llama.cpp Releases
684 releases of ggml-org/llama.cpp
- b9827
Optimized CUDA memory copy operations by adding a fast path for 2D strided tensor copies using cudaMemcpy2DAsync.
Jun 27, 2026
- b9826
Fixed unit tests related to normalization operations in the SYCL backend.
Jun 27, 2026
- b9825
Fixed a bug in the Vulkan backend where the step operator failed with zero inputs.
Jun 27, 2026
- b9824
Renamed RPC server binary to ggml-rpc-server and standardized naming for graph export tools.
Jun 27, 2026
- b9823
Added Windows OpenVINO builds to the CI check-release pipeline.
Jun 27, 2026
- b9822
Bug fix for the chat template test runner to correctly handle the --no-common option.
Jun 27, 2026
- b9821
Added command-line flags to display version, licenses, and help information.
Jun 26, 2026
- b9820
Performance improvements to the scheduler by reducing synchronization overhead during split compute and adding async CPU-to-GPU copy capabilities.
Jun 26, 2026
- b9817
Major update to the OpenVINO backend including version upgrade to 2026.2.1, removal of hardcoded compute types, and new operator support like GLU SwiGLU OAI.
Jun 26, 2026
- b9816
GGML synchronization updates to improve thread safety and consistency across the library.
Jun 26, 2026
- b9814
Optimizes the Vulkan backend's mul_mat_vecq operation for AMD Radeon MI50 GPUs, improving performance for quantized matrix multiplication operations.
Jun 26, 2026
- b9813
Adds support for Intel Xe1 architecture and enables cooperative matrix operations (coopmat1) on Intel Xe-LPG Plus GPUs, improving performance for Intel GPU users.
Jun 26, 2026
- b9811
Workaround for a compiler bug in the Vulkan backend's conv2d coopmat2 path, with the same fix applied to CONV_3D operations.
Jun 26, 2026
- b9810
Adds cublasSgemmBatched mapping for HIP/MUSA vendor headers, improving cross-platform compatibility between CUDA and HIP/MUSA.
Jun 26, 2026
- v0.6.3
Note: This release appears to be from a different repository (WeKnora) rather than ggml-org/llama.cpp, containing numerous frontend and backend improvements including UI enhancements, knowledge base features, and debugging fixes.
Jun 26, 2026
- b9803
Improves OpenCL profiling by flushing incomplete batches at shutdown, ensuring profiling data is captured even when processing is interrupted.
Jun 26, 2026
- b9802
Minor release with no specific changes documented in the release notes.
Jun 25, 2026
- b9789
Fixes a quantization bug affecting Mixture of Experts (MoE) models when using MTP (Mixture of Token Pruning).
Jun 25, 2026
- b9788
Adds SYCL tensor parallelism support for dual-GPU setups, implementing a BF16-compressed all-reduce path for large tensors and achieving significant performance improvements on Intel Arc Pro B70.
Jun 25, 2026
- v0.8.23
Adds support for CUDA 13.3, introduces Hunyuan v1 dense and MoE models, adds ISQ (Int8/4 Quantization) executor, and includes various performance and stability fixes.
Jun 25, 2026