Open-Source Models & Communities — September 29, 2026

Findings

1. [1] 2026-09-29 b11259

   common : stop accepting draft tokens at EOG (#29638) common : stop accepting draft tokens at EOG cont : remove the test Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/51199980 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramework Linux: Ubuntu x64 (CPU) Ubuntu arm64 (CPU) Ubuntu s390x (CPU) Ubuntu x64 (Vulkan) Ubuntu arm64 (Vulkan) Ubuntu…

2. [2] 2026-09-29 b11258

   server : remove the built-in UI's service worker when the UI is not served (#29565) With –path or –no-ui, /sw.js returned 404, and a 404 does not remove a service worker, so browsers kept showing the cached built-in UI. Serve a worker that unregisters itself, clears its caches and reloads open tabs. A sw.js in the –path folder is still…

3. [3] 2026-09-29 b11257

   common : use fs::path for config dir (#29649) Signed-off-by: Adrien Gallouët angt@huggingface.co Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/51176378 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramework Linux: Ubuntu x64 (CPU) Ubuntu arm64 (CPU) Ubuntu s390x (CPU) Ubuntu x64 (Vulkan) Ubuntu arm64 (Vulkan) Ubuntu x64 (CUDA 12) – CUDA 12.8 libraries Ubuntu x64 (CUDA…

4. [4] 2026-09-29 b11256

   tests : adjust server string regex to also match m2 utlra results (#29648) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/51122498 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramework Linux: Ubuntu x64 (CPU) Ubuntu arm64 (CPU) Ubuntu s390x (CPU) Ubuntu x64 (Vulkan) Ubuntu arm64 (Vulkan) Ubuntu x64 (CUDA 12) – CUDA 12.8 libraries Ubuntu x64…

5. [5] 2026-09-29 b11255

   common : add fs_write_atomic() (#29642) Check for buffered write errors when closing downloaded files. Use UTF-8 paths when writing ETag files on Windows. Write in binary mode on Windows. Signed-off-by: Adrien Gallouët angt@huggingface.co Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/51111496 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramework Linux: Ubuntu x64 (CPU) Ubuntu arm64…

6. [6] 2026-09-29 b11254

   ggml : collect all input tensors into graph_inputs (#29634) graph_inputs was populated while splitting the graph, so it only contained the inputs that are used as srcs of some node. With pipeline parallelism (n_copies > 1), each graph input contributes n_copies leafs to graph_copy, so switching between batches that consume different inputs (e.g. token batches that do not use the…

7. [7] 2026-09-29 b11249

   llama : fix init in several tools/examples (#29632) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/51066139 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramework Linux: Ubuntu x64 (CPU) Ubuntu arm64 (CPU) Ubuntu s390x (CPU) Ubuntu x64 (Vulkan) Ubuntu arm64 (Vulkan) Ubuntu x64 (CUDA 12) – CUDA 12.8 libraries Ubuntu x64 (CUDA 13) – CUDA 13.4…

8. [8] 2026-09-29 b11247

   vulkan : reuse descriptor sets when bindings are constant (#29280) vulkan : reuse descriptor sets when bindings are constant vulkan : bump buffer_destroy_count before destroying the buffer Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/51033526 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramework Linux: Ubuntu x64 (CPU) Ubuntu arm64 (CPU) Ubuntu s390x (CPU) Ubuntu x64…

9. [9] 2026-09-29 b11246

   chat : fix Muse Glimmer ignoring response_format json_schema with –jinja (#29615) chat : fix Muse Glimmer ignoring response_format json_schema with –jinja Fixes #29613 chat : accept json fences and clean up chat : fix choice parenthesis Co-authored-by: Alde Rojas hello@alde.dev Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/51023533 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS…

10. [10] 2026-09-29 b11245

    common : use fs::path for cache dirs (#29595) Avoid useless string conversions on Windows. No need for BSD or emscripten special cases. Signed-off-by: Adrien Gallouët angt@huggingface.co Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/51016898 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramework Linux: Ubuntu x64 (CPU) Ubuntu arm64 (CPU) Ubuntu s390x (CPU) Ubuntu x64 (Vulkan)…

11. [11] 2026-09-29 v0.31.0rc1: [CI/Build] Skip the snapshot runtime on CUDA 12.x images (#59118)

    Signed-off-by: khluu khluu000@gmail.com Co-authored-by: Claude Opus 5.5 noreply@anthropic.com (cherry picked from commit aedaba8)

Sources

1. [1] b11259
2. [2] b11258
3. [3] b11257
4. [4] b11256
5. [5] b11255
6. [6] b11254
7. [7] b11249
8. [8] b11247
9. [9] b11246
10. [10] b11245
11. [11] v0.31.0rc1: [CI/Build] Skip the snapshot runtime on CUDA 12.x images (#59118)