llama.cpp Releases
684 releases of ggml-org/llama.cpp
- b9929
Focuses on Vulkan optimizations for small AMD GPUs and includes the usual comprehensive binary builds for macOS, Linux, Windows, and Android.
Jul 8, 2026
- b9928
Focuses on performance improvements to the Hexagon backend, specifically regarding memory management and kernel pipelines.
Jul 8, 2026
- b9927
Migrates the CLI implementation to use HTTP communication, supporting router mode and improved UI display.
Jul 8, 2026
- b9925
Adds support for f16->f16 GGML_OP_SET_ROWS operation on CUDA.
Jul 8, 2026
- b9924
Refactors the implementation of fused operations.
Jul 8, 2026
- b9923
Refactors server streaming implementation to use the PImpl pattern, improves thread safety with mutexes, and cleans up public headers.
Jul 8, 2026
- b9922
Adds n_keep_tail support in the split_equal function for better handling of recurrent models during batch processing.
Jul 8, 2026
- b9918
Adds support for f16->f16 GGML_OP_SET_ROWS operation on Metal (Apple Silicon).
Jul 8, 2026
- b9917
Fixes out-of-bounds reads in the UGM tokenizer to prevent heap-buffer-overflow vulnerabilities in T5/UGM GGUF file parsing.
Jul 8, 2026
- b9916
Fixes incorrect A-matrix indexing in the SIMD GEMM scalar tail-column path for full row blocks.
Jul 8, 2026
- b9915
Adds support for f16->f16 GGML_OP_SET_ROWS on the CPU, including type checks and merging implementation functions.
Jul 8, 2026
- b9914
Fixes a potential crash in the OpenCL AOS (Array Of Structures) reconstruction logic.
Jul 8, 2026
- b9913
Introduces support for Q2_0 quantization, a 2-bit quantization scheme, specifically for the CPU backend, allowing for smaller model sizes.
Jul 8, 2026
- b9912
A minor code cleanup release fixing naming conventions and spacing issues in the speculative decoding module.
Jul 8, 2026
- b9911
Implements fused matrix-vector quantization (MMVQ) post-scale operations specifically for NVIDIA FP4 (NVFP4) quantization on CUDA, resulting in performance improvements.
Jul 8, 2026
- b9910
Resolves inconsistencies between how draft models are fitted and loaded in the server, improving the stability of speculative decoding implementations.
Jul 8, 2026
- b9909
Enhances the `/responses` API stream endpoint by providing detailed timing metrics and progress updates to improve observability for users.
Jul 8, 2026
- b9908
Enforces strict RAM limits for prompt caching in the server API to prevent memory overruns and improves eviction logic by allowing the last entry to be removed.
Jul 8, 2026
- b9907
A minor maintenance fix adding a necessary header file (`<fstream>`) to the common library module to prevent potential compilation errors.
Jul 8, 2026
- b9906
Corrects a compilation error where `-ffast-math` was inadvertently disabling Infinity and NaN handling under ROCm 22, which caused build failures in CI.
Jul 8, 2026