llama.cpp Releases
609 releases of ggml-org/llama.cpp
- b9938
Enabled fast math optimizations for HIP/AMD GPU backend to match CUDA performance.
Jul 9, 2026
- b9937
CUDA backend fix aligning snake fusion matcher logic with other backends.
Jul 9, 2026
- b9936
Server-side fix ensuring prompt batch splitting respects the minimum step size.
Jul 9, 2026
- b9935
Adds RoPE (Rotary Positional Embedding) support for Vision tasks in the Hexagon backend.
Jul 9, 2026
- b9934
Tuning of subgroup splitting in WebGPU for better Flash Attention vector operations.
Jul 9, 2026
- b9933
Fixes garbled output in OpenCL for Q6_K weights with specific alignment requirements.
Jul 8, 2026
- b9932
Vulkan backend performance tuning for GCN GPUs and attention masking optimization.
Jul 8, 2026
- b9931
OpenCL optimizations for MoE (Mixture of Experts) prefill operations.
Jul 8, 2026
- b9930
Fixes a bug in the llama-batch system allowing positions to decrease within a sequence.
Jul 8, 2026
- 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