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 0.20.0 no summary available
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