github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 16:40:08 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #15518] can not run every model #56431

New Issue
Closed
opened 2026-04-29 10:49:06 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-29 10:49:06 -05:00
Owner
Copy Link

Originally created by @robin2026-code on GitHub (Apr 12, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/15518

What is the issue?

From version 0.17.x to 0.20.5, models that previously worked can no longer run。
qwen3.5:9b-q4_K_M worked in 0.17.x，but it not work in 0.20.5
download gemma4:e4b-it-q4_K_M also not work in 0.20.5

Error
500 Internal Server Error: model failed to load, this may be due to resource limitations or an internal error, check ollama server logs for details

Relevant log output

time=2026-04-12T20:33:02.285+08:00 level=INFO source=server.go:259 msg="enabling flash attention"
time=2026-04-12T20:33:02.286+08:00 level=INFO source=server.go:444 msg="starting runner" cmd="/Applications/Ollama.app/Contents/Resources/ollama runner --ollama-engine --model /Users/robinliu/.ollama/models/blobs/sha256-dec52a44569a2a25341c4e4d3fee25846eed4f6f0b936278e3a3c900bb99d37c --port 50337"
time=2026-04-12T20:33:02.287+08:00 level=INFO source=sched.go:484 msg="system memory" total="32.0 GiB" free="13.3 GiB" free_swap="0 B"
time=2026-04-12T20:33:02.287+08:00 level=INFO source=server.go:771 msg="loading model" "model layers"=33 requested=-1
time=2026-04-12T20:33:02.330+08:00 level=INFO source=runner.go:1417 msg="starting ollama engine"
time=2026-04-12T20:33:02.330+08:00 level=INFO source=runner.go:1452 msg="Server listening on 127.0.0.1:50337"
time=2026-04-12T20:33:02.330+08:00 level=INFO source=runner.go:1290 msg=load request="{Operation:fit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:4096 KvCacheType: NumThreads:4 GPULayers:[] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
time=2026-04-12T20:33:02.350+08:00 level=INFO source=ggml.go:136 msg="" architecture=qwen35 file_type=Q4_K_M name="" description="" num_tensors=883 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 /Applications/Ollama.app/Contents/Resources/libggml-cpu.so
time=2026-04-12T20:33:03.288+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                              0x0000000103b43a58 ggml_print_backtrace + 276
1   ollama                              0x0000000103b43c44 ggml_abort + 156
2   ollama                              0x0000000103b5d544 ggml_backend_get_default_buffer_type + 76
3   ollama                              0x0000000103ad9838 _cgo_c81fd19bee02_Cfunc_ggml_backend_get_default_buffer_type + 36
4   ollama                              0x0000000102c006ac ollama + 509612
SIGABRT: abort
PC=0x1950d35b0 m=11 sigcode=0
signal arrived during cgo execution

goroutine 21 gp=0x140002b96c0 m=11 mp=0x1400018a808 [syscall]:
runtime.cgocall(0x103ad9814, 0x14000044c88)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/cgocall.go:167 +0x44 fp=0x14000044c50 sp=0x14000044c10 pc=0x102bf4d24
github.com/ollama/ollama/ml/backend/ggml._Cfunc_ggml_backend_get_default_buffer_type(0x0)
	_cgo_gotypes.go:878 +0x34 fp=0x14000044c80 sp=0x14000044c50 pc=0x103094034
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({0x16d27b732, 0x6c}, {0x0, 0x4, {0x104ed3980, 0x0, 0x0}, 0x1})
	/Users/runner/work/ollama/ollama/ml/backend/ggml/ggml.go:361 +0x12e0 fp=0x14000045540 sp=0x14000044c80 pc=0x10309a560
github.com/ollama/ollama/ml.NewBackend({0x16d27b732, 0x6c}, {0x0, 0x4, {0x104ed3980, 0x0, 0x0}, 0x1})
	/Users/runner/work/ollama/ollama/ml/backend.go:88 +0x88 fp=0x14000045590 sp=0x14000045540 pc=0x1030425c8
github.com/ollama/ollama/model.New({0x16d27b732?, 0x0?}, {0x0, 0x4, {0x104ed3980, 0x0, 0x0}, 0x1})
	/Users/runner/work/ollama/ollama/model/model.go:120 +0x50 fp=0x14000045660 sp=0x14000045590 pc=0x1030d8240
github.com/ollama/ollama/runner/ollamarunner.(*Server).allocModel(0x140000352c0, {0x16d27b732?, 0x0?}, {0x0, 0x4, {0x104ed3980, 0x0, 0x0}, 0x1}, {0x0?, ...}, ...)
	/Users/runner/work/ollama/ollama/runner/ollamarunner/runner.go:1202 +0xac fp=0x14000045710 sp=0x14000045660 pc=0x1031a219c
github.com/ollama/ollama/runner/ollamarunner.(*Server).load(0x140000352c0, {0x1043c6860, 0x140001aa000}, 0x140002fe000)
	/Users/runner/work/ollama/ollama/runner/ollamarunner/runner.go:1317 +0x460 fp=0x14000045aa0 sp=0x14000045710 pc=0x1031a2da0
github.com/ollama/ollama/runner/ollamarunner.(*Server).load-fm({0x1043c6860?, 0x140001aa000?}, 0x140001a5b28?)
	<autogenerated>:1 +0x40 fp=0x14000045ad0 sp=0x14000045aa0 pc=0x1031a4c50
net/http.HandlerFunc.ServeHTTP(0x1400068e840?, {0x1043c6860?, 0x140001aa000?}, 0x140001a5b10?)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/net/http/server.go:2294 +0x38 fp=0x14000045b00 sp=0x14000045ad0 pc=0x102ec0778
net/http.(*ServeMux).ServeHTTP(0x10?, {0x1043c6860, 0x140001aa000}, 0x140002fe000)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/net/http/server.go:2822 +0x1b4 fp=0x14000045b50 sp=0x14000045b00 pc=0x102ec2304
net/http.serverHandler.ServeHTTP({0x1043c28d0?}, {0x1043c6860?, 0x140001aa000?}, 0x1?)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/net/http/server.go:3301 +0xbc fp=0x14000045b80 sp=0x14000045b50 pc=0x102eddfec
net/http.(*conn).serve(0x1400036e510, {0x1043c90e8, 0x14000177890})
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/net/http/server.go:2102 +0x52c fp=0x14000045fa0 sp=0x14000045b80 pc=0x102ebef1c
net/http.(*Server).Serve.gowrap3()
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/net/http/server.go:3454 +0x30 fp=0x14000045fd0 sp=0x14000045fa0 pc=0x102ec40e0
runtime.goexit({})
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x14000045fd0 sp=0x14000045fd0 pc=0x102c008b4
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, locked to thread]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x14000e2f710 sp=0x14000e2f6f0 pc=0x102bf8248
runtime.netpollblock(0x140004f17a8?, 0x2c7d050?, 0x1?)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/netpoll.go:575 +0x158 fp=0x14000e2f750 sp=0x14000e2f710 pc=0x102bbdca8
internal/poll.runtime_pollWait(0x105254210, 0x72)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/netpoll.go:351 +0xa0 fp=0x14000e2f780 sp=0x14000e2f750 pc=0x102bf7400
internal/poll.(*pollDesc).wait(0x1400015b400?, 0x102c7f2b8?, 0x0)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/internal/poll/fd_poll_runtime.go:84 +0x28 fp=0x14000e2f7b0 sp=0x14000e2f780 pc=0x102c78868
internal/poll.(*pollDesc).waitRead(...)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/internal/poll/fd_poll_runtime.go:89
internal/poll.(*FD).Accept(0x1400015b400)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/internal/poll/fd_unix.go:620 +0x24c fp=0x14000e2f860 sp=0x14000e2f7b0 pc=0x102c7d13c
net.(*netFD).accept(0x1400015b400)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/net/fd_unix.go:172 +0x28 fp=0x14000e2f920 sp=0x14000e2f860 pc=0x102ced478
net.(*TCPListener).accept(0x140003079c0)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/net/tcpsock_posix.go:159 +0x24 fp=0x14000e2f970 sp=0x14000e2f920 pc=0x102d01c54
net.(*TCPListener).Accept(0x140003079c0)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/net/tcpsock.go:380 +0x2c fp=0x14000e2f9b0 sp=0x14000e2f970 pc=0x102d00c3c
net/http.(*onceCloseListener).Accept(0x1400036e510?)
	<autogenerated>:1 +0x30 fp=0x14000e2f9d0 sp=0x14000e2f9b0 pc=0x102eea610
net/http.(*Server).Serve(0x1400026fb00, {0x1043c6680, 0x140003079c0})
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/net/http/server.go:3424 +0x290 fp=0x14000e2fb00 sp=0x14000e2f9d0 pc=0x102ec3d50
github.com/ollama/ollama/runner/ollamarunner.Execute({0x140000320a0, 0x4, 0x4})
	/Users/runner/work/ollama/ollama/runner/ollamarunner/runner.go:1453 +0x7fc fp=0x14000e2fcd0 sp=0x14000e2fb00 pc=0x1031a467c
github.com/ollama/ollama/runner.Execute({0x14000032080?, 0x0?, 0x0?})
	/Users/runner/work/ollama/ollama/runner/runner.go:18 +0x14c fp=0x14000e2fd10 sp=0x14000e2fcd0 pc=0x103237c2c
github.com/ollama/ollama/cmd.NewCLI.func3(0x1400026f800?, {0x103dfb093?, 0x4?, 0x103dfb097?})
	/Users/runner/work/ollama/ollama/cmd/cmd.go:2274 +0x54 fp=0x14000e2fd40 sp=0x14000e2fd10 pc=0x10394fcb4
github.com/spf13/cobra.(*Command).execute(0x1400017fb08, {0x14000150c30, 0x5, 0x5})
	/Users/runner/go/pkg/mod/github.com/spf13/cobra@v1.7.0/command.go:940 +0x648 fp=0x14000e2fe60 sp=0x14000e2fd40 pc=0x102d5c318
github.com/spf13/cobra.(*Command).ExecuteC(0x1400013c908)
	/Users/runner/go/pkg/mod/github.com/spf13/cobra@v1.7.0/command.go:1068 +0x320 fp=0x14000e2ff20 sp=0x14000e2fe60 pc=0x102d5ca60
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=0x14000e2ff40 sp=0x14000e2ff20 pc=0x103951394
runtime.main()
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:283 +0x284 fp=0x14000e2ffd0 sp=0x14000e2ff40 pc=0x102bc4814
runtime.goexit({})
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x14000e2ffd0 sp=0x14000e2ffd0 pc=0x102c008b4

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=0x1400006ef90 sp=0x1400006ef70 pc=0x102bf8248
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=0x1400006efd0 sp=0x1400006ef90 pc=0x102bc4b68
runtime.goexit({})
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x1400006efd0 sp=0x1400006efd0 pc=0x102c008b4
created by runtime.init.7 in goroutine 1
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:336 +0x24

goroutine 18 gp=0x14000102380 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=0x1400006a760 sp=0x1400006a740 pc=0x102bf8248
runtime.goparkunlock(...)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:441
runtime.bgsweep(0x1400009a000)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgcsweep.go:316 +0x108 fp=0x1400006a7b0 sp=0x1400006a760 pc=0x102bafc48
runtime.gcenable.gowrap1()
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:204 +0x28 fp=0x1400006a7d0 sp=0x1400006a7b0 pc=0x102ba3a48
runtime.goexit({})
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x1400006a7d0 sp=0x1400006a7d0 pc=0x102c008b4
created by runtime.gcenable in goroutine 1
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:204 +0x6c

goroutine 19 gp=0x14000102540 m=nil [GC scavenge wait]:
runtime.gopark(0x10000?, 0x104020c80?, 0x0?, 0x0?, 0x0?)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x1400006af60 sp=0x1400006af40 pc=0x102bf8248
runtime.goparkunlock(...)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:441
runtime.(*scavengerState).park(0x104e88900)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgcscavenge.go:425 +0x5c fp=0x1400006af90 sp=0x1400006af60 pc=0x102bad6dc
runtime.bgscavenge(0x1400009a000)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgcscavenge.go:658 +0xac fp=0x1400006afb0 sp=0x1400006af90 pc=0x102badc7c
runtime.gcenable.gowrap2()
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:205 +0x28 fp=0x1400006afd0 sp=0x1400006afb0 pc=0x102ba39e8
runtime.goexit({})
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x1400006afd0 sp=0x1400006afd0 pc=0x102c008b4
created by runtime.gcenable in goroutine 1
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:205 +0xac

goroutine 3 gp=0x14000003880 m=nil [finalizer wait]:
runtime.gopark(0x180006e5c8?, 0x105063ef0?, 0x8?, 0x81?, 0x1c0?)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x1400006e590 sp=0x1400006e570 pc=0x102bf8248
runtime.runfinq()
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mfinal.go:196 +0x108 fp=0x1400006e7d0 sp=0x1400006e590 pc=0x102ba2a48
runtime.goexit({})
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x1400006e7d0 sp=0x1400006e7d0 pc=0x102c008b4
created by runtime.createfing in goroutine 1
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mfinal.go:166 +0x80

goroutine 34 gp=0x140003261c0 m=nil [chan receive]:
runtime.gopark(0x140003028c0?, 0x1400000e198?, 0x48?, 0x87?, 0x102cc15a8?)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x140003786f0 sp=0x140003786d0 pc=0x102bf8248
runtime.chanrecv(0x140003301c0, 0x0, 0x1)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/chan.go:664 +0x42c fp=0x14000378770 sp=0x140003786f0 pc=0x102b94cec
runtime.chanrecv1(0x0?, 0x0?)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/chan.go:506 +0x14 fp=0x140003787a0 sp=0x14000378770 pc=0x102b94884
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=0x140003787d0 sp=0x140003787a0 pc=0x102ba6c6c
runtime.goexit({})
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x140003787d0 sp=0x140003787d0 pc=0x102c008b4
created by unique.runtime_registerUniqueMapCleanup in goroutine 1
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1794 +0x78

goroutine 35 gp=0x14000326380 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=0x14000378f10 sp=0x14000378ef0 pc=0x102bf8248
runtime.gcBgMarkWorker(0x14000331420)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1423 +0xdc fp=0x14000378fb0 sp=0x14000378f10 pc=0x102ba5edc
runtime.gcBgMarkStartWorkers.gowrap1()
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x28 fp=0x14000378fd0 sp=0x14000378fb0 pc=0x102ba5dc8
runtime.goexit({})
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x14000378fd0 sp=0x14000378fd0 pc=0x102c008b4
created by runtime.gcBgMarkStartWorkers in goroutine 1
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x140

goroutine 4 gp=0x140002b81c0 m=nil [GC worker (idle)]:
runtime.gopark(0x82d68827ce87?, 0x0?, 0x0?, 0x0?, 0x0?)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x1400006f710 sp=0x1400006f6f0 pc=0x102bf8248
runtime.gcBgMarkWorker(0x14000331420)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1423 +0xdc fp=0x1400006f7b0 sp=0x1400006f710 pc=0x102ba5edc
runtime.gcBgMarkStartWorkers.gowrap1()
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x28 fp=0x1400006f7d0 sp=0x1400006f7b0 pc=0x102ba5dc8
runtime.goexit({})
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x1400006f7d0 sp=0x1400006f7d0 pc=0x102c008b4
created by runtime.gcBgMarkStartWorkers in goroutine 1
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x140

goroutine 50 gp=0x14000186000 m=nil [GC worker (idle)]:
runtime.gopark(0x82d68827d6fd?, 0x0?, 0x0?, 0x0?, 0x0?)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x14000374710 sp=0x140003746f0 pc=0x102bf8248
runtime.gcBgMarkWorker(0x14000331420)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1423 +0xdc fp=0x140003747b0 sp=0x14000374710 pc=0x102ba5edc
runtime.gcBgMarkStartWorkers.gowrap1()
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x28 fp=0x140003747d0 sp=0x140003747b0 pc=0x102ba5dc8
runtime.goexit({})
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x140003747d0 sp=0x140003747d0 pc=0x102c008b4
created by runtime.gcBgMarkStartWorkers in goroutine 1
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x140

goroutine 36 gp=0x14000326540 m=nil [GC worker (idle)]:
runtime.gopark(0x82d688304ef5?, 0x0?, 0x0?, 0x0?, 0x0?)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x14000379710 sp=0x140003796f0 pc=0x102bf8248
runtime.gcBgMarkWorker(0x14000331420)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1423 +0xdc fp=0x140003797b0 sp=0x14000379710 pc=0x102ba5edc
runtime.gcBgMarkStartWorkers.gowrap1()
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x28 fp=0x140003797d0 sp=0x140003797b0 pc=0x102ba5dc8
runtime.goexit({})
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x140003797d0 sp=0x140003797d0 pc=0x102c008b4
created by runtime.gcBgMarkStartWorkers in goroutine 1
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x140

goroutine 5 gp=0x140002b8380 m=nil [GC worker (idle)]:
runtime.gopark(0x104ed5fe0?, 0x1?, 0xb0?, 0x0?, 0x0?)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x1400006ff10 sp=0x1400006fef0 pc=0x102bf8248
runtime.gcBgMarkWorker(0x14000331420)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1423 +0xdc fp=0x1400006ffb0 sp=0x1400006ff10 pc=0x102ba5edc
runtime.gcBgMarkStartWorkers.gowrap1()
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x28 fp=0x1400006ffd0 sp=0x1400006ffb0 pc=0x102ba5dc8
runtime.goexit({})
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x1400006ffd0 sp=0x1400006ffd0 pc=0x102c008b4
created by runtime.gcBgMarkStartWorkers in goroutine 1
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x140

goroutine 6 gp=0x140002b8540 m=nil [GC worker (idle)]:
runtime.gopark(0x82d6882c71b3?, 0x3?, 0xf3?, 0x10?, 0x0?)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x14000070710 sp=0x140000706f0 pc=0x102bf8248
runtime.gcBgMarkWorker(0x14000331420)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1423 +0xdc fp=0x140000707b0 sp=0x14000070710 pc=0x102ba5edc
runtime.gcBgMarkStartWorkers.gowrap1()
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x28 fp=0x140000707d0 sp=0x140000707b0 pc=0x102ba5dc8
runtime.goexit({})
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x140000707d0 sp=0x140000707d0 pc=0x102c008b4
created by runtime.gcBgMarkStartWorkers in goroutine 1
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x140

goroutine 51 gp=0x140001861c0 m=nil [GC worker (idle)]:
runtime.gopark(0x104ed5fe0?, 0x1?, 0xa5?, 0x9a?, 0x0?)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x14000374f10 sp=0x14000374ef0 pc=0x102bf8248
runtime.gcBgMarkWorker(0x14000331420)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1423 +0xdc fp=0x14000374fb0 sp=0x14000374f10 pc=0x102ba5edc
runtime.gcBgMarkStartWorkers.gowrap1()
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x28 fp=0x14000374fd0 sp=0x14000374fb0 pc=0x102ba5dc8
runtime.goexit({})
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x14000374fd0 sp=0x14000374fd0 pc=0x102c008b4
created by runtime.gcBgMarkStartWorkers in goroutine 1
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x140

goroutine 37 gp=0x14000326700 m=nil [GC worker (idle)]:
runtime.gopark(0x82d68827818a?, 0x1?, 0xc?, 0xde?, 0x0?)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x14000379f10 sp=0x14000379ef0 pc=0x102bf8248
runtime.gcBgMarkWorker(0x14000331420)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1423 +0xdc fp=0x14000379fb0 sp=0x14000379f10 pc=0x102ba5edc
runtime.gcBgMarkStartWorkers.gowrap1()
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x28 fp=0x14000379fd0 sp=0x14000379fb0 pc=0x102ba5dc8
runtime.goexit({})
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x14000379fd0 sp=0x14000379fd0 pc=0x102c008b4
created by runtime.gcBgMarkStartWorkers in goroutine 1
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x140

goroutine 7 gp=0x140002b8700 m=nil [GC worker (idle)]:
runtime.gopark(0x82d68827818a?, 0x0?, 0x0?, 0x0?, 0x0?)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x14000070f10 sp=0x14000070ef0 pc=0x102bf8248
runtime.gcBgMarkWorker(0x14000331420)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1423 +0xdc fp=0x14000070fb0 sp=0x14000070f10 pc=0x102ba5edc
runtime.gcBgMarkStartWorkers.gowrap1()
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x28 fp=0x14000070fd0 sp=0x14000070fb0 pc=0x102ba5dc8
runtime.goexit({})
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x14000070fd0 sp=0x14000070fd0 pc=0x102c008b4
created by runtime.gcBgMarkStartWorkers in goroutine 1
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x140

goroutine 52 gp=0x14000186380 m=nil [GC worker (idle)]:
runtime.gopark(0x82d6883072c4?, 0x3?, 0xa6?, 0x10?, 0x0?)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x14000375710 sp=0x140003756f0 pc=0x102bf8248
runtime.gcBgMarkWorker(0x14000331420)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1423 +0xdc fp=0x140003757b0 sp=0x14000375710 pc=0x102ba5edc
runtime.gcBgMarkStartWorkers.gowrap1()
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x28 fp=0x140003757d0 sp=0x140003757b0 pc=0x102ba5dc8
runtime.goexit({})
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x140003757d0 sp=0x140003757d0 pc=0x102c008b4
created by runtime.gcBgMarkStartWorkers in goroutine 1
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x140

goroutine 20 gp=0x140002b9500 m=nil [sync.WaitGroup.Wait]:
runtime.gopark(0x104e9b120?, 0x0?, 0x0?, 0x40?, 0x0?)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x14000083a90 sp=0x14000083a70 pc=0x102bf8248
runtime.goparkunlock(...)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:441
runtime.semacquire1(0x14000035378, 0x0, 0x1, 0x0, 0x18)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/sema.go:188 +0x204 fp=0x14000083ae0 sp=0x14000083a90 pc=0x102bd8cf4
sync.runtime_SemacquireWaitGroup(0x0?)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/sema.go:110 +0x2c fp=0x14000083b20 sp=0x14000083ae0 pc=0x102bf9cbc
sync.(*WaitGroup).Wait(0x14000035370)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/sync/waitgroup.go:118 +0x70 fp=0x14000083b40 sp=0x14000083b20 pc=0x102c0c2b0
github.com/ollama/ollama/runner/ollamarunner.(*Server).run(0x140000352c0, {0x1043c9120, 0x14000150cd0})
	/Users/runner/work/ollama/ollama/runner/ollamarunner/runner.go:442 +0x38 fp=0x14000083fa0 sp=0x14000083b40 pc=0x10319c988
github.com/ollama/ollama/runner/ollamarunner.Execute.gowrap1()
	/Users/runner/work/ollama/ollama/runner/ollamarunner/runner.go:1430 +0x30 fp=0x14000083fd0 sp=0x14000083fa0 pc=0x1031a48a0
runtime.goexit({})
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x14000083fd0 sp=0x14000083fd0 pc=0x102c008b4
created by github.com/ollama/ollama/runner/ollamarunner.Execute in goroutine 1
	/Users/runner/work/ollama/ollama/runner/ollamarunner/runner.go:1430 +0x448

goroutine 8 gp=0x140002b9880 m=nil [IO wait]:
runtime.gopark(0xffffffffffffffff?, 0xffffffffffffffff?, 0x23?, 0x0?, 0x102c1c4b0?)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x14000376d80 sp=0x14000376d60 pc=0x102bf8248
runtime.netpollblock(0x0?, 0x0?, 0x0?)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/netpoll.go:575 +0x158 fp=0x14000376dc0 sp=0x14000376d80 pc=0x102bbdca8
internal/poll.runtime_pollWait(0x1052540f8, 0x72)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/netpoll.go:351 +0xa0 fp=0x14000376df0 sp=0x14000376dc0 pc=0x102bf7400
internal/poll.(*pollDesc).wait(0x1400015b480?, 0x14000177991?, 0x0)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/internal/poll/fd_poll_runtime.go:84 +0x28 fp=0x14000376e20 sp=0x14000376df0 pc=0x102c78868
internal/poll.(*pollDesc).waitRead(...)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/internal/poll/fd_poll_runtime.go:89
internal/poll.(*FD).Read(0x1400015b480, {0x14000177991, 0x1, 0x1})
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/internal/poll/fd_unix.go:165 +0x1fc fp=0x14000376ec0 sp=0x14000376e20 pc=0x102c79b1c
net.(*netFD).Read(0x1400015b480, {0x14000177991?, 0x14000376f58?, 0x102eb9994?})
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/net/fd_posix.go:55 +0x28 fp=0x14000376f10 sp=0x14000376ec0 pc=0x102ceba48
net.(*conn).Read(0x140000729a8, {0x14000177991?, 0x0?, 0x0?})
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/net/net.go:194 +0x34 fp=0x14000376f60 sp=0x14000376f10 pc=0x102cf8914
net/http.(*connReader).backgroundRead(0x14000177980)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/net/http/server.go:690 +0x40 fp=0x14000376fb0 sp=0x14000376f60 pc=0x102eb9890
net/http.(*connReader).startBackgroundRead.gowrap2()
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/net/http/server.go:686 +0x28 fp=0x14000376fd0 sp=0x14000376fb0 pc=0x102eb9778
runtime.goexit({})
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x14000376fd0 sp=0x14000376fd0 pc=0x102c008b4
created by net/http.(*connReader).startBackgroundRead in goroutine 21
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/net/http/server.go:686 +0xc4

r0      0x0
r1      0x0
r2      0x0
r3      0x0
r4      0x195015a08
r5      0x172419d20
r6      0x32
r7      0x0
r8      0x6710e1eadfcdc77f
r9      0x6710e1ebad8c777f
r10     0x2
r11     0x10000000000
r12     0xfffffffd
r13     0x0
r14     0x0
r15     0x0
r16     0x148
r17     0x2035ec990
r18     0x0
r19     0x6
r20     0x3403
r21     0x17241b0e0
r22     0x0
r23     0x0
r24     0x0
r25     0x1400005ab98
r26     0x1043af8e8
r27     0x828
r28     0x140001028c0
r29     0x17241a610
lr      0x19510d888
sp      0x17241a5f0
pc      0x1950d35b0
fault   0x1950d35b0
time=2026-04-12T20:33:04.299+08:00 level=ERROR source=server.go:1219 msg="do load request" error="Post \"http://127.0.0.1:50337/load\": EOF"
time=2026-04-12T20:33:04.299+08:00 level=ERROR source=server.go:316 msg="llama runner terminated" error="exit status 2"
time=2026-04-12T20:33:04.299+08:00 level=ERROR source=server.go:1219 msg="do load request" error="Post \"http://127.0.0.1:50337/load\": dial tcp 127.0.0.1:50337: connect: connection refused"
time=2026-04-12T20:33:04.299+08:00 level=INFO source=sched.go:511 msg="Load failed" model=/Users/robinliu/.ollama/models/blobs/sha256-dec52a44569a2a25341c4e4d3fee25846eed4f6f0b936278e3a3c900bb99d37c error="model failed to load, this may be due to resource limitations or an internal error, check ollama server logs for details"

OS

macOS

GPU

Apple

CPU

Apple

Ollama version

0.20.5

Originally created by @robin2026-code on GitHub (Apr 12, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/15518 ### What is the issue? From version 0.17.x to 0.20.5, models that previously worked can no longer run。 qwen3.5:9b-q4_K_M worked in 0.17.x，but it not work in 0.20.5 download gemma4:e4b-it-q4_K_M also not work in 0.20.5 Error 500 Internal Server Error: model failed to load, this may be due to resource limitations or an internal error, check ollama server logs for details ### Relevant log output ```shell time=2026-04-12T20:33:02.285+08:00 level=INFO source=server.go:259 msg="enabling flash attention" time=2026-04-12T20:33:02.286+08:00 level=INFO source=server.go:444 msg="starting runner" cmd="/Applications/Ollama.app/Contents/Resources/ollama runner --ollama-engine --model /Users/robinliu/.ollama/models/blobs/sha256-dec52a44569a2a25341c4e4d3fee25846eed4f6f0b936278e3a3c900bb99d37c --port 50337" time=2026-04-12T20:33:02.287+08:00 level=INFO source=sched.go:484 msg="system memory" total="32.0 GiB" free="13.3 GiB" free_swap="0 B" time=2026-04-12T20:33:02.287+08:00 level=INFO source=server.go:771 msg="loading model" "model layers"=33 requested=-1 time=2026-04-12T20:33:02.330+08:00 level=INFO source=runner.go:1417 msg="starting ollama engine" time=2026-04-12T20:33:02.330+08:00 level=INFO source=runner.go:1452 msg="Server listening on 127.0.0.1:50337" time=2026-04-12T20:33:02.330+08:00 level=INFO source=runner.go:1290 msg=load request="{Operation:fit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:4096 KvCacheType: NumThreads:4 GPULayers:[] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" time=2026-04-12T20:33:02.350+08:00 level=INFO source=ggml.go:136 msg="" architecture=qwen35 file_type=Q4_K_M name="" description="" num_tensors=883 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 /Applications/Ollama.app/Contents/Resources/libggml-cpu.so time=2026-04-12T20:33:03.288+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 0x0000000103b43a58 ggml_print_backtrace + 276 1 ollama 0x0000000103b43c44 ggml_abort + 156 2 ollama 0x0000000103b5d544 ggml_backend_get_default_buffer_type + 76 3 ollama 0x0000000103ad9838 _cgo_c81fd19bee02_Cfunc_ggml_backend_get_default_buffer_type + 36 4 ollama 0x0000000102c006ac ollama + 509612 SIGABRT: abort PC=0x1950d35b0 m=11 sigcode=0 signal arrived during cgo execution goroutine 21 gp=0x140002b96c0 m=11 mp=0x1400018a808 [syscall]: runtime.cgocall(0x103ad9814, 0x14000044c88) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/cgocall.go:167 +0x44 fp=0x14000044c50 sp=0x14000044c10 pc=0x102bf4d24 github.com/ollama/ollama/ml/backend/ggml._Cfunc_ggml_backend_get_default_buffer_type(0x0) _cgo_gotypes.go:878 +0x34 fp=0x14000044c80 sp=0x14000044c50 pc=0x103094034 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({0x16d27b732, 0x6c}, {0x0, 0x4, {0x104ed3980, 0x0, 0x0}, 0x1}) /Users/runner/work/ollama/ollama/ml/backend/ggml/ggml.go:361 +0x12e0 fp=0x14000045540 sp=0x14000044c80 pc=0x10309a560 github.com/ollama/ollama/ml.NewBackend({0x16d27b732, 0x6c}, {0x0, 0x4, {0x104ed3980, 0x0, 0x0}, 0x1}) /Users/runner/work/ollama/ollama/ml/backend.go:88 +0x88 fp=0x14000045590 sp=0x14000045540 pc=0x1030425c8 github.com/ollama/ollama/model.New({0x16d27b732?, 0x0?}, {0x0, 0x4, {0x104ed3980, 0x0, 0x0}, 0x1}) /Users/runner/work/ollama/ollama/model/model.go:120 +0x50 fp=0x14000045660 sp=0x14000045590 pc=0x1030d8240 github.com/ollama/ollama/runner/ollamarunner.(*Server).allocModel(0x140000352c0, {0x16d27b732?, 0x0?}, {0x0, 0x4, {0x104ed3980, 0x0, 0x0}, 0x1}, {0x0?, ...}, ...) /Users/runner/work/ollama/ollama/runner/ollamarunner/runner.go:1202 +0xac fp=0x14000045710 sp=0x14000045660 pc=0x1031a219c github.com/ollama/ollama/runner/ollamarunner.(*Server).load(0x140000352c0, {0x1043c6860, 0x140001aa000}, 0x140002fe000) /Users/runner/work/ollama/ollama/runner/ollamarunner/runner.go:1317 +0x460 fp=0x14000045aa0 sp=0x14000045710 pc=0x1031a2da0 github.com/ollama/ollama/runner/ollamarunner.(*Server).load-fm({0x1043c6860?, 0x140001aa000?}, 0x140001a5b28?) <autogenerated>:1 +0x40 fp=0x14000045ad0 sp=0x14000045aa0 pc=0x1031a4c50 net/http.HandlerFunc.ServeHTTP(0x1400068e840?, {0x1043c6860?, 0x140001aa000?}, 0x140001a5b10?) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/net/http/server.go:2294 +0x38 fp=0x14000045b00 sp=0x14000045ad0 pc=0x102ec0778 net/http.(*ServeMux).ServeHTTP(0x10?, {0x1043c6860, 0x140001aa000}, 0x140002fe000) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/net/http/server.go:2822 +0x1b4 fp=0x14000045b50 sp=0x14000045b00 pc=0x102ec2304 net/http.serverHandler.ServeHTTP({0x1043c28d0?}, {0x1043c6860?, 0x140001aa000?}, 0x1?) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/net/http/server.go:3301 +0xbc fp=0x14000045b80 sp=0x14000045b50 pc=0x102eddfec net/http.(*conn).serve(0x1400036e510, {0x1043c90e8, 0x14000177890}) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/net/http/server.go:2102 +0x52c fp=0x14000045fa0 sp=0x14000045b80 pc=0x102ebef1c net/http.(*Server).Serve.gowrap3() /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/net/http/server.go:3454 +0x30 fp=0x14000045fd0 sp=0x14000045fa0 pc=0x102ec40e0 runtime.goexit({}) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x14000045fd0 sp=0x14000045fd0 pc=0x102c008b4 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, locked to thread]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x14000e2f710 sp=0x14000e2f6f0 pc=0x102bf8248 runtime.netpollblock(0x140004f17a8?, 0x2c7d050?, 0x1?) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/netpoll.go:575 +0x158 fp=0x14000e2f750 sp=0x14000e2f710 pc=0x102bbdca8 internal/poll.runtime_pollWait(0x105254210, 0x72) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/netpoll.go:351 +0xa0 fp=0x14000e2f780 sp=0x14000e2f750 pc=0x102bf7400 internal/poll.(*pollDesc).wait(0x1400015b400?, 0x102c7f2b8?, 0x0) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/internal/poll/fd_poll_runtime.go:84 +0x28 fp=0x14000e2f7b0 sp=0x14000e2f780 pc=0x102c78868 internal/poll.(*pollDesc).waitRead(...) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/internal/poll/fd_poll_runtime.go:89 internal/poll.(*FD).Accept(0x1400015b400) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/internal/poll/fd_unix.go:620 +0x24c fp=0x14000e2f860 sp=0x14000e2f7b0 pc=0x102c7d13c net.(*netFD).accept(0x1400015b400) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/net/fd_unix.go:172 +0x28 fp=0x14000e2f920 sp=0x14000e2f860 pc=0x102ced478 net.(*TCPListener).accept(0x140003079c0) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/net/tcpsock_posix.go:159 +0x24 fp=0x14000e2f970 sp=0x14000e2f920 pc=0x102d01c54 net.(*TCPListener).Accept(0x140003079c0) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/net/tcpsock.go:380 +0x2c fp=0x14000e2f9b0 sp=0x14000e2f970 pc=0x102d00c3c net/http.(*onceCloseListener).Accept(0x1400036e510?) <autogenerated>:1 +0x30 fp=0x14000e2f9d0 sp=0x14000e2f9b0 pc=0x102eea610 net/http.(*Server).Serve(0x1400026fb00, {0x1043c6680, 0x140003079c0}) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/net/http/server.go:3424 +0x290 fp=0x14000e2fb00 sp=0x14000e2f9d0 pc=0x102ec3d50 github.com/ollama/ollama/runner/ollamarunner.Execute({0x140000320a0, 0x4, 0x4}) /Users/runner/work/ollama/ollama/runner/ollamarunner/runner.go:1453 +0x7fc fp=0x14000e2fcd0 sp=0x14000e2fb00 pc=0x1031a467c github.com/ollama/ollama/runner.Execute({0x14000032080?, 0x0?, 0x0?}) /Users/runner/work/ollama/ollama/runner/runner.go:18 +0x14c fp=0x14000e2fd10 sp=0x14000e2fcd0 pc=0x103237c2c github.com/ollama/ollama/cmd.NewCLI.func3(0x1400026f800?, {0x103dfb093?, 0x4?, 0x103dfb097?}) /Users/runner/work/ollama/ollama/cmd/cmd.go:2274 +0x54 fp=0x14000e2fd40 sp=0x14000e2fd10 pc=0x10394fcb4 github.com/spf13/cobra.(*Command).execute(0x1400017fb08, {0x14000150c30, 0x5, 0x5}) /Users/runner/go/pkg/mod/github.com/spf13/cobra@v1.7.0/command.go:940 +0x648 fp=0x14000e2fe60 sp=0x14000e2fd40 pc=0x102d5c318 github.com/spf13/cobra.(*Command).ExecuteC(0x1400013c908) /Users/runner/go/pkg/mod/github.com/spf13/cobra@v1.7.0/command.go:1068 +0x320 fp=0x14000e2ff20 sp=0x14000e2fe60 pc=0x102d5ca60 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=0x14000e2ff40 sp=0x14000e2ff20 pc=0x103951394 runtime.main() /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:283 +0x284 fp=0x14000e2ffd0 sp=0x14000e2ff40 pc=0x102bc4814 runtime.goexit({}) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x14000e2ffd0 sp=0x14000e2ffd0 pc=0x102c008b4 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=0x1400006ef90 sp=0x1400006ef70 pc=0x102bf8248 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=0x1400006efd0 sp=0x1400006ef90 pc=0x102bc4b68 runtime.goexit({}) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x1400006efd0 sp=0x1400006efd0 pc=0x102c008b4 created by runtime.init.7 in goroutine 1 /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:336 +0x24 goroutine 18 gp=0x14000102380 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=0x1400006a760 sp=0x1400006a740 pc=0x102bf8248 runtime.goparkunlock(...) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:441 runtime.bgsweep(0x1400009a000) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgcsweep.go:316 +0x108 fp=0x1400006a7b0 sp=0x1400006a760 pc=0x102bafc48 runtime.gcenable.gowrap1() /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:204 +0x28 fp=0x1400006a7d0 sp=0x1400006a7b0 pc=0x102ba3a48 runtime.goexit({}) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x1400006a7d0 sp=0x1400006a7d0 pc=0x102c008b4 created by runtime.gcenable in goroutine 1 /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:204 +0x6c goroutine 19 gp=0x14000102540 m=nil [GC scavenge wait]: runtime.gopark(0x10000?, 0x104020c80?, 0x0?, 0x0?, 0x0?) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x1400006af60 sp=0x1400006af40 pc=0x102bf8248 runtime.goparkunlock(...) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:441 runtime.(*scavengerState).park(0x104e88900) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgcscavenge.go:425 +0x5c fp=0x1400006af90 sp=0x1400006af60 pc=0x102bad6dc runtime.bgscavenge(0x1400009a000) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgcscavenge.go:658 +0xac fp=0x1400006afb0 sp=0x1400006af90 pc=0x102badc7c runtime.gcenable.gowrap2() /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:205 +0x28 fp=0x1400006afd0 sp=0x1400006afb0 pc=0x102ba39e8 runtime.goexit({}) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x1400006afd0 sp=0x1400006afd0 pc=0x102c008b4 created by runtime.gcenable in goroutine 1 /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:205 +0xac goroutine 3 gp=0x14000003880 m=nil [finalizer wait]: runtime.gopark(0x180006e5c8?, 0x105063ef0?, 0x8?, 0x81?, 0x1c0?) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x1400006e590 sp=0x1400006e570 pc=0x102bf8248 runtime.runfinq() /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mfinal.go:196 +0x108 fp=0x1400006e7d0 sp=0x1400006e590 pc=0x102ba2a48 runtime.goexit({}) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x1400006e7d0 sp=0x1400006e7d0 pc=0x102c008b4 created by runtime.createfing in goroutine 1 /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mfinal.go:166 +0x80 goroutine 34 gp=0x140003261c0 m=nil [chan receive]: runtime.gopark(0x140003028c0?, 0x1400000e198?, 0x48?, 0x87?, 0x102cc15a8?) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x140003786f0 sp=0x140003786d0 pc=0x102bf8248 runtime.chanrecv(0x140003301c0, 0x0, 0x1) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/chan.go:664 +0x42c fp=0x14000378770 sp=0x140003786f0 pc=0x102b94cec runtime.chanrecv1(0x0?, 0x0?) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/chan.go:506 +0x14 fp=0x140003787a0 sp=0x14000378770 pc=0x102b94884 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=0x140003787d0 sp=0x140003787a0 pc=0x102ba6c6c runtime.goexit({}) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x140003787d0 sp=0x140003787d0 pc=0x102c008b4 created by unique.runtime_registerUniqueMapCleanup in goroutine 1 /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1794 +0x78 goroutine 35 gp=0x14000326380 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=0x14000378f10 sp=0x14000378ef0 pc=0x102bf8248 runtime.gcBgMarkWorker(0x14000331420) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1423 +0xdc fp=0x14000378fb0 sp=0x14000378f10 pc=0x102ba5edc runtime.gcBgMarkStartWorkers.gowrap1() /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x28 fp=0x14000378fd0 sp=0x14000378fb0 pc=0x102ba5dc8 runtime.goexit({}) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x14000378fd0 sp=0x14000378fd0 pc=0x102c008b4 created by runtime.gcBgMarkStartWorkers in goroutine 1 /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x140 goroutine 4 gp=0x140002b81c0 m=nil [GC worker (idle)]: runtime.gopark(0x82d68827ce87?, 0x0?, 0x0?, 0x0?, 0x0?) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x1400006f710 sp=0x1400006f6f0 pc=0x102bf8248 runtime.gcBgMarkWorker(0x14000331420) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1423 +0xdc fp=0x1400006f7b0 sp=0x1400006f710 pc=0x102ba5edc runtime.gcBgMarkStartWorkers.gowrap1() /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x28 fp=0x1400006f7d0 sp=0x1400006f7b0 pc=0x102ba5dc8 runtime.goexit({}) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x1400006f7d0 sp=0x1400006f7d0 pc=0x102c008b4 created by runtime.gcBgMarkStartWorkers in goroutine 1 /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x140 goroutine 50 gp=0x14000186000 m=nil [GC worker (idle)]: runtime.gopark(0x82d68827d6fd?, 0x0?, 0x0?, 0x0?, 0x0?) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x14000374710 sp=0x140003746f0 pc=0x102bf8248 runtime.gcBgMarkWorker(0x14000331420) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1423 +0xdc fp=0x140003747b0 sp=0x14000374710 pc=0x102ba5edc runtime.gcBgMarkStartWorkers.gowrap1() /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x28 fp=0x140003747d0 sp=0x140003747b0 pc=0x102ba5dc8 runtime.goexit({}) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x140003747d0 sp=0x140003747d0 pc=0x102c008b4 created by runtime.gcBgMarkStartWorkers in goroutine 1 /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x140 goroutine 36 gp=0x14000326540 m=nil [GC worker (idle)]: runtime.gopark(0x82d688304ef5?, 0x0?, 0x0?, 0x0?, 0x0?) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x14000379710 sp=0x140003796f0 pc=0x102bf8248 runtime.gcBgMarkWorker(0x14000331420) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1423 +0xdc fp=0x140003797b0 sp=0x14000379710 pc=0x102ba5edc runtime.gcBgMarkStartWorkers.gowrap1() /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x28 fp=0x140003797d0 sp=0x140003797b0 pc=0x102ba5dc8 runtime.goexit({}) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x140003797d0 sp=0x140003797d0 pc=0x102c008b4 created by runtime.gcBgMarkStartWorkers in goroutine 1 /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x140 goroutine 5 gp=0x140002b8380 m=nil [GC worker (idle)]: runtime.gopark(0x104ed5fe0?, 0x1?, 0xb0?, 0x0?, 0x0?) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x1400006ff10 sp=0x1400006fef0 pc=0x102bf8248 runtime.gcBgMarkWorker(0x14000331420) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1423 +0xdc fp=0x1400006ffb0 sp=0x1400006ff10 pc=0x102ba5edc runtime.gcBgMarkStartWorkers.gowrap1() /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x28 fp=0x1400006ffd0 sp=0x1400006ffb0 pc=0x102ba5dc8 runtime.goexit({}) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x1400006ffd0 sp=0x1400006ffd0 pc=0x102c008b4 created by runtime.gcBgMarkStartWorkers in goroutine 1 /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x140 goroutine 6 gp=0x140002b8540 m=nil [GC worker (idle)]: runtime.gopark(0x82d6882c71b3?, 0x3?, 0xf3?, 0x10?, 0x0?) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x14000070710 sp=0x140000706f0 pc=0x102bf8248 runtime.gcBgMarkWorker(0x14000331420) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1423 +0xdc fp=0x140000707b0 sp=0x14000070710 pc=0x102ba5edc runtime.gcBgMarkStartWorkers.gowrap1() /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x28 fp=0x140000707d0 sp=0x140000707b0 pc=0x102ba5dc8 runtime.goexit({}) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x140000707d0 sp=0x140000707d0 pc=0x102c008b4 created by runtime.gcBgMarkStartWorkers in goroutine 1 /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x140 goroutine 51 gp=0x140001861c0 m=nil [GC worker (idle)]: runtime.gopark(0x104ed5fe0?, 0x1?, 0xa5?, 0x9a?, 0x0?) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x14000374f10 sp=0x14000374ef0 pc=0x102bf8248 runtime.gcBgMarkWorker(0x14000331420) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1423 +0xdc fp=0x14000374fb0 sp=0x14000374f10 pc=0x102ba5edc runtime.gcBgMarkStartWorkers.gowrap1() /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x28 fp=0x14000374fd0 sp=0x14000374fb0 pc=0x102ba5dc8 runtime.goexit({}) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x14000374fd0 sp=0x14000374fd0 pc=0x102c008b4 created by runtime.gcBgMarkStartWorkers in goroutine 1 /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x140 goroutine 37 gp=0x14000326700 m=nil [GC worker (idle)]: runtime.gopark(0x82d68827818a?, 0x1?, 0xc?, 0xde?, 0x0?) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x14000379f10 sp=0x14000379ef0 pc=0x102bf8248 runtime.gcBgMarkWorker(0x14000331420) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1423 +0xdc fp=0x14000379fb0 sp=0x14000379f10 pc=0x102ba5edc runtime.gcBgMarkStartWorkers.gowrap1() /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x28 fp=0x14000379fd0 sp=0x14000379fb0 pc=0x102ba5dc8 runtime.goexit({}) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x14000379fd0 sp=0x14000379fd0 pc=0x102c008b4 created by runtime.gcBgMarkStartWorkers in goroutine 1 /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x140 goroutine 7 gp=0x140002b8700 m=nil [GC worker (idle)]: runtime.gopark(0x82d68827818a?, 0x0?, 0x0?, 0x0?, 0x0?) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x14000070f10 sp=0x14000070ef0 pc=0x102bf8248 runtime.gcBgMarkWorker(0x14000331420) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1423 +0xdc fp=0x14000070fb0 sp=0x14000070f10 pc=0x102ba5edc runtime.gcBgMarkStartWorkers.gowrap1() /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x28 fp=0x14000070fd0 sp=0x14000070fb0 pc=0x102ba5dc8 runtime.goexit({}) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x14000070fd0 sp=0x14000070fd0 pc=0x102c008b4 created by runtime.gcBgMarkStartWorkers in goroutine 1 /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x140 goroutine 52 gp=0x14000186380 m=nil [GC worker (idle)]: runtime.gopark(0x82d6883072c4?, 0x3?, 0xa6?, 0x10?, 0x0?) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x14000375710 sp=0x140003756f0 pc=0x102bf8248 runtime.gcBgMarkWorker(0x14000331420) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1423 +0xdc fp=0x140003757b0 sp=0x14000375710 pc=0x102ba5edc runtime.gcBgMarkStartWorkers.gowrap1() /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x28 fp=0x140003757d0 sp=0x140003757b0 pc=0x102ba5dc8 runtime.goexit({}) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x140003757d0 sp=0x140003757d0 pc=0x102c008b4 created by runtime.gcBgMarkStartWorkers in goroutine 1 /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x140 goroutine 20 gp=0x140002b9500 m=nil [sync.WaitGroup.Wait]: runtime.gopark(0x104e9b120?, 0x0?, 0x0?, 0x40?, 0x0?) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x14000083a90 sp=0x14000083a70 pc=0x102bf8248 runtime.goparkunlock(...) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:441 runtime.semacquire1(0x14000035378, 0x0, 0x1, 0x0, 0x18) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/sema.go:188 +0x204 fp=0x14000083ae0 sp=0x14000083a90 pc=0x102bd8cf4 sync.runtime_SemacquireWaitGroup(0x0?) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/sema.go:110 +0x2c fp=0x14000083b20 sp=0x14000083ae0 pc=0x102bf9cbc sync.(*WaitGroup).Wait(0x14000035370) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/sync/waitgroup.go:118 +0x70 fp=0x14000083b40 sp=0x14000083b20 pc=0x102c0c2b0 github.com/ollama/ollama/runner/ollamarunner.(*Server).run(0x140000352c0, {0x1043c9120, 0x14000150cd0}) /Users/runner/work/ollama/ollama/runner/ollamarunner/runner.go:442 +0x38 fp=0x14000083fa0 sp=0x14000083b40 pc=0x10319c988 github.com/ollama/ollama/runner/ollamarunner.Execute.gowrap1() /Users/runner/work/ollama/ollama/runner/ollamarunner/runner.go:1430 +0x30 fp=0x14000083fd0 sp=0x14000083fa0 pc=0x1031a48a0 runtime.goexit({}) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x14000083fd0 sp=0x14000083fd0 pc=0x102c008b4 created by github.com/ollama/ollama/runner/ollamarunner.Execute in goroutine 1 /Users/runner/work/ollama/ollama/runner/ollamarunner/runner.go:1430 +0x448 goroutine 8 gp=0x140002b9880 m=nil [IO wait]: runtime.gopark(0xffffffffffffffff?, 0xffffffffffffffff?, 0x23?, 0x0?, 0x102c1c4b0?) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x14000376d80 sp=0x14000376d60 pc=0x102bf8248 runtime.netpollblock(0x0?, 0x0?, 0x0?) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/netpoll.go:575 +0x158 fp=0x14000376dc0 sp=0x14000376d80 pc=0x102bbdca8 internal/poll.runtime_pollWait(0x1052540f8, 0x72) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/netpoll.go:351 +0xa0 fp=0x14000376df0 sp=0x14000376dc0 pc=0x102bf7400 internal/poll.(*pollDesc).wait(0x1400015b480?, 0x14000177991?, 0x0) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/internal/poll/fd_poll_runtime.go:84 +0x28 fp=0x14000376e20 sp=0x14000376df0 pc=0x102c78868 internal/poll.(*pollDesc).waitRead(...) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/internal/poll/fd_poll_runtime.go:89 internal/poll.(*FD).Read(0x1400015b480, {0x14000177991, 0x1, 0x1}) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/internal/poll/fd_unix.go:165 +0x1fc fp=0x14000376ec0 sp=0x14000376e20 pc=0x102c79b1c net.(*netFD).Read(0x1400015b480, {0x14000177991?, 0x14000376f58?, 0x102eb9994?}) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/net/fd_posix.go:55 +0x28 fp=0x14000376f10 sp=0x14000376ec0 pc=0x102ceba48 net.(*conn).Read(0x140000729a8, {0x14000177991?, 0x0?, 0x0?}) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/net/net.go:194 +0x34 fp=0x14000376f60 sp=0x14000376f10 pc=0x102cf8914 net/http.(*connReader).backgroundRead(0x14000177980) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/net/http/server.go:690 +0x40 fp=0x14000376fb0 sp=0x14000376f60 pc=0x102eb9890 net/http.(*connReader).startBackgroundRead.gowrap2() /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/net/http/server.go:686 +0x28 fp=0x14000376fd0 sp=0x14000376fb0 pc=0x102eb9778 runtime.goexit({}) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x14000376fd0 sp=0x14000376fd0 pc=0x102c008b4 created by net/http.(*connReader).startBackgroundRead in goroutine 21 /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/net/http/server.go:686 +0xc4 r0 0x0 r1 0x0 r2 0x0 r3 0x0 r4 0x195015a08 r5 0x172419d20 r6 0x32 r7 0x0 r8 0x6710e1eadfcdc77f r9 0x6710e1ebad8c777f r10 0x2 r11 0x10000000000 r12 0xfffffffd r13 0x0 r14 0x0 r15 0x0 r16 0x148 r17 0x2035ec990 r18 0x0 r19 0x6 r20 0x3403 r21 0x17241b0e0 r22 0x0 r23 0x0 r24 0x0 r25 0x1400005ab98 r26 0x1043af8e8 r27 0x828 r28 0x140001028c0 r29 0x17241a610 lr 0x19510d888 sp 0x17241a5f0 pc 0x1950d35b0 fault 0x1950d35b0 time=2026-04-12T20:33:04.299+08:00 level=ERROR source=server.go:1219 msg="do load request" error="Post \"http://127.0.0.1:50337/load\": EOF" time=2026-04-12T20:33:04.299+08:00 level=ERROR source=server.go:316 msg="llama runner terminated" error="exit status 2" time=2026-04-12T20:33:04.299+08:00 level=ERROR source=server.go:1219 msg="do load request" error="Post \"http://127.0.0.1:50337/load\": dial tcp 127.0.0.1:50337: connect: connection refused" time=2026-04-12T20:33:04.299+08:00 level=INFO source=sched.go:511 msg="Load failed" model=/Users/robinliu/.ollama/models/blobs/sha256-dec52a44569a2a25341c4e4d3fee25846eed4f6f0b936278e3a3c900bb99d37c error="model failed to load, this may be due to resource limitations or an internal error, check ollama server logs for details" ``` ### OS macOS ### GPU Apple ### CPU Apple ### Ollama version 0.20.5
GiteaMirror added the bug label 2026-04-29 10:49:06 -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#56431
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?