Up to [cvs.NetBSD.org] / pkgsrc / math / ggml
Request diff between arbitrary revisions
Keyword substitution: kv
Default branch: MAIN
ggml: update to 1.0.0. ggml 1.0.0 prunes the deprecated public API and the legacy DIAG_MASK ops, adds configurable YaRN truncation and FP8 support, and brings broad performance work across backends: few-row quantized matmuls and MoE fusion on CUDA/Metal, a Vulkan prefill FlashAttention path, a device-side MoE scheduler on SYCL, decomposed Adreno FlashAttention in OpenCL, new WebGPU kernels, expanded Hexagon op coverage, and scheduler improvements that avoid uploading unused inputs.
ggml: update to 0.29.0. ggml v0.29.0 adds an OCP FP8 E4M3 tensor type, a new ggml_flash_attn_ext_rows op where each query slice attends to its own list of K/V rows, a batched tensor copy API, and initial support for multi-node tensor parallelism through a new multi-process communicator interface. Core improvements include bounding tensor views by the bytes their strides reach, zero-copy GGUF export of host-buffer tensors, and vm_allocate-based allocations on Apple platforms. Performance work spans all major backends: new SVE kernels in the CPU backend, DPAS flash attention for quantized KV in SYCL, fused MoE MMQ in CUDA, faster MXFP4 mat-vec in Metal, split-K tuning in Vulkan, and a large expansion of quantized GEMM/GEMV coverage in OpenCL. The Hexagon backend gains support for several new ops, including the lightning indexer, top-k mask, conv2d and upscale.
ggml: update to 0.28.0. This release adds a fused sparse-attention masking operation (GGML_OP_TOP_K_MASK) with CPU, CUDA and Metal implementations, plus accessors to read the precision configured on a compute node. MoE and sparse-attention dispatch got cleaner semantics: an index of -1 in MUL_MAT_ID / ADD_ID now means "skip this slot", so backends skip the work and zero the output row instead of relying on out-of-range index patching. The core relaxes SCALE to non-contiguous views and SUM to non-contiguous inputs. Backends gained a lot of throughput: MoE top-k and gate/up+GLU fusions and chunked graph launches on CUDA, graph record/replay and XMX matrix-engine kernels on SYCL, cooperative GEMMs, Q2_K/Q3_K weights and a lightning indexer on OpenCL, subgroup reductions and src1 precision control on Vulkan, and a restructured HTP backend with new repacking and fusion machinery on Hexagon. ZDNN gained flash attention and WebGPU gained Q2_0.
ggml: update to 0.27.0. ggml v0.27.0 extends the backend scheduler API with user callbacks for split weight copying and compute-buffer reallocation, and bumps the RPC protocol to v8 to support tensor-parallel RPC servers. Backends gained substantial new fast paths: chunked gated-delta-net kernels on CUDA/HIP, KleidiAI SME2 k-quant matmuls and AVX2 Q2_0 dot products on CPU, L2-aware coopmat2 matmul scheduling and bf16 activations on Vulkan, reordered-layout MoE kernels (MXFP4, IQ3, Q5_K, grouped XMX GEMM) on SYCL, dp4a MoE GEMMs on OpenCL, tensor-API and wider-head-dim flash attention on Metal, and a DMA/HVX copy overhaul with new pooling and 3D im2col ops on Hexagon. Correctness work concentrated on non-contiguous and strided views, grid/workgroup size limits, out-of-bounds accesses, and well-defined mul_mat_id behavior for duplicate expert ids.
ggml: update to 0.26.0. ggml v0.26.0 brings a new alloc_buffer_n/get_alloc_size_n buffer allocation API, sparse flash attention kernels on SYCL, Vulkan and Metal, and major lightning indexer improvements (halved score memory, tiling, MUSA support). The CPU backend gains BF16 ops and a tiled k-quant mul_mat, CUDA gains a model-driven W4A4 (NVFP4/MXFP4) mul_mat path plus MMVQ shared-expert fusion, and the Hexagon backend adds a sampler and more quant types. Model loading is faster with stricter GGUF size validation, Windows ARM64 MSVC builds are enabled, and WebGPU/OpenVINO/OpenCL/SYCL pick up numerous new kernels, ops and fixes.
ggml: update to 0.25.3. 0.25.3 A small maintenance release: the core graph size calculation (ggml_graph_nbytes) no longer triggers a UBSan "non-zero offset to null pointer" diagnostic, and the CI setup moves CUDA builds to the hf-jobs runner and adds a new AMD Vulkan build job. 0.25.2 A small point release focused on backend improvements: a new CUDA convolution kernel with an implicit-GEMM fast path, Vulkan fixes and tuning (misalignment handling in convolution shaders and cooperative-matrix support for Adreno GPUs), an optimized DP4A binary kernel for OpenCL Q6_K GEMM, and a precision guard in the Hexagon backend. 0.25.1 A hotfix release focused on the CUDA backend: sparse flash attention, which had been disabled due to a batch-dependent gate, is re-enabled for long-context prefill (up to ~1.4x prefill speedup at 131k context), with the supporting sparse mask scan kernel significantly sped up. Additionally, Metal gains the missing f32 × bf16 matmul kernels (fixing depthwise convolutions with bf16 weights) and its flash-attention tuning tables are now keyed by GPU family instead of individual SKU, while Vulkan adds MMQ/MMV matmul kernels for the IQ4_XS quantization type. 0.25.0 This release expands hyper-connection, flash-attention, and fused MoE/SSM support across CPU, GPU, and accelerator backends. It also improves backend robustness, quantization, data-layout handling, and RPC/meta buffer management. Numerous correctness fixes and performance tuning land across all major backends, including new kernels, fusions, and op coverage. 0.24.0 This release focuses on expanding backend coverage and robustness, with a new precision-control API, major Vulkan/SYCL/Hexagon/OpenCL work, and numerous correctness and performance fixes across CPU, CUDA, Metal, and other backends.
ggml: update to 0.23.0. Version 0.23.0 adds new operators and backend scheduling APIs for sparse attention, asynchronous execution, and allocation-dependency tracking. It includes broad correctness and performance work across CPU, GPU, and accelerator backends, plus an expanded RPC stack with Apple RDMA support.
ggml: update to 0.22.0. This release adds tensor-split support to the multi-backend (meta) backend with improved split-state propagation, reworks the Metal kernels into per-op sources with parallel compilation, and fixes ggml_clamp to be a proper non-in-place op. It also brings new ops (POOL_1D, PAD_REFLECT_1D), Q2_K SYCL kernels, MoE bias fusion on OpenCL, and assorted fixes across the CUDA, Metal, SYCL, Vulkan, OpenCL and WebGPU backends.
ggml: update to 0.21.0. Changes not found.
ggml: update to 0.20.2. Changes not found.
ggml: update to 0.20.1. No changelog found.
ggml: update to 0.20.0 no summary available
ggml: update to 0.19.0. No summary found.
ggml: update to 0.18.1. Summary not found.
ggml: update to 0.18.0. Another two weeks of updates.
ggml: update to 0.17.0. No changes summary found.
ggml: remove patch for stable-diffusion.cpp stable-diffusion.cpp uses local copy anyway.
ggml: update to 0.16.0. No summary of changes found.
math/ggml: import ggml-0.15.3 Tensor library for machine learning ## Features - Low-level cross-platform implementation - Integer quantization support - Broad hardware support - Automatic differentiation - ADAM and L-BFGS optimizers - No third-party dependencies - Zero memory allocations during runtime