b10066
opencl: load and use kernel_gemm_moe_q6_k_f32_ns from bin kernel lib (#25797) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel…
Latest
b10064
opencl: transpose q4_K noshuffle scales for coalesced reads (#25805) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64)…
b10063
sync : ggml Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramework Linux: Ubuntu x64 (CPU)…
b10061
tests : initialize all tensors in test_dsv4_hc to avoid NaNs in sentinel tensors (#25822) Co-authored-by: Stanisław Szymczyk sszymczy@gmail.com Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS…
b10059
ggml-blas: default hadamard mul_mat to cpu routine (#25710) Signed-off-by: Aaron Teo aaron.teo1@ibm.com Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED…
b10058
vulkan: Support Q2_0 (#25430) vulkan: Support Q2_0 The backend perf tests for mat-vec-mul weren't very good at first (worse than q2_k), doubling the rows per workgroup…
b10057
sycl: fix row calculation when K_QUANTS_PER_ITERATION is 1 (#25690) sycl: fix incorrect row calculation when K_QUANTS_PER_ITERATION=1 Signed-off-by: Todd Malsbary todd.malsbary@intel.com sycl: use K_QUANTS_PER_ITERATION for non-reordered Q5_K…
b10056
opencl: add ABS op (#25115)
b10054
docs: added a note about using OpenCl with Adreno 810 (#25786) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS…
b10052
hexagon: L2 cache handling rework (dirty bit tracking with lazy flushing) and more MUL_MAT updates (#25762) hex-mm: fix artificial limit in the solver that restricted number…