Skip to content
AI NEWS.ccAI正在发生 未来正在更新
Bookmarks
THE JOURNAL
AI NEWS JOURNAL
AI, IN PERSPECTIVE

Search AI news

Search headlines, summaries and articles to connect the dots.

Newest first

llama.cpp releases

b12191

The latest update to llama.cpp introduces enhanced MoE (Mixture of Experts) cache functionality, enabling computation of cache misses on the CPU with a configurable CPU share. A new tuning script, moe-cache-tune.py, automatically determines optimal cache size and CPU share settings based on system performance. The update also improves scheduling efficiency, removes redundant sync operations, and refactors code for better maintainability, while maintaining compatibility across multiple platforms including macOS, Linux, Windows, and Android.

llama.cpp releases

b12195

The llama.cpp release b12195 introduces a change to refuse device buffers that would exceed VRAM, improving memory management. It includes precompiled binaries for multiple platforms including macOS, Linux, Windows, Android, and openEuler, with support for various backends such as CUDA, ROCm, Vulkan, OpenVINO, SYCL, and others. Some builds are marked as disabled or experimental.

llama.cpp releases

b12208

The ggml library has been updated to make tied selections in the radix Top-K algorithm deterministic on CUDA and Metal backends by replacing atomic compaction loops with a deterministic scheme using simdgroup scans and coalesced memory accesses. This change ensures byte-identical outputs across runs, improves performance by 20-45% on M5 Ultra hardware, and enables deterministic testing for Metal and ROCm. Redundant CUDA kernel resets were removed, and Vulkan/Metal changes were reduced or skipped.

llama.cpp releases

b12180

The release adds the Kimi-K3.1-Pro text model to llama.cpp, replacing full-attention MLA layers in K3 with DSA (Dynamic Sparse Attention) layers featuring a lightning indexer. The indexer uses an additive mask over the cache and reuses sparse flash attention paths, while preserving existing KDA layers and MoE components. The model's architecture includes four indexer tensors per DSA layer, hybrid memory for caching, and maintains quantization integrity by excluding indexer parameters from quant overrides. Verified against HF checkpoint with identical PPL beyond context length, and supports multiple platforms including macOS, Linux, Windows, Android, and iOS.

llama.cpp releases

b12185

A fix for shared memory bank conflicts in the lightning indexer has been implemented for CUDA support in llama.cpp version b12185, improving performance and stability on CUDA-enabled devices.

llama.cpp releases

b12136

The update addresses an issue in llama.cpp where the number of GPU layers was incorrectly calculated by not accounting for skipped NextN layers, leading to improper layer distribution between CPU and GPU. The fix ensures that skipped NextN layers are included in the n_gpu_layers count and properly assigned during model loading, resolving a bug where layer 0 remained on the CPU despite offloading all other layers.

llama.cpp releases

b12141

The latest update to llama.cpp introduces reference-counted checkpoints instead of deep-copies, reducing memory overhead and improving efficiency. This change adapts the slot save/restore checkpoint mechanism to shared_ptr checkpoint lists and common_state_data buffers, with contributions from multiple developers and AI assistants.

llama.cpp releases

b12143

The Vulkan implementation of the Fast Walsh-Hadamard Transform (FWHT) has been enhanced to support block widths up to 8192, using shared-memory shaders for larger blocks, and now includes F16 input capability via shader-float16, with pipelines created only when device limits allow. This update aligns Vulkan with CUDA's capabilities and improves efficiency by eliminating the need for F32-to-F16 conversions.

llama.cpp releases

b12114

Fixed get_max_size to return maxBufferSize and improved the memset shader to handle buffer sizes exceeding the maximum binding size, preventing issues with whole-buffer bindings in memset and clear operations.

llama.cpp releases

b12101

The gguf writer now writes host-buffer tensor data directly to the file, skipping the temporary staging vector, which eliminates per-tensor allocation, zero-initialization, and memcpy operations.

llama.cpp releases

b11944

server: expose the reasoning effort levels of the chat template (#31271) * server: expose the reasoning effort levels of the chat template The capability probe renders a user turn for each candidate level (minimal, low, medium, high, xhigh, max) and for an unknown level. A level is honored when it renders without raising and differently from the unknown level, which shows the template fallback. Levels sharing a render are aliases and the highest one is kept. The caps serialize to JSON, and chat_template_caps in /props reports the list as reasoning_effort_levels, from lowest to highest. * jinja: keep the caps free of the json dependency The caps keep reporting their flags as a map, and the effort levels stay a plain member. common_chat_templates_get_caps() builds the JSON the server reports

Timeline and related coverage

llama.cpp releases

b11930

server: add router device memory margin parameter for dynamic unloading (#21231) * server: add --models-memory-max parameter to allow dynamically unloading models when they exceed a memory size threshold estimate with to-be-loaded model size included use no_alloc to get memory requirements for model load only set model memory_mb if not previously calculated use memory margin instead of total size limit, apply to each device separately add server memory debug logging move llama_context_device_memory function to llama-ext.h fix model count exceeded check improve memory_per_device map naming improve variable naming, fix style also strip models memory margin from child processes cont : clean-up replace device memory map with buft memory map. Use llama_get_memory_breakdown extract duplicated ch

Timeline and related coverage
llama.cpp releases

b11922

tests : fix multi-seq split replay and partial-state cases for trained models (#31216) * tests : fix multi-seq split replay against trained models The rollback snapshot is captured by the graph that decoded the rolled-back tail, while the reference context decodes the same prefix with different batch shapes. The two states differ in the last bits and trained models amplify the difference with every replayed token. Compare only the first replayed token of each seq, then restore the rollback state into the reference context before the seq-1-only tail. Assisted-by: dsh:llama.cpp/ggml-org/Qwen3.8-Flash-Next-GGUF (MacBook, M5 Max, 128GB) * tests : require bit-exact seq-1 isolation in split replay The seq state save is not always bit-lossless - SWA-masked cells are not saved - so reload the rest

Timeline and related coverage
llama.cpp releases

b11921

llama : remove obsolete n_pad from memory instances (#31200) Every caller passes n_pad = 1 and the only two users clamp it to 256. Drop the parameter, the members and the trivially true kv_size assert. Assisted-by: dsh:llama.cpp/ggml-org/Qwen3.8-Flash-Next-GGUF (MacBook, M5 Max, 128GB) **Website:** - **Attestations:** - **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b11921/llama-b11921-bin-macos-arm64.tar.gz) - macOS Apple Silicon (arm64, KleidiAI enabled) [DISABLED](https://github.com/ggml-org/llama.cpp/pull/23780) - [macOS Intel (x64)](https://github.com/ggml-org/llama.cpp/releases/download/b11921/llama-b11921-bin-macos-x64.tar.gz) - [iOS XCFramework](https://github.com/ggml-org/llama.cpp/releases/download/b11921/llama-b11921-xcfram

Timeline and related coverage
llama.cpp releases

b11906

ggml-cpu : rewrite concat as one row kernel for all types (#31179) Every dst row comes from src0 or src1, or for dim 0 from the row of src0 followed by the row of src1, so a single kernel covers every type: a dense source row is one memcpy, quantized types included, and a strided source is copied element by element with the element size known at compile time. Rows are split across threads instead of i2 alone, which is often 1, and are copied in tiles of 32: for a transposed source the elements are walked in the outer loop, so the rows of a tile read neighboring addresses instead of jumping a full row stride per element. Add transposed b cases to test_concat, the layout of the delta-net conv input, and a perf case for it. **Website:** - **Attestations:** - **macOS/iOS:** - [macOS Apple Sili

Timeline and related coverage
llama.cpp releases

b11901

sycl : bound reorder temp memory to 32 MiB (#31062) **Website:** - **Attestations:** - **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b11901/llama-b11901-bin-macos-arm64.tar.gz) - macOS Apple Silicon (arm64, KleidiAI enabled) [DISABLED](https://github.com/ggml-org/llama.cpp/pull/23780) - [macOS Intel (x64)](https://github.com/ggml-org/llama.cpp/releases/download/b11901/llama-b11901-bin-macos-x64.tar.gz) - [iOS XCFramework](https://github.com/ggml-org/llama.cpp/releases/download/b11901/llama-b11901-xcframework.zip) **Linux:** - [Ubuntu x64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b11901/llama-b11901-bin-ubuntu-x64.tar.gz) - [Ubuntu arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b11901/llama-b

Timeline and related coverage

llama.cpp releases

b11896

ci : fix race in webgpu memset (#31162) **Website:** - **Attestations:** - **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b11896/llama-b11896-bin-macos-arm64.tar.gz) - macOS Apple Silicon (arm64, KleidiAI enabled) [DISABLED](https://github.com/ggml-org/llama.cpp/pull/23780) - [macOS Intel (x64)](https://github.com/ggml-org/llama.cpp/releases/download/b11896/llama-b11896-bin-macos-x64.tar.gz) - [iOS XCFramework](https://github.com/ggml-org/llama.cpp/releases/download/b11896/llama-b11896-xcframework.zip) **Linux:** - [Ubuntu x64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b11896/llama-b11896-bin-ubuntu-x64.tar.gz) - [Ubuntu arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b11896/llama-b11896-bin-ub

Timeline and related coverage
llama.cpp releases

b11884

llama: fix exhausting CPU and MEM caused by dry sequence breaker (#31035) **Website:** - **Attestations:** - **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b11884/llama-b11884-bin-macos-arm64.tar.gz) - macOS Apple Silicon (arm64, KleidiAI enabled) [DISABLED](https://github.com/ggml-org/llama.cpp/pull/23780) - [macOS Intel (x64)](https://github.com/ggml-org/llama.cpp/releases/download/b11884/llama-b11884-bin-macos-x64.tar.gz) - [iOS XCFramework](https://github.com/ggml-org/llama.cpp/releases/download/b11884/llama-b11884-xcframework.zip) **Linux:** - [Ubuntu x64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/download/b11884/llama-b11884-bin-ubuntu-x64.tar.gz) - [Ubuntu arm64 (CPU)](https://github.com/ggml-org/llama.cpp/releases/d

Timeline and related coverage
llama.cpp releases

b11881

llama : respect no_alloc in all memory caches (#31087) * llama : respect no_alloc in memory caches Assisted-by: dsh:llama.cpp/ggml-org/DeepSeek-V4-Flash-Vision-Exp-GGUF (Mac Studio, M2 Ultra, 192GB) * llama : TODO: move no_alloc out of llama_hparams Assisted-by: dsh:llama.cpp/ggml-org/DeepSeek-V4-Flash-Vision-Exp-GGUF (Mac Studio, M2 Ultra, 192GB) * llama : TODO: move no_alloc out of llama_hparams Assisted-by: dsh:llama.cpp/ggml-org/DeepSeek-V4-Flash-Vision-Exp-GGUF (Mac Studio, M2 Ultra, 192GB) **Website:** - **Attestations:** - **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b11881/llama-b11881-bin-macos-arm64.tar.gz) - macOS Apple Silicon (arm64, KleidiAI enabled) [DISABLED](https://github.com/ggml-org/llama.cpp/pull/23780) - [macOS

Timeline and related coverage

llama.cpp releases

b11877

vulkan: Add a larger tile size for conv3d (coopmat2 only) (#29920) * vulkan: Add a larger tile size for conv3d (coopmat2 only) This adds a larger tile size, in practice it is only for coopmat2 where we don't need shared memory to store the output (would use more than 64KB). Add some additional representative backend tests. At least, this is what codex came up with from looking at sd.cpp Wan VAE. * only apply large tile size for newer driver versions **Website:** - **Attestations:** - **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b11877/llama-b11877-bin-macos-arm64.tar.gz) - macOS Apple Silicon (arm64, KleidiAI enabled) [DISABLED](https://github.com/ggml-org/llama.cpp/pull/23780) - [macOS Intel (x64)](https://github.com/ggml-org/llama

Timeline and related coverage