b10669

sycl: bind the f16 KV cache in place for the oneDNN SDPA path (#27468) Measured at a live KV length of 34816 (32768 depth plus one 2048 ubatch), on Qwen3.8 27B Q4_K_S: per tensor 4 * 34816 * 256 * 2 B = 71.3 MB staged per call K and V, so 2x = 142.6 MB traffic per call read once, write once = 285.2 MB traffic per ubatch 285.2 MB * 16 calls = 4.56 GB One ubatch is one ggml_cgraph submission (llama_context::process_ubatch -> graph_compute), so that 4.56 GB is the cost of a single 2048-token prefill chunk, and it scales with the live KV length: the first ubatch of the same run, at seq = 2048, moves 0.27 GB. Reproduce the two measured inputs with: GGML_SCHED_DEBUG=2 llama-bench -m MODEL -p 8 -n 0 -r 1 -ngl 0 -fa on -ctk f16 -ctv f16 -v > nd.txt 2>&1 grep -E 'n_layer|n_head_kv|n_embd_head_k' nd.txt awk '/node # 0 /{g++} g==1 && /(FLASH_ATTN)/{n++} END{print n+0}' nd.txt Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/43654339 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramework Linux: Ubuntu x64 (CPU) Ubuntu arm64 (CPU) Ubuntu s390x (CPU) Ubuntu x64 (Vulkan) Ubuntu arm64 (Vulkan) Ubuntu x64 (ROCm 7.14) Ubuntu x64 (OpenVINO) Ubuntu x64 (SYCL FP32) Ubuntu x64 (SYCL FP16) Android: Android arm64 (CPU) Windows: Windows x64 (CPU) Windows arm64 (CPU) Windows arm64 (OpenCL Adreno) Windows x64 (CUDA 12) - CUDA 12.4 DLLs Windows x64 (CUDA 13) - CUDA 13.3 DLLs Windows arm64 (CUDA 13) (preview) - CUDA 13.4 DLLs Windows x64 (Vulkan) Windows x64 (OpenVINO) Windows x64 (SYCL) Windows x64 (ROCm 7.14) openEuler: DISABLED openEuler x86 (310p) openEuler x86 (910b, ACL Graph) openEuler aarch64 (310p) openEuler aarch64 (910b, ACL Graph) UI: UI

Source: llama.cpp Releases | 2026-08-28

Related