llama.cpp Releases
609 releases of ggml-org/llama.cpp
- b9860
Adds a new public C API function to retrieve the name of the model quantization file type (e.g., 'Q8_0'), improving introspection capabilities for applications.
Jul 2, 2026
- b9859
Enhances OpenCL backend performance by allowing the loading of precompiled binary kernels from a shared library for GEMM operations, including support for MOE and various quantization types.
Jul 1, 2026
- b9858
Fixes a bug where the Hugging Face primary split wasn't being used as the model path, ensuring correct model loading behavior.
Jul 1, 2026
- b9857
Performs a major rework of the Hexagon Flash Attention implementation, focusing on performance optimizations, accuracy improvements, and code refactoring including fp16 math usage and mask processing.
Jul 1, 2026
- b9856
Refactors CUDA Flash Attention code to consistently use pointer restrictions and PDL (Pointer Distance Logic) for better code optimization and consistency.
Jul 1, 2026
- b9855
Enhances CPU performance by adding AVX2 optimizations for NVFP4 dot product operations and utilizing the UE4M3 lookup table for improved efficiency.
Jul 1, 2026
- b9852
Introduces support for the q1_0 quantization format in the OpenCL backend, including specific optimizations for Adreno GPUs to accelerate GEMM and GEMV operations.
Jul 1, 2026
- b9851
Addresses critical bug fixes in the CUDA Flash Attention implementation by preventing integer overflow and truncation errors when calculating KQ mask strides.
Jun 30, 2026
- b9850
Focuses on Qwen3Next model support by registering a new tensor for attention normalization and fixing input assignment issues in the layer processing loop to ensure correct DFLASH functionality.
Jun 30, 2026
- b9849
This release adds support for bracketed IPv6 literals in URL parsing for the server and common components, improving compliance with RFC 3986 standards. It also fixes URL parsing logic to correctly handle proxy headers and client rebuilds.
Jun 30, 2026
- b9848
This release addresses a limitation in the CUDA backend where `get_rows_back` failed for tables exceeding 65,535 rows by implementing grid-y clamping and stride adjustments. Standard binaries are provided for all major platforms.
Jun 30, 2026
- b9847
This release fixes a critical bug in the FlashAttention implementation for the Gemma E4B (4 Billion parameter) model with MTP (Multi-Token Prediction) on the CUDA backend. Standard binaries are included for all supported platforms.
Jun 30, 2026
- b9846
This release optimizes the Vulkan backend for Asahi Linux by rolling back the BK loop in matrix multiplication, likely improving performance or correctness on that specific platform. Standard binaries are provided for all major operating systems.
Jun 30, 2026
- b9844
This release introduces support for NVIDIA FP4 precision in the WebGPU backend, optimizing memory usage and performance for specific hardware. It provides standard binaries for all supported platforms.
Jun 30, 2026
- b9843
This release reverts a previous optimization regarding synchronizations during split compute to address potential issues. It maintains the same comprehensive platform support and binary distribution as the previous release.
Jun 30, 2026
- b9842
This release optimizes the API by removing duplicate entries for presets and cached models in the `/v1/models` endpoint. It includes standard binary builds for various platforms including macOS, Linux, Android, Windows, and openEuler.
Jun 29, 2026
- b9840
Adds comprehensive support for DeepSeek V4 models, including conversion, graph optimization, and multi-sequence processing.
Jun 29, 2026
- b9839
Fixes a tooling issue where Tailwind CSS scanning was disabled in ignored worktrees.
Jun 29, 2026
- b9838
Performs code cleanup by removing unused regex-partial functionality from the common module.
Jun 29, 2026
- b9837
Adds a new flag to preserve reasoning content when generating chat outputs using Jinja templates.
Jun 29, 2026