b9859
opencl: allow loading precompiled binary kernels from library (#23042) opencl: allow loading binary kernel opencl: add libdl.h ggml-backend-dl is in ggml, which depends backend libs, thus…
Latest
b9858
common : use hf primary split as model path (#25194) Fixes #25181 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel…
b9857
hexagon: flash attention rework (optimizations, accuracy improvements, etc) (#25085) hex-mm: fold mm quant tasks into the main matmul threads hex-mm: minor formatting fixes hex-mm: cleanup is_quant…
b9856
CUDA: consistent use of restrict + PDL for FA (#25185) macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS…
b9855
ggml-cpu: add AVX2 optimization for nvfp4 dot product and use UE4M3 LUT (#23961) macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS…
b9853
ui: Remove PWA navigate fallback to prevent caching API endpoint requ…
b9852
opencl: initial q1_0 support (#25160) opencl: general q1_0 support opencl: add Adreno GEMM/GEMV for q1_0 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled)…
b9851
cuda : prevent integer truncation and overflow errors when using KQ mask strides in flash_attn_mask_to_KV_max kernel (#24945) Co-authored-by: Stanisław Szymczyk sszymczy@gmail.com macOS/iOS: macOS Apple Silicon (arm64)…
b9850
model : register t_layer_inp for qwen3next (#25141) Fix input assignment in layer processing loop Fix DFLASH for qwen-coder-next add line break Added tensor for attention normalization…
b9849
common,server: handle bracketed IPv6 literals in URL authority (#25140) common,server: handle bracketed IPv6 literals in URL authority Parse the [host]:port form (RFC 3986) and bracket IPv6…