b10051
kleidiai: Add SME vs SME2 distinction in kernel dispatch (#25478) The current integration treats SME as a single capability (CPU_FEATURE_SME) with no distinction between SME(v1) and…
Latest
b10050
vulkan: when using transfer queue for async copies, sync on event_wait to avoid race (#25229) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64,…
b10048
TP: fix Phi3, Bert, Plamo2/3, ChatGLM (#25536) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramework…
b10047
vendor: update BoringSSL to 0.20260713.0 (#25624) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramework Linux:…
b10046
tests: actually exercise test-recurrent-state-rollback (#25758) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramework Linux: Ubuntu…
b10045
server : allow text-only slot save/restore with mtmd (#25076) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64)…
b10043
CUDA: Support CUDA Virtual Devices (#25228) support cuda virtual devices disable NCCL path when virtual devices are used label virtual devices in description; add GPUx2 server…
b10042
Enable CUDA graphs on volta+turing (#25749) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramework Linux:…
b10041
server: Ignore empty / non-existing Origin headers (#25756) Otherwise this gives lots of unnecessary warnings: W srv operator(): (CORS) skip non-localhost origin: Website: https://llama.app macOS/iOS: macOS…
b10040
ggml-cuda : restore prop.integrated on HIP builds (#24233) PR #16308 set info.devices[id].integrated = false unconditionally for all CUDA/HIP devices as a workaround for corrupted output on…