{
 "case": "fail-truncated",
 "machine": "macos-15-arm64",
 "run": "ci-2",
 "args": [
  "--model",
  "results/ci-2/macos-15-arm64/_files/truncated.gguf"
 ],
 "started": "2026-11-13T13:25:59+0000",
 "start": {
  "ready": false,
  "exit_code": 3,
  "seconds": 6.37
 },
 "peak_rss_mb": 161.8,
 "log_lines": [
  "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-2/macos-15-arm64/_files/truncated.gguf'], model_param='results/ci-2/macos-15-arm64/_files/truncated.gguf', config=None, contextsize=16384, gpulayers=200, host='', launch=False, tensor_split=None, threads=1, port=49689, port_param=49689, 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=<redacted> nommq=False, nomodel=False, noshift=False, noswa=False, onready='', allow_config_onready=False, overridekv='', overridenativecontext=0, overridetensors='', parallelrequests=1, paralleltotalcontext=0, password=<redacted> 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=<redacted> 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=<redacted> proxy_port=None)",
  "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/<user>/work/test-KoboldCpp/test-KoboldCpp/results/ci-2/macos-15-arm64/_files/truncated.gguf'",
  "Load Text Model OK: False"
 ],
 "log_tail": [
  "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/<user>/work/test-KoboldCpp/test-KoboldCpp/results/ci-2/macos-15-arm64/_files/truncated.gguf'",
  "Load Text Model OK: False",
  "Could not load text model: /Users/<user>/work/test-KoboldCpp/test-KoboldCpp/results/ci-2/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"
 ],
 "finished": "2026-11-13T13:26:05+0000"
}