Search headlines, summaries and articles to connect the dots.
The update introduces graceful failure handling for unreachable RPC endpoints and failed handshakes in ggml-rpc, replacing fatal aborts with reportable errors. Functions now return appropriate values (e.g., false, nullptr) on connection failures, allowing host applications to handle issues without crashing. A regression test was added for unreachable endpoints, and low-value comments were removed. Mid-stream failures remain unchanged to prevent silent corruption.
The latest release of llama.cpp (b12259) adds support for Kimi K3.1 Vision, includes fixes for preprocessing and projector MLP in both K2.5 and K3.1 models, and features minor renaming changes. The release provides precompiled binaries for multiple platforms including macOS, Linux, Windows, Android, and openEuler, with support for various backends such as CUDA, Vulkan, ROCm, OpenVINO, SYCL, and Snapdragon-specific hardware.
The update addresses CUDA out of memory errors by reducing the VMM pool reservation size to 8 GB on GPUs with combined memory, halving the reservation size and retrying on failure only when encountering CUDA_ERROR_OUT_OF_MEMORY, while also logging a warning when the reservation is less than the maximum size.
A bug fix in n8n version 1.123.94 ensures that retry backoff settings are preserved when a trigger fails immediately after being reactivated, improving reliability in workflow execution.
A fix was implemented to ensure the OpenAI-compatible chat completions endpoint correctly processes JSON schema when provided at the top level in response_format.schema, rather than requiring it to be nested within response_format.json_schema.schema. The update also improves error messages, documents the correct usage in the README, and adds test cases to verify behavior, resolving issue #10732.
On Qualcomm Adreno GPUs, scalar flash attention was limited to 8 rows per workgroup when head size exceeds 128 to prevent register spilling and performance degradation. This change improved performance significantly, reducing execution time from several seconds to milliseconds and enabling completion of the test-backend-ops case.
The n8n 3.2.0 release introduces several bug fixes addressing issues in AI Builder, core functionality, editor UI, and node-specific behaviors, including improved handling of JSON, XML, CSV, and YAML responses, enhanced security through expanded IP blocking, and better error reporting. New features include support for Microsoft Work IQ OAuth2 credentials, a new App bindings UI, and updated default Assistant models. The release also reverts some previous changes due to compatibility or stability concerns.
The Metal kernel for ggml_tri has been updated to use a select operation instead of scaling by comparison, aligning its behavior with the CPU kernel. This change ensures that values outside the triangle are set to zero rather than becoming NaN when encountering ±inf. A new test, test_tri_special, validates this fix across all four triangle types, confirming it passes with the update but failed previously.
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.
The latest release of llama.cpp adds support for the MageVL-Cowork model and adjusts how rope frequencies are handled, now stored at the model level within clip_model instead of being copied into each clip_layer. The loader verifies that rope_freqs is a 32-bit floating-point array with dimensions matching d_head, ensuring compatibility with expected 4:6:6 splits in the computational graph.
The llama.cpp release b12193 includes a change to move log-mel computation to the cgraph, removes stray files, updates mtmd_audio_track to include source, and adds tests. It provides precompiled binaries for macOS, Linux, Windows, Android, and openEuler across various architectures and backends including CUDA, Vulkan, ROCm, OpenVINO, SYCL, and Snapdragon-specific platforms.
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.
The release includes updates for SYCL backend with exact rounding support in CPY operations for Q4_1, Q5_1, and Q8_0 quantization formats.
The update introduces support for automatic loading of libhtp without relying on legacy environment variables, enhances path handling for non-ASCII directories and long paths, adds platform-wide support for FASTRPC_MANAGE_DSP_LIBRARY_PATH and GGML_HEXAGON_LIBHTP_DIR, maintains forward slashes in absolute paths on Android and Linux, ensures absolute path precedence with fallback mechanisms, and includes CDSP1,2,3 in the fallback chain for IQ10 compatibility.
The llama.cpp release b12198 includes a change to downgrade per-request proxy logs to trace level, along with numerous precompiled binaries for macOS, Linux, Windows, Android, and other platforms, supporting various backends like CUDA, Vulkan, ROCm, OpenVINO, and SYCL. Some builds are disabled or experimental, including openEuler and KleidiAI-enabled macOS versions.
The release addresses the issue of invalid UTF-8 characters in arguments passed to PEG tool calls, improving input handling and robustness.
Enhancements to OpenCL support in llama.cpp include adding new kernel functions for quantized matrix operations, improving small-n MoE GEMV performance across multiple quantization types, optimizing Adreno GPU kernel floor settings, renaming functions for clarity, and disabling bin FA for small verification batches.
The llama.cpp project has released version b12201, offering pre-compiled binaries for multiple platforms including macOS, Linux, Windows, Android, and iOS. The release includes support for various backends such as CUDA, Vulkan, ROCm, OpenVINO, SYCL, and Snapdragon hardware. Notably, the MoE cache feature is disabled for the draft model in this release. Additional resources include setup guides for Snapdragon devices and separate downloads for CUDA and OpenVINO libraries.
The llama.cpp v1.220.2 release introduces enhanced BF16 precision support across multiple components, aligning with reference implementations by moving specific operations like GLM4 family projections, MiMoVL vision matmuls, and Qwen3-TTS speaker encoder conv1d to BF16 where appropriate. Backends such as CUDA, Hexagon, OpenCL, WebGPU, and Vulkan now uniformly handle GGML_PREC_BF16 similarly to F32, while CPU, SpaceMIT, and ET backends extend flash attention support to BF16 with F32 accumulation. Flash attention tests now include BF16 cases, and the KQ multiplication in Llama is updated to request BF16 precision. A TODO remains in clip.cpp for future work.
A new fast path for d_state=64 has been added to the SSM_SCAN kernel in ggml-cuda, improving generation throughput for Zamba2-7B-Instruct from 11 to 15.1 tok/s—approximately a 35% increase—by eliminating CPU fallbacks for this state size. The change was verified with real-world Zamba2 hyperparameters and maintains correctness, though a separate 28% of scan calls still fall back to CPU due to an undiagnosed issue.
