b9928
hexagon: new vtcm layouts and improved pipelines for MUL_MAT, MUL_MAT_ID and FLASH_ATTN_EXT (#25425) hex-fa: refactor kernel param compute to use common layout builder hmx: add explicit…
Latest
b9927
cli : move to HTTP-based implementation (#24948) cli: move to HTTP-based implementation wip working remote server ok cli support router mode Co-authored-by: Piotr Wilkin ilintar@gmail.com case:…
b9925
cuda : add support for f16->f16 GGML_OP_SET_ROWS (#25367) macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramework Linux:…
b9924
llama: refactor fused ops (#24646) macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramework Linux: Ubuntu x64 (CPU)…
b9923
server-stream: follow-up on SSE Replay Buffer (#23226) (#25047) server-stream : pimpl server-stream: prefix free functions with server_stream_ address review from ggerganov: scope the public stream functions…
b9922
llama-batch: add n_keep_tail in split_equal for recurrent models (#25278) macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramework…
b9918
metal : add set_rows with src0 f16 (#25434) Co-authored-by: Georgi Gerganov ggerganov@gmail.com macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel…
b9916
ggml : fix A indexing in simd_gemm scalar tail-column path (#25390) simd_gemm() has an incorrect A-matrix index in the scalar tail-column path for full row blocks.…
b9915
ggml : add support for CPU f16->f16 GGML_OP_SET_ROWS (#25344) ggml : add support for CPU f16->f16 GGML_OP_SET_ROWS ggml : add missing type checks in f16 GGML_OP_SET_ROWS…
b9914
opencl: fix potential crash in aos reconstruct (#25383) macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramework Linux:…