨ What’s New in v0.14.1? ✨
vLLM v0.6.5. Source highlight: Significant progress on the V1 engine refactor and multimodal support: New model executable interfaces for text-only and multimodal models, multiprocessing, improved configuration handling, and profiling enhancements (#10374, #10570, #10699, #11074, #11076, #10382, #10665, #10564, #11125, #11185, #1
Ollama v0.5.4. Source highlight: Falcon3: A family of efficient AI models under 10B parameters performant in science, math, and coding through innovative training techniques.
Hugging Face Transformers v4.47.1. Source highlight: Patch release v4.47.1
Ollama v0.5.3. Source highlight: Fixed runtime errors on older Intel Macs
Dify 0.14.0. Source highlight: ✨ Discover What's New in v0.14.0 ✨
Ollama v0.5.2. Source highlight: EXAONE 3.5: a collection of instruction-tuned bilingual (English and Korean) generative models ranging from 2.4B to 32B parameters, developed and released by LG AI Research.
LocalAI v2.24.2. Source highlight: chore: :arrow_up: Update ggerganov/llama.cpp to `26a8406ba9198eb6fdd8329fa717555b4f77f05f`
Dify 0.13.2. Source highlight: ✨ What’s New in v0.13.2? ✨
LocalAI v2.24.1. Source highlight: This is a patch release to fix https://github.com/mudler/LocalAI/issues/4334
Open WebUI v0.4.8. Source highlight: [0.4.8] - 2024-12-07
Ollama v0.5.1. Source highlight: Fixed issue where Ollama's API would generate JSON output when specifying `"format": null`
Hugging Face Transformers v4.47.0. Source highlight: PaliGemma 2 and PaliGemma are lightweight open vision-language models (VLM) inspired by PaLI-3, and based on open components like the SigLIP vision model and the Gemma language model. PaliGemma takes both images and text as inputs and can answer questions about images with detail and context, meanin
Dify 0.13.1. Source highlight: ✨ What's New in v0.13.1? ✨
Ollama v0.5.0. Source highlight: Llama 3.3: a new state of the art 70B model. Llama 3.3 70B offers similar performance compared to Llama 3.1 405B model.
LocalAI v2.24.0. Source highlight: LocalAI release v2.24.0!
Dify 0.13.0. Source highlight: 🚀 What’s New in v0.13.0? 🚀
Open WebUI v0.4.7. Source highlight: [0.4.7] - 2024-12-01
Ollama v0.4.7. Source highlight: The OpenAI compatible chat endpoint now includes index fields for tool calls, fixing issue when using `chat.completions.stream` and other methods
Ollama v0.4.6. Source highlight: QwQ: an experimental research model by the Qwen team, focused on advancing AI reasoning capabilities.
Open WebUI v0.4.6. Source highlight: [0.4.6] - 2024-11-26
Open WebUI v0.4.5. Source highlight: [0.4.5] - 2024-11-26
Dify 0.12.1. Source highlight: Bug Fixes in v0.12.1
Ollama v0.4.5. Source highlight: Ollama Python library improvements
Dify 0.12.0. Source highlight: ✨ What’s New in v0.12.0? ✨
Open WebUI v0.4.4. Source highlight: [0.4.4] - 2024-11-22
Ollama v0.4.4. Source highlight: Marco-o1: An open large reasoning model for real-world solutions by the Alibaba International Digital Commerce Group (AIDC-AI).
Open WebUI v0.4.3. Source highlight: [0.4.3] - 2024-11-21
Ollama v0.4.3. Source highlight: Tülu 3: Tülu 3 is a leading instruction following model family, offering fully open-source data, code, and recipes by the The Allen Institute for AI.
Open WebUI v0.4.2. Source highlight: [0.4.2] - 2024-11-20
Open WebUI v0.4.1. Source highlight: [0.4.1] - 2024-11-19
Open WebUI v0.4.0. Source highlight: [0.4.0] - 2024-11-19
Hugging Face Transformers v4.46.3. Source highlight: One small fix for FSDP + gradient accumulation loss issue!
Dify 0.11.2. Source highlight: ✨ What’s New in v0.11.2? ✨
vLLM v0.6.4.post1. Source highlight: This patch release covers bug fixes (#10347, #10349, #10348, #10352, #10363), keep compatibility for `vLLMConfig` usage in out of tree models (#10356)
vLLM v0.6.4. Source highlight: Significant progress in V1 engine core refactor (#9826, #10135, #10288, #10211, #10225, #10228, #10268, #9954, #10272, #9971, #10224, #10166, #9289, #10058, #9888, #9972, #10059, #9945, #9679, #9871, #10227, #10245, #9629, #10097, #10203, #10148). You can checkout more details regarding the design a
Ollama v0.4.2. Source highlight: Ollama now supports NVIDIA Jetson. To install Ollama on NVIDIA Jetson devices, run:
Dify 0.11.1. Source highlight: ✨ What's New in v0.11.1? ✨
LocalAI v2.23.0. Source highlight: feat(templates): use a single template for multimodals messages
Ollama v0.4.1. Source highlight: Fixed an issue where the cuda v12 runner on linux was incorrectly linked
Hugging Face Transformers v4.46.2. Source highlight: Patch release v4.46.2
Dify 0.11.0. Source highlight: 🌟 What's New in v0.11.0? 🌟
Hugging Face Transformers v4.46.1. Source highlight: Patch release v4.4.61
Dify 0.10.2. Source highlight: ✨ What’s New in v0.10.2? ✨
Open WebUI v0.3.35. Source highlight: [0.3.35] - 2024-10-26
Open WebUI v0.3.34. Source highlight: [0.3.34] - 2024-10-26
Open WebUI v0.3.33. Source highlight: [0.3.33] - 2024-10-24
Hugging Face Transformers v4.46.0. Source highlight: The Moshi model was proposed in Moshi: a speech-text foundation model for real-time dialogue by Alexandre Défossez,