Ollama v0.32.4 — Release Notes & Engineering Impact
Ollama v0.32.4. Source highlight: Support Laguna on Apple GPUs via the MLX engine
AI Models & LLM Frameworks archive — Page 3
1172 tracked entries. Older history is imported progressively; see source coverage.
Ollama v0.32.3 — Release Notes & Engineering Impact
Ollama v0.32.3. Source highlight: Fixed model downloads that stall before sending data.
Dify: v1.16.0
Dify 1.16.0. Source highlight: Introducing Dify Agent *(Beta)*: A New Agent Experience in Dify
LangChain langchain==1.3.14 — Release Notes & Engineering Impact
LangChain langchain==1.3.14. Source highlight: Changes since langchain==1.3.13
Hugging Face Transformers: Patch release: v5.14.1
Hugging Face Transformers v5.14.1. Source highlight: Patch release v5.14.1
Ollama v0.32.1 — Release Notes & Engineering Impact
Ollama v0.32.1. Source highlight: Improved Gemma 4 tool calling and multi-turn reasoning, including more reliable tool-response continuations
Hugging Face Transformers: Release v5.14.0
Hugging Face Transformers v5.14.0. Source highlight: Inkling (fresh from Thinking Machines): 975B total, 41B active
LocalAI v4.7.1 — Release Notes & Engineering Impact
LocalAI v4.7.1. Source highlight: fix(config): only inject llama.cpp serving options on the llama.cpp path
LocalAI v4.7.0 — Release Notes & Engineering Impact
LocalAI v4.7.0. Source highlight: 🎉 LocalAI 4.7.0 Release! 🚀
vLLM v0.25.1 — Release Notes & Engineering Impact
vLLM v0.25.1. Source highlight: This release features 2 commits from 2 contributors (1 new)!
vLLM v0.25.0 — Release Notes & Engineering Impact
vLLM v0.25.0. Source highlight: vLLM v0.25.0 Release Notes
Hugging Face Transformers: Patch release v5.13.1
Hugging Face Transformers v5.13.1. Source highlight: Patch release v5.13.1
Ollama v0.32.0 — Release Notes & Engineering Impact
Ollama v0.32.0. Source highlight: New interactive agent experience: running `ollama` now launches an agent to help you code and delegate work
LangChain langchain==1.3.13 — Release Notes & Engineering Impact
LangChain langchain==1.3.13. Source highlight: Changes since langchain==1.3.12
LangChain langchain==1.3.12 — Release Notes & Engineering Impact
LangChain langchain==1.3.12. Source highlight: Changes since langchain==1.3.11
Ollama v0.31.2 — Release Notes & Engineering Impact
Ollama v0.31.2. Source highlight: Enabled flash attention on older NVIDIA GPUs (compute capability 6.x)
LocalAI v4.6.2 — Release Notes & Engineering Impact
LocalAI v4.6.2. Source highlight: chore(deps): bump actions/cache from 4 to 6 by @dependabot[bot] in https://github.com/mudler/LocalAI/pull/10704
LocalAI v4.6.1 — Release Notes & Engineering Impact
LocalAI v4.6.1. Source highlight: fix(auth): log the real cause of OIDC/OAuth user-info failures
LocalAI v4.6.0 — Release Notes & Engineering Impact
LocalAI v4.6.0. Source highlight: 🎉 LocalAI 4.6.0 Release! 🚀
Hugging Face Transformers: Release v5.13.0
Hugging Face Transformers v5.13.0. Source highlight: KimiK 2.5, 2.6, and 2.7
Open WebUI v0.10.2 — Release Notes & Engineering Impact
Open WebUI v0.10.2. Source highlight: 💭 **Streamed reasoning display.** Models that emit thinking or reasoning now show that content as it streams, and it renders correctly in the chat overview and in exported conversations. Commit, Commit, Commit, Commit
Ollama v0.31.1 — Release Notes & Engineering Impact
Ollama v0.31.1. Source highlight: Faster Gemma 4 on Apple Silicon
LocalAI v4.5.6 — Release Notes & Engineering Impact
LocalAI v4.5.6. Source highlight: chore(deps): bump actions/cache from 4 to 6 by @dependabot[bot] in https://github.com/mudler/LocalAI/pull/10593
vLLM v0.24.0 — Release Notes & Engineering Impact
vLLM v0.24.0. Source highlight: vLLM v0.24.0 Release Notes
Open WebUI v0.10.1 — Release Notes & Engineering Impact
Open WebUI v0.10.1. Source highlight: 🤝 **Shared folder read-only chats no longer sign users out.** Opening or reading chats from shared folders now keeps the current session active when a resource-level access error is returned, instead of incorrectly showing "Session expired. Please sign in again."
Open WebUI v0.10.0 — Release Notes & Engineering Impact
Open WebUI v0.10.0. Source highlight: 🤝 **Share folders with your team.** You can now share a folder and the chats inside it with specific users, groups, or everyone, with read or write access; people you share with see shared folders in their sidebar and open the chats in a read-only view when they are not the owner, and administrators
LocalAI v4.5.5 — Release Notes & Engineering Impact
LocalAI v4.5.5. Source highlight: fix(backends): repair release CI build/test breaks (kokoros, fish-speech, llama-cpp-quantization, sglang)
LocalAI v4.5.4 — Release Notes & Engineering Impact
LocalAI v4.5.4. Source highlight: fix(backends): derive darwin RUN_BINARY from the exec line only
LocalAI v4.5.3 — Release Notes & Engineering Impact
LocalAI v4.5.3. Source highlight: feat(macos): sign and notarize the DMG, app, and server binary
LocalAI v4.5.2 — Release Notes & Engineering Impact
LocalAI v4.5.2. Source highlight: fix(backends): make the opus backend build and package on macOS/Darwin
LocalAI v4.5.1 — Release Notes & Engineering Impact
LocalAI v4.5.1. Source highlight: chore(model gallery): :robot: add 1 new models via gallery agent
Dify 1.15.0 — Release Notes & Engineering Impact
Dify 1.15.0. Source highlight: Dify 1.15.0 Release Note
Ollama v0.30.11 — Release Notes & Engineering Impact
Ollama v0.30.11. Source highlight: launch: add thinking capability detection to opencode
LangChain langchain==1.3.11 — Release Notes & Engineering Impact
LangChain langchain==1.3.11. Source highlight: Changes since langchain==1.3.10
LangChain langchain==1.3.10 — Release Notes & Engineering Impact
LangChain langchain==1.3.10. Source highlight: Changes since langchain==1.3.9
Ollama v0.30.10 — Release Notes & Engineering Impact
Ollama v0.30.10. Source highlight: Command A and North family models now run on Apple Silicon with the MLX engine
Ollama v0.30.9 — Release Notes & Engineering Impact
Ollama v0.30.9. Source highlight: Support for Cohere2Moe architecture
Hugging Face Transformers: Patch release v5.12.1
Hugging Face Transformers v5.12.1. Source highlight: Patch release v5.12.1
Hugging Face Transformers: Patch release v5.10.4
Hugging Face Transformers v5.10.3. Source highlight: Patch release v5.10.4
vLLM v0.23.0 — Release Notes & Engineering Impact
vLLM v0.23.0. Source highlight: vLLM v0.23.0 Release Notes
LocalAI v4.4.3 — Release Notes & Engineering Impact
LocalAI v4.4.3. Source highlight: chore: :arrow_up: Update CrispStrobe/CrispASR to `d745bda4386ae0f9d1d2f23fff8ec95d76428221`
Ollama v0.30.8 — Release Notes & Engineering Impact
Ollama v0.30.8. Source highlight: Fixed `ollama launch` selecting the wrong provider in some cases
LangChain langchain==1.3.9 — Release Notes & Engineering Impact
LangChain langchain==1.3.9. Source highlight: Changes since langchain==1.3.8
Hugging Face Transformers: Release v5.12.0
Hugging Face Transformers v5.12.0. Source highlight: MiniMax-M3-VL is the vision-language member of the MiniMax-M3 family that pairs a CLIP-style vision tower with 3D rotary position embeddings with the MiniMax-M3 text backbone. It uses a mixed dense/sparse Mixture-of-Experts decoder with SwiGLU-OAI gated experts and a lightning indexer for block-spar
LangChain langchain==1.3.8 — Release Notes & Engineering Impact
LangChain langchain==1.3.8. Source highlight: Changes since langchain==1.3.7
LocalAI v4.4.2 — Release Notes & Engineering Impact
LocalAI v4.4.2. Source highlight: chore: :arrow_up: Update ggml-org/llama.cpp to `ac4cddeb0dbd778f650bf568f6f08344a06abe3a`
LocalAI v4.4.1 — Release Notes & Engineering Impact
LocalAI v4.4.1. Source highlight: docs: :arrow_up: update docs version mudler/LocalAI
LocalAI v4.4.0 — Release Notes & Engineering Impact
LocalAI v4.4.0. Source highlight: 🎉 LocalAI 4.4.0 Release! 🚀
LangChain langchain==1.3.7 — Release Notes & Engineering Impact
LangChain langchain==1.3.7. Source highlight: Changes since langchain==1.3.6
Hugging Face Transformers: Release v5.11.0
Hugging Face Transformers v5.11.0. Source highlight: DiffusionGemma is engineered to reduce the sequential bottlenecks of standard causal language models by employing an encoder-decoder architecture specifically optimized for inference speed. During inference, DiffusionGemma leverages multi-canvas sampling, where rather than generating one token at a