*** Welcome to KoboldCpp - Version 1.124.2 Loading Chat Completions Adapter: /var/folders/2s/vty41l455yv698g4xkgfv7z00000gn/T/_MEI000064deQJvS6E/kcpp_adapters/AutoGuess.json Chat Completions Adapter Loaded MacOS detected: Auto GPU layers set to maximum System: Darwin Darwin Kernel Version 24.6.0: Sun Oct 11 23:44:11 PDT 2026; root:xnu-11417.140.69.x.x~2/RELEASE_ARM64_VMAPPLE arm64 arm Unable to determine GPU Memory Unable to determine available RAM Initializing dynamic library: koboldcpp_default.so ========== Namespace(usecuda=None, usevulkan=None, usecpu=False, model=['results/ci-1/macos-15-arm64/_files/truncated.gguf'], model_param='results/ci-1/macos-15-arm64/_files/truncated.gguf', config=None, contextsize=16384, gpulayers=200, host='', launch=False, tensor_split=None, threads=1, port=49652, port_param=49652, version=False, agent=False, agentload='', analyze='', autofit=False, autofitpadding=1024, batchsize=512, ubatchsize=-1, benchmark=None, blasthreads=0, chatcompletionsadapter='AutoGuess', cli=False, debugmode=0, defaultgenamt=2048, device='', downloaddir='', draftamount=4, draftgpulayers=999, draftgpusplit=None, draftmodel='', enableguidance=False, exportconfig='', exporttemplate='', failsafe=False, foreground=False, gendefaults='', gendefaultsoverwrite=False, genlimit=0, highpriority=False, ignoremissing=False, jinja=False, jinja_kwargs='', jinjatemplate='', jinjathink='default', lora=None, loramult=1.0, lowvram=False, maingpu=-1, maxrequestsize=32, mcpfile='', mmproj='', mmprojcpu=False, lazy_mode='auto', moe_cache_mib=0, moecpu=0, ffncpu=0, moeexperts=-1, multiplayer=False, nocertify=False, nofastforward=False, noflashattention=False, noavx2=False, nobostoken= nommq=False, nomodel=False, noshift=False, noswa=False, onready='', allow_config_onready=False, overridekv='', overridenativecontext=0, overridetensors='', parallelrequests=1, paralleltotalcontext=0, password= preloadstory='', prompt='', quantkv='f16', queuelimit=10, quiet=False, ratelimit=0, reasoningeffort='default', remotetunnel=False, ropeconfig=[0.0, 10000.0], savedatafile='', singleinstance=False, smartcache=0, smartcontext=False, splitmode='layer', ssl=None, swapadding=0, unpack='', usemtp=False, usemlock=False, usemmap=False, usedirectio=False, visionmaxres=1024, visionmaxtokens=-1, visionmintokens=-1, websearch=False, showgui=False, skiplauncher=True, hordemodelname='', hordeworkername='', hordekey='', hordemaxctx=0, hordegenlen=0, sdaudiovae='', sdclamped=0, sdclampedsoft=0, sdclip1='', sdclip2='', sdclipdevice=-2, sdconvdirect='off', sdflashattention=False, sdlora=[], sdloramult=[1.0], sdmaingpu=None, sdmodel='', sdoffloadcpu=False, sdphotomaker='', sdquant=0, sdllm='', sdthreads=0, sdtiledvae=512, sdupscaler='', sdvae='', sdvaeauto=False, sdvaedevice=-1, sdvramlimit=0, whispermodel='', ttsmodel='', ttswavtokenizer='', ttsgpu=False, ttsmaxlen=4096, ttsthreads=0, ttsdir='', musicllm='', musicembeddings='', musicdiffusion='', musicvae='', musiclowvram=False, embeddingsmodel='', embeddingsmaxctx=4096, embeddingsgpu=False, rpcmode='disabled', rpcport=5551, rpchost='0.0.0.0', rpcdevice='', rpccache='', rpctargets='', admin=False, adminpassword= admindir='', adminunloadtimeout=0, routermode=False, reqtimeout=600, autoswapmode=False, autoswapthreshold=256, baseconfig='', hordeconfig=None, sdconfig=None, noblas=False, nommap=False, nopipelineparallel=False, pipelineparallel=False, sdnotile=False, sdt5xxl=None, sdvaecpu=False, sdclipgpu=False, forceversion=False, sdgendefaults=False, flashattention=False, useswa=False, multiuser=None, testmemory=False, run_bundled_agent=False, agent_base_url=None, agent_api_key= proxy_port=None) ========== Loading Text Model: /Users//work/test-KoboldCpp/test-KoboldCpp/results/ci-1/macos-15-arm64/_files/truncated.gguf ggml_metal_device_init: tensor API disabled for pre-M5 and pre-A19 devices ggml_metal_library_init: default.metallib not found, loading kernel sources ggml_metal_library_init: GGML_METAL_PATH_RESOURCES = /private/var/folders/2s/vty41l455yv698g4xkgfv7z00000gn/T/_MEI000064deQJvS6E ggml_metal_library_init: loading '/private/var/folders/2s/vty41l455yv698g4xkgfv7z00000gn/T/_MEI000064deQJvS6E/kernels/fa_aux.metal' ggml_metal_library_init: loading '/private/var/folders/2s/vty41l455yv698g4xkgfv7z00000gn/T/_MEI000064deQJvS6E/kernels/fa_f16.metal' ggml_metal_library_init: loading '/private/var/folders/2s/vty41l455yv698g4xkgfv7z00000gn/T/_MEI000064deQJvS6E/kernels/fa_f32.metal' ggml_metal_library_init: loading '/private/var/folders/2s/vty41l455yv698g4xkgfv7z00000gn/T/_MEI000064deQJvS6E/kernels/fa_q4_0.metal' ggml_metal_library_init: loading '/private/var/folders/2s/vty41l455yv698g4xkgfv7z00000gn/T/_MEI000064deQJvS6E/kernels/fa_q4_1.metal' ggml_metal_library_init: loading '/private/var/folders/2s/vty41l455yv698g4xkgfv7z00000gn/T/_MEI000064deQJvS6E/kernels/fa_q5_0.metal' ggml_metal_library_init: loading '/private/var/folders/2s/vty41l455yv698g4xkgfv7z00000gn/T/_MEI000064deQJvS6E/kernels/fa_q5_1.metal' ggml_metal_library_init: loading '/private/var/folders/2s/vty41l455yv698g4xkgfv7z00000gn/T/_MEI000064deQJvS6E/kernels/fa_q8_0.metal' ggml_metal_library_init: loading '/private/var/folders/2s/vty41l455yv698g4xkgfv7z00000gn/T/_MEI000064deQJvS6E/kernels/fa_tensor.metal' ggml_metal_library_init: loading '/private/var/folders/2s/vty41l455yv698g4xkgfv7z00000gn/T/_MEI000064deQJvS6E/kernels/fa_vec_f16.metal' ggml_metal_library_init: loading '/private/var/folders/2s/vty41l455yv698g4xkgfv7z00000gn/T/_MEI000064deQJvS6E/kernels/fa_vec_f32.metal' ggml_metal_library_init: loading '/private/var/folders/2s/vty41l455yv698g4xkgfv7z00000gn/T/_MEI000064deQJvS6E/kernels/fa_vec_q4_0.metal' ggml_metal_library_init: loading '/private/var/folders/2s/vty41l455yv698g4xkgfv7z00000gn/T/_MEI000064deQJvS6E/kernels/fa_vec_q4_1.metal' ggml_metal_library_init: loading '/private/var/folders/2s/vty41l455yv698g4xkgfv7z00000gn/T/_MEI000064deQJvS6E/kernels/fa_vec_q5_0.metal' ggml_metal_library_init: loading '/private/var/folders/2s/vty41l455yv698g4xkgfv7z00000gn/T/_MEI000064deQJvS6E/kernels/fa_vec_q5_1.metal' ggml_metal_library_init: loading '/private/var/folders/2s/vty41l455yv698g4xkgfv7z00000gn/T/_MEI000064deQJvS6E/kernels/fa_vec_q8_0.metal' ggml_metal_library_init: loading '/private/var/folders/2s/vty41l455yv698g4xkgfv7z00000gn/T/_MEI000064deQJvS6E/kernels/mul_mv.metal' ggml_metal_library_init: loading '/private/var/folders/2s/vty41l455yv698g4xkgfv7z00000gn/T/_MEI000064deQJvS6E/kernels/mul_mv_mma.metal' ggml_metal_library_init: loading '/private/var/folders/2s/vty41l455yv698g4xkgfv7z00000gn/T/_MEI000064deQJvS6E/kernels/mul_mm.metal' ggml_metal_library_init: loading '/private/var/folders/2s/vty41l455yv698g4xkgfv7z00000gn/T/_MEI000064deQJvS6E/kernels/quantize.metal' ggml_metal_library_init: loading '/private/var/folders/2s/vty41l455yv698g4xkgfv7z00000gn/T/_MEI000064deQJvS6E/kernels/softmax.metal' ggml_metal_library_init: loading '/private/var/folders/2s/vty41l455yv698g4xkgfv7z00000gn/T/_MEI000064deQJvS6E/kernels/norm.metal' ggml_metal_library_init: loading '/private/var/folders/2s/vty41l455yv698g4xkgfv7z00000gn/T/_MEI000064deQJvS6E/kernels/unary.metal' ggml_metal_library_init: loading '/private/var/folders/2s/vty41l455yv698g4xkgfv7z00000gn/T/_MEI000064deQJvS6E/kernels/binbcast.metal' ggml_metal_library_init: loading '/private/var/folders/2s/vty41l455yv698g4xkgfv7z00000gn/T/_MEI000064deQJvS6E/kernels/reduce.metal' ggml_metal_library_init: loading '/private/var/folders/2s/vty41l455yv698g4xkgfv7z00000gn/T/_MEI000064deQJvS6E/kernels/tri.metal' ggml_metal_library_init: loading '/private/var/folders/2s/vty41l455yv698g4xkgfv7z00000gn/T/_MEI000064deQJvS6E/kernels/ssm.metal' ggml_metal_library_init: loading '/private/var/folders/2s/vty41l455yv698g4xkgfv7z00000gn/T/_MEI000064deQJvS6E/kernels/wkv.metal' ggml_metal_library_init: loading '/private/var/folders/2s/vty41l455yv698g4xkgfv7z00000gn/T/_MEI000064deQJvS6E/kernels/gated_delta_net.metal' ggml_metal_library_init: loading '/private/var/folders/2s/vty41l455yv698g4xkgfv7z00000gn/T/_MEI000064deQJvS6E/kernels/solve_tri.metal' ggml_metal_library_init: loading '/private/var/folders/2s/vty41l455yv698g4xkgfv7z00000gn/T/_MEI000064deQJvS6E/kernels/rope.metal' ggml_metal_library_init: loading '/private/var/folders/2s/vty41l455yv698g4xkgfv7z00000gn/T/_MEI000064deQJvS6E/kernels/conv.metal' ggml_metal_library_init: loading '/private/var/folders/2s/vty41l455yv698g4xkgfv7z00000gn/T/_MEI000064deQJvS6E/kernels/upscale.metal' ggml_metal_library_init: loading '/private/var/folders/2s/vty41l455yv698g4xkgfv7z00000gn/T/_MEI000064deQJvS6E/kernels/argsort.metal' ggml_metal_library_init: loading '/private/var/folders/2s/vty41l455yv698g4xkgfv7z00000gn/T/_MEI000064deQJvS6E/kernels/pool.metal' ggml_metal_library_init: loading '/private/var/folders/2s/vty41l455yv698g4xkgfv7z00000gn/T/_MEI000064deQJvS6E/kernels/misc.metal' ggml_metal_library_compile_all: compiled 'fa_aux' library in 0.009 sec ggml_metal_library_compile_all: compiled 'fa_f16' library in 0.012 sec ggml_metal_library_compile_all: compiled 'fa_f32' library in 0.010 sec ggml_metal_library_compile_all: compiled 'fa_q4_0' library in 0.009 sec ggml_metal_library_compile_all: compiled 'fa_q4_1' library in 0.008 sec ggml_metal_library_compile_all: compiled 'fa_q5_0' library in 0.009 sec ggml_metal_library_compile_all: compiled 'fa_q5_1' library in 0.008 sec ggml_metal_library_compile_all: compiled 'fa_q8_0' library in 0.008 sec ggml_metal_library_compile_all: compiled 'fa_tensor' library in 0.002 sec ggml_metal_library_compile_all: compiled 'fa_vec_f16' library in 0.010 sec ggml_metal_library_compile_all: compiled 'fa_vec_f32' library in 0.009 sec ggml_metal_library_compile_all: compiled 'fa_vec_q4_0' library in 0.011 sec ggml_metal_library_compile_all: compiled 'fa_vec_q4_1' library in 0.011 sec ggml_metal_library_compile_all: compiled 'fa_vec_q5_0' library in 0.012 sec ggml_metal_library_compile_all: compiled 'fa_vec_q5_1' library in 0.011 sec ggml_metal_library_compile_all: compiled 'fa_vec_q8_0' library in 0.011 sec ggml_metal_library_compile_all: compiled 'mul_mv' library in 0.016 sec ggml_metal_library_compile_all: compiled 'mul_mv_mma' library in 0.011 sec ggml_metal_library_compile_all: compiled 'mul_mm' library in 0.011 sec ggml_metal_library_compile_all: compiled 'quantize' library in 0.010 sec ggml_metal_library_compile_all: compiled 'softmax' library in 0.004 sec ggml_metal_library_compile_all: compiled 'norm' library in 0.004 sec ggml_metal_library_compile_all: compiled 'unary' library in 0.004 sec ggml_metal_library_compile_all: compiled 'binbcast' library in 0.003 sec ggml_metal_library_compile_all: compiled 'reduce' library in 0.002 sec ggml_metal_library_compile_all: compiled 'tri' library in 0.002 sec ggml_metal_library_compile_all: compiled 'ssm' library in 0.003 sec ggml_metal_library_compile_all: compiled 'wkv' library in 0.002 sec ggml_metal_library_compile_all: compiled 'gated_delta_net' library in 0.002 sec ggml_metal_library_compile_all: compiled 'solve_tri' library in 0.002 sec ggml_metal_library_compile_all: compiled 'rope' library in 0.003 sec ggml_metal_library_compile_all: compiled 'conv' library in 0.003 sec ggml_metal_library_compile_all: compiled 'upscale' library in 0.002 sec ggml_metal_library_compile_all: compiled 'argsort' library in 0.003 sec ggml_metal_library_compile_all: compiled 'pool' library in 0.002 sec ggml_metal_library_compile_all: compiled 'misc' library in 0.004 sec ggml_metal_library_compile_all: loaded 36 libraries from source in 0.084 sec (max single = 0.016 sec) ggml_metal_rsets_init: creating a residency set collection (keep_alive = 180 s) ggml_metal_device_init: GPU name: MTL0 (Apple Paravirtual device) ggml_metal_device_init: GPU family: MTLGPUFamilyApple5 (1005) ggml_metal_device_init: simdgroup reduction = false ggml_metal_device_init: simdgroup matrix mul. = false ggml_metal_device_init: has unified memory = true ggml_metal_device_init: has bfloat = false ggml_metal_device_init: has tensor = false ggml_metal_device_init: use residency sets = true ggml_metal_device_init: use shared buffers = true ggml_metal_device_init: recommendedMaxWorkingSetSize = 5010.80 MB llama_model_load: error loading model: tensor 'output.weight' data is not within the file bounds, model is corrupted or incomplete llama_model_load_from_file_impl: failed to load model gpttype_load_model: error: failed to load model '/Users//work/test-KoboldCpp/test-KoboldCpp/results/ci-1/macos-15-arm64/_files/truncated.gguf' Load Text Model OK: False Could not load text model: /Users//work/test-KoboldCpp/test-KoboldCpp/results/ci-1/macos-15-arm64/_files/truncated.gguf The reported GGUF Arch is: qwen2 Arch Category: 24 --- Identified as GGUF model. Attempting to Load... --- Using automatic RoPE scaling for GGUF. If the model has custom RoPE settings, they'll be used directly instead! System Info: AVX = 0 | AVX_VNNI = 0 | AVX2 = 0 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | AVX512_BF16 = 0 | AMX_INT8 = 0 | FMA = 0 | NEON = 1 | SVE = 0 | ARM_FMA = 1 | F16C = 0 | FP16_VA = 1 | RISCV_VECT = 0 | WASM_SIMD = 0 | SSE3 = 0 | SSSE3 = 0 | VSX = 0 | MATMUL_INT8 = 0 | LLAMAFILE = 1 | Number of Backends: 4 Backend 0: MTL Backend 1: BLAS Backend 2: RPC Backend 3: CPU