Model VS AI Radar
This timeline tracks published GitHub releases from a transparent, curated list of widely used open AI projects. Release activity is kept separate from benchmark rankings.
32 verified source records in this snapshot. Updated . Source: GitHub Releases API.
Method: Published GitHub releases from a transparent curated list of widely used open AI projects.
Limits: Release notes are publisher-provided metadata. They do not independently verify changes, compatibility, or production readiness.
Source identity: ggml-org/llama.cpp
<details open> caps : recheck typed content if template checks for string (#28511) </details> **Website:** - <https://llama.app> **Attestations:** - <https://github.com/ggml-org/llama.cpp/attestations/45690927> **macOS/iOS:** - [macOS Apple Silicon (arm64)](h…
Recorded signal: b10837; prerelease
Source date:
Source identity: ggml-org/llama.cpp
<details open> ggml-cuda: fix divergent barrier in f16 flash attention (#27870) * ggml-cuda: fix divergent barrier in f16 flash attention * ggml-cuda: avoid duplicate metadata pointer setup </details> **Website:** - <https://llama.app> **Attestations:** - <ht…
Recorded signal: b10835; prerelease
Source date:
Source identity: ggml-org/llama.cpp
<details open> ggml: allow backend inputs to not create another split (#28387) </details> **Website:** - <https://llama.app> **Attestations:** - <https://github.com/ggml-org/llama.cpp/attestations/45674860> **macOS/iOS:** - [macOS Apple Silicon (arm64)](https…
Recorded signal: b10834; prerelease
Source date:
Source identity: ggml-org/llama.cpp
<details open> vulkan: rms_norm fusion opportunities (#28024) Support RMS_NORM + MUL + ADD (+ MUL) and RMS_NORM + VIEW + SET_ROWS. Extend ROPE + VIEW + SET_ROWS to support IMROPE. Worth around 4% in gemma4 on my system. </details> **Website:** - <https://llam…
Recorded signal: b10833; prerelease
Source date:
Source identity: ggml-org/llama.cpp
<details open> vulkan: add TQ1_0 support (mm, mat-vec, mat-vec-id, dequant, get_rows) (#27765) * vulkan: add TQ1_0 support (mm, mat-vec, dequant, get_rows) * vulkan: pack TQ1_0 powers of 3 into a 32-bit constant Replaces the constant array with a packed 32-bi…
Recorded signal: b10831; prerelease
Source date:
Source identity: ollama/ollama
## Use Ollama models in ChatGPT Desktop Ollama models can now be used directly in ChatGPT Desktop, so you can keep your existing workflow while running open models. Setup is available from the Ollama app on MacOS. This release also improves structured output…
Recorded signal: v0.34.0-rc1; prerelease
Source date:
Source identity: langchain-ai/langchain
Changes since langchain-core==1.6.1 release(core): 1.6.2 (#40209) feat(openai): support async tools (#40208) chore(deps): bump mistune from 3.3.0 to 3.3.3 in /libs/core (#40150) chore(deps): bump tornado from 6.5.7 to 6.5.8 in /libs/core (#40113) fix(core): a…
Recorded signal: langchain-core==1.6.2
Source date:
Source identity: langchain-ai/langchain
Changes since langchain==1.3.18 docs(langchain): runnable `langchain.mcp` examples (#39976) feat(langchain): `langchain.mcp` namespace, `MCPAdapter` (#39939) perf(anthropic,langchain): omit middleware trace inputs (#40098) fix(langchain): include model destin…
Recorded signal: langchain==1.4.0
Source date:
Source identity: langchain-ai/langchain
Changes since langchain-anthropic==1.7.0 release(anthropic): 1.7.1 (#40181) perf(anthropic,langchain): omit middleware trace inputs (#40098) feat(anthropic): add Claude Fable 5.1 support (#40106)
Recorded signal: langchain-anthropic==1.7.1
Source date:
Source identity: langchain-ai/langchain
Initial release release(langchain): 1.4.0a4 test(langchain): cover mixed-era ClientGroup and group elicitation Update libs/langchain_v1/langchain/mcp/adapter.py fix(langchain): drive MCP elicitation via member session for fastmcp 4.0.1 fix(sdk): use latest fa…
Recorded signal: langchain==1.4.0a4
Source date:
Source identity: ollama/ollama
## What's Changed * gemma4 now supports images and audio on MLX engine * Report cached prompt tokens * Honor GGUF model defined default parameters * MLX, MLX-C, llama.cpp update ## New Contributors * @marcelpetrick made their first contribution in https://git…
Recorded signal: v0.33.3
Source date:
Source identity: langchain-ai/langchain
Third alpha of the `1.4.0` line. This release focuses on the new `langchain.mcp` namespace for adapting MCP servers into LangChain tools. ## `langchain.mcp` highlights - **`MCPAdapter`** adapts any target `fastmcp.Client` accepts — a URL, a local script, an i…
Recorded signal: langchain==1.4.0a3
Source date:
Explore the interactive index to search and sort all 32 records. Each title links to its original source record.