OpenSourcePulse

🚀 New Release Alert! 📦 llama.cpp 🏷 Category: AI 🔖 Version: b9837 📅 Released: 2026-06-29 00:05 UTC 📊 Assets: 25 files 📝 What's New: <details open> jinja, chat: add --reasoning-preserve flag (#25105) jinja, chat: add --reasoning-preserve flag correct help message </details> macOS/iOS: - macOS Apple Silicon (arm64) - macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED 📥 Download Release

🚀 New Release Alert! 📦 llama.cpp 🏷 Category: AI 🔖 Version: b9835 📅 Released: 2026-06-28 19:37 UTC 📊 Assets: 25 files 📝 What's New: <details open> ui: fix stop and reasoning skip in single-model mode (#25084) </details> macOS/iOS: - macOS Apple Silicon (arm64) - macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED - macOS Intel (x64) 📥 Download Release

🚀 New Release Alert! 📦 llama.cpp 🏷 Category: AI 🔖 Version: b9832 📅 Released: 2026-06-28 14:18 UTC 📊 Assets: 25 files 📝 What's New: <details open> jinja: add --dump-prog for debugging (#25086) jinja: add --dump-prog for debugging Update common/jinja/runtime.cpp Co-authored-by: Sigbjørn Skjæret <1629204+CISC@users.noreply.github.com> --------- Co-authored-by: Sigbjørn Skjæret <1629204+CISC@users.noreply.github.com> </details> macOS/iOS: - macOS Apple Silicon (arm64) 📥 Download Release

🚀 New Release Alert! 📦 llama.cpp 🏷 Category: AI 🔖 Version: b9830 📅 Released: 2026-06-28 11:03 UTC 📊 Assets: 25 files 📝 What's New: <details open> common : allow --offline in llama download (#25091) Expose the existing --offline flag to llama download so a script can run it to check whether a model is already cached and ready to be served without touching the network. Also fix a latent use-after-free in the URL-task ondone callback: firstpath is block-scoped and was captured by reference, but invoked after the block ... 🔗 View on GitHub 📥 Download Release

🚀 New Release Alert! 📦 karing 🏷 Category: Community Suggested 🔖 Version: v1.2.21.2402 📅 Released: 2026-06-28 03:47 UTC 📊 Assets: 9 files 📝 What's New: 1. Fixes some WebDAV 405 connection failure issues. #1670 IOS/TvOS AppStore: (Search Keywords: karing vpn) https://apps.apple.com/us/app/karing/id6472431552 🔗 View on GitHub 📥 Download Release

🚀 New Release Alert! 📦 llama.cpp 🏷 Category: AI 🔖 Version: b9829 📅 Released: 2026-06-28 06:46 UTC 📊 Assets: 25 files 📝 What's New: <details open> logs : reduce v2 (#25078) server : reduce logs cont : common cont : spec cont : CMN -> COM </details> macOS/iOS: - macOS Apple Silicon (arm64) - macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED - macOS ... 🔗 [View on GitHub 📥 Download Release

🚀 New Release Alert! 📦 llama.cpp 🏷 Category: AI 🔖 Version: b9828 📅 Released: 2026-06-27 23:15 UTC 📊 Assets: 25 files 📝 What's New: <details open> opencl: flash attention improvement (#25069) opencl: rework FA kernel for f16 and f32 opencl: flash-attention prefill prepass kernels - flashattnkvpadf16 pads the tail KV tile to a BLOCKN multiple - flashattnmaskpadf16 pads the matching mask tile - flashattnblkf16 classifies each KV tile per query block as fully masked / mi... 🔗 View on GitHub 📥 Download Release

🚀 New Release Alert! 📦 llama.cpp 🏷 Category: AI 🔖 Version: b9826 📅 Released: 2026-06-27 11:00 UTC 📊 Assets: 25 files 📝 What's New: <details open> sycl : fix failed ut cases of norm (#25044) </details> macOS/iOS: - macOS Apple Silicon (arm64) - macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED - macOS Intel (x64) 📥 Download Release

🚀 New Release Alert! 📦 llama.cpp 🏷 Category: AI 🔖 Version: b9824 📅 Released: 2026-06-27 10:03 UTC 📊 Assets: 25 files 📝 What's New: <details open> binaries : Improve rpc-server and export-graph-ops names. (#25045) Tests are generally prefixed with -test, so rename export-graph-ops accordingly. rpc-server is probably too generic a name for /usr/bin. Because it should work with any ggml application, it is renamed to ggml-rpc-server. </details> macOS/iOS: - macOS Apple Silicon (arm64) 📥 Download Release

🚀 New Release Alert! 📦 llama.cpp 🏷 Category: AI 🔖 Version: b9823 📅 Released: 2026-06-27 09:13 UTC 📊 Assets: 25 files 📝 What's New: <details open> ci : add windows-openvino to check-release (#25022) </details> macOS/iOS: - macOS Apple Silicon (arm64) - macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED - macOS Intel (x64) 📥 Download Release

🚀 New Release Alert! 📦 claude-code 🏷 Category: Community Suggested 🔖 Version: v2.1.195 📅 Released: 2026-06-26 21:29 UTC 📊 Assets: 10 files 📝 What's New: ## What's changed - Added CLAUDE_CODE_DISABLE_MOUSE_CLICKS to disable mouse click/drag/hover in fullscreen mode while keeping wheel scroll - Fixed hook matchers with hyphenated identifiers (e.g. code-reviewer, mcp__brave-search) accidentally substring-matching — they now exact-match. Use mcp__brave-search__.* to match all tools from a hyphenated MCP server. - Fixed voice dictation on m... 🔗 View on GitHub 📥 Download Release

🚀 New Release Alert! 📦 llama.cpp 🏷 Category: AI 🔖 Version: b9821 📅 Released: 2026-06-26 21:55 UTC 📊 Assets: 25 files 📝 What's New: <details open> app : allow --version, --licenses & --help (#25054) Signed-off-by: Adrien Gallouët <angt@huggingface.co> </details> macOS/iOS: - macOS Apple Silicon (arm64) - macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED - macOS... 🔗 [View on GitHub 📥 Download Release

🚀 New Release Alert! 📦 Ollama 🏷 Category: AI 🔖 Version: v0.30.11 📅 Released: 2026-06-25 01:52 UTC 📊 Assets: 17 files 📝 What's New: ## What's Changed launch: add thinking capability detection to opencode by @hoyyeva in https://github.com/ollama/ollama/pull/15434 launch: auto-install Claude Code by @hoyyeva in https://github.com/ollama/ollama/pull/16802 launch: auto-install opencode when missing by @hoyyeva in https://github.com/ollama/ollama/pull/16806 discover: fix inverted iGPU/dGPU Vulkan classification on Wi... 🔗 View on GitHub 📥 Download Release

🚀 New Release Alert! 📦 shadcn/ui 🏷 Category: UI Library 🔖 Version: shadcn@4.12.0 📅 Released: 2026-06-26 17:26 UTC 📊 Assets: 0 files 📝 What's New: ### Minor Changes - #11022 `18fcf0f766857a7249cc0daac3c1609610edd158` Thanks @shadcn! - add scroll-fade and shimmer utilities 🔗 View on GitHub 📥 Download Release

🚀 New Release Alert! 📦 llama.cpp 🏷 Category: AI 🔖 Version: b9816 📅 Released: 2026-06-26 16:48 UTC 📊 Assets: 25 files 📝 What's New: <details open> sync : ggml </details> macOS/iOS: - macOS Apple Silicon (arm64) - macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED - macOS Intel (x64) 📥 Download Release

🚀 New Release Alert! 📦 llama.cpp 🏷 Category: AI 🔖 Version: b9814 📅 Released: 2026-06-26 16:14 UTC 📊 Assets: 25 files 📝 What's New: <details open> vulkan: opt mulmatvecq for mi50 (#22933) </details> macOS/iOS: - macOS Apple Silicon (arm64) - macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED - macOS Intel (x64) 📥 Download Release

🚀 New Release Alert! 📦 llama.cpp 🏷 Category: AI 🔖 Version: b9810 📅 Released: 2026-06-26 11:44 UTC 📊 Assets: 25 files 📝 What's New: <details open> CUDA: add cublasSgemmBatched mapping for HIP/MUSA vendor headers (#25033) </details> macOS/iOS: - macOS Apple Silicon (arm64) - macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED - macOS Intel (x64) 📥 Download Release

🚀 New Release Alert! 📦 llama.cpp 🏷 Category: AI 🔖 Version: b9804 📅 Released: 2026-06-26 07:15 UTC 📊 Assets: 25 files 📝 What's New: <details open> mamba2: remove hardcoded 2x expansion factor and invalid dinner % dstate check (#23082) mamba2: remove hardcoded 2x expansion factor, support any expand value mamba2: remove invalid dinner %% dstate check (unrelated parameters) Update convert_hf_to_gguf.py: make expand optional with default 2 Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> mamba2:... 🔗 View on GitHub 📥 Download Release

🚀 New Release Alert! 📦 shadcn/ui 🏷 Category: UI Library 🔖 Version: shadcn@4.11.1 📅 Released: 2026-06-26 07:16 UTC 📊 Assets: 0 files 📝 What's New: ### Patch Changes - #10905 `9197676b3d09b77f51b17b63e5978db29e498ca4` Thanks @shadcn! - replace node-fetch with native fetch - #10967 `365d53b590a6ddb79c1487a9dbeabcde5f4ac37f` 📥 Download Release

🚀 New Release Alert! 📦 llama.cpp 🏷 Category: AI 🔖 Version: b9803 📅 Released: 2026-06-26 02:26 UTC 📊 Assets: 25 files 📝 What's New: <details open> opencl: flush profiling batch at shutdown for incomplete batches (#25016) </details> macOS/iOS: - macOS Apple Silicon (arm64) - macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED - macOS Intel (x64) 📥 Download Release