github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 00:22:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #15470] Apple Silicon M5 run gemma:26b crash! #9887

New Issue
Closed
opened 2026-04-12 22:44:42 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-12 22:44:42 -05:00
Owner
Copy Link

Originally created by @dht-hedaihua on GitHub (Apr 10, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/15470

What is the issue?

Based on the logs you provided, Ollama encountered a low-level crash (SIGABRT) while loading a model on your macOS system with Apple Silicon (the logs indicate an Apple M5).

Root cause analysis:
The direct cause of the crash is a shader compilation failure in the GPU (Metal) driver layer.

Specifically, this segment from the logs:

error: static_assert failed due to requirement '__tensor_ops_detail::__is_same_v<bfloat, half>' "Input types must match cooperative tensor types"

This indicates that when Ollama’s underlying inference engine (llama.cpp) attempted to initialize Apple’s Metal GPU acceleration library, the Metal compiler (Metal Performance Primitives) rejected the code. The compiler strictly requires that tensor types in matrix multiplication match (here it found a mix of bfloat and half / float16 data types), causing ggml_metal_init to fail and the program to abort.

Given that your device is reported as an M5 and running a very recent environment, this typically occurs when a new version (or beta release) of macOS has tightened the validation of Metal API code conventions, making the current version of Ollama/llama.cpp incompatible.

Image

Relevant log output

time=2026-04-10T11:25:15.072+08:00 level=INFO source=routes.go:1744 msg="server config" env="map[HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:65536 OLLAMA_DEBUG:INFO OLLAMA_DEBUG_LOG_REQUESTS:false OLLAMA_EDITOR: OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/Users/hedaihua/.ollama/models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NO_CLOUD:true OLLAMA_NUM_PARALLEL:1 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://* vscode-file://*] OLLAMA_REMOTES:[ollama.com] OLLAMA_SCHED_SPREAD:false http_proxy: https_proxy: no_proxy:]"
time=2026-04-10T11:25:15.073+08:00 level=INFO source=routes.go:1746 msg="Ollama cloud disabled: true"
time=2026-04-10T11:25:15.074+08:00 level=INFO source=images.go:499 msg="total blobs: 8"
time=2026-04-10T11:25:15.074+08:00 level=INFO source=images.go:506 msg="total unused blobs removed: 0"
time=2026-04-10T11:25:15.074+08:00 level=INFO source=routes.go:1802 msg="Listening on 127.0.0.1:11434 (version 0.20.4)"
time=2026-04-10T11:25:15.075+08:00 level=INFO source=runner.go:67 msg="discovering available GPUs..."
time=2026-04-10T11:25:15.077+08:00 level=INFO source=server.go:444 msg="starting runner" cmd="/private/var/folders/6r/wc7km6294llbshkqy9c4hgw80000gn/T/AppTranslocation/70F21D0A-0093-45A5-9195-88CFF0181E67/d/Ollama.app/Contents/Resources/ollama runner --ollama-engine --port 59312"
time=2026-04-10T11:25:17.227+08:00 level=INFO source=types.go:60 msg="inference compute" id=cpu library=cpu compute="" name=cpu description=cpu libdirs=ollama driver="" pci_id="" type="" total="32.0 GiB" available="9.0 GiB"
time=2026-04-10T11:25:17.227+08:00 level=INFO source=routes.go:1852 msg="vram-based default context" total_vram="0 B" default_num_ctx=4096
[GIN] 2026/04/10 - 11:25:17 | 200 |       152.5µs |       127.0.0.1 | GET      "/api/version"
[GIN] 2026/04/10 - 11:25:17 | 200 |     112.208µs |       127.0.0.1 | GET      "/api/version"
[GIN] 2026/04/10 - 11:25:17 | 200 |     291.709��s |       127.0.0.1 | GET      "/api/version"
[GIN] 2026/04/10 - 11:25:17 | 200 |    1.440042ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2026/04/10 - 11:25:17 | 200 |   113.25525ms |       127.0.0.1 | POST     "/api/show"
[GIN] 2026/04/10 - 11:25:18 | 401 |  871.861667ms |       127.0.0.1 | POST     "/api/me"
[GIN] 2026/04/10 - 11:25:18 | 401 |     874.498ms |       127.0.0.1 | POST     "/api/me"
[GIN] 2026/04/10 - 11:25:20 | 200 |         633µs |       127.0.0.1 | GET      "/api/tags"
[GIN] 2026/04/10 - 11:25:20 | 200 |  139.930584ms |       127.0.0.1 | POST     "/api/show"
[GIN] 2026/04/10 - 11:25:21 | 200 |  104.620541ms |       127.0.0.1 | POST     "/api/show"
time=2026-04-10T11:25:21.175+08:00 level=INFO source=model.go:97 msg="gemma4: token IDs" image=255999 image_end=258882 audio=256000 audio_end=258883
time=2026-04-10T11:25:21.175+08:00 level=INFO source=server.go:259 msg="enabling flash attention"
time=2026-04-10T11:25:21.176+08:00 level=INFO source=server.go:444 msg="starting runner" cmd="/private/var/folders/6r/wc7km6294llbshkqy9c4hgw80000gn/T/AppTranslocation/70F21D0A-0093-45A5-9195-88CFF0181E67/d/Ollama.app/Contents/Resources/ollama runner --ollama-engine --model /Users/hedaihua/.ollama/models/blobs/sha256-7121486771cbfe218851513210c40b35dbdee93ab1ef43fe36283c883980f0df --port 59329"
time=2026-04-10T11:25:21.177+08:00 level=INFO source=sched.go:484 msg="system memory" total="32.0 GiB" free="9.1 GiB" free_swap="0 B"
time=2026-04-10T11:25:21.177+08:00 level=INFO source=server.go:771 msg="loading model" "model layers"=31 requested=-1
time=2026-04-10T11:25:21.185+08:00 level=INFO source=runner.go:1417 msg="starting ollama engine"
time=2026-04-10T11:25:21.185+08:00 level=INFO source=runner.go:1452 msg="Server listening on 127.0.0.1:59329"
time=2026-04-10T11:25:21.188+08:00 level=INFO source=runner.go:1290 msg=load request="{Operation:fit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:65536 KvCacheType: NumThreads:4 GPULayers:[] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
time=2026-04-10T11:25:21.213+08:00 level=INFO source=ggml.go:136 msg="" architecture=gemma4 file_type=Q4_K_M name="" description="" num_tensors=1014 num_key_values=52
ggml_metal_device_init: testing tensor API for f16 support
ggml_metal_device_init: testing tensor API for bfloat support
ggml_metal_library_init: using embedded metal library
ggml_metal_library_init: error: Error Domain=MTLLibraryErrorDomain Code=3 "program_source:7131:28: warning: variable 'theta_base' is used uninitialized whenever 'if' condition is false [-Wsometimes-uninitialized]
                } else if (sector % 3 == 0 && sector < 3 * args.sect_0) { // t
                           ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
program_source:7251:76: note: in instantiation of function template specialization 'kernel_rope_multi<float>' requested here
template [[host_name("kernel_rope_multi_f32")]] kernel kernel_rope_multi_t kernel_rope_multi<float>;
                                                                           ^
program_source:7149:33: note: uninitialized use occurs here
            const float theta = theta_base * pow(args.freq_base, inv_ndims*i0);
                                ^~~~~~~~~~
program_source:7131:24: note: remove the 'if' if its condition is always true
                } else if (sector % 3 == 0 && sector < 3 * args.sect_0) { // t
                       ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
program_source:7131:28: warning: variable 'theta_base' is used uninitialized whenever '&&' condition is false [-Wsometimes-uninitialized]
                } else if (sector % 3 == 0 && sector < 3 * args.sect_0) { // t
                           ^~~~~~~~~~~~~~~
program_source:7149:33: note: uninitialized use occurs here
            const float theta = theta_base * pow(args.freq_base, inv_ndims*i0);
                                ^~~~~~~~~~
program_source:7131:28: note: remove the '&&' if its condition is always true
                } else if (sector % 3 == 0 && sector < 3 * args.sect_0) { // t
                           ^~~~~~~~~~~~~~~~~~
program_source:7125:29: note: initialize the variable 'theta_base' to silence this warning
            float theta_base;
                            ^
                             = 0.0
program_source:7131:28: warning: variable 'theta_base' is used uninitialized whenever 'if' condition is false [-Wsometimes-uninitialized]
                } else if (sector % 3 == 0 && sector < 3 * args.sect_0) { // t
                           ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
program_source:7252:76: note: in instantiation of function template specialization 'kernel_rope_multi<half>' requested here
template [[host_name("kernel_rope_multi_f16")]] kernel kernel_rope_multi_t kernel_rope_multi<half>;
                                                                           ^
program_source:7149:33: note: uninitialized use occurs here
            const float theta = theta_base * pow(args.freq_base, inv_ndims*i0);
                                ^~~~~~~~~~
program_source:7131:24: note: remove the 'if' if its condition is always true
                } else if (sector % 3 == 0 && sector < 3 * args.sect_0) { // t
                       ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
program_source:7131:28: warning: variable 'theta_base' is used uninitialized whenever '&&' condition is false [-Wsometimes-uninitialized]
                } else if (sector % 3 == 0 && sector < 3 * args.sect_0) { // t
                           ^~~~~~~~~~~~~~~
program_source:7149:33: note: uninitialized use occurs here
            const float theta = theta_base * pow(args.freq_base, inv_ndims*i0);
                                ^~~~~~~~~~
program_source:7131:28: note: remove the '&&' if its condition is always true
                } else if (sector % 3 == 0 && sector < 3 * args.sect_0) { // t
                           ^~~~~~~~~~~~~~~~~~
program_source:7125:29: note: initialize the variable 'theta_base' to silence this warning
            float theta_base;
                            ^
                             = 0.0
In file included from program_source:2837:
In file included from /System/Library/Frameworks/MetalPerformancePrimitives.framework/Headers/MetalPerformancePrimitives.h:10:
In file included from /System/Library/Frameworks/MetalPerformancePrimitives.framework/Headers/MPPTensorOpsMatMul2d.h:368:
/System/Library/Frameworks/MetalPerformancePrimitives.framework/Headers/__impl/MPPTensorOpsMatMul2dImpl.h:3266:5: error: static_assert failed due to requirement '__tensor_ops_detail::__is_same_v<bfloat, half>' "Input types must match cooperative tensor types"
    static_assert(__tensor_ops_detail::__is_same_v<_leftType, leftValueType>, "Input types must match cooperative tensor types");
    ^             ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
/System/Library/Frameworks/MetalPerformancePrimitives.framework/Headers/MPPTensorOpsMatMul2d.h:394:24: note: in instantiation of function template specialization 'mpp::tensor_ops::__mutmul2d_detail::__run<{32, 64, 32, false, true, false, 1}, metal::execution_simdgroups<4>, metal::tensor<threadgroup half, metal::extents<int, 18446744073709551615, 18446744073709551615>, metal::tensor_inline>, metal::tensor<threadgroup bfloat, metal::extents<int, 18446744073709551615, 18446744073709551615>, metal::tensor_inline>, metal::cooperative_tensor<float, metal::extents<int, 18446744073709551615, 18446744073709551615>, mpp::tensor_ops::__mutmul2d_detail::__operand_layout<{32, 64, 32, false, true, false, 1}, mpp::tensor_ops::__mutmul2d_detail::__matmul2d_cooperative_operand_index::destination, metal::execution_simdgroups<4>, bfloat, half, float, int>>>' requested here
    __mutmul2d_detail::__run<Descriptor, Scope, LeftOperandType,
                       ^
program_source:12147:12: note: in instantiation of function template specialization 'mpp::tensor_ops::matmul2d<{32, 64, 32, false, true, false, 1}, metal::execution_simdgroups<4>>::run<metal::tensor<threadgroup half, metal::extents<int, 18446744073709551615, 18446744073709551615>, metal::tensor_inline>, metal::tensor<threadgroup bfloat, metal::extents<int, 18446744073709551615, 18446744073709551615>, metal::tensor_inline>, metal::cooperative_tensor<float, metal::extents<int, 18446744073709551615, 18446744073709551615>, mpp::tensor_ops::__mutmul2d_detail::__operand_layout<{32, 64, 32, false, true, false, 1}, mpp::tensor_ops::__mutmul2d_detail::__matmul2d_cooperative_operand_index::destination, metal::execution_simdgroups<4>, bfloat, half, float, int>>, void>' requested here
        mm.run(sB, sA, cT);
           ^
In file included from program_source:2837:
In file included from /System/Library/Frameworks/MetalPerformancePrimitives.framework/Headers/MetalPerformancePrimitives.h:10:
In file included from /System/Library/Frameworks/MetalPerformancePrimitives.framework/Headers/MPPTensorOpsMatMul2d.h:368:
/System/Library/Frameworks/MetalPerformancePrimitives.framework/Headers/__impl/MPPTensorOpsMatMul2dImpl.h:3267:5: error: static_assert failed due to requirement '__tensor_ops_detail::__is_same_v<half, bfloat>' "Input types must match cooperative tensor types"
    static_assert(__tensor_ops_detail::__is_same_v<_rightType, rightValueType>, "Input types must match cooperative tensor types");
    ^             ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
" UserInfo={NSLocalizedDescription=program_source:7131:28: warning: variable 'theta_base' is used uninitialized whenever 'if' condition is false [-Wsometimes-uninitialized]
                } else if (sector % 3 == 0 && sector < 3 * args.sect_0) { // t
                           ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
program_source:7251:76: note: in instantiation of function template specialization 'kernel_rope_multi<float>' requested here
template [[host_name("kernel_rope_multi_f32")]] kernel kernel_rope_multi_t kernel_rope_multi<float>;
                                                                           ^
program_source:7149:33: note: uninitialized use occurs here
            const float theta = theta_base * pow(args.freq_base, inv_ndims*i0);
                                ^~~~~~~~~~
program_source:7131:24: note: remove the 'if' if its condition is always true
                } else if (sector % 3 == 0 && sector < 3 * args.sect_0) { // t
                       ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
program_source:7131:28: warning: variable 'theta_base' is used uninitialized whenever '&&' condition is false [-Wsometimes-uninitialized]
                } else if (sector % 3 == 0 && sector < 3 * args.sect_0) { // t
                           ^~~~~~~~~~~~~~~
program_source:7149:33: note: uninitialized use occurs here
            const float theta = theta_base * pow(args.freq_base, inv_ndims*i0);
                                ^~~~~~~~~~
program_source:7131:28: note: remove the '&&' if its condition is always true
                } else if (sector % 3 == 0 && sector < 3 * args.sect_0) { // t
                           ^~~~~~~~~~~~~~~~~~
program_source:7125:29: note: initialize the variable 'theta_base' to silence this warning
            float theta_base;
                            ^
                             = 0.0
program_source:7131:28: warning: variable 'theta_base' is used uninitialized whenever 'if' condition is false [-Wsometimes-uninitialized]
                } else if (sector % 3 == 0 && sector < 3 * args.sect_0) { // t
                           ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
program_source:7252:76: note: in instantiation of function template specialization 'kernel_rope_multi<half>' requested here
template [[host_name("kernel_rope_multi_f16")]] kernel kernel_rope_multi_t kernel_rope_multi<half>;
                                                                           ^
program_source:7149:33: note: uninitialized use occurs here
            const float theta = theta_base * pow(args.freq_base, inv_ndims*i0);
                                ^~~~~~~~~~
program_source:7131:24: note: remove the 'if' if its condition is always true
                } else if (sector % 3 == 0 && sector < 3 * args.sect_0) { // t
                       ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
program_source:7131:28: warning: variable 'theta_base' is used uninitialized whenever '&&' condition is false [-Wsometimes-uninitialized]
                } else if (sector % 3 == 0 && sector < 3 * args.sect_0) { // t
                           ^~~~~~~~~~~~~~~
program_source:7149:33: note: uninitialized use occurs here
            const float theta = theta_base * pow(args.freq_base, inv_ndims*i0);
                                ^~~~~~~~~~
program_source:7131:28: note: remove the '&&' if its condition is always true
                } else if (sector % 3 == 0 && sector < 3 * args.sect_0) { // t
                           ^~~~~~~~~~~~~~~~~~
program_source:7125:29: note: initialize the variable 'theta_base' to silence this warning
            float theta_base;
                            ^
                             = 0.0
In file included from program_source:2837:
In file included from /System/Library/Frameworks/MetalPerformancePrimitives.framework/Headers/MetalPerformancePrimitives.h:10:
In file included from /System/Library/Frameworks/MetalPerformancePrimitives.framework/Headers/MPPTensorOpsMatMul2d.h:368:
/System/Library/Frameworks/MetalPerformancePrimitives.framework/Headers/__impl/MPPTensorOpsMatMul2dImpl.h:3266:5: error: static_assert failed due to requirement '__tensor_ops_detail::__is_same_v<bfloat, half>' "Input types must match cooperative tensor types"
    static_assert(__tensor_ops_detail::__is_same_v<_leftType, leftValueType>, "Input types must match cooperative tensor types");
    ^             ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
/System/Library/Frameworks/MetalPerformancePrimitives.framework/Headers/MPPTensorOpsMatMul2d.h:394:24: note: in instantiation of function template specialization 'mpp::tensor_ops::__mutmul2d_detail::__run<{32, 64, 32, false, true, false, 1}, metal::execution_simdgroups<4>, metal::tensor<threadgroup half, metal::extents<int, 18446744073709551615, 18446744073709551615>, metal::tensor_inline>, metal::tensor<threadgroup bfloat, metal::extents<int, 18446744073709551615, 18446744073709551615>, metal::tensor_inline>, metal::cooperative_tensor<float, metal::extents<int, 18446744073709551615, 18446744073709551615>, mpp::tensor_ops::__mutmul2d_detail::__operand_layout<{32, 64, 32, false, true, false, 1}, mpp::tensor_ops::__mutmul2d_detail::__matmul2d_cooperative_operand_index::destination, metal::execution_simdgroups<4>, bfloat, half, float, int>>>' requested here
    __mutmul2d_detail::__run<Descriptor, Scope, LeftOperandType,
                       ^
program_source:12147:12: note: in instantiation of function template specialization 'mpp::tensor_ops::matmul2d<{32, 64, 32, false, true, false, 1}, metal::execution_simdgroups<4>>::run<metal::tensor<threadgroup half, metal::extents<int, 18446744073709551615, 18446744073709551615>, metal::tensor_inline>, metal::tensor<threadgroup bfloat, metal::extents<int, 18446744073709551615, 18446744073709551615>, metal::tensor_inline>, metal::cooperative_tensor<float, metal::extents<int, 18446744073709551615, 18446744073709551615>, mpp::tensor_ops::__mutmul2d_detail::__operand_layout<{32, 64, 32, false, true, false, 1}, mpp::tensor_ops::__mutmul2d_detail::__matmul2d_cooperative_operand_index::destination, metal::execution_simdgroups<4>, bfloat, half, float, int>>, void>' requested here
        mm.run(sB, sA, cT);
           ^
In file included from program_source:2837:
In file included from /System/Library/Frameworks/MetalPerformancePrimitives.framework/Headers/MetalPerformancePrimitives.h:10:
In file included from /System/Library/Frameworks/MetalPerformancePrimitives.framework/Headers/MPPTensorOpsMatMul2d.h:368:
/System/Library/Frameworks/MetalPerformancePrimitives.framework/Headers/__impl/MPPTensorOpsMatMul2dImpl.h:3267:5: error: static_assert failed due to requirement '__tensor_ops_detail::__is_same_v<half, bfloat>' "Input types must match cooperative tensor types"
    static_assert(__tensor_ops_detail::__is_same_v<_rightType, rightValueType>, "Input types must match cooperative tensor types");
    ^             ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
}
ggml_metal_device_init: error: failed to create library
ggml_metal_rsets_init: creating a residency set collection (keep_alive = 180 s)
ggml_metal_device_init: GPU name:   Apple M5
ggml_metal_device_init: GPU family: MTLGPUFamilyApple10  (1010)
ggml_metal_device_init: GPU family: MTLGPUFamilyCommon3 (3003)
ggml_metal_device_init: GPU family: MTLGPUFamilyMetal4  (5002)
ggml_metal_device_init: simdgroup reduction   = true
ggml_metal_device_init: simdgroup matrix mul. = true
ggml_metal_device_init: has unified memory    = true
ggml_metal_device_init: has bfloat            = true
ggml_metal_device_init: has tensor            = true
ggml_metal_device_init: use residency sets    = true
ggml_metal_device_init: use shared buffers    = true
ggml_metal_device_init: recommendedMaxWorkingSetSize  = 26800.60 MB
load_backend: loaded CPU backend from /private/var/folders/6r/wc7km6294llbshkqy9c4hgw80000gn/T/AppTranslocation/70F21D0A-0093-45A5-9195-88CFF0181E67/d/Ollama.app/Contents/Resources/libggml-cpu.so
time=2026-04-10T11:25:22.216+08:00 level=INFO source=ggml.go:104 msg=system Metal.0.EMBED_LIBRARY=1 CPU.0.NEON=1 CPU.0.ARM_FMA=1 CPU.0.FP16_VA=1 CPU.0.DOTPROD=1 CPU.0.LLAMAFILE=1 CPU.0.ACCELERATE=1 CPU.1.NEON=1 CPU.1.ARM_FMA=1 CPU.1.FP16_VA=1 CPU.1.DOTPROD=1 CPU.1.LLAMAFILE=1 compiler=cgo(clang)
ggml_metal_init: allocating
ggml_metal_init: picking default device: Apple M5
ggml_metal_init: the device does not have a precompiled Metal library - this is unexpected
ggml_metal_init: will try to compile it on the fly
ggml_metal_library_init: using embedded metal library
ggml_metal_library_init: error: Error Domain=MTLLibraryErrorDomain Code=3 "program_source:7131:28: warning: variable 'theta_base' is used uninitialized whenever 'if' condition is false [-Wsometimes-uninitialized]
                } else if (sector % 3 == 0 && sector < 3 * args.sect_0) { // t
                           ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
program_source:7251:76: note: in instantiation of function template specialization 'kernel_rope_multi<float>' requested here
template [[host_name("kernel_rope_multi_f32")]] kernel kernel_rope_multi_t kernel_rope_multi<float>;
                                                                           ^
program_source:7149:33: note: uninitialized use occurs here
            const float theta = theta_base * pow(args.freq_base, inv_ndims*i0);
                                ^~~~~~~~~~
program_source:7131:24: note: remove the 'if' if its condition is always true
                } else if (sector % 3 == 0 && sector < 3 * args.sect_0) { // t
                       ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
program_source:7131:28: warning: variable 'theta_base' is used uninitialized whenever '&&' condition is false [-Wsometimes-uninitialized]
                } else if (sector % 3 == 0 && sector < 3 * args.sect_0) { // t
                           ^~~~~~~~~~~~~~~
program_source:7149:33: note: uninitialized use occurs here
            const float theta = theta_base * pow(args.freq_base, inv_ndims*i0);
                                ^~~~~~~~~~
program_source:7131:28: note: remove the '&&' if its condition is always true
                } else if (sector % 3 == 0 && sector < 3 * args.sect_0) { // t
                           ^~~~~~~~~~~~~~~~~~
program_source:7125:29: note: initialize the variable 'theta_base' to silence this warning
            float theta_base;
                            ^
                             = 0.0
program_source:7131:28: warning: variable 'theta_base' is used uninitialized whenever 'if' condition is false [-Wsometimes-uninitialized]
                } else if (sector % 3 == 0 && sector < 3 * args.sect_0) { // t
                           ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
program_source:7252:76: note: in instantiation of function template specialization 'kernel_rope_multi<half>' requested here
template [[host_name("kernel_rope_multi_f16")]] kernel kernel_rope_multi_t kernel_rope_multi<half>;
                                                                           ^
program_source:7149:33: note: uninitialized use occurs here
            const float theta = theta_base * pow(args.freq_base, inv_ndims*i0);
                                ^~~~~~~~~~
program_source:7131:24: note: remove the 'if' if its condition is always true
                } else if (sector % 3 == 0 && sector < 3 * args.sect_0) { // t
                       ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
program_source:7131:28: warning: variable 'theta_base' is used uninitialized whenever '&&' condition is false [-Wsometimes-uninitialized]
                } else if (sector % 3 == 0 && sector < 3 * args.sect_0) { // t
                           ^~~~~~~~~~~~~~~
program_source:7149:33: note: uninitialized use occurs here
            const float theta = theta_base * pow(args.freq_base, inv_ndims*i0);
                                ^~~~~~~~~~
program_source:7131:28: note: remove the '&&' if its condition is always true
                } else if (sector % 3 == 0 && sector < 3 * args.sect_0) { // t
                           ^~~~~~~~~~~~~~~~~~
program_source:7125:29: note: initialize the variable 'theta_base' to silence this warning
            float theta_base;
                            ^
                             = 0.0
In file included from program_source:2837:
In file included from /System/Library/Frameworks/MetalPerformancePrimitives.framework/Headers/MetalPerformancePrimitives.h:10:
In file included from /System/Library/Frameworks/MetalPerformancePrimitives.framework/Headers/MPPTensorOpsMatMul2d.h:368:
/System/Library/Frameworks/MetalPerformancePrimitives.framework/Headers/__impl/MPPTensorOpsMatMul2dImpl.h:3266:5: error: static_assert failed due to requirement '__tensor_ops_detail::__is_same_v<bfloat, half>' "Input types must match cooperative tensor types"
    static_assert(__tensor_ops_detail::__is_same_v<_leftType, leftValueType>, "Input types must match cooperative tensor types");
    ^             ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
/System/Library/Frameworks/MetalPerformancePrimitives.framework/Headers/MPPTensorOpsMatMul2d.h:394:24: note: in instantiation of function template specialization 'mpp::tensor_ops::__mutmul2d_detail::__run<{32, 64, 32, false, true, false, 1}, metal::execution_simdgroups<4>, metal::tensor<threadgroup half, metal::extents<int, 18446744073709551615, 18446744073709551615>, metal::tensor_inline>, metal::tensor<threadgroup bfloat, metal::extents<int, 18446744073709551615, 18446744073709551615>, metal::tensor_inline>, metal::cooperative_tensor<float, metal::extents<int, 18446744073709551615, 18446744073709551615>, mpp::tensor_ops::__mutmul2d_detail::__operand_layout<{32, 64, 32, false, true, false, 1}, mpp::tensor_ops::__mutmul2d_detail::__matmul2d_cooperative_operand_index::destination, metal::execution_simdgroups<4>, bfloat, half, float, int>>>' requested here
    __mutmul2d_detail::__run<Descriptor, Scope, LeftOperandType,
                       ^
program_source:12147:12: note: in instantiation of function template specialization 'mpp::tensor_ops::matmul2d<{32, 64, 32, false, true, false, 1}, metal::execution_simdgroups<4>>::run<metal::tensor<threadgroup half, metal::extents<int, 18446744073709551615, 18446744073709551615>, metal::tensor_inline>, metal::tensor<threadgroup bfloat, metal::extents<int, 18446744073709551615, 18446744073709551615>, metal::tensor_inline>, metal::cooperative_tensor<float, metal::extents<int, 18446744073709551615, 18446744073709551615>, mpp::tensor_ops::__mutmul2d_detail::__operand_layout<{32, 64, 32, false, true, false, 1}, mpp::tensor_ops::__mutmul2d_detail::__matmul2d_cooperative_operand_index::destination, metal::execution_simdgroups<4>, bfloat, half, float, int>>, void>' requested here
        mm.run(sB, sA, cT);
           ^
In file included from program_source:2837:
In file included from /System/Library/Frameworks/MetalPerformancePrimitives.framework/Headers/MetalPerformancePrimitives.h:10:
In file included from /System/Library/Frameworks/MetalPerformancePrimitives.framework/Headers/MPPTensorOpsMatMul2d.h:368:
/System/Library/Frameworks/MetalPerformancePrimitives.framework/Headers/__impl/MPPTensorOpsMatMul2dImpl.h:3267:5: error: static_assert failed due to requirement '__tensor_ops_detail::__is_same_v<half, bfloat>' "Input types must match cooperative tensor types"
    static_assert(__tensor_ops_detail::__is_same_v<_rightType, rightValueType>, "Input types must match cooperative tensor types");
    ^             ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
" UserInfo={NSLocalizedDescription=program_source:7131:28: warning: variable 'theta_base' is used uninitialized whenever 'if' condition is false [-Wsometimes-uninitialized]
                } else if (sector % 3 == 0 && sector < 3 * args.sect_0) { // t
                           ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
program_source:7251:76: note: in instantiation of function template specialization 'kernel_rope_multi<float>' requested here
template [[host_name("kernel_rope_multi_f32")]] kernel kernel_rope_multi_t kernel_rope_multi<float>;
                                                                           ^
program_source:7149:33: note: uninitialized use occurs here
            const float theta = theta_base * pow(args.freq_base, inv_ndims*i0);
                                ^~~~~~~~~~
program_source:7131:24: note: remove the 'if' if its condition is always true
                } else if (sector % 3 == 0 && sector < 3 * args.sect_0) { // t
                       ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
program_source:7131:28: warning: variable 'theta_base' is used uninitialized whenever '&&' condition is false [-Wsometimes-uninitialized]
                } else if (sector % 3 == 0 && sector < 3 * args.sect_0) { // t
                           ^~~~~~~~~~~~~~~
program_source:7149:33: note: uninitialized use occurs here
            const float theta = theta_base * pow(args.freq_base, inv_ndims*i0);
                                ^~~~~~~~~~
program_source:7131:28: note: remove the '&&' if its condition is always true
                } else if (sector % 3 == 0 && sector < 3 * args.sect_0) { // t
                           ^~~~~~~~~~~~~~~~~~
program_source:7125:29: note: initialize the variable 'theta_base' to silence this warning
            float theta_base;
                            ^
                             = 0.0
program_source:7131:28: warning: variable 'theta_base' is used uninitialized whenever 'if' condition is false [-Wsometimes-uninitialized]
                } else if (sector % 3 == 0 && sector < 3 * args.sect_0) { // t
                           ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
program_source:7252:76: note: in instantiation of function template specialization 'kernel_rope_multi<half>' requested here
template [[host_name("kernel_rope_multi_f16")]] kernel kernel_rope_multi_t kernel_rope_multi<half>;
                                                                           ^
program_source:7149:33: note: uninitialized use occurs here
            const float theta = theta_base * pow(args.freq_base, inv_ndims*i0);
                                ^~~~~~~~~~
program_source:7131:24: note: remove the 'if' if its condition is always true
                } else if (sector % 3 == 0 && sector < 3 * args.sect_0) { // t
                       ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
program_source:7131:28: warning: variable 'theta_base' is used uninitialized whenever '&&' condition is false [-Wsometimes-uninitialized]
                } else if (sector % 3 == 0 && sector < 3 * args.sect_0) { // t
                           ^~~~~~~~~~~~~~~
program_source:7149:33: note: uninitialized use occurs here
            const float theta = theta_base * pow(args.freq_base, inv_ndims*i0);
                                ^~~~~~~~~~
program_source:7131:28: note: remove the '&&' if its condition is always true
                } else if (sector % 3 == 0 && sector < 3 * args.sect_0) { // t
                           ^~~~~~~~~~~~~~~~~~
program_source:7125:29: note: initialize the variable 'theta_base' to silence this warning
            float theta_base;
                            ^
                             = 0.0
In file included from program_source:2837:
In file included from /System/Library/Frameworks/MetalPerformancePrimitives.framework/Headers/MetalPerformancePrimitives.h:10:
In file included from /System/Library/Frameworks/MetalPerformancePrimitives.framework/Headers/MPPTensorOpsMatMul2d.h:368:
/System/Library/Frameworks/MetalPerformancePrimitives.framework/Headers/__impl/MPPTensorOpsMatMul2dImpl.h:3266:5: error: static_assert failed due to requirement '__tensor_ops_detail::__is_same_v<bfloat, half>' "Input types must match cooperative tensor types"
    static_assert(__tensor_ops_detail::__is_same_v<_leftType, leftValueType>, "Input types must match cooperative tensor types");
    ^             ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
/System/Library/Frameworks/MetalPerformancePrimitives.framework/Headers/MPPTensorOpsMatMul2d.h:394:24: note: in instantiation of function template specialization 'mpp::tensor_ops::__mutmul2d_detail::__run<{32, 64, 32, false, true, false, 1}, metal::execution_simdgroups<4>, metal::tensor<threadgroup half, metal::extents<int, 18446744073709551615, 18446744073709551615>, metal::tensor_inline>, metal::tensor<threadgroup bfloat, metal::extents<int, 18446744073709551615, 18446744073709551615>, metal::tensor_inline>, metal::cooperative_tensor<float, metal::extents<int, 18446744073709551615, 18446744073709551615>, mpp::tensor_ops::__mutmul2d_detail::__operand_layout<{32, 64, 32, false, true, false, 1}, mpp::tensor_ops::__mutmul2d_detail::__matmul2d_cooperative_operand_index::destination, metal::execution_simdgroups<4>, bfloat, half, float, int>>>' requested here
    __mutmul2d_detail::__run<Descriptor, Scope, LeftOperandType,
                       ^
program_source:12147:12: note: in instantiation of function template specialization 'mpp::tensor_ops::matmul2d<{32, 64, 32, false, true, false, 1}, metal::execution_simdgroups<4>>::run<metal::tensor<threadgroup half, metal::extents<int, 18446744073709551615, 18446744073709551615>, metal::tensor_inline>, metal::tensor<threadgroup bfloat, metal::extents<int, 18446744073709551615, 18446744073709551615>, metal::tensor_inline>, metal::cooperative_tensor<float, metal::extents<int, 18446744073709551615, 18446744073709551615>, mpp::tensor_ops::__mutmul2d_detail::__operand_layout<{32, 64, 32, false, true, false, 1}, mpp::tensor_ops::__mutmul2d_detail::__matmul2d_cooperative_operand_index::destination, metal::execution_simdgroups<4>, bfloat, half, float, int>>, void>' requested here
        mm.run(sB, sA, cT);
           ^
In file included from program_source:2837:
In file included from /System/Library/Frameworks/MetalPerformancePrimitives.framework/Headers/MetalPerformancePrimitives.h:10:
In file included from /System/Library/Frameworks/MetalPerformancePrimitives.framework/Headers/MPPTensorOpsMatMul2d.h:368:
/System/Library/Frameworks/MetalPerformancePrimitives.framework/Headers/__impl/MPPTensorOpsMatMul2dImpl.h:3267:5: error: static_assert failed due to requirement '__tensor_ops_detail::__is_same_v<half, bfloat>' "Input types must match cooperative tensor types"
    static_assert(__tensor_ops_detail::__is_same_v<_rightType, rightValueType>, "Input types must match cooperative tensor types");
    ^             ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
}
ggml_metal_init: error: failed to initialize the Metal library
ggml_backend_metal_device_init: error: failed to allocate context
ggml-backend.cpp:258: GGML_ASSERT(backend) failed
WARNING: Using native backtrace. Set GGML_BACKTRACE_LLDB for more info.
WARNING: GGML_BACKTRACE_LLDB may cause native MacOS Terminal.app to crash.
See: https://github.com/ggml-org/llama.cpp/pull/17869
0   ollama                              0x0000000105ce1958 ggml_print_backtrace + 276
1   ollama                              0x0000000105ce1b44 ggml_abort + 156
2   ollama                              0x0000000105cfb444 ggml_backend_get_default_buffer_type + 76
3   ollama                              0x0000000105c77738 _cgo_c81fd19bee02_Cfunc_ggml_backend_get_default_buffer_type + 36
4   ollama                              0x0000000104da06ac ollama + 509612
SIGABRT: abort
PC=0x19bb7f5b0 m=13 sigcode=0
signal arrived during cgo execution

goroutine 12 gp=0x14000602c40 m=13 mp=0x14000601008 [syscall]:
runtime.cgocall(0x105c77714, 0x14000046c88)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/cgocall.go:167 +0x44 fp=0x14000046c50 sp=0x14000046c10 pc=0x104d94d24
github.com/ollama/ollama/ml/backend/ggml._Cfunc_ggml_backend_get_default_buffer_type(0x0)
	_cgo_gotypes.go:878 +0x34 fp=0x14000046c80 sp=0x14000046c50 pc=0x105233614
github.com/ollama/ollama/ml/backend/ggml.New.func17(...)
	/Users/runner/work/ollama/ollama/ml/backend/ggml/ggml.go:361
github.com/ollama/ollama/ml/backend/ggml.New({0x16b0db9cd, 0x6c}, {0x0, 0x4, {0x10706f8a0, 0x0, 0x0}, 0x1})
	/Users/runner/work/ollama/ollama/ml/backend/ggml/ggml.go:361 +0x12e0 fp=0x14000047540 sp=0x14000046c80 pc=0x105239b40
github.com/ollama/ollama/ml.NewBackend({0x16b0db9cd, 0x6c}, {0x0, 0x4, {0x10706f8a0, 0x0, 0x0}, 0x1})
	/Users/runner/work/ollama/ollama/ml/backend.go:88 +0x88 fp=0x14000047590 sp=0x14000047540 pc=0x1051e1ba8
github.com/ollama/ollama/model.New({0x16b0db9cd?, 0x0?}, {0x0, 0x4, {0x10706f8a0, 0x0, 0x0}, 0x1})
	/Users/runner/work/ollama/ollama/model/model.go:120 +0x50 fp=0x14000047660 sp=0x14000047590 pc=0x105277820
github.com/ollama/ollama/runner/ollamarunner.(*Server).allocModel(0x1400014c5a0, {0x16b0db9cd?, 0x0?}, {0x0, 0x4, {0x10706f8a0, 0x0, 0x0}, 0x1}, {0x0?, ...}, ...)
	/Users/runner/work/ollama/ollama/runner/ollamarunner/runner.go:1202 +0xac fp=0x14000047710 sp=0x14000047660 pc=0x10534177c
github.com/ollama/ollama/runner/ollamarunner.(*Server).load(0x1400014c5a0, {0x106562740, 0x140000fec40}, 0x14000394c80)
	/Users/runner/work/ollama/ollama/runner/ollamarunner/runner.go:1317 +0x460 fp=0x14000047aa0 sp=0x14000047710 pc=0x105342380
github.com/ollama/ollama/runner/ollamarunner.(*Server).load-fm({0x106562740?, 0x140000fec40?}, 0x140004e7b28?)
	<autogenerated>:1 +0x40 fp=0x14000047ad0 sp=0x14000047aa0 pc=0x105344230
net/http.HandlerFunc.ServeHTTP(0x14000153800?, {0x106562740?, 0x140000fec40?}, 0x140004e7b10?)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/net/http/server.go:2294 +0x38 fp=0x14000047b00 sp=0x14000047ad0 pc=0x105060778
net/http.(*ServeMux).ServeHTTP(0x10?, {0x106562740, 0x140000fec40}, 0x14000394c80)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/net/http/server.go:2822 +0x1b4 fp=0x14000047b50 sp=0x14000047b00 pc=0x105062304
net/http.serverHandler.ServeHTTP({0x10655e7b0?}, {0x106562740?, 0x140000fec40?}, 0x1?)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/net/http/server.go:3301 +0xbc fp=0x14000047b80 sp=0x14000047b50 pc=0x10507dfec
net/http.(*conn).serve(0x140004c0510, {0x106564fc8, 0x14000681860})
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/net/http/server.go:2102 +0x52c fp=0x14000047fa0 sp=0x14000047b80 pc=0x10505ef1c
net/http.(*Server).Serve.gowrap3()
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/net/http/server.go:3454 +0x30 fp=0x14000047fd0 sp=0x14000047fa0 pc=0x1050640e0
runtime.goexit({})
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x14000047fd0 sp=0x14000047fd0 pc=0x104da08b4
created by net/http.(*Server).Serve in goroutine 1
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/net/http/server.go:3454 +0x3d8

goroutine 1 gp=0x140000021c0 m=nil [IO wait]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x14001605710 sp=0x140016056f0 pc=0x104d98248
runtime.netpollblock(0x140001257a8?, 0x4e1d050?, 0x1?)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/netpoll.go:575 +0x158 fp=0x14001605750 sp=0x14001605710 pc=0x104d5dca8
internal/poll.runtime_pollWait(0x15288db10, 0x72)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/netpoll.go:351 +0xa0 fp=0x14001605780 sp=0x14001605750 pc=0x104d97400
internal/poll.(*pollDesc).wait(0x14000507480?, 0x104e1f2b8?, 0x0)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/internal/poll/fd_poll_runtime.go:84 +0x28 fp=0x140016057b0 sp=0x14001605780 pc=0x104e18868
internal/poll.(*pollDesc).waitRead(...)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/internal/poll/fd_poll_runtime.go:89
internal/poll.(*FD).Accept(0x14000507480)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/internal/poll/fd_unix.go:620 +0x24c fp=0x14001605860 sp=0x140016057b0 pc=0x104e1d13c
net.(*netFD).accept(0x14000507480)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/net/fd_unix.go:172 +0x28 fp=0x14001605920 sp=0x14001605860 pc=0x104e8d478
net.(*TCPListener).accept(0x140003eb2c0)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/net/tcpsock_posix.go:159 +0x24 fp=0x14001605970 sp=0x14001605920 pc=0x104ea1c54
net.(*TCPListener).Accept(0x140003eb2c0)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/net/tcpsock.go:380 +0x2c fp=0x140016059b0 sp=0x14001605970 pc=0x104ea0c3c
net/http.(*onceCloseListener).Accept(0x140004c0510?)
	<autogenerated>:1 +0x30 fp=0x140016059d0 sp=0x140016059b0 pc=0x10508a610
net/http.(*Server).Serve(0x140001f1b00, {0x106562560, 0x140003eb2c0})
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/net/http/server.go:3424 +0x290 fp=0x14001605b00 sp=0x140016059d0 pc=0x105063d50
github.com/ollama/ollama/runner/ollamarunner.Execute({0x140000320a0, 0x4, 0x4})
	/Users/runner/work/ollama/ollama/runner/ollamarunner/runner.go:1453 +0x7fc fp=0x14001605cd0 sp=0x14001605b00 pc=0x105343c5c
github.com/ollama/ollama/runner.Execute({0x14000032080?, 0x0?, 0x0?})
	/Users/runner/work/ollama/ollama/runner/runner.go:18 +0x14c fp=0x14001605d10 sp=0x14001605cd0 pc=0x1053d720c
github.com/ollama/ollama/cmd.NewCLI.func3(0x140001f1800?, {0x105f98f8a?, 0x4?, 0x105f98f8e?})
	/Users/runner/work/ollama/ollama/cmd/cmd.go:2267 +0x54 fp=0x14001605d40 sp=0x14001605d10 pc=0x105aedb14
github.com/spf13/cobra.(*Command).execute(0x140004c7b08, {0x14000370fa0, 0x5, 0x5})
	/Users/runner/go/pkg/mod/github.com/spf13/cobra@v1.7.0/command.go:940 +0x648 fp=0x14001605e60 sp=0x14001605d40 pc=0x104efc318
github.com/spf13/cobra.(*Command).ExecuteC(0x1400015b508)
	/Users/runner/go/pkg/mod/github.com/spf13/cobra@v1.7.0/command.go:1068 +0x320 fp=0x14001605f20 sp=0x14001605e60 pc=0x104efca60
github.com/spf13/cobra.(*Command).Execute(...)
	/Users/runner/go/pkg/mod/github.com/spf13/cobra@v1.7.0/command.go:992
github.com/spf13/cobra.(*Command).ExecuteContext(...)
	/Users/runner/go/pkg/mod/github.com/spf13/cobra@v1.7.0/command.go:985
main.main()
	/Users/runner/work/ollama/ollama/main.go:12 +0x54 fp=0x14001605f40 sp=0x14001605f20 pc=0x105aef294
runtime.main()
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:283 +0x284 fp=0x14001605fd0 sp=0x14001605f40 pc=0x104d64814
runtime.goexit({})
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x14001605fd0 sp=0x14001605fd0 pc=0x104da08b4

goroutine 2 gp=0x14000002c40 m=nil [force gc (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x14000070f90 sp=0x14000070f70 pc=0x104d98248
runtime.goparkunlock(...)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:441
runtime.forcegchelper()
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:348 +0xb8 fp=0x14000070fd0 sp=0x14000070f90 pc=0x104d64b68
runtime.goexit({})
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x14000070fd0 sp=0x14000070fd0 pc=0x104da08b4
created by runtime.init.7 in goroutine 1
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:336 +0x24

goroutine 3 gp=0x14000003180 m=nil [GC sweep wait]:
runtime.gopark(0x1?, 0x0?, 0x0?, 0x0?, 0x0?)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x14000071760 sp=0x14000071740 pc=0x104d98248
runtime.goparkunlock(...)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:441
runtime.bgsweep(0x1400009c000)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgcsweep.go:316 +0x108 fp=0x140000717b0 sp=0x14000071760 pc=0x104d4fc48
runtime.gcenable.gowrap1()
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:204 +0x28 fp=0x140000717d0 sp=0x140000717b0 pc=0x104d43a48
runtime.goexit({})
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x140000717d0 sp=0x140000717d0 pc=0x104da08b4
created by runtime.gcenable in goroutine 1
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:204 +0x6c

goroutine 4 gp=0x14000003340 m=nil [GC scavenge wait]:
runtime.gopark(0x10000?, 0x1061be068?, 0x0?, 0x0?, 0x0?)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x14000071f60 sp=0x14000071f40 pc=0x104d98248
runtime.goparkunlock(...)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:441
runtime.(*scavengerState).park(0x107024820)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgcscavenge.go:425 +0x5c fp=0x14000071f90 sp=0x14000071f60 pc=0x104d4d6dc
runtime.bgscavenge(0x1400009c000)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgcscavenge.go:658 +0xac fp=0x14000071fb0 sp=0x14000071f90 pc=0x104d4dc7c
runtime.gcenable.gowrap2()
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:205 +0x28 fp=0x14000071fd0 sp=0x14000071fb0 pc=0x104d439e8
runtime.goexit({})
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x14000071fd0 sp=0x14000071fd0 pc=0x104da08b4
created by runtime.gcenable in goroutine 1
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:205 +0xac

goroutine 5 gp=0x14000003c00 m=nil [finalizer wait]:
runtime.gopark(0x18000705c8?, 0x1071bbef0?, 0x8?, 0x1?, 0x1c0?)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x14000070590 sp=0x14000070570 pc=0x104d98248
runtime.runfinq()
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mfinal.go:196 +0x108 fp=0x140000707d0 sp=0x14000070590 pc=0x104d42a48
runtime.goexit({})
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x140000707d0 sp=0x140000707d0 pc=0x104da08b4
created by runtime.createfing in goroutine 1
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mfinal.go:166 +0x80

goroutine 6 gp=0x140001dc700 m=nil [chan receive]:
runtime.gopark(0x140000f9cc0?, 0x1400000e198?, 0x48?, 0x27?, 0x104e615a8?)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x140000726f0 sp=0x140000726d0 pc=0x104d98248
runtime.chanrecv(0x1400003c540, 0x0, 0x1)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/chan.go:664 +0x42c fp=0x14000072770 sp=0x140000726f0 pc=0x104d34cec
runtime.chanrecv1(0x0?, 0x0?)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/chan.go:506 +0x14 fp=0x140000727a0 sp=0x14000072770 pc=0x104d34884
runtime.unique_runtime_registerUniqueMapCleanup.func2(...)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1796
runtime.unique_runtime_registerUniqueMapCleanup.gowrap1()
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1799 +0x3c fp=0x140000727d0 sp=0x140000727a0 pc=0x104d46c6c
runtime.goexit({})
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x140000727d0 sp=0x140000727d0 pc=0x104da08b4
created by unique.runtime_registerUniqueMapCleanup in goroutine 1
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1794 +0x78

goroutine 7 gp=0x140001dca80 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x14000072f10 sp=0x14000072ef0 pc=0x104d98248
runtime.gcBgMarkWorker(0x1400003d960)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1423 +0xdc fp=0x14000072fb0 sp=0x14000072f10 pc=0x104d45edc
runtime.gcBgMarkStartWorkers.gowrap1()
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x28 fp=0x14000072fd0 sp=0x14000072fb0 pc=0x104d45dc8
runtime.goexit({})
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x14000072fd0 sp=0x14000072fd0 pc=0x104da08b4
created by runtime.gcBgMarkStartWorkers in goroutine 1
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x140

goroutine 18 gp=0x14000504000 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x1400006c710 sp=0x1400006c6f0 pc=0x104d98248
runtime.gcBgMarkWorker(0x1400003d960)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1423 +0xdc fp=0x1400006c7b0 sp=0x1400006c710 pc=0x104d45edc
runtime.gcBgMarkStartWorkers.gowrap1()
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x28 fp=0x1400006c7d0 sp=0x1400006c7b0 pc=0x104d45dc8
runtime.goexit({})
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x1400006c7d0 sp=0x1400006c7d0 pc=0x104da08b4
created by runtime.gcBgMarkStartWorkers in goroutine 1
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x140

goroutine 34 gp=0x14000102380 m=nil [GC worker (idle)]:
runtime.gopark(0x107071f00?, 0x1?, 0x48?, 0x83?, 0x0?)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x1400011a710 sp=0x1400011a6f0 pc=0x104d98248
runtime.gcBgMarkWorker(0x1400003d960)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1423 +0xdc fp=0x1400011a7b0 sp=0x1400011a710 pc=0x104d45edc
runtime.gcBgMarkStartWorkers.gowrap1()
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x28 fp=0x1400011a7d0 sp=0x1400011a7b0 pc=0x104d45dc8
runtime.goexit({})
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x1400011a7d0 sp=0x1400011a7d0 pc=0x104da08b4
created by runtime.gcBgMarkStartWorkers in goroutine 1
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x140

goroutine 8 gp=0x140001dcc40 m=nil [GC worker (idle)]:
runtime.gopark(0x6c4b98c37f8?, 0x0?, 0x0?, 0x0?, 0x0?)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x14000073710 sp=0x140000736f0 pc=0x104d98248
runtime.gcBgMarkWorker(0x1400003d960)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1423 +0xdc fp=0x140000737b0 sp=0x14000073710 pc=0x104d45edc
runtime.gcBgMarkStartWorkers.gowrap1()
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x28 fp=0x140000737d0 sp=0x140000737b0 pc=0x104d45dc8
runtime.goexit({})
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x140000737d0 sp=0x140000737d0 pc=0x104da08b4
created by runtime.gcBgMarkStartWorkers in goroutine 1
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x140

goroutine 19 gp=0x140005041c0 m=nil [GC worker (idle)]:
runtime.gopark(0x6c4b98c12b2?, 0x3?, 0xb2?, 0x6f?, 0x0?)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x1400006cf10 sp=0x1400006cef0 pc=0x104d98248
runtime.gcBgMarkWorker(0x1400003d960)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1423 +0xdc fp=0x1400006cfb0 sp=0x1400006cf10 pc=0x104d45edc
runtime.gcBgMarkStartWorkers.gowrap1()
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x28 fp=0x1400006cfd0 sp=0x1400006cfb0 pc=0x104d45dc8
runtime.goexit({})
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x1400006cfd0 sp=0x1400006cfd0 pc=0x104da08b4
created by runtime.gcBgMarkStartWorkers in goroutine 1
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x140

goroutine 35 gp=0x14000102540 m=nil [GC worker (idle)]:
runtime.gopark(0x6c4b98c1811?, 0x3?, 0xc6?, 0x55?, 0x0?)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x1400011af10 sp=0x1400011aef0 pc=0x104d98248
runtime.gcBgMarkWorker(0x1400003d960)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1423 +0xdc fp=0x1400011afb0 sp=0x1400011af10 pc=0x104d45edc
runtime.gcBgMarkStartWorkers.gowrap1()
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x28 fp=0x1400011afd0 sp=0x1400011afb0 pc=0x104d45dc8
runtime.goexit({})
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x1400011afd0 sp=0x1400011afd0 pc=0x104da08b4
created by runtime.gcBgMarkStartWorkers in goroutine 1
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x140

goroutine 9 gp=0x140001dce00 m=nil [GC worker (idle)]:
runtime.gopark(0x107071f00?, 0x3?, 0x45?, 0xa2?, 0x0?)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x14000073f10 sp=0x14000073ef0 pc=0x104d98248
runtime.gcBgMarkWorker(0x1400003d960)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1423 +0xdc fp=0x14000073fb0 sp=0x14000073f10 pc=0x104d45edc
runtime.gcBgMarkStartWorkers.gowrap1()
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x28 fp=0x14000073fd0 sp=0x14000073fb0 pc=0x104d45dc8
runtime.goexit({})
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x14000073fd0 sp=0x14000073fd0 pc=0x104da08b4
created by runtime.gcBgMarkStartWorkers in goroutine 1
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x140

goroutine 20 gp=0x14000504380 m=nil [GC worker (idle)]:
runtime.gopark(0x107071f00?, 0x1?, 0xa9?, 0xd5?, 0x0?)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x1400006d710 sp=0x1400006d6f0 pc=0x104d98248
runtime.gcBgMarkWorker(0x1400003d960)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1423 +0xdc fp=0x1400006d7b0 sp=0x1400006d710 pc=0x104d45edc
runtime.gcBgMarkStartWorkers.gowrap1()
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x28 fp=0x1400006d7d0 sp=0x1400006d7b0 pc=0x104d45dc8
runtime.goexit({})
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x1400006d7d0 sp=0x1400006d7d0 pc=0x104da08b4
created by runtime.gcBgMarkStartWorkers in goroutine 1
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x140

goroutine 36 gp=0x14000102700 m=nil [GC worker (idle)]:
runtime.gopark(0x6c4b98bea7e?, 0x1?, 0xc?, 0x6e?, 0x0?)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x1400011b710 sp=0x1400011b6f0 pc=0x104d98248
runtime.gcBgMarkWorker(0x1400003d960)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1423 +0xdc fp=0x1400011b7b0 sp=0x1400011b710 pc=0x104d45edc
runtime.gcBgMarkStartWorkers.gowrap1()
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x28 fp=0x1400011b7d0 sp=0x1400011b7b0 pc=0x104d45dc8
runtime.goexit({})
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x1400011b7d0 sp=0x1400011b7d0 pc=0x104da08b4
created by runtime.gcBgMarkStartWorkers in goroutine 1
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x140

goroutine 10 gp=0x140001dcfc0 m=nil [GC worker (idle)]:
runtime.gopark(0x6c4b99d26c4?, 0x3?, 0xe9?, 0x6c?, 0x0?)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x14000116710 sp=0x140001166f0 pc=0x104d98248
runtime.gcBgMarkWorker(0x1400003d960)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1423 +0xdc fp=0x140001167b0 sp=0x14000116710 pc=0x104d45edc
runtime.gcBgMarkStartWorkers.gowrap1()
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x28 fp=0x140001167d0 sp=0x140001167b0 pc=0x104d45dc8
runtime.goexit({})
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x140001167d0 sp=0x140001167d0 pc=0x104da08b4
created by runtime.gcBgMarkStartWorkers in goroutine 1
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x140

goroutine 11 gp=0x14000602a80 m=nil [sync.WaitGroup.Wait]:
runtime.gopark(0x10703acc0?, 0x0?, 0x0?, 0xc0?, 0x0?)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x14000083a90 sp=0x14000083a70 pc=0x104d98248
runtime.goparkunlock(...)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:441
runtime.semacquire1(0x1400014c658, 0x0, 0x1, 0x0, 0x18)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/sema.go:188 +0x204 fp=0x14000083ae0 sp=0x14000083a90 pc=0x104d78cf4
sync.runtime_SemacquireWaitGroup(0x0?)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/sema.go:110 +0x2c fp=0x14000083b20 sp=0x14000083ae0 pc=0x104d99cbc
sync.(*WaitGroup).Wait(0x1400014c650)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/sync/waitgroup.go:118 +0x70 fp=0x14000083b40 sp=0x14000083b20 pc=0x104dac2b0
github.com/ollama/ollama/runner/ollamarunner.(*Server).run(0x1400014c5a0, {0x106565000, 0x14000371040})
	/Users/runner/work/ollama/ollama/runner/ollamarunner/runner.go:442 +0x38 fp=0x14000083fa0 sp=0x14000083b40 pc=0x10533bf68
github.com/ollama/ollama/runner/ollamarunner.Execute.gowrap1()
	/Users/runner/work/ollama/ollama/runner/ollamarunner/runner.go:1430 +0x30 fp=0x14000083fd0 sp=0x14000083fa0 pc=0x105343e80
runtime.goexit({})
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x14000083fd0 sp=0x14000083fd0 pc=0x104da08b4
created by github.com/ollama/ollama/runner/ollamarunner.Execute in goroutine 1
	/Users/runner/work/ollama/ollama/runner/ollamarunner/runner.go:1430 +0x448

goroutine 14 gp=0x14000602e00 m=nil [IO wait]:
runtime.gopark(0xffffffffffffffff?, 0xffffffffffffffff?, 0x23?, 0x0?, 0x104dbc4b0?)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x14000119580 sp=0x14000119560 pc=0x104d98248
runtime.netpollblock(0x0?, 0x0?, 0x0?)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/netpoll.go:575 +0x158 fp=0x140001195c0 sp=0x14000119580 pc=0x104d5dca8
internal/poll.runtime_pollWait(0x15288d9f8, 0x72)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/netpoll.go:351 +0xa0 fp=0x140001195f0 sp=0x140001195c0 pc=0x104d97400
internal/poll.(*pollDesc).wait(0x14000507500?, 0x14000681961?, 0x0)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/internal/poll/fd_poll_runtime.go:84 +0x28 fp=0x14000119620 sp=0x140001195f0 pc=0x104e18868
internal/poll.(*pollDesc).waitRead(...)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/internal/poll/fd_poll_runtime.go:89
internal/poll.(*FD).Read(0x14000507500, {0x14000681961, 0x1, 0x1})
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/internal/poll/fd_unix.go:165 +0x1fc fp=0x140001196c0 sp=0x14000119620 pc=0x104e19b1c
net.(*netFD).Read(0x14000507500, {0x14000681961?, 0x14000119758?, 0x105059994?})
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/net/fd_posix.go:55 +0x28 fp=0x14000119710 sp=0x140001196c0 pc=0x104e8ba48
net.(*conn).Read(0x14000136638, {0x14000681961?, 0x0?, 0x0?})
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/net/net.go:194 +0x34 fp=0x14000119760 sp=0x14000119710 pc=0x104e98914
net/http.(*connReader).backgroundRead(0x14000681950)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/net/http/server.go:690 +0x40 fp=0x140001197b0 sp=0x14000119760 pc=0x105059890
net/http.(*connReader).startBackgroundRead.gowrap2()
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/net/http/server.go:686 +0x28 fp=0x140001197d0 sp=0x140001197b0 pc=0x105059778
runtime.goexit({})
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x140001197d0 sp=0x140001197d0 pc=0x104da08b4
created by net/http.(*connReader).startBackgroundRead in goroutine 12
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/net/http/server.go:686 +0xc4

r0      0x0
r1      0x0
r2      0x0
r3      0x0
r4      0x19bac1a08
r5      0x171165d20
r6      0x32
r7      0x0
r8      0xacdd3d7f0a78f2f5
r9      0xacdd3d7e7b6e82f5
r10     0x2
r11     0x10000000000
r12     0xfffffffd
r13     0x0
r14     0x0
r15     0x0
r16     0x148
r17     0x20a098990
r18     0x0
r19     0x6
r20     0x1703
r21     0x1711670e0
r22     0x0
r23     0x0
r24     0x0
r25     0x14000066198
r26     0x10654b868
r27     0x818
r28     0x14000103180
r29     0x171166610
lr      0x19bbb9888
sp      0x1711665f0
pc      0x19bb7f5b0
fault   0x19bb7f5b0
time=2026-04-10T11:25:23.220+08:00 level=ERROR source=server.go:1219 msg="do load request" error="Post \"http://127.0.0.1:59329/load\": EOF"
time=2026-04-10T11:25:23.220+08:00 level=ERROR source=server.go:316 msg="llama runner terminated" error="exit status 2"
time=2026-04-10T11:25:23.220+08:00 level=ERROR source=server.go:1219 msg="do load request" error="Post \"http://127.0.0.1:59329/load\": dial tcp 127.0.0.1:59329: connect: connection refused"
time=2026-04-10T11:25:23.220+08:00 level=INFO source=sched.go:511 msg="Load failed" model=/Users/hedaihua/.ollama/models/blobs/sha256-7121486771cbfe218851513210c40b35dbdee93ab1ef43fe36283c883980f0df error="model failed to load, this may be due to resource limitations or an internal error, check ollama server logs for details"
[GIN] 2026/04/10 - 11:25:23 | 500 |  2.208098792s |       127.0.0.1 | POST     "/api/chat"
[GIN] 2026/04/10 - 11:25:50 | 200 |    1.271875ms |       127.0.0.1 | GET      "/api/tags"

OS

macOS

GPU

Apple

CPU

Apple

Ollama version

0.20.4 and 0.20.5

Originally created by @dht-hedaihua on GitHub (Apr 10, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/15470 ### What is the issue? Based on the logs you provided, Ollama encountered a low-level crash (SIGABRT) while loading a model on your macOS system with Apple Silicon (the logs indicate an Apple M5). **Root cause analysis:** The direct cause of the crash is a shader compilation failure in the GPU (Metal) driver layer. Specifically, this segment from the logs: ``` error: static_assert failed due to requirement '__tensor_ops_detail::__is_same_v<bfloat, half>' "Input types must match cooperative tensor types" ``` This indicates that when Ollama’s underlying inference engine (llama.cpp) attempted to initialize Apple’s Metal GPU acceleration library, the Metal compiler (Metal Performance Primitives) rejected the code. The compiler strictly requires that tensor types in matrix multiplication match (here it found a mix of `bfloat` and `half` / `float16` data types), causing `ggml_metal_init` to fail and the program to abort. Given that your device is reported as an M5 and running a very recent environment, this typically occurs when a new version (or beta release) of macOS has tightened the validation of Metal API code conventions, making the current version of Ollama/llama.cpp incompatible. <img width="176" height="96" alt="Image" src="https://github.com/user-attachments/assets/56b24794-d418-4407-98dd-d7d5c12f6df5" /> ### Relevant log output ```shell time=2026-04-10T11:25:15.072+08:00 level=INFO source=routes.go:1744 msg="server config" env="map[HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:65536 OLLAMA_DEBUG:INFO OLLAMA_DEBUG_LOG_REQUESTS:false OLLAMA_EDITOR: OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/Users/hedaihua/.ollama/models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NO_CLOUD:true OLLAMA_NUM_PARALLEL:1 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://* vscode-file://*] OLLAMA_REMOTES:[ollama.com] OLLAMA_SCHED_SPREAD:false http_proxy: https_proxy: no_proxy:]" time=2026-04-10T11:25:15.073+08:00 level=INFO source=routes.go:1746 msg="Ollama cloud disabled: true" time=2026-04-10T11:25:15.074+08:00 level=INFO source=images.go:499 msg="total blobs: 8" time=2026-04-10T11:25:15.074+08:00 level=INFO source=images.go:506 msg="total unused blobs removed: 0" time=2026-04-10T11:25:15.074+08:00 level=INFO source=routes.go:1802 msg="Listening on 127.0.0.1:11434 (version 0.20.4)" time=2026-04-10T11:25:15.075+08:00 level=INFO source=runner.go:67 msg="discovering available GPUs..." time=2026-04-10T11:25:15.077+08:00 level=INFO source=server.go:444 msg="starting runner" cmd="/private/var/folders/6r/wc7km6294llbshkqy9c4hgw80000gn/T/AppTranslocation/70F21D0A-0093-45A5-9195-88CFF0181E67/d/Ollama.app/Contents/Resources/ollama runner --ollama-engine --port 59312" time=2026-04-10T11:25:17.227+08:00 level=INFO source=types.go:60 msg="inference compute" id=cpu library=cpu compute="" name=cpu description=cpu libdirs=ollama driver="" pci_id="" type="" total="32.0 GiB" available="9.0 GiB" time=2026-04-10T11:25:17.227+08:00 level=INFO source=routes.go:1852 msg="vram-based default context" total_vram="0 B" default_num_ctx=4096 [GIN] 2026/04/10 - 11:25:17 | 200 | 152.5µs | 127.0.0.1 | GET "/api/version" [GIN] 2026/04/10 - 11:25:17 | 200 | 112.208µs | 127.0.0.1 | GET "/api/version" [GIN] 2026/04/10 - 11:25:17 | 200 | 291.709��s | 127.0.0.1 | GET "/api/version" [GIN] 2026/04/10 - 11:25:17 | 200 | 1.440042ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/04/10 - 11:25:17 | 200 | 113.25525ms | 127.0.0.1 | POST "/api/show" [GIN] 2026/04/10 - 11:25:18 | 401 | 871.861667ms | 127.0.0.1 | POST "/api/me" [GIN] 2026/04/10 - 11:25:18 | 401 | 874.498ms | 127.0.0.1 | POST "/api/me" [GIN] 2026/04/10 - 11:25:20 | 200 | 633µs | 127.0.0.1 | GET "/api/tags" [GIN] 2026/04/10 - 11:25:20 | 200 | 139.930584ms | 127.0.0.1 | POST "/api/show" [GIN] 2026/04/10 - 11:25:21 | 200 | 104.620541ms | 127.0.0.1 | POST "/api/show" time=2026-04-10T11:25:21.175+08:00 level=INFO source=model.go:97 msg="gemma4: token IDs" image=255999 image_end=258882 audio=256000 audio_end=258883 time=2026-04-10T11:25:21.175+08:00 level=INFO source=server.go:259 msg="enabling flash attention" time=2026-04-10T11:25:21.176+08:00 level=INFO source=server.go:444 msg="starting runner" cmd="/private/var/folders/6r/wc7km6294llbshkqy9c4hgw80000gn/T/AppTranslocation/70F21D0A-0093-45A5-9195-88CFF0181E67/d/Ollama.app/Contents/Resources/ollama runner --ollama-engine --model /Users/hedaihua/.ollama/models/blobs/sha256-7121486771cbfe218851513210c40b35dbdee93ab1ef43fe36283c883980f0df --port 59329" time=2026-04-10T11:25:21.177+08:00 level=INFO source=sched.go:484 msg="system memory" total="32.0 GiB" free="9.1 GiB" free_swap="0 B" time=2026-04-10T11:25:21.177+08:00 level=INFO source=server.go:771 msg="loading model" "model layers"=31 requested=-1 time=2026-04-10T11:25:21.185+08:00 level=INFO source=runner.go:1417 msg="starting ollama engine" time=2026-04-10T11:25:21.185+08:00 level=INFO source=runner.go:1452 msg="Server listening on 127.0.0.1:59329" time=2026-04-10T11:25:21.188+08:00 level=INFO source=runner.go:1290 msg=load request="{Operation:fit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:65536 KvCacheType: NumThreads:4 GPULayers:[] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" time=2026-04-10T11:25:21.213+08:00 level=INFO source=ggml.go:136 msg="" architecture=gemma4 file_type=Q4_K_M name="" description="" num_tensors=1014 num_key_values=52 ggml_metal_device_init: testing tensor API for f16 support ggml_metal_device_init: testing tensor API for bfloat support ggml_metal_library_init: using embedded metal library ggml_metal_library_init: error: Error Domain=MTLLibraryErrorDomain Code=3 "program_source:7131:28: warning: variable 'theta_base' is used uninitialized whenever 'if' condition is false [-Wsometimes-uninitialized] } else if (sector % 3 == 0 && sector < 3 * args.sect_0) { // t ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ program_source:7251:76: note: in instantiation of function template specialization 'kernel_rope_multi<float>' requested here template [[host_name("kernel_rope_multi_f32")]] kernel kernel_rope_multi_t kernel_rope_multi<float>; ^ program_source:7149:33: note: uninitialized use occurs here const float theta = theta_base * pow(args.freq_base, inv_ndims*i0); ^~~~~~~~~~ program_source:7131:24: note: remove the 'if' if its condition is always true } else if (sector % 3 == 0 && sector < 3 * args.sect_0) { // t ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ program_source:7131:28: warning: variable 'theta_base' is used uninitialized whenever '&&' condition is false [-Wsometimes-uninitialized] } else if (sector % 3 == 0 && sector < 3 * args.sect_0) { // t ^~~~~~~~~~~~~~~ program_source:7149:33: note: uninitialized use occurs here const float theta = theta_base * pow(args.freq_base, inv_ndims*i0); ^~~~~~~~~~ program_source:7131:28: note: remove the '&&' if its condition is always true } else if (sector % 3 == 0 && sector < 3 * args.sect_0) { // t ^~~~~~~~~~~~~~~~~~ program_source:7125:29: note: initialize the variable 'theta_base' to silence this warning float theta_base; ^ = 0.0 program_source:7131:28: warning: variable 'theta_base' is used uninitialized whenever 'if' condition is false [-Wsometimes-uninitialized] } else if (sector % 3 == 0 && sector < 3 * args.sect_0) { // t ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ program_source:7252:76: note: in instantiation of function template specialization 'kernel_rope_multi<half>' requested here template [[host_name("kernel_rope_multi_f16")]] kernel kernel_rope_multi_t kernel_rope_multi<half>; ^ program_source:7149:33: note: uninitialized use occurs here const float theta = theta_base * pow(args.freq_base, inv_ndims*i0); ^~~~~~~~~~ program_source:7131:24: note: remove the 'if' if its condition is always true } else if (sector % 3 == 0 && sector < 3 * args.sect_0) { // t ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ program_source:7131:28: warning: variable 'theta_base' is used uninitialized whenever '&&' condition is false [-Wsometimes-uninitialized] } else if (sector % 3 == 0 && sector < 3 * args.sect_0) { // t ^~~~~~~~~~~~~~~ program_source:7149:33: note: uninitialized use occurs here const float theta = theta_base * pow(args.freq_base, inv_ndims*i0); ^~~~~~~~~~ program_source:7131:28: note: remove the '&&' if its condition is always true } else if (sector % 3 == 0 && sector < 3 * args.sect_0) { // t ^~~~~~~~~~~~~~~~~~ program_source:7125:29: note: initialize the variable 'theta_base' to silence this warning float theta_base; ^ = 0.0 In file included from program_source:2837: In file included from /System/Library/Frameworks/MetalPerformancePrimitives.framework/Headers/MetalPerformancePrimitives.h:10: In file included from /System/Library/Frameworks/MetalPerformancePrimitives.framework/Headers/MPPTensorOpsMatMul2d.h:368: /System/Library/Frameworks/MetalPerformancePrimitives.framework/Headers/__impl/MPPTensorOpsMatMul2dImpl.h:3266:5: error: static_assert failed due to requirement '__tensor_ops_detail::__is_same_v<bfloat, half>' "Input types must match cooperative tensor types" static_assert(__tensor_ops_detail::__is_same_v<_leftType, leftValueType>, "Input types must match cooperative tensor types"); ^ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ /System/Library/Frameworks/MetalPerformancePrimitives.framework/Headers/MPPTensorOpsMatMul2d.h:394:24: note: in instantiation of function template specialization 'mpp::tensor_ops::__mutmul2d_detail::__run<{32, 64, 32, false, true, false, 1}, metal::execution_simdgroups<4>, metal::tensor<threadgroup half, metal::extents<int, 18446744073709551615, 18446744073709551615>, metal::tensor_inline>, metal::tensor<threadgroup bfloat, metal::extents<int, 18446744073709551615, 18446744073709551615>, metal::tensor_inline>, metal::cooperative_tensor<float, metal::extents<int, 18446744073709551615, 18446744073709551615>, mpp::tensor_ops::__mutmul2d_detail::__operand_layout<{32, 64, 32, false, true, false, 1}, mpp::tensor_ops::__mutmul2d_detail::__matmul2d_cooperative_operand_index::destination, metal::execution_simdgroups<4>, bfloat, half, float, int>>>' requested here __mutmul2d_detail::__run<Descriptor, Scope, LeftOperandType, ^ program_source:12147:12: note: in instantiation of function template specialization 'mpp::tensor_ops::matmul2d<{32, 64, 32, false, true, false, 1}, metal::execution_simdgroups<4>>::run<metal::tensor<threadgroup half, metal::extents<int, 18446744073709551615, 18446744073709551615>, metal::tensor_inline>, metal::tensor<threadgroup bfloat, metal::extents<int, 18446744073709551615, 18446744073709551615>, metal::tensor_inline>, metal::cooperative_tensor<float, metal::extents<int, 18446744073709551615, 18446744073709551615>, mpp::tensor_ops::__mutmul2d_detail::__operand_layout<{32, 64, 32, false, true, false, 1}, mpp::tensor_ops::__mutmul2d_detail::__matmul2d_cooperative_operand_index::destination, metal::execution_simdgroups<4>, bfloat, half, float, int>>, void>' requested here mm.run(sB, sA, cT); ^ In file included from program_source:2837: In file included from /System/Library/Frameworks/MetalPerformancePrimitives.framework/Headers/MetalPerformancePrimitives.h:10: In file included from /System/Library/Frameworks/MetalPerformancePrimitives.framework/Headers/MPPTensorOpsMatMul2d.h:368: /System/Library/Frameworks/MetalPerformancePrimitives.framework/Headers/__impl/MPPTensorOpsMatMul2dImpl.h:3267:5: error: static_assert failed due to requirement '__tensor_ops_detail::__is_same_v<half, bfloat>' "Input types must match cooperative tensor types" static_assert(__tensor_ops_detail::__is_same_v<_rightType, rightValueType>, "Input types must match cooperative tensor types"); ^ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ " UserInfo={NSLocalizedDescription=program_source:7131:28: warning: variable 'theta_base' is used uninitialized whenever 'if' condition is false [-Wsometimes-uninitialized] } else if (sector % 3 == 0 && sector < 3 * args.sect_0) { // t ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ program_source:7251:76: note: in instantiation of function template specialization 'kernel_rope_multi<float>' requested here template [[host_name("kernel_rope_multi_f32")]] kernel kernel_rope_multi_t kernel_rope_multi<float>; ^ program_source:7149:33: note: uninitialized use occurs here const float theta = theta_base * pow(args.freq_base, inv_ndims*i0); ^~~~~~~~~~ program_source:7131:24: note: remove the 'if' if its condition is always true } else if (sector % 3 == 0 && sector < 3 * args.sect_0) { // t ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ program_source:7131:28: warning: variable 'theta_base' is used uninitialized whenever '&&' condition is false [-Wsometimes-uninitialized] } else if (sector % 3 == 0 && sector < 3 * args.sect_0) { // t ^~~~~~~~~~~~~~~ program_source:7149:33: note: uninitialized use occurs here const float theta = theta_base * pow(args.freq_base, inv_ndims*i0); ^~~~~~~~~~ program_source:7131:28: note: remove the '&&' if its condition is always true } else if (sector % 3 == 0 && sector < 3 * args.sect_0) { // t ^~~~~~~~~~~~~~~~~~ program_source:7125:29: note: initialize the variable 'theta_base' to silence this warning float theta_base; ^ = 0.0 program_source:7131:28: warning: variable 'theta_base' is used uninitialized whenever 'if' condition is false [-Wsometimes-uninitialized] } else if (sector % 3 == 0 && sector < 3 * args.sect_0) { // t ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ program_source:7252:76: note: in instantiation of function template specialization 'kernel_rope_multi<half>' requested here template [[host_name("kernel_rope_multi_f16")]] kernel kernel_rope_multi_t kernel_rope_multi<half>; ^ program_source:7149:33: note: uninitialized use occurs here const float theta = theta_base * pow(args.freq_base, inv_ndims*i0); ^~~~~~~~~~ program_source:7131:24: note: remove the 'if' if its condition is always true } else if (sector % 3 == 0 && sector < 3 * args.sect_0) { // t ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ program_source:7131:28: warning: variable 'theta_base' is used uninitialized whenever '&&' condition is false [-Wsometimes-uninitialized] } else if (sector % 3 == 0 && sector < 3 * args.sect_0) { // t ^~~~~~~~~~~~~~~ program_source:7149:33: note: uninitialized use occurs here const float theta = theta_base * pow(args.freq_base, inv_ndims*i0); ^~~~~~~~~~ program_source:7131:28: note: remove the '&&' if its condition is always true } else if (sector % 3 == 0 && sector < 3 * args.sect_0) { // t ^~~~~~~~~~~~~~~~~~ program_source:7125:29: note: initialize the variable 'theta_base' to silence this warning float theta_base; ^ = 0.0 In file included from program_source:2837: In file included from /System/Library/Frameworks/MetalPerformancePrimitives.framework/Headers/MetalPerformancePrimitives.h:10: In file included from /System/Library/Frameworks/MetalPerformancePrimitives.framework/Headers/MPPTensorOpsMatMul2d.h:368: /System/Library/Frameworks/MetalPerformancePrimitives.framework/Headers/__impl/MPPTensorOpsMatMul2dImpl.h:3266:5: error: static_assert failed due to requirement '__tensor_ops_detail::__is_same_v<bfloat, half>' "Input types must match cooperative tensor types" static_assert(__tensor_ops_detail::__is_same_v<_leftType, leftValueType>, "Input types must match cooperative tensor types"); ^ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ /System/Library/Frameworks/MetalPerformancePrimitives.framework/Headers/MPPTensorOpsMatMul2d.h:394:24: note: in instantiation of function template specialization 'mpp::tensor_ops::__mutmul2d_detail::__run<{32, 64, 32, false, true, false, 1}, metal::execution_simdgroups<4>, metal::tensor<threadgroup half, metal::extents<int, 18446744073709551615, 18446744073709551615>, metal::tensor_inline>, metal::tensor<threadgroup bfloat, metal::extents<int, 18446744073709551615, 18446744073709551615>, metal::tensor_inline>, metal::cooperative_tensor<float, metal::extents<int, 18446744073709551615, 18446744073709551615>, mpp::tensor_ops::__mutmul2d_detail::__operand_layout<{32, 64, 32, false, true, false, 1}, mpp::tensor_ops::__mutmul2d_detail::__matmul2d_cooperative_operand_index::destination, metal::execution_simdgroups<4>, bfloat, half, float, int>>>' requested here __mutmul2d_detail::__run<Descriptor, Scope, LeftOperandType, ^ program_source:12147:12: note: in instantiation of function template specialization 'mpp::tensor_ops::matmul2d<{32, 64, 32, false, true, false, 1}, metal::execution_simdgroups<4>>::run<metal::tensor<threadgroup half, metal::extents<int, 18446744073709551615, 18446744073709551615>, metal::tensor_inline>, metal::tensor<threadgroup bfloat, metal::extents<int, 18446744073709551615, 18446744073709551615>, metal::tensor_inline>, metal::cooperative_tensor<float, metal::extents<int, 18446744073709551615, 18446744073709551615>, mpp::tensor_ops::__mutmul2d_detail::__operand_layout<{32, 64, 32, false, true, false, 1}, mpp::tensor_ops::__mutmul2d_detail::__matmul2d_cooperative_operand_index::destination, metal::execution_simdgroups<4>, bfloat, half, float, int>>, void>' requested here mm.run(sB, sA, cT); ^ In file included from program_source:2837: In file included from /System/Library/Frameworks/MetalPerformancePrimitives.framework/Headers/MetalPerformancePrimitives.h:10: In file included from /System/Library/Frameworks/MetalPerformancePrimitives.framework/Headers/MPPTensorOpsMatMul2d.h:368: /System/Library/Frameworks/MetalPerformancePrimitives.framework/Headers/__impl/MPPTensorOpsMatMul2dImpl.h:3267:5: error: static_assert failed due to requirement '__tensor_ops_detail::__is_same_v<half, bfloat>' "Input types must match cooperative tensor types" static_assert(__tensor_ops_detail::__is_same_v<_rightType, rightValueType>, "Input types must match cooperative tensor types"); ^ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ } ggml_metal_device_init: error: failed to create library ggml_metal_rsets_init: creating a residency set collection (keep_alive = 180 s) ggml_metal_device_init: GPU name: Apple M5 ggml_metal_device_init: GPU family: MTLGPUFamilyApple10 (1010) ggml_metal_device_init: GPU family: MTLGPUFamilyCommon3 (3003) ggml_metal_device_init: GPU family: MTLGPUFamilyMetal4 (5002) ggml_metal_device_init: simdgroup reduction = true ggml_metal_device_init: simdgroup matrix mul. = true ggml_metal_device_init: has unified memory = true ggml_metal_device_init: has bfloat = true ggml_metal_device_init: has tensor = true ggml_metal_device_init: use residency sets = true ggml_metal_device_init: use shared buffers = true ggml_metal_device_init: recommendedMaxWorkingSetSize = 26800.60 MB load_backend: loaded CPU backend from /private/var/folders/6r/wc7km6294llbshkqy9c4hgw80000gn/T/AppTranslocation/70F21D0A-0093-45A5-9195-88CFF0181E67/d/Ollama.app/Contents/Resources/libggml-cpu.so time=2026-04-10T11:25:22.216+08:00 level=INFO source=ggml.go:104 msg=system Metal.0.EMBED_LIBRARY=1 CPU.0.NEON=1 CPU.0.ARM_FMA=1 CPU.0.FP16_VA=1 CPU.0.DOTPROD=1 CPU.0.LLAMAFILE=1 CPU.0.ACCELERATE=1 CPU.1.NEON=1 CPU.1.ARM_FMA=1 CPU.1.FP16_VA=1 CPU.1.DOTPROD=1 CPU.1.LLAMAFILE=1 compiler=cgo(clang) ggml_metal_init: allocating ggml_metal_init: picking default device: Apple M5 ggml_metal_init: the device does not have a precompiled Metal library - this is unexpected ggml_metal_init: will try to compile it on the fly ggml_metal_library_init: using embedded metal library ggml_metal_library_init: error: Error Domain=MTLLibraryErrorDomain Code=3 "program_source:7131:28: warning: variable 'theta_base' is used uninitialized whenever 'if' condition is false [-Wsometimes-uninitialized] } else if (sector % 3 == 0 && sector < 3 * args.sect_0) { // t ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ program_source:7251:76: note: in instantiation of function template specialization 'kernel_rope_multi<float>' requested here template [[host_name("kernel_rope_multi_f32")]] kernel kernel_rope_multi_t kernel_rope_multi<float>; ^ program_source:7149:33: note: uninitialized use occurs here const float theta = theta_base * pow(args.freq_base, inv_ndims*i0); ^~~~~~~~~~ program_source:7131:24: note: remove the 'if' if its condition is always true } else if (sector % 3 == 0 && sector < 3 * args.sect_0) { // t ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ program_source:7131:28: warning: variable 'theta_base' is used uninitialized whenever '&&' condition is false [-Wsometimes-uninitialized] } else if (sector % 3 == 0 && sector < 3 * args.sect_0) { // t ^~~~~~~~~~~~~~~ program_source:7149:33: note: uninitialized use occurs here const float theta = theta_base * pow(args.freq_base, inv_ndims*i0); ^~~~~~~~~~ program_source:7131:28: note: remove the '&&' if its condition is always true } else if (sector % 3 == 0 && sector < 3 * args.sect_0) { // t ^~~~~~~~~~~~~~~~~~ program_source:7125:29: note: initialize the variable 'theta_base' to silence this warning float theta_base; ^ = 0.0 program_source:7131:28: warning: variable 'theta_base' is used uninitialized whenever 'if' condition is false [-Wsometimes-uninitialized] } else if (sector % 3 == 0 && sector < 3 * args.sect_0) { // t ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ program_source:7252:76: note: in instantiation of function template specialization 'kernel_rope_multi<half>' requested here template [[host_name("kernel_rope_multi_f16")]] kernel kernel_rope_multi_t kernel_rope_multi<half>; ^ program_source:7149:33: note: uninitialized use occurs here const float theta = theta_base * pow(args.freq_base, inv_ndims*i0); ^~~~~~~~~~ program_source:7131:24: note: remove the 'if' if its condition is always true } else if (sector % 3 == 0 && sector < 3 * args.sect_0) { // t ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ program_source:7131:28: warning: variable 'theta_base' is used uninitialized whenever '&&' condition is false [-Wsometimes-uninitialized] } else if (sector % 3 == 0 && sector < 3 * args.sect_0) { // t ^~~~~~~~~~~~~~~ program_source:7149:33: note: uninitialized use occurs here const float theta = theta_base * pow(args.freq_base, inv_ndims*i0); ^~~~~~~~~~ program_source:7131:28: note: remove the '&&' if its condition is always true } else if (sector % 3 == 0 && sector < 3 * args.sect_0) { // t ^~~~~~~~~~~~~~~~~~ program_source:7125:29: note: initialize the variable 'theta_base' to silence this warning float theta_base; ^ = 0.0 In file included from program_source:2837: In file included from /System/Library/Frameworks/MetalPerformancePrimitives.framework/Headers/MetalPerformancePrimitives.h:10: In file included from /System/Library/Frameworks/MetalPerformancePrimitives.framework/Headers/MPPTensorOpsMatMul2d.h:368: /System/Library/Frameworks/MetalPerformancePrimitives.framework/Headers/__impl/MPPTensorOpsMatMul2dImpl.h:3266:5: error: static_assert failed due to requirement '__tensor_ops_detail::__is_same_v<bfloat, half>' "Input types must match cooperative tensor types" static_assert(__tensor_ops_detail::__is_same_v<_leftType, leftValueType>, "Input types must match cooperative tensor types"); ^ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ /System/Library/Frameworks/MetalPerformancePrimitives.framework/Headers/MPPTensorOpsMatMul2d.h:394:24: note: in instantiation of function template specialization 'mpp::tensor_ops::__mutmul2d_detail::__run<{32, 64, 32, false, true, false, 1}, metal::execution_simdgroups<4>, metal::tensor<threadgroup half, metal::extents<int, 18446744073709551615, 18446744073709551615>, metal::tensor_inline>, metal::tensor<threadgroup bfloat, metal::extents<int, 18446744073709551615, 18446744073709551615>, metal::tensor_inline>, metal::cooperative_tensor<float, metal::extents<int, 18446744073709551615, 18446744073709551615>, mpp::tensor_ops::__mutmul2d_detail::__operand_layout<{32, 64, 32, false, true, false, 1}, mpp::tensor_ops::__mutmul2d_detail::__matmul2d_cooperative_operand_index::destination, metal::execution_simdgroups<4>, bfloat, half, float, int>>>' requested here __mutmul2d_detail::__run<Descriptor, Scope, LeftOperandType, ^ program_source:12147:12: note: in instantiation of function template specialization 'mpp::tensor_ops::matmul2d<{32, 64, 32, false, true, false, 1}, metal::execution_simdgroups<4>>::run<metal::tensor<threadgroup half, metal::extents<int, 18446744073709551615, 18446744073709551615>, metal::tensor_inline>, metal::tensor<threadgroup bfloat, metal::extents<int, 18446744073709551615, 18446744073709551615>, metal::tensor_inline>, metal::cooperative_tensor<float, metal::extents<int, 18446744073709551615, 18446744073709551615>, mpp::tensor_ops::__mutmul2d_detail::__operand_layout<{32, 64, 32, false, true, false, 1}, mpp::tensor_ops::__mutmul2d_detail::__matmul2d_cooperative_operand_index::destination, metal::execution_simdgroups<4>, bfloat, half, float, int>>, void>' requested here mm.run(sB, sA, cT); ^ In file included from program_source:2837: In file included from /System/Library/Frameworks/MetalPerformancePrimitives.framework/Headers/MetalPerformancePrimitives.h:10: In file included from /System/Library/Frameworks/MetalPerformancePrimitives.framework/Headers/MPPTensorOpsMatMul2d.h:368: /System/Library/Frameworks/MetalPerformancePrimitives.framework/Headers/__impl/MPPTensorOpsMatMul2dImpl.h:3267:5: error: static_assert failed due to requirement '__tensor_ops_detail::__is_same_v<half, bfloat>' "Input types must match cooperative tensor types" static_assert(__tensor_ops_detail::__is_same_v<_rightType, rightValueType>, "Input types must match cooperative tensor types"); ^ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ " UserInfo={NSLocalizedDescription=program_source:7131:28: warning: variable 'theta_base' is used uninitialized whenever 'if' condition is false [-Wsometimes-uninitialized] } else if (sector % 3 == 0 && sector < 3 * args.sect_0) { // t ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ program_source:7251:76: note: in instantiation of function template specialization 'kernel_rope_multi<float>' requested here template [[host_name("kernel_rope_multi_f32")]] kernel kernel_rope_multi_t kernel_rope_multi<float>; ^ program_source:7149:33: note: uninitialized use occurs here const float theta = theta_base * pow(args.freq_base, inv_ndims*i0); ^~~~~~~~~~ program_source:7131:24: note: remove the 'if' if its condition is always true } else if (sector % 3 == 0 && sector < 3 * args.sect_0) { // t ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ program_source:7131:28: warning: variable 'theta_base' is used uninitialized whenever '&&' condition is false [-Wsometimes-uninitialized] } else if (sector % 3 == 0 && sector < 3 * args.sect_0) { // t ^~~~~~~~~~~~~~~ program_source:7149:33: note: uninitialized use occurs here const float theta = theta_base * pow(args.freq_base, inv_ndims*i0); ^~~~~~~~~~ program_source:7131:28: note: remove the '&&' if its condition is always true } else if (sector % 3 == 0 && sector < 3 * args.sect_0) { // t ^~~~~~~~~~~~~~~~~~ program_source:7125:29: note: initialize the variable 'theta_base' to silence this warning float theta_base; ^ = 0.0 program_source:7131:28: warning: variable 'theta_base' is used uninitialized whenever 'if' condition is false [-Wsometimes-uninitialized] } else if (sector % 3 == 0 && sector < 3 * args.sect_0) { // t ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ program_source:7252:76: note: in instantiation of function template specialization 'kernel_rope_multi<half>' requested here template [[host_name("kernel_rope_multi_f16")]] kernel kernel_rope_multi_t kernel_rope_multi<half>; ^ program_source:7149:33: note: uninitialized use occurs here const float theta = theta_base * pow(args.freq_base, inv_ndims*i0); ^~~~~~~~~~ program_source:7131:24: note: remove the 'if' if its condition is always true } else if (sector % 3 == 0 && sector < 3 * args.sect_0) { // t ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ program_source:7131:28: warning: variable 'theta_base' is used uninitialized whenever '&&' condition is false [-Wsometimes-uninitialized] } else if (sector % 3 == 0 && sector < 3 * args.sect_0) { // t ^~~~~~~~~~~~~~~ program_source:7149:33: note: uninitialized use occurs here const float theta = theta_base * pow(args.freq_base, inv_ndims*i0); ^~~~~~~~~~ program_source:7131:28: note: remove the '&&' if its condition is always true } else if (sector % 3 == 0 && sector < 3 * args.sect_0) { // t ^~~~~~~~~~~~~~~~~~ program_source:7125:29: note: initialize the variable 'theta_base' to silence this warning float theta_base; ^ = 0.0 In file included from program_source:2837: In file included from /System/Library/Frameworks/MetalPerformancePrimitives.framework/Headers/MetalPerformancePrimitives.h:10: In file included from /System/Library/Frameworks/MetalPerformancePrimitives.framework/Headers/MPPTensorOpsMatMul2d.h:368: /System/Library/Frameworks/MetalPerformancePrimitives.framework/Headers/__impl/MPPTensorOpsMatMul2dImpl.h:3266:5: error: static_assert failed due to requirement '__tensor_ops_detail::__is_same_v<bfloat, half>' "Input types must match cooperative tensor types" static_assert(__tensor_ops_detail::__is_same_v<_leftType, leftValueType>, "Input types must match cooperative tensor types"); ^ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ /System/Library/Frameworks/MetalPerformancePrimitives.framework/Headers/MPPTensorOpsMatMul2d.h:394:24: note: in instantiation of function template specialization 'mpp::tensor_ops::__mutmul2d_detail::__run<{32, 64, 32, false, true, false, 1}, metal::execution_simdgroups<4>, metal::tensor<threadgroup half, metal::extents<int, 18446744073709551615, 18446744073709551615>, metal::tensor_inline>, metal::tensor<threadgroup bfloat, metal::extents<int, 18446744073709551615, 18446744073709551615>, metal::tensor_inline>, metal::cooperative_tensor<float, metal::extents<int, 18446744073709551615, 18446744073709551615>, mpp::tensor_ops::__mutmul2d_detail::__operand_layout<{32, 64, 32, false, true, false, 1}, mpp::tensor_ops::__mutmul2d_detail::__matmul2d_cooperative_operand_index::destination, metal::execution_simdgroups<4>, bfloat, half, float, int>>>' requested here __mutmul2d_detail::__run<Descriptor, Scope, LeftOperandType, ^ program_source:12147:12: note: in instantiation of function template specialization 'mpp::tensor_ops::matmul2d<{32, 64, 32, false, true, false, 1}, metal::execution_simdgroups<4>>::run<metal::tensor<threadgroup half, metal::extents<int, 18446744073709551615, 18446744073709551615>, metal::tensor_inline>, metal::tensor<threadgroup bfloat, metal::extents<int, 18446744073709551615, 18446744073709551615>, metal::tensor_inline>, metal::cooperative_tensor<float, metal::extents<int, 18446744073709551615, 18446744073709551615>, mpp::tensor_ops::__mutmul2d_detail::__operand_layout<{32, 64, 32, false, true, false, 1}, mpp::tensor_ops::__mutmul2d_detail::__matmul2d_cooperative_operand_index::destination, metal::execution_simdgroups<4>, bfloat, half, float, int>>, void>' requested here mm.run(sB, sA, cT); ^ In file included from program_source:2837: In file included from /System/Library/Frameworks/MetalPerformancePrimitives.framework/Headers/MetalPerformancePrimitives.h:10: In file included from /System/Library/Frameworks/MetalPerformancePrimitives.framework/Headers/MPPTensorOpsMatMul2d.h:368: /System/Library/Frameworks/MetalPerformancePrimitives.framework/Headers/__impl/MPPTensorOpsMatMul2dImpl.h:3267:5: error: static_assert failed due to requirement '__tensor_ops_detail::__is_same_v<half, bfloat>' "Input types must match cooperative tensor types" static_assert(__tensor_ops_detail::__is_same_v<_rightType, rightValueType>, "Input types must match cooperative tensor types"); ^ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ } ggml_metal_init: error: failed to initialize the Metal library ggml_backend_metal_device_init: error: failed to allocate context ggml-backend.cpp:258: GGML_ASSERT(backend) failed WARNING: Using native backtrace. Set GGML_BACKTRACE_LLDB for more info. WARNING: GGML_BACKTRACE_LLDB may cause native MacOS Terminal.app to crash. See: https://github.com/ggml-org/llama.cpp/pull/17869 0 ollama 0x0000000105ce1958 ggml_print_backtrace + 276 1 ollama 0x0000000105ce1b44 ggml_abort + 156 2 ollama 0x0000000105cfb444 ggml_backend_get_default_buffer_type + 76 3 ollama 0x0000000105c77738 _cgo_c81fd19bee02_Cfunc_ggml_backend_get_default_buffer_type + 36 4 ollama 0x0000000104da06ac ollama + 509612 SIGABRT: abort PC=0x19bb7f5b0 m=13 sigcode=0 signal arrived during cgo execution goroutine 12 gp=0x14000602c40 m=13 mp=0x14000601008 [syscall]: runtime.cgocall(0x105c77714, 0x14000046c88) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/cgocall.go:167 +0x44 fp=0x14000046c50 sp=0x14000046c10 pc=0x104d94d24 github.com/ollama/ollama/ml/backend/ggml._Cfunc_ggml_backend_get_default_buffer_type(0x0) _cgo_gotypes.go:878 +0x34 fp=0x14000046c80 sp=0x14000046c50 pc=0x105233614 github.com/ollama/ollama/ml/backend/ggml.New.func17(...) /Users/runner/work/ollama/ollama/ml/backend/ggml/ggml.go:361 github.com/ollama/ollama/ml/backend/ggml.New({0x16b0db9cd, 0x6c}, {0x0, 0x4, {0x10706f8a0, 0x0, 0x0}, 0x1}) /Users/runner/work/ollama/ollama/ml/backend/ggml/ggml.go:361 +0x12e0 fp=0x14000047540 sp=0x14000046c80 pc=0x105239b40 github.com/ollama/ollama/ml.NewBackend({0x16b0db9cd, 0x6c}, {0x0, 0x4, {0x10706f8a0, 0x0, 0x0}, 0x1}) /Users/runner/work/ollama/ollama/ml/backend.go:88 +0x88 fp=0x14000047590 sp=0x14000047540 pc=0x1051e1ba8 github.com/ollama/ollama/model.New({0x16b0db9cd?, 0x0?}, {0x0, 0x4, {0x10706f8a0, 0x0, 0x0}, 0x1}) /Users/runner/work/ollama/ollama/model/model.go:120 +0x50 fp=0x14000047660 sp=0x14000047590 pc=0x105277820 github.com/ollama/ollama/runner/ollamarunner.(*Server).allocModel(0x1400014c5a0, {0x16b0db9cd?, 0x0?}, {0x0, 0x4, {0x10706f8a0, 0x0, 0x0}, 0x1}, {0x0?, ...}, ...) /Users/runner/work/ollama/ollama/runner/ollamarunner/runner.go:1202 +0xac fp=0x14000047710 sp=0x14000047660 pc=0x10534177c github.com/ollama/ollama/runner/ollamarunner.(*Server).load(0x1400014c5a0, {0x106562740, 0x140000fec40}, 0x14000394c80) /Users/runner/work/ollama/ollama/runner/ollamarunner/runner.go:1317 +0x460 fp=0x14000047aa0 sp=0x14000047710 pc=0x105342380 github.com/ollama/ollama/runner/ollamarunner.(*Server).load-fm({0x106562740?, 0x140000fec40?}, 0x140004e7b28?) <autogenerated>:1 +0x40 fp=0x14000047ad0 sp=0x14000047aa0 pc=0x105344230 net/http.HandlerFunc.ServeHTTP(0x14000153800?, {0x106562740?, 0x140000fec40?}, 0x140004e7b10?) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/net/http/server.go:2294 +0x38 fp=0x14000047b00 sp=0x14000047ad0 pc=0x105060778 net/http.(*ServeMux).ServeHTTP(0x10?, {0x106562740, 0x140000fec40}, 0x14000394c80) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/net/http/server.go:2822 +0x1b4 fp=0x14000047b50 sp=0x14000047b00 pc=0x105062304 net/http.serverHandler.ServeHTTP({0x10655e7b0?}, {0x106562740?, 0x140000fec40?}, 0x1?) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/net/http/server.go:3301 +0xbc fp=0x14000047b80 sp=0x14000047b50 pc=0x10507dfec net/http.(*conn).serve(0x140004c0510, {0x106564fc8, 0x14000681860}) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/net/http/server.go:2102 +0x52c fp=0x14000047fa0 sp=0x14000047b80 pc=0x10505ef1c net/http.(*Server).Serve.gowrap3() /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/net/http/server.go:3454 +0x30 fp=0x14000047fd0 sp=0x14000047fa0 pc=0x1050640e0 runtime.goexit({}) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x14000047fd0 sp=0x14000047fd0 pc=0x104da08b4 created by net/http.(*Server).Serve in goroutine 1 /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/net/http/server.go:3454 +0x3d8 goroutine 1 gp=0x140000021c0 m=nil [IO wait]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x14001605710 sp=0x140016056f0 pc=0x104d98248 runtime.netpollblock(0x140001257a8?, 0x4e1d050?, 0x1?) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/netpoll.go:575 +0x158 fp=0x14001605750 sp=0x14001605710 pc=0x104d5dca8 internal/poll.runtime_pollWait(0x15288db10, 0x72) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/netpoll.go:351 +0xa0 fp=0x14001605780 sp=0x14001605750 pc=0x104d97400 internal/poll.(*pollDesc).wait(0x14000507480?, 0x104e1f2b8?, 0x0) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/internal/poll/fd_poll_runtime.go:84 +0x28 fp=0x140016057b0 sp=0x14001605780 pc=0x104e18868 internal/poll.(*pollDesc).waitRead(...) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/internal/poll/fd_poll_runtime.go:89 internal/poll.(*FD).Accept(0x14000507480) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/internal/poll/fd_unix.go:620 +0x24c fp=0x14001605860 sp=0x140016057b0 pc=0x104e1d13c net.(*netFD).accept(0x14000507480) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/net/fd_unix.go:172 +0x28 fp=0x14001605920 sp=0x14001605860 pc=0x104e8d478 net.(*TCPListener).accept(0x140003eb2c0) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/net/tcpsock_posix.go:159 +0x24 fp=0x14001605970 sp=0x14001605920 pc=0x104ea1c54 net.(*TCPListener).Accept(0x140003eb2c0) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/net/tcpsock.go:380 +0x2c fp=0x140016059b0 sp=0x14001605970 pc=0x104ea0c3c net/http.(*onceCloseListener).Accept(0x140004c0510?) <autogenerated>:1 +0x30 fp=0x140016059d0 sp=0x140016059b0 pc=0x10508a610 net/http.(*Server).Serve(0x140001f1b00, {0x106562560, 0x140003eb2c0}) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/net/http/server.go:3424 +0x290 fp=0x14001605b00 sp=0x140016059d0 pc=0x105063d50 github.com/ollama/ollama/runner/ollamarunner.Execute({0x140000320a0, 0x4, 0x4}) /Users/runner/work/ollama/ollama/runner/ollamarunner/runner.go:1453 +0x7fc fp=0x14001605cd0 sp=0x14001605b00 pc=0x105343c5c github.com/ollama/ollama/runner.Execute({0x14000032080?, 0x0?, 0x0?}) /Users/runner/work/ollama/ollama/runner/runner.go:18 +0x14c fp=0x14001605d10 sp=0x14001605cd0 pc=0x1053d720c github.com/ollama/ollama/cmd.NewCLI.func3(0x140001f1800?, {0x105f98f8a?, 0x4?, 0x105f98f8e?}) /Users/runner/work/ollama/ollama/cmd/cmd.go:2267 +0x54 fp=0x14001605d40 sp=0x14001605d10 pc=0x105aedb14 github.com/spf13/cobra.(*Command).execute(0x140004c7b08, {0x14000370fa0, 0x5, 0x5}) /Users/runner/go/pkg/mod/github.com/spf13/cobra@v1.7.0/command.go:940 +0x648 fp=0x14001605e60 sp=0x14001605d40 pc=0x104efc318 github.com/spf13/cobra.(*Command).ExecuteC(0x1400015b508) /Users/runner/go/pkg/mod/github.com/spf13/cobra@v1.7.0/command.go:1068 +0x320 fp=0x14001605f20 sp=0x14001605e60 pc=0x104efca60 github.com/spf13/cobra.(*Command).Execute(...) /Users/runner/go/pkg/mod/github.com/spf13/cobra@v1.7.0/command.go:992 github.com/spf13/cobra.(*Command).ExecuteContext(...) /Users/runner/go/pkg/mod/github.com/spf13/cobra@v1.7.0/command.go:985 main.main() /Users/runner/work/ollama/ollama/main.go:12 +0x54 fp=0x14001605f40 sp=0x14001605f20 pc=0x105aef294 runtime.main() /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:283 +0x284 fp=0x14001605fd0 sp=0x14001605f40 pc=0x104d64814 runtime.goexit({}) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x14001605fd0 sp=0x14001605fd0 pc=0x104da08b4 goroutine 2 gp=0x14000002c40 m=nil [force gc (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x14000070f90 sp=0x14000070f70 pc=0x104d98248 runtime.goparkunlock(...) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:441 runtime.forcegchelper() /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:348 +0xb8 fp=0x14000070fd0 sp=0x14000070f90 pc=0x104d64b68 runtime.goexit({}) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x14000070fd0 sp=0x14000070fd0 pc=0x104da08b4 created by runtime.init.7 in goroutine 1 /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:336 +0x24 goroutine 3 gp=0x14000003180 m=nil [GC sweep wait]: runtime.gopark(0x1?, 0x0?, 0x0?, 0x0?, 0x0?) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x14000071760 sp=0x14000071740 pc=0x104d98248 runtime.goparkunlock(...) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:441 runtime.bgsweep(0x1400009c000) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgcsweep.go:316 +0x108 fp=0x140000717b0 sp=0x14000071760 pc=0x104d4fc48 runtime.gcenable.gowrap1() /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:204 +0x28 fp=0x140000717d0 sp=0x140000717b0 pc=0x104d43a48 runtime.goexit({}) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x140000717d0 sp=0x140000717d0 pc=0x104da08b4 created by runtime.gcenable in goroutine 1 /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:204 +0x6c goroutine 4 gp=0x14000003340 m=nil [GC scavenge wait]: runtime.gopark(0x10000?, 0x1061be068?, 0x0?, 0x0?, 0x0?) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x14000071f60 sp=0x14000071f40 pc=0x104d98248 runtime.goparkunlock(...) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:441 runtime.(*scavengerState).park(0x107024820) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgcscavenge.go:425 +0x5c fp=0x14000071f90 sp=0x14000071f60 pc=0x104d4d6dc runtime.bgscavenge(0x1400009c000) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgcscavenge.go:658 +0xac fp=0x14000071fb0 sp=0x14000071f90 pc=0x104d4dc7c runtime.gcenable.gowrap2() /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:205 +0x28 fp=0x14000071fd0 sp=0x14000071fb0 pc=0x104d439e8 runtime.goexit({}) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x14000071fd0 sp=0x14000071fd0 pc=0x104da08b4 created by runtime.gcenable in goroutine 1 /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:205 +0xac goroutine 5 gp=0x14000003c00 m=nil [finalizer wait]: runtime.gopark(0x18000705c8?, 0x1071bbef0?, 0x8?, 0x1?, 0x1c0?) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x14000070590 sp=0x14000070570 pc=0x104d98248 runtime.runfinq() /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mfinal.go:196 +0x108 fp=0x140000707d0 sp=0x14000070590 pc=0x104d42a48 runtime.goexit({}) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x140000707d0 sp=0x140000707d0 pc=0x104da08b4 created by runtime.createfing in goroutine 1 /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mfinal.go:166 +0x80 goroutine 6 gp=0x140001dc700 m=nil [chan receive]: runtime.gopark(0x140000f9cc0?, 0x1400000e198?, 0x48?, 0x27?, 0x104e615a8?) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x140000726f0 sp=0x140000726d0 pc=0x104d98248 runtime.chanrecv(0x1400003c540, 0x0, 0x1) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/chan.go:664 +0x42c fp=0x14000072770 sp=0x140000726f0 pc=0x104d34cec runtime.chanrecv1(0x0?, 0x0?) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/chan.go:506 +0x14 fp=0x140000727a0 sp=0x14000072770 pc=0x104d34884 runtime.unique_runtime_registerUniqueMapCleanup.func2(...) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1796 runtime.unique_runtime_registerUniqueMapCleanup.gowrap1() /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1799 +0x3c fp=0x140000727d0 sp=0x140000727a0 pc=0x104d46c6c runtime.goexit({}) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x140000727d0 sp=0x140000727d0 pc=0x104da08b4 created by unique.runtime_registerUniqueMapCleanup in goroutine 1 /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1794 +0x78 goroutine 7 gp=0x140001dca80 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x14000072f10 sp=0x14000072ef0 pc=0x104d98248 runtime.gcBgMarkWorker(0x1400003d960) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1423 +0xdc fp=0x14000072fb0 sp=0x14000072f10 pc=0x104d45edc runtime.gcBgMarkStartWorkers.gowrap1() /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x28 fp=0x14000072fd0 sp=0x14000072fb0 pc=0x104d45dc8 runtime.goexit({}) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x14000072fd0 sp=0x14000072fd0 pc=0x104da08b4 created by runtime.gcBgMarkStartWorkers in goroutine 1 /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x140 goroutine 18 gp=0x14000504000 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x1400006c710 sp=0x1400006c6f0 pc=0x104d98248 runtime.gcBgMarkWorker(0x1400003d960) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1423 +0xdc fp=0x1400006c7b0 sp=0x1400006c710 pc=0x104d45edc runtime.gcBgMarkStartWorkers.gowrap1() /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x28 fp=0x1400006c7d0 sp=0x1400006c7b0 pc=0x104d45dc8 runtime.goexit({}) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x1400006c7d0 sp=0x1400006c7d0 pc=0x104da08b4 created by runtime.gcBgMarkStartWorkers in goroutine 1 /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x140 goroutine 34 gp=0x14000102380 m=nil [GC worker (idle)]: runtime.gopark(0x107071f00?, 0x1?, 0x48?, 0x83?, 0x0?) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x1400011a710 sp=0x1400011a6f0 pc=0x104d98248 runtime.gcBgMarkWorker(0x1400003d960) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1423 +0xdc fp=0x1400011a7b0 sp=0x1400011a710 pc=0x104d45edc runtime.gcBgMarkStartWorkers.gowrap1() /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x28 fp=0x1400011a7d0 sp=0x1400011a7b0 pc=0x104d45dc8 runtime.goexit({}) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x1400011a7d0 sp=0x1400011a7d0 pc=0x104da08b4 created by runtime.gcBgMarkStartWorkers in goroutine 1 /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x140 goroutine 8 gp=0x140001dcc40 m=nil [GC worker (idle)]: runtime.gopark(0x6c4b98c37f8?, 0x0?, 0x0?, 0x0?, 0x0?) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x14000073710 sp=0x140000736f0 pc=0x104d98248 runtime.gcBgMarkWorker(0x1400003d960) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1423 +0xdc fp=0x140000737b0 sp=0x14000073710 pc=0x104d45edc runtime.gcBgMarkStartWorkers.gowrap1() /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x28 fp=0x140000737d0 sp=0x140000737b0 pc=0x104d45dc8 runtime.goexit({}) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x140000737d0 sp=0x140000737d0 pc=0x104da08b4 created by runtime.gcBgMarkStartWorkers in goroutine 1 /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x140 goroutine 19 gp=0x140005041c0 m=nil [GC worker (idle)]: runtime.gopark(0x6c4b98c12b2?, 0x3?, 0xb2?, 0x6f?, 0x0?) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x1400006cf10 sp=0x1400006cef0 pc=0x104d98248 runtime.gcBgMarkWorker(0x1400003d960) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1423 +0xdc fp=0x1400006cfb0 sp=0x1400006cf10 pc=0x104d45edc runtime.gcBgMarkStartWorkers.gowrap1() /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x28 fp=0x1400006cfd0 sp=0x1400006cfb0 pc=0x104d45dc8 runtime.goexit({}) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x1400006cfd0 sp=0x1400006cfd0 pc=0x104da08b4 created by runtime.gcBgMarkStartWorkers in goroutine 1 /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x140 goroutine 35 gp=0x14000102540 m=nil [GC worker (idle)]: runtime.gopark(0x6c4b98c1811?, 0x3?, 0xc6?, 0x55?, 0x0?) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x1400011af10 sp=0x1400011aef0 pc=0x104d98248 runtime.gcBgMarkWorker(0x1400003d960) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1423 +0xdc fp=0x1400011afb0 sp=0x1400011af10 pc=0x104d45edc runtime.gcBgMarkStartWorkers.gowrap1() /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x28 fp=0x1400011afd0 sp=0x1400011afb0 pc=0x104d45dc8 runtime.goexit({}) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x1400011afd0 sp=0x1400011afd0 pc=0x104da08b4 created by runtime.gcBgMarkStartWorkers in goroutine 1 /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x140 goroutine 9 gp=0x140001dce00 m=nil [GC worker (idle)]: runtime.gopark(0x107071f00?, 0x3?, 0x45?, 0xa2?, 0x0?) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x14000073f10 sp=0x14000073ef0 pc=0x104d98248 runtime.gcBgMarkWorker(0x1400003d960) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1423 +0xdc fp=0x14000073fb0 sp=0x14000073f10 pc=0x104d45edc runtime.gcBgMarkStartWorkers.gowrap1() /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x28 fp=0x14000073fd0 sp=0x14000073fb0 pc=0x104d45dc8 runtime.goexit({}) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x14000073fd0 sp=0x14000073fd0 pc=0x104da08b4 created by runtime.gcBgMarkStartWorkers in goroutine 1 /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x140 goroutine 20 gp=0x14000504380 m=nil [GC worker (idle)]: runtime.gopark(0x107071f00?, 0x1?, 0xa9?, 0xd5?, 0x0?) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x1400006d710 sp=0x1400006d6f0 pc=0x104d98248 runtime.gcBgMarkWorker(0x1400003d960) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1423 +0xdc fp=0x1400006d7b0 sp=0x1400006d710 pc=0x104d45edc runtime.gcBgMarkStartWorkers.gowrap1() /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x28 fp=0x1400006d7d0 sp=0x1400006d7b0 pc=0x104d45dc8 runtime.goexit({}) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x1400006d7d0 sp=0x1400006d7d0 pc=0x104da08b4 created by runtime.gcBgMarkStartWorkers in goroutine 1 /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x140 goroutine 36 gp=0x14000102700 m=nil [GC worker (idle)]: runtime.gopark(0x6c4b98bea7e?, 0x1?, 0xc?, 0x6e?, 0x0?) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x1400011b710 sp=0x1400011b6f0 pc=0x104d98248 runtime.gcBgMarkWorker(0x1400003d960) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1423 +0xdc fp=0x1400011b7b0 sp=0x1400011b710 pc=0x104d45edc runtime.gcBgMarkStartWorkers.gowrap1() /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x28 fp=0x1400011b7d0 sp=0x1400011b7b0 pc=0x104d45dc8 runtime.goexit({}) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x1400011b7d0 sp=0x1400011b7d0 pc=0x104da08b4 created by runtime.gcBgMarkStartWorkers in goroutine 1 /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x140 goroutine 10 gp=0x140001dcfc0 m=nil [GC worker (idle)]: runtime.gopark(0x6c4b99d26c4?, 0x3?, 0xe9?, 0x6c?, 0x0?) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x14000116710 sp=0x140001166f0 pc=0x104d98248 runtime.gcBgMarkWorker(0x1400003d960) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1423 +0xdc fp=0x140001167b0 sp=0x14000116710 pc=0x104d45edc runtime.gcBgMarkStartWorkers.gowrap1() /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x28 fp=0x140001167d0 sp=0x140001167b0 pc=0x104d45dc8 runtime.goexit({}) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x140001167d0 sp=0x140001167d0 pc=0x104da08b4 created by runtime.gcBgMarkStartWorkers in goroutine 1 /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x140 goroutine 11 gp=0x14000602a80 m=nil [sync.WaitGroup.Wait]: runtime.gopark(0x10703acc0?, 0x0?, 0x0?, 0xc0?, 0x0?) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x14000083a90 sp=0x14000083a70 pc=0x104d98248 runtime.goparkunlock(...) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:441 runtime.semacquire1(0x1400014c658, 0x0, 0x1, 0x0, 0x18) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/sema.go:188 +0x204 fp=0x14000083ae0 sp=0x14000083a90 pc=0x104d78cf4 sync.runtime_SemacquireWaitGroup(0x0?) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/sema.go:110 +0x2c fp=0x14000083b20 sp=0x14000083ae0 pc=0x104d99cbc sync.(*WaitGroup).Wait(0x1400014c650) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/sync/waitgroup.go:118 +0x70 fp=0x14000083b40 sp=0x14000083b20 pc=0x104dac2b0 github.com/ollama/ollama/runner/ollamarunner.(*Server).run(0x1400014c5a0, {0x106565000, 0x14000371040}) /Users/runner/work/ollama/ollama/runner/ollamarunner/runner.go:442 +0x38 fp=0x14000083fa0 sp=0x14000083b40 pc=0x10533bf68 github.com/ollama/ollama/runner/ollamarunner.Execute.gowrap1() /Users/runner/work/ollama/ollama/runner/ollamarunner/runner.go:1430 +0x30 fp=0x14000083fd0 sp=0x14000083fa0 pc=0x105343e80 runtime.goexit({}) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x14000083fd0 sp=0x14000083fd0 pc=0x104da08b4 created by github.com/ollama/ollama/runner/ollamarunner.Execute in goroutine 1 /Users/runner/work/ollama/ollama/runner/ollamarunner/runner.go:1430 +0x448 goroutine 14 gp=0x14000602e00 m=nil [IO wait]: runtime.gopark(0xffffffffffffffff?, 0xffffffffffffffff?, 0x23?, 0x0?, 0x104dbc4b0?) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x14000119580 sp=0x14000119560 pc=0x104d98248 runtime.netpollblock(0x0?, 0x0?, 0x0?) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/netpoll.go:575 +0x158 fp=0x140001195c0 sp=0x14000119580 pc=0x104d5dca8 internal/poll.runtime_pollWait(0x15288d9f8, 0x72) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/netpoll.go:351 +0xa0 fp=0x140001195f0 sp=0x140001195c0 pc=0x104d97400 internal/poll.(*pollDesc).wait(0x14000507500?, 0x14000681961?, 0x0) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/internal/poll/fd_poll_runtime.go:84 +0x28 fp=0x14000119620 sp=0x140001195f0 pc=0x104e18868 internal/poll.(*pollDesc).waitRead(...) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/internal/poll/fd_poll_runtime.go:89 internal/poll.(*FD).Read(0x14000507500, {0x14000681961, 0x1, 0x1}) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/internal/poll/fd_unix.go:165 +0x1fc fp=0x140001196c0 sp=0x14000119620 pc=0x104e19b1c net.(*netFD).Read(0x14000507500, {0x14000681961?, 0x14000119758?, 0x105059994?}) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/net/fd_posix.go:55 +0x28 fp=0x14000119710 sp=0x140001196c0 pc=0x104e8ba48 net.(*conn).Read(0x14000136638, {0x14000681961?, 0x0?, 0x0?}) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/net/net.go:194 +0x34 fp=0x14000119760 sp=0x14000119710 pc=0x104e98914 net/http.(*connReader).backgroundRead(0x14000681950) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/net/http/server.go:690 +0x40 fp=0x140001197b0 sp=0x14000119760 pc=0x105059890 net/http.(*connReader).startBackgroundRead.gowrap2() /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/net/http/server.go:686 +0x28 fp=0x140001197d0 sp=0x140001197b0 pc=0x105059778 runtime.goexit({}) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x140001197d0 sp=0x140001197d0 pc=0x104da08b4 created by net/http.(*connReader).startBackgroundRead in goroutine 12 /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/net/http/server.go:686 +0xc4 r0 0x0 r1 0x0 r2 0x0 r3 0x0 r4 0x19bac1a08 r5 0x171165d20 r6 0x32 r7 0x0 r8 0xacdd3d7f0a78f2f5 r9 0xacdd3d7e7b6e82f5 r10 0x2 r11 0x10000000000 r12 0xfffffffd r13 0x0 r14 0x0 r15 0x0 r16 0x148 r17 0x20a098990 r18 0x0 r19 0x6 r20 0x1703 r21 0x1711670e0 r22 0x0 r23 0x0 r24 0x0 r25 0x14000066198 r26 0x10654b868 r27 0x818 r28 0x14000103180 r29 0x171166610 lr 0x19bbb9888 sp 0x1711665f0 pc 0x19bb7f5b0 fault 0x19bb7f5b0 time=2026-04-10T11:25:23.220+08:00 level=ERROR source=server.go:1219 msg="do load request" error="Post \"http://127.0.0.1:59329/load\": EOF" time=2026-04-10T11:25:23.220+08:00 level=ERROR source=server.go:316 msg="llama runner terminated" error="exit status 2" time=2026-04-10T11:25:23.220+08:00 level=ERROR source=server.go:1219 msg="do load request" error="Post \"http://127.0.0.1:59329/load\": dial tcp 127.0.0.1:59329: connect: connection refused" time=2026-04-10T11:25:23.220+08:00 level=INFO source=sched.go:511 msg="Load failed" model=/Users/hedaihua/.ollama/models/blobs/sha256-7121486771cbfe218851513210c40b35dbdee93ab1ef43fe36283c883980f0df error="model failed to load, this may be due to resource limitations or an internal error, check ollama server logs for details" [GIN] 2026/04/10 - 11:25:23 | 500 | 2.208098792s | 127.0.0.1 | POST "/api/chat" [GIN] 2026/04/10 - 11:25:50 | 200 | 1.271875ms | 127.0.0.1 | GET "/api/tags" ``` ### OS macOS ### GPU Apple ### CPU Apple ### Ollama version 0.20.4 and 0.20.5
GiteaMirror added the bug label 2026-04-12 22:44:42 -05:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#9887
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?