Ollama v0.2.1 — Release Notes & Engineering Impact
Ollama v0.2.1. Source highlight: Fixed issue where setting `OLLAMA_NUM_PARALLEL` would cause models to be reloaded after each request
AI Models & LLM Frameworks archive — Page 16
1172 tracked entries. Older history is imported progressively; see source coverage.
Dify: v0.6.13
Dify 0.6.13. Source highlight: ✨ What’s New in v0.6.13? ✨
vLLM v0.5.1 — Release Notes & Engineering Impact
vLLM v0.5.1. Source highlight: vLLM now has pipeline parallelism! (#4412, #5408, #6115, #6120). You can now run the API server with `--pipeline-parallel-size`. This feature is in early stage, please let us know your feedback.
Ollama v0.2.0 — Release Notes & Engineering Impact
Ollama v0.2.0. Source highlight: Ollama 0.2.0 is now available with concurrency support. This unlocks 2 specific features:
LocalAI v2.18.1 — Release Notes & Engineering Impact
LocalAI v2.18.1. Source highlight: fix(talk): identify the model by ID instead of name
Open WebUI v0.3.7 — Release Notes & Engineering Impact
Open WebUI v0.3.7. Source highlight: [0.3.7] - 2024-06-29
Dify: v0.6.12-fix1
Dify 0.6.12-fix1. Source highlight: Fixed the issue where the WebApp URL was incorrect and the problem where the model and tools icons weren’t showing up after starting from Docker Compose with default `.env`.
Ollama v0.1.48 — Release Notes & Engineering Impact
Ollama v0.1.48. Source highlight: Fixed issue where Gemma 2 would continuously output when reaching context limits
Hugging Face Transformers: Patch release v4.42.3
Hugging Face Transformers v4.42.3. Source highlight: Make sure we have attention softcapping for "eager" GEMMA2 model
LocalAI v2.18.0 — Release Notes & Engineering Impact
LocalAI v2.18.0. Source highlight: Here’s a quick overview of what’s new in 2.18.0:
Dify: v0.6.12
Dify 0.6.12. Source highlight: ✨ What’s New in v0.6.12? ✨
Hugging Face Transformers: Patch release v4.42.2
Hugging Face Transformers v4.42.2. Source highlight: Thanks to our 2 contributors for their prompt fixing mostly applies for training and FA2!
Open WebUI v0.3.6 — Release Notes & Engineering Impact
Open WebUI v0.3.6. Source highlight: [0.3.6] - 2024-06-27
Hugging Face Transformers: v4.42.1: Patch release
Hugging Face Transformers v4.42.1 is published, but the available notes are too limited to assess upgrade impact. Review the official source before upgrading.
Hugging Face Transformers: v4.42.0: Gemma 2, RTDETR, InstructBLIP, LLAVa Next, New Model Adder
Hugging Face Transformers v4.42.0. Source highlight: The Gemma2 model was proposed in Gemma2: Open Models Based on Gemini Technology and Research by Gemma2 Team, Google.
Ollama v0.1.47 — Release Notes & Engineering Impact
Ollama v0.1.47. Source highlight: Added support for Google Gemma 2 models (9B and 27B)
Ollama v0.1.46 — Release Notes & Engineering Impact
Ollama v0.1.46. Source highlight: Increased model loading speed with `ollama run`, especially if running an already-loaded model
LocalAI v2.17.1 — Release Notes & Engineering Impact
LocalAI v2.17.1. Source highlight: This is a patch release to address issues with Linux single binary releases. It also adds support for Stable diffusion 3!
LocalAI v2.17.0 — Release Notes & Engineering Impact
LocalAI v2.17.0. Source highlight: Ahoj! this new release of LocalAI comes with tons of updates, and enhancements behind the scenes!
Open WebUI v0.3.5 — Release Notes & Engineering Impact
Open WebUI v0.3.5. Source highlight: [0.3.5] - 2024-06-16
Ollama v0.1.45 — Release Notes & Engineering Impact
Ollama v0.1.45. Source highlight: DeepSeek-Coder-V2: A 16B & 236B open-source Mixture-of-Experts code language model that achieves performance comparable to GPT4-Turbo in code-specific tasks.
Dify: v0.6.11
Dify 0.6.11. Source highlight: ✨ What’s New in v0.6.11? ✨
vLLM v0.5.0.post1 — Release Notes & Engineering Impact
vLLM v0.5.0.post1. Source highlight: Add initial TPU integration (#5292)
Ollama v0.1.44 — Release Notes & Engineering Impact
Ollama v0.1.44. Source highlight: Fixed issue where unicode characters such as emojis would not be loaded correctly when running `ollama create`
Open WebUI v0.3.4 — Release Notes & Engineering Impact
Open WebUI v0.3.4. Source highlight: [0.3.4] - 2024-06-12
Open WebUI v0.3.3 — Release Notes & Engineering Impact
Open WebUI v0.3.3. Source highlight: [0.3.3] - 2024-06-12
vLLM v0.5.0 — Release Notes & Engineering Impact
vLLM v0.5.0. Source highlight: FP8 support is ready for testing. By quantizing the portion model weights to 8 bit precision float point, the inference speed gets 1.5x boost. Please try it out and let us know your thoughts! (#5352, #5388, #5159, #5238, #5294, #5183, #5144, #5231)
Ollama v0.1.43 — Release Notes & Engineering Impact
Ollama v0.1.43. Source highlight: New import.md guide for converting and importing models to Ollama
Open WebUI v0.3.2 — Release Notes & Engineering Impact
Open WebUI v0.3.2. Source highlight: [0.3.2] - 2024-06-10
Open WebUI v0.3.1 — Release Notes & Engineering Impact
Open WebUI v0.3.1. Source highlight: [0.3.1] - 2024-06-09
Open WebUI v0.3.0 — Release Notes & Engineering Impact
Open WebUI v0.3.0. Source highlight: [0.3.0] - 2024-06-09
Ollama v0.1.42 — Release Notes & Engineering Impact
Ollama v0.1.42. Source highlight: Qwen 2: a new series of large language models from Alibaba group
Open WebUI v0.2.5 — Release Notes & Engineering Impact
Open WebUI v0.2.5. Source highlight: [0.2.5] - 2024-06-05
Dify: v0.6.10
Dify 0.6.10. Source highlight: ✨ What’s New in v0.6.10? ✨
Open WebUI v0.2.4 — Release Notes & Engineering Impact
Open WebUI v0.2.4. Source highlight: [0.2.4] - 2024-06-03
Open WebUI v0.2.3 — Release Notes & Engineering Impact
Open WebUI v0.2.3. Source highlight: [0.2.3] - 2024-06-03
Open WebUI v0.2.2 — Release Notes & Engineering Impact
Open WebUI v0.2.2. Source highlight: [0.2.2] - 2024-06-02
Open WebUI v0.2.1 — Release Notes & Engineering Impact
Open WebUI v0.2.1. Source highlight: [0.2.1] - 2024-06-02
Open WebUI v0.2.0 — Release Notes & Engineering Impact
Open WebUI v0.2.0. Source highlight: 📢 We are thrilled to announce that our project has been selected as one of the 11 projects shaping open-source AI by the GitHub Accelerator program! 🎉
Ollama v0.1.41 — Release Notes & Engineering Impact
Ollama v0.1.41. Source highlight: Fixed issue on Windows 10 and 11 with Intel CPUs with integrated GPUs where Ollama would encounter an error
vLLM v0.4.3 — Release Notes & Engineering Impact
vLLM v0.4.3. Source highlight: Added support for Falcon (#5069)
Ollama v0.1.40 — Release Notes & Engineering Impact
Ollama v0.1.40. Source highlight: Codestral: Codestral is Mistral AI’s first-ever code model designed for code generation tasks.
Hugging Face Transformers: Release v4.41.2
Hugging Face Transformers v4.41.2. Source highlight: Mostly fixing some stuff related to `trust_remote_code=True` and `from_pretrained`
Dify: v0.6.9 Workflow as Tool
Dify 0.6.9. Source highlight: ✨ Dify v0.6.9 has landed! ✨
LocalAI v2.16.0 — Release Notes & Engineering Impact
LocalAI v2.16.0. Source highlight: Welcome to LocalAI's latest update!
Hugging Face Transformers: Release v4.41.1 Fix PaliGemma finetuning, and some small bugs
Hugging Face Transformers v4.41.1. Source highlight: Fix PaliGemma finetuning:
Ollama v0.1.39 — Release Notes & Engineering Impact
Ollama v0.1.39. Source highlight: Cohere Aya 23: A new state-of-the-art, multilingual LLM covering 23 different languages.
Open WebUI v0.1.125 — Release Notes & Engineering Impact
Open WebUI v0.1.125. Source highlight: [0.1.125] - 2024-05-19
Hugging Face Transformers: v4.41.0: Phi3, JetMoE, PaliGemma, VideoLlava, Falcon2, FalconVLM & GGUF support
Hugging Face Transformers v4.41.0. Source highlight: The Phi-3 model was proposed in Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone by Microsoft.
Ollama v0.1.38 — Release Notes & Engineering Impact
Ollama v0.1.38. Source highlight: Falcon 2: A new 11B parameters causal decoder-only model built by TII and trained over 5T tokens.