[GH-ISSUE #13506] Nemotron-3-nano: Assertion failed: (found), function llama_sampler_dist_apply, file llama-sampling.cpp, line 660. #34664

Open
opened 2026-04-22 18:24:39 -05:00 by GiteaMirror · 2 comments
Owner

Originally created by @chigkim on GitHub (Dec 16, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/13506

What is the issue?

I hit nemotron-3-nano via api, and I got an error.

Relevant log output

time=2025-12-16T18:33:43.547-05:00 level=DEBUG source=sched.go:529 msg="finished setting up" runner.name=registry.ollama.ai/library/nemotron-3-nano:30b-a3b-q8_0 runner.inference="[{ID:0 Library:Metal}]" runner.size="32.7 GiB" runner.vram="32.7 GiB" runner.parallel=1 runner.pid=37058 runner.model=/Users/cgk/.ollama/models/blobs/sha256-9c57f6ad9b291e7a7ea07b62711c60fcdf652a72e47efdd466ec953544a1c5eb runner.num_ctx=32000
time=2025-12-16T18:33:43.582-05:00 level=DEBUG source=server.go:1509 msg="completion request" images=0 prompt=37460 format=""
time=2025-12-16T18:33:43.618-05:00 level=DEBUG source=cache.go:104 msg="loading cache slot" id=0 cache=0 prompt=8248 used=0 remaining=8248
ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_scale_f32_4', name = 'kernel_scale_f32_4'
ggml_metal_library_compile_pipeline: loaded kernel_scale_f32_4                            0x107623d70 | th_max = 1024 | th_width =   32
ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_rms_norm_mul_f32_4', name = 'kernel_rms_norm_mul_f32_4'
ggml_metal_library_compile_pipeline: loaded kernel_rms_norm_mul_f32_4                     0x107624570 | th_max = 1024 | th_width =   32
ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_get_rows_f32', name = 'kernel_get_rows_f32'
ggml_metal_library_compile_pipeline: loaded kernel_get_rows_f32                           0x107624d70 | th_max = 1024 | th_width =   32
ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_mul_mm_q8_0_f32', name = 'kernel_mul_mm_q8_0_f32_bci=0_bco=0'
ggml_metal_library_compile_pipeline: loaded kernel_mul_mm_q8_0_f32_bci=0_bco=0            0x107625870 | th_max = 1024 | th_width =   32
ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_concat', name = 'kernel_concat'
ggml_metal_library_compile_pipeline: loaded kernel_concat                                 0x107625b70 | th_max = 1024 | th_width =   32
ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_cpy_f32_f32', name = 'kernel_cpy_f32_f32'
ggml_metal_library_compile_pipeline: loaded kernel_cpy_f32_f32                            0x107625e70 | th_max = 1024 | th_width =   32
ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_ssm_conv_f32_f32_batched_4', name = 'kernel_ssm_conv_f32_f32_batched_4_ssm_conv_bs=256'
ggml_metal_library_compile_pipeline: loaded kernel_ssm_conv_f32_f32_batched_4_ssm_conv_bs=256      0x107626470 | th_max = 1024 | th_width =   32
ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_add_row_c4_fuse_1', name = 'kernel_add_row_c4_fuse_1'
ggml_metal_library_compile_pipeline: loaded kernel_add_row_c4_fuse_1                      0x107626770 | th_max = 1024 | th_width =   32
ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_silu_f32_4', name = 'kernel_silu_f32_4'
ggml_metal_library_compile_pipeline: loaded kernel_silu_f32_4                             0x91ed9c000 | th_max = 1024 | th_width =   32
ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_ssm_scan_f32', name = 'kernel_ssm_scan_f32_nsg=4'
ggml_metal_library_compile_pipeline: loaded kernel_ssm_scan_f32_nsg=4                     0x91ed9c300 | th_max = 1024 | th_width =   32
ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_mul_fuse_1', name = 'kernel_mul_fuse_1'
ggml_metal_library_compile_pipeline: loaded kernel_mul_fuse_1                             0x91ed9c600 | th_max = 1024 | th_width =   32
ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_add_fuse_1', name = 'kernel_add_fuse_1'
ggml_metal_library_compile_pipeline: loaded kernel_add_fuse_1                             0x91ed9c900 | th_max = 1024 | th_width =   32
ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_swiglu_f32', name = 'kernel_swiglu_f32'
ggml_metal_library_compile_pipeline: loaded kernel_swiglu_f32                             0x91ed9cc00 | th_max = 1024 | th_width =   32
ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_mul_mm_f32_f32', name = 'kernel_mul_mm_f32_f32_bci=0_bco=0'
ggml_metal_library_compile_pipeline: loaded kernel_mul_mm_f32_f32_bci=0_bco=0             0x91ed9cf00 | th_max = 1024 | th_width =   32
ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_sigmoid_f32_4', name = 'kernel_sigmoid_f32_4'
ggml_metal_library_compile_pipeline: loaded kernel_sigmoid_f32_4                          0x91ed9d200 | th_max = 1024 | th_width =   32
ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_argsort_f32_i32_desc', name = 'kernel_argsort_f32_i32_desc'
ggml_metal_library_compile_pipeline: loaded kernel_argsort_f32_i32_desc                   0x91ed9d500 | th_max = 1024 | th_width =   32
ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_argsort_merge_f32_i32_desc', name = 'kernel_argsort_merge_f32_i32_desc'
ggml_metal_library_compile_pipeline: loaded kernel_argsort_merge_f32_i32_desc             0x91ed9d800 | th_max = 1024 | th_width =   32
ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_sum_rows_f32', name = 'kernel_sum_rows_f32'
ggml_metal_library_compile_pipeline: loaded kernel_sum_rows_f32                           0x91ed9db00 | th_max = 1024 | th_width =   32
ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_clamp_f32_4', name = 'kernel_clamp_f32_4'
ggml_metal_library_compile_pipeline: loaded kernel_clamp_f32_4                            0x91ed9de00 | th_max = 1024 | th_width =   32
ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_mul_mm_id_map0_ne20_6', name = 'kernel_mul_mm_id_map0_ne20_6_ne02=128'
ggml_metal_library_compile_pipeline: loaded kernel_mul_mm_id_map0_ne20_6_ne02=128         0x91ed9e100 | th_max = 1024 | th_width =   32
ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_mul_mm_id_q8_0_f32', name = 'kernel_mul_mm_id_q8_0_f32_bci=0'
ggml_metal_library_compile_pipeline: loaded kernel_mul_mm_id_q8_0_f32_bci=0               0x91ed9e400 | th_max = 1024 | th_width =   32
ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_div_fuse_1', name = 'kernel_div_fuse_1'
ggml_metal_library_compile_pipeline: loaded kernel_div_fuse_1                             0x91ed9e700 | th_max = 1024 | th_width =   32
ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_relu_f32_4', name = 'kernel_relu_f32_4'
ggml_metal_library_compile_pipeline: loaded kernel_relu_f32_4                             0x91ed9ea00 | th_max = 1024 | th_width =   32
ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_sqr_f32_4', name = 'kernel_sqr_f32_4'
ggml_metal_library_compile_pipeline: loaded kernel_sqr_f32_4                              0x91ed9ed00 | th_max = 1024 | th_width =   32
ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_add_fuse_5', name = 'kernel_add_fuse_5'
ggml_metal_library_compile_pipeline: loaded kernel_add_fuse_5                             0x91ed9f000 | th_max = 1024 | th_width =   32
ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_add_fuse_2', name = 'kernel_add_fuse_2'
ggml_metal_library_compile_pipeline: loaded kernel_add_fuse_2                             0x91ed9f300 | th_max = 1024 | th_width =   32
ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_set_rows_f16_i64', name = 'kernel_set_rows_f16_i64'
ggml_metal_library_compile_pipeline: loaded kernel_set_rows_f16_i64                       0x91ed9f600 | th_max = 1024 | th_width =   32
ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_cpy_f32_f16', name = 'kernel_cpy_f32_f16'
ggml_metal_library_compile_pipeline: loaded kernel_cpy_f32_f16                            0x91ed9f900 | th_max = 1024 | th_width =   32
ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_flash_attn_ext_blk', name = 'kernel_flash_attn_ext_blk_nqptg=8_ncpsg=64'
ggml_metal_library_compile_pipeline: loaded kernel_flash_attn_ext_blk_nqptg=8_ncpsg=64      0x91ed9fc00 | th_max = 1024 | th_width =   32
ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_flash_attn_ext_f16_dk128_dv128', name = 'kernel_flash_attn_ext_f16_dk128_dv128_mask=1_sinks=0_bias=0_scap=0_kvpad=0_bcm=0_ns10=256_ns20=256_nsg=4'
ggml_metal_library_compile_pipeline: loaded kernel_flash_attn_ext_f16_dk128_dv128_mask=1_sinks=0_bias=0_scap=0_kvpad=0_bcm=0_ns10=256_ns20=256_nsg=4      0x91edbc000 | th_max = 1024 | th_width =   32
[GIN] 2025/12/16 - 18:33:48 | 200 |      17.125µs |       127.0.0.1 | HEAD     "/"
[GIN] 2025/12/16 - 18:33:48 | 200 |      14.708µs |       127.0.0.1 | GET      "/api/ps"
ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_mul_mm_q8_0_f32', name = 'kernel_mul_mm_q8_0_f32_bci=0_bco=1'
ggml_metal_library_compile_pipeline: loaded kernel_mul_mm_q8_0_f32_bci=0_bco=1            0x91edbc300 | th_max = 1024 | th_width =   32
ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_ssm_conv_f32_f32_batched_4', name = 'kernel_ssm_conv_f32_f32_batched_4_ssm_conv_bs=64'
ggml_metal_library_compile_pipeline: loaded kernel_ssm_conv_f32_f32_batched_4_ssm_conv_bs=64      0x91edbc600 | th_max = 1024 | th_width =   32
ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_mul_mm_f32_f32', name = 'kernel_mul_mm_f32_f32_bci=0_bco=1'
ggml_metal_library_compile_pipeline: loaded kernel_mul_mm_f32_f32_bci=0_bco=1             0x91edbc900 | th_max = 1024 | th_width =   32
ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_mul_mv_q8_0_f32', name = 'kernel_mul_mv_q8_0_f32_nsg=4'
ggml_metal_library_compile_pipeline: loaded kernel_mul_mv_q8_0_f32_nsg=4                  0x91edbcc00 | th_max = 1024 | th_width =   32
Assertion failed: (found), function llama_sampler_dist_apply, file llama-sampling.cpp, line 660.
SIGABRT: abort
PC=0x1970db5b0 m=12 sigcode=0
signal arrived during cgo execution

goroutine 13 gp=0x14000504a80 m=12 mp=0x14000326008 [syscall]:
runtime.cgocall(0x105762e1c, 0x14000099c48)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/cgocall.go:167 +0x44 fp=0x14000099c00 sp=0x14000099bc0 pc=0x104bdfb64
github.com/ollama/ollama/llama._Cfunc_common_sampler_csample(0x10761efd0, 0x107617850, 0x37)
	_cgo_gotypes.go:417 +0x34 fp=0x14000099c40 sp=0x14000099c00 pc=0x104f42734
github.com/ollama/ollama/runner/llamarunner.(*Server).processBatch.(*SamplingContext).Sample.func1(...)
	/Users/runner/work/ollama/ollama/llama/llama.go:678
github.com/ollama/ollama/llama.(*SamplingContext).Sample(...)
	/Users/runner/work/ollama/ollama/llama/llama.go:678
github.com/ollama/ollama/runner/llamarunner.(*Server).processBatch(0x140004a6140, 0x1400059ca00, 0x14000099f18)
	/Users/runner/work/ollama/ollama/runner/llamarunner/runner.go:539 +0x510 fp=0x14000099ed0 sp=0x14000099c40 pc=0x104fe8920
github.com/ollama/ollama/runner/llamarunner.(*Server).run(0x140004a6140, {0x106297170, 0x140006a23c0})
	/Users/runner/work/ollama/ollama/runner/llamarunner/runner.go:387 +0x164 fp=0x14000099fa0 sp=0x14000099ed0 pc=0x104fe82a4
github.com/ollama/ollama/runner/llamarunner.Execute.gowrap1()
	/Users/runner/work/ollama/ollama/runner/llamarunner/runner.go:981 +0x30 fp=0x14000099fd0 sp=0x14000099fa0 pc=0x104fec7b0
runtime.goexit({})
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x14000099fd0 sp=0x14000099fd0 pc=0x104beb354
created by github.com/ollama/ollama/runner/llamarunner.Execute in goroutine 1
	/Users/runner/work/ollama/ollama/runner/llamarunner/runner.go:981 +0x44c

goroutine 1 gp=0x140000021c0 m=nil [IO wait]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x140003a9720 sp=0x140003a9700 pc=0x104be3088
runtime.netpollblock(0x140005177b8?, 0x4c676c0?, 0x1?)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/netpoll.go:575 +0x158 fp=0x140003a9760 sp=0x140003a9720 pc=0x104ba8c98
internal/poll.runtime_pollWait(0x13242d950, 0x72)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/netpoll.go:351 +0xa0 fp=0x140003a9790 sp=0x140003a9760 pc=0x104be2240
internal/poll.(*pollDesc).wait(0x14000052b00?, 0x104c69928?, 0x0)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/internal/poll/fd_poll_runtime.go:84 +0x28 fp=0x140003a97c0 sp=0x140003a9790 pc=0x104c62ed8
internal/poll.(*pollDesc).waitRead(...)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/internal/poll/fd_poll_runtime.go:89
internal/poll.(*FD).Accept(0x14000052b00)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/internal/poll/fd_unix.go:620 +0x24c fp=0x140003a9870 sp=0x140003a97c0 pc=0x104c677ac
net.(*netFD).accept(0x14000052b00)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/net/fd_unix.go:172 +0x28 fp=0x140003a9930 sp=0x140003a9870 pc=0x104cd7538
net.(*TCPListener).accept(0x140005ac540)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/net/tcpsock_posix.go:159 +0x24 fp=0x140003a9980 sp=0x140003a9930 pc=0x104ceb794
net.(*TCPListener).Accept(0x140005ac540)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/net/tcpsock.go:380 +0x2c fp=0x140003a99c0 sp=0x140003a9980 pc=0x104cea77c
net/http.(*onceCloseListener).Accept(0x140004ae090?)
	<autogenerated>:1 +0x30 fp=0x140003a99e0 sp=0x140003a99c0 pc=0x104ec5b40
net/http.(*Server).Serve(0x1400011e200, {0x106294b20, 0x140005ac540})
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/net/http/server.go:3424 +0x290 fp=0x140003a9b10 sp=0x140003a99e0 pc=0x104e9f280
github.com/ollama/ollama/runner/llamarunner.Execute({0x14000032260, 0x4, 0x4})
	/Users/runner/work/ollama/ollama/runner/llamarunner/runner.go:1002 +0x7ac fp=0x140003a9ce0 sp=0x140003a9b10 pc=0x104fec58c
github.com/ollama/ollama/runner.Execute({0x14000032250?, 0x0?, 0x0?})
	/Users/runner/work/ollama/ollama/runner/runner.go:22 +0x130 fp=0x140003a9d10 sp=0x140003a9ce0 pc=0x105071530
github.com/ollama/ollama/cmd.NewCLI.func2(0x14000203200?, {0x105d9d152?, 0x4?, 0x105d9d156?})
	/Users/runner/work/ollama/ollama/cmd/cmd.go:1841 +0x54 fp=0x140003a9d40 sp=0x140003a9d10 pc=0x105710a44
github.com/spf13/cobra.(*Command).execute(0x140005afb08, {0x140005307c0, 0x4, 0x4})
	/Users/runner/go/pkg/mod/github.com/spf13/cobra@v1.7.0/command.go:940 +0x648 fp=0x140003a9e60 sp=0x140003a9d40 pc=0x104d45ad8
github.com/spf13/cobra.(*Command).ExecuteC(0x140004a0c08)
	/Users/runner/go/pkg/mod/github.com/spf13/cobra@v1.7.0/command.go:1068 +0x320 fp=0x140003a9f20 sp=0x140003a9e60 pc=0x104d46220
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=0x140003a9f40 sp=0x140003a9f20 pc=0x105711594
runtime.main()
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:283 +0x284 fp=0x140003a9fd0 sp=0x140003a9f40 pc=0x104baf804
runtime.goexit({})
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x140003a9fd0 sp=0x140003a9fd0 pc=0x104beb354

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=0x14000084f90 sp=0x14000084f70 pc=0x104be3088
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=0x14000084fd0 sp=0x14000084f90 pc=0x104bafb58
runtime.goexit({})
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x14000084fd0 sp=0x14000084fd0 pc=0x104beb354
created by runtime.init.7 in goroutine 1
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:336 +0x24

goroutine 3 gp=0x14000003180 m=nil [GC sweep wait]:
runtime.gopark(0x1?, 0x0?, 0x0?, 0x0?, 0x0?)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x14000085760 sp=0x14000085740 pc=0x104be3088
runtime.goparkunlock(...)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:441
runtime.bgsweep(0x140000ae000)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgcsweep.go:316 +0x108 fp=0x140000857b0 sp=0x14000085760 pc=0x104b9ac38
runtime.gcenable.gowrap1()
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:204 +0x28 fp=0x140000857d0 sp=0x140000857b0 pc=0x104b8ea38
runtime.goexit({})
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x140000857d0 sp=0x140000857d0 pc=0x104beb354
created by runtime.gcenable in goroutine 1
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:204 +0x6c

goroutine 4 gp=0x14000003340 m=nil [GC scavenge wait]:
runtime.gopark(0x10000?, 0x105f65b00?, 0x0?, 0x0?, 0x0?)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x14000085f60 sp=0x14000085f40 pc=0x104be3088
runtime.goparkunlock(...)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:441
runtime.(*scavengerState).park(0x106bb0280)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgcscavenge.go:425 +0x5c fp=0x14000085f90 sp=0x14000085f60 pc=0x104b986cc
runtime.bgscavenge(0x140000ae000)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgcscavenge.go:658 +0xac fp=0x14000085fb0 sp=0x14000085f90 pc=0x104b98c6c
runtime.gcenable.gowrap2()
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:205 +0x28 fp=0x14000085fd0 sp=0x14000085fb0 pc=0x104b8e9d8
runtime.goexit({})
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x14000085fd0 sp=0x14000085fd0 pc=0x104beb354
created by runtime.gcenable in goroutine 1
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:205 +0xac

goroutine 5 gp=0x14000003c00 m=nil [finalizer wait]:
runtime.gopark(0x0?, 0x106281048?, 0x30?, 0xe0?, 0x1000000010?)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x14000084590 sp=0x14000084570 pc=0x104be3088
runtime.runfinq()
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mfinal.go:196 +0x108 fp=0x140000847d0 sp=0x14000084590 pc=0x104b8da38
runtime.goexit({})
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x140000847d0 sp=0x140000847d0 pc=0x104beb354
created by runtime.createfing in goroutine 1
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mfinal.go:166 +0x80

goroutine 6 gp=0x140001ee700 m=nil [chan receive]:
runtime.gopark(0x14000189a40?, 0x1400038a018?, 0x48?, 0x67?, 0x104cab708?)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x140000866f0 sp=0x140000866d0 pc=0x104be3088
runtime.chanrecv(0x14000044380, 0x0, 0x1)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/chan.go:664 +0x42c fp=0x14000086770 sp=0x140000866f0 pc=0x104b7fdac
runtime.chanrecv1(0x0?, 0x0?)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/chan.go:506 +0x14 fp=0x140000867a0 sp=0x14000086770 pc=0x104b7f944
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=0x140000867d0 sp=0x140000867a0 pc=0x104b91c5c
runtime.goexit({})
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x140000867d0 sp=0x140000867d0 pc=0x104beb354
created by unique.runtime_registerUniqueMapCleanup in goroutine 1
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1794 +0x78

goroutine 7 gp=0x140001eea80 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=0x14000086f10 sp=0x14000086ef0 pc=0x104be3088
runtime.gcBgMarkWorker(0x140000457a0)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1423 +0xdc fp=0x14000086fb0 sp=0x14000086f10 pc=0x104b90ecc
runtime.gcBgMarkStartWorkers.gowrap1()
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x28 fp=0x14000086fd0 sp=0x14000086fb0 pc=0x104b90db8
runtime.goexit({})
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x14000086fd0 sp=0x14000086fd0 pc=0x104beb354
created by runtime.gcBgMarkStartWorkers in goroutine 1
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x140

goroutine 18 gp=0x14000504000 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x14000080710 sp=0x140000806f0 pc=0x104be3088
runtime.gcBgMarkWorker(0x140000457a0)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1423 +0xdc fp=0x140000807b0 sp=0x14000080710 pc=0x104b90ecc
runtime.gcBgMarkStartWorkers.gowrap1()
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x28 fp=0x140000807d0 sp=0x140000807b0 pc=0x104b90db8
runtime.goexit({})
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x140000807d0 sp=0x140000807d0 pc=0x104beb354
created by runtime.gcBgMarkStartWorkers in goroutine 1
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x140

goroutine 34 gp=0x14000102380 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x1400011a710 sp=0x1400011a6f0 pc=0x104be3088
runtime.gcBgMarkWorker(0x140000457a0)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1423 +0xdc fp=0x1400011a7b0 sp=0x1400011a710 pc=0x104b90ecc
runtime.gcBgMarkStartWorkers.gowrap1()
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x28 fp=0x1400011a7d0 sp=0x1400011a7b0 pc=0x104b90db8
runtime.goexit({})
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x1400011a7d0 sp=0x1400011a7d0 pc=0x104beb354
created by runtime.gcBgMarkStartWorkers in goroutine 1
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x140

goroutine 8 gp=0x140001eec40 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=0x14000087710 sp=0x140000876f0 pc=0x104be3088
runtime.gcBgMarkWorker(0x140000457a0)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1423 +0xdc fp=0x140000877b0 sp=0x14000087710 pc=0x104b90ecc
runtime.gcBgMarkStartWorkers.gowrap1()
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x28 fp=0x140000877d0 sp=0x140000877b0 pc=0x104b90db8
runtime.goexit({})
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x140000877d0 sp=0x140000877d0 pc=0x104beb354
created by runtime.gcBgMarkStartWorkers in goroutine 1
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x140

goroutine 9 gp=0x140001eee00 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=0x14000087f10 sp=0x14000087ef0 pc=0x104be3088
runtime.gcBgMarkWorker(0x140000457a0)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1423 +0xdc fp=0x14000087fb0 sp=0x14000087f10 pc=0x104b90ecc
runtime.gcBgMarkStartWorkers.gowrap1()
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x28 fp=0x14000087fd0 sp=0x14000087fb0 pc=0x104b90db8
runtime.goexit({})
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x14000087fd0 sp=0x14000087fd0 pc=0x104beb354
created by runtime.gcBgMarkStartWorkers in goroutine 1
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x140

goroutine 35 gp=0x14000102540 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x1400011af10 sp=0x1400011aef0 pc=0x104be3088
runtime.gcBgMarkWorker(0x140000457a0)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1423 +0xdc fp=0x1400011afb0 sp=0x1400011af10 pc=0x104b90ecc
runtime.gcBgMarkStartWorkers.gowrap1()
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x28 fp=0x1400011afd0 sp=0x1400011afb0 pc=0x104b90db8
runtime.goexit({})
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x1400011afd0 sp=0x1400011afd0 pc=0x104beb354
created by runtime.gcBgMarkStartWorkers in goroutine 1
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x140

goroutine 10 gp=0x140001eefc0 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=0x14000116710 sp=0x140001166f0 pc=0x104be3088
runtime.gcBgMarkWorker(0x140000457a0)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1423 +0xdc fp=0x140001167b0 sp=0x14000116710 pc=0x104b90ecc
runtime.gcBgMarkStartWorkers.gowrap1()
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x28 fp=0x140001167d0 sp=0x140001167b0 pc=0x104b90db8
runtime.goexit({})
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x140001167d0 sp=0x140001167d0 pc=0x104beb354
created by runtime.gcBgMarkStartWorkers in goroutine 1
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x140

goroutine 19 gp=0x140005041c0 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x14000080f10 sp=0x14000080ef0 pc=0x104be3088
runtime.gcBgMarkWorker(0x140000457a0)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1423 +0xdc fp=0x14000080fb0 sp=0x14000080f10 pc=0x104b90ecc
runtime.gcBgMarkStartWorkers.gowrap1()
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x28 fp=0x14000080fd0 sp=0x14000080fb0 pc=0x104b90db8
runtime.goexit({})
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x14000080fd0 sp=0x14000080fd0 pc=0x104beb354
created by runtime.gcBgMarkStartWorkers in goroutine 1
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x140

goroutine 36 gp=0x14000102700 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x1400011b710 sp=0x1400011b6f0 pc=0x104be3088
runtime.gcBgMarkWorker(0x140000457a0)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1423 +0xdc fp=0x1400011b7b0 sp=0x1400011b710 pc=0x104b90ecc
runtime.gcBgMarkStartWorkers.gowrap1()
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x28 fp=0x1400011b7d0 sp=0x1400011b7b0 pc=0x104b90db8
runtime.goexit({})
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x1400011b7d0 sp=0x1400011b7d0 pc=0x104beb354
created by runtime.gcBgMarkStartWorkers in goroutine 1
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x140

goroutine 37 gp=0x140001028c0 m=nil [GC worker (idle)]:
runtime.gopark(0x106be1ee0?, 0x1?, 0xb7?, 0x96?, 0x0?)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x1400011bf10 sp=0x1400011bef0 pc=0x104be3088
runtime.gcBgMarkWorker(0x140000457a0)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1423 +0xdc fp=0x1400011bfb0 sp=0x1400011bf10 pc=0x104b90ecc
runtime.gcBgMarkStartWorkers.gowrap1()
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x28 fp=0x1400011bfd0 sp=0x1400011bfb0 pc=0x104b90db8
runtime.goexit({})
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x1400011bfd0 sp=0x1400011bfd0 pc=0x104beb354
created by runtime.gcBgMarkStartWorkers in goroutine 1
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x140

goroutine 38 gp=0x14000102a80 m=nil [GC worker (idle)]:
runtime.gopark(0x142eee86827ad?, 0x1?, 0xc6?, 0x55?, 0x0?)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x1400011c710 sp=0x1400011c6f0 pc=0x104be3088
runtime.gcBgMarkWorker(0x140000457a0)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1423 +0xdc fp=0x1400011c7b0 sp=0x1400011c710 pc=0x104b90ecc
runtime.gcBgMarkStartWorkers.gowrap1()
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x28 fp=0x1400011c7d0 sp=0x1400011c7b0 pc=0x104b90db8
runtime.goexit({})
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x1400011c7d0 sp=0x1400011c7d0 pc=0x104beb354
created by runtime.gcBgMarkStartWorkers in goroutine 1
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x140

goroutine 39 gp=0x14000102c40 m=nil [GC worker (idle)]:
runtime.gopark(0x106be1ee0?, 0x1?, 0x59?, 0x83?, 0x0?)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x1400011cf10 sp=0x1400011cef0 pc=0x104be3088
runtime.gcBgMarkWorker(0x140000457a0)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1423 +0xdc fp=0x1400011cfb0 sp=0x1400011cf10 pc=0x104b90ecc
runtime.gcBgMarkStartWorkers.gowrap1()
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x28 fp=0x1400011cfd0 sp=0x1400011cfb0 pc=0x104b90db8
runtime.goexit({})
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x1400011cfd0 sp=0x1400011cfd0 pc=0x104beb354
created by runtime.gcBgMarkStartWorkers in goroutine 1
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x140

goroutine 11 gp=0x140001ef180 m=nil [GC worker (idle)]:
runtime.gopark(0x142eee86811de?, 0x1?, 0x5d?, 0x3d?, 0x0?)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x14000116f10 sp=0x14000116ef0 pc=0x104be3088
runtime.gcBgMarkWorker(0x140000457a0)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1423 +0xdc fp=0x14000116fb0 sp=0x14000116f10 pc=0x104b90ecc
runtime.gcBgMarkStartWorkers.gowrap1()
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x28 fp=0x14000116fd0 sp=0x14000116fb0 pc=0x104b90db8
runtime.goexit({})
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x14000116fd0 sp=0x14000116fd0 pc=0x104beb354
created by runtime.gcBgMarkStartWorkers in goroutine 1
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x140

goroutine 20 gp=0x14000504380 m=nil [GC worker (idle)]:
runtime.gopark(0x142eee86810ba?, 0x1?, 0x6d?, 0xe1?, 0x0?)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x14000081710 sp=0x140000816f0 pc=0x104be3088
runtime.gcBgMarkWorker(0x140000457a0)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1423 +0xdc fp=0x140000817b0 sp=0x14000081710 pc=0x104b90ecc
runtime.gcBgMarkStartWorkers.gowrap1()
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x28 fp=0x140000817d0 sp=0x140000817b0 pc=0x104b90db8
runtime.goexit({})
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x140000817d0 sp=0x140000817d0 pc=0x104beb354
created by runtime.gcBgMarkStartWorkers in goroutine 1
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x140

goroutine 12 gp=0x140001ef340 m=nil [GC worker (idle)]:
runtime.gopark(0x142eee8681355?, 0x3?, 0xb6?, 0x3c?, 0x0?)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x14000117710 sp=0x140001176f0 pc=0x104be3088
runtime.gcBgMarkWorker(0x140000457a0)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1423 +0xdc fp=0x140001177b0 sp=0x14000117710 pc=0x104b90ecc
runtime.gcBgMarkStartWorkers.gowrap1()
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x28 fp=0x140001177d0 sp=0x140001177b0 pc=0x104b90db8
runtime.goexit({})
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x140001177d0 sp=0x140001177d0 pc=0x104beb354
created by runtime.gcBgMarkStartWorkers in goroutine 1
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x140

goroutine 40 gp=0x14000102e00 m=nil [GC worker (idle)]:
runtime.gopark(0x106be1ee0?, 0x3?, 0x8c?, 0xb2?, 0x0?)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x1400011d710 sp=0x1400011d6f0 pc=0x104be3088
runtime.gcBgMarkWorker(0x140000457a0)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1423 +0xdc fp=0x1400011d7b0 sp=0x1400011d710 pc=0x104b90ecc
runtime.gcBgMarkStartWorkers.gowrap1()
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x28 fp=0x1400011d7d0 sp=0x1400011d7b0 pc=0x104b90db8
runtime.goexit({})
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x1400011d7d0 sp=0x1400011d7d0 pc=0x104beb354
created by runtime.gcBgMarkStartWorkers in goroutine 1
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x140

goroutine 14 gp=0x14000504c40 m=nil [select]:
runtime.gopark(0x1400004ba60?, 0x2?, 0xa?, 0x0?, 0x1400004b864?)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x1400004b6b0 sp=0x1400004b690 pc=0x104be3088
runtime.selectgo(0x1400004ba60, 0x1400004b860, 0x2038?, 0x0, 0x1?, 0x1)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/select.go:351 +0x6c4 fp=0x1400004b7e0 sp=0x1400004b6b0 pc=0x104bc2e74
github.com/ollama/ollama/runner/llamarunner.(*Server).completion(0x140004a6140, {0x106294d00, 0x1400051ee00}, 0x14000154500)
	/Users/runner/work/ollama/ollama/runner/llamarunner/runner.go:716 +0xa1c fp=0x1400004baa0 sp=0x1400004b7e0 pc=0x104fe9f7c
github.com/ollama/ollama/runner/llamarunner.(*Server).completion-fm({0x106294d00?, 0x1400051ee00?}, 0x1400004bb28?)
	<autogenerated>:1 +0x40 fp=0x1400004bad0 sp=0x1400004baa0 pc=0x104fecba0
net/http.HandlerFunc.ServeHTTP(0x1400053a300?, {0x106294d00?, 0x1400051ee00?}, 0x1400004bb10?)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/net/http/server.go:2294 +0x38 fp=0x1400004bb00 sp=0x1400004bad0 pc=0x104e9bca8
net/http.(*ServeMux).ServeHTTP(0x10?, {0x106294d00, 0x1400051ee00}, 0x14000154500)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/net/http/server.go:2822 +0x1b4 fp=0x1400004bb50 sp=0x1400004bb00 pc=0x104e9d834
net/http.serverHandler.ServeHTTP({0x1062912f0?}, {0x106294d00?, 0x1400051ee00?}, 0x1?)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/net/http/server.go:3301 +0xbc fp=0x1400004bb80 sp=0x1400004bb50 pc=0x104eb951c
net/http.(*conn).serve(0x140004ae090, {0x106297138, 0x140000ffb00})
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/net/http/server.go:2102 +0x52c fp=0x1400004bfa0 sp=0x1400004bb80 pc=0x104e9a44c
net/http.(*Server).Serve.gowrap3()
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/net/http/server.go:3454 +0x30 fp=0x1400004bfd0 sp=0x1400004bfa0 pc=0x104e9f610
runtime.goexit({})
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x1400004bfd0 sp=0x1400004bfd0 pc=0x104beb354
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 46 gp=0x14000504fc0 m=nil [IO wait]:
runtime.gopark(0xffffffffffffffff?, 0xffffffffffffffff?, 0x23?, 0x0?, 0x104c06b70?)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x14000152580 sp=0x14000152560 pc=0x104be3088
runtime.netpollblock(0x0?, 0x0?, 0x0?)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/netpoll.go:575 +0x158 fp=0x140001525c0 sp=0x14000152580 pc=0x104ba8c98
internal/poll.runtime_pollWait(0x13242d838, 0x72)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/netpoll.go:351 +0xa0 fp=0x140001525f0 sp=0x140001525c0 pc=0x104be2240
internal/poll.(*pollDesc).wait(0x14000052b80?, 0x140000ffc01?, 0x0)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/internal/poll/fd_poll_runtime.go:84 +0x28 fp=0x14000152620 sp=0x140001525f0 pc=0x104c62ed8
internal/poll.(*pollDesc).waitRead(...)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/internal/poll/fd_poll_runtime.go:89
internal/poll.(*FD).Read(0x14000052b80, {0x140000ffc01, 0x1, 0x1})
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/internal/poll/fd_unix.go:165 +0x1fc fp=0x140001526c0 sp=0x14000152620 pc=0x104c6418c
net.(*netFD).Read(0x14000052b80, {0x140000ffc01?, 0x14000152758?, 0x104e94ec4?})
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/net/fd_posix.go:55 +0x28 fp=0x14000152710 sp=0x140001526c0 pc=0x104cd5b08
net.(*conn).Read(0x14000526098, {0x140000ffc01?, 0x0?, 0x0?})
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/net/net.go:194 +0x34 fp=0x14000152760 sp=0x14000152710 pc=0x104ce29d4
net/http.(*connReader).backgroundRead(0x140000ffbf0)
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/net/http/server.go:690 +0x40 fp=0x140001527b0 sp=0x14000152760 pc=0x104e94dc0
net/http.(*connReader).startBackgroundRead.gowrap2()
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/net/http/server.go:686 +0x28 fp=0x140001527d0 sp=0x140001527b0 pc=0x104e94ca8
runtime.goexit({})
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x140001527d0 sp=0x140001527d0 pc=0x104beb354
created by net/http.(*connReader).startBackgroundRead in goroutine 14
	/Users/runner/hostedtoolcache/go/1.24.1/arm64/src/net/http/server.go:686 +0xc4

r0      0x0
r1      0x0
r2      0x0
r3      0x0
r4      0x0
r5      0x2e
r6      0x91b400000
r7      0x0
r8      0x502f0da86a09699e
r9      0x502f0da91ef6599e
r10     0x2
r11     0x10000000000
r12     0xfffffffd
r13     0x0
r14     0x0
r15     0x0
r16     0x148
r17     0x2055f4990
r18     0x0
r19     0x6
r20     0x330f
r21     0x174ff30e0
r22     0x1665e8000
r23     0x105f96bfc
r24     0x201631000
r25     0x14000067c90
r26     0x14000099b08
r27     0x818
r28     0x14000582540
r29     0x174ff2ba0
lr      0x197115888
sp      0x174ff2b80
pc      0x1970db5b0
fault   0x1970db5b0
time=2025-12-16T18:33:51.700-05:00 level=ERROR source=server.go:1583 msg="post predict" error="Post \"http://127.0.0.1:52036/completion\": EOF"
[GIN] 2025/12/16 - 18:33:51 | 500 | 10.776447958s |  192.168.99.177 | POST     "/api/chat"
time=2025-12-16T18:33:51.700-05:00 level=DEBUG source=sched.go:537 msg="context for request finished"
time=2025-12-16T18:33:51.700-05:00 level=DEBUG source=sched.go:290 msg="runner with non-zero duration has gone idle, adding timer" runner.name=registry.ollama.ai/library/nemotron-3-nano:30b-a3b-q8_0 runner.inference="[{ID:0 Library:Metal}]" runner.size="32.7 GiB" runner.vram="32.7 GiB" runner.parallel=1 runner.pid=37058 runner.model=/Users/cgk/.ollama/models/blobs/sha256-9c57f6ad9b291e7a7ea07b62711c60fcdf652a72e47efdd466ec953544a1c5eb runner.num_ctx=32000 duration=5m0s
time=2025-12-16T18:33:51.700-05:00 level=DEBUG source=sched.go:308 msg="after processing request finished event" runner.name=registry.ollama.ai/library/nemotron-3-nano:30b-a3b-q8_0 runner.inference="[{ID:0 Library:Metal}]" runner.size="32.7 GiB" runner.vram="32.7 GiB" runner.parallel=1 runner.pid=37058 runner.model=/Users/cgk/.ollama/models/blobs/sha256-9c57f6ad9b291e7a7ea07b62711c60fcdf652a72e47efdd466ec953544a1c5eb runner.num_ctx=32000 refCount=0

OS

macOS

GPU

Apple

CPU

Apple

Ollama version

0.13.4

Originally created by @chigkim on GitHub (Dec 16, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/13506 ### What is the issue? I hit nemotron-3-nano via api, and I got an error. ### Relevant log output ```shell time=2025-12-16T18:33:43.547-05:00 level=DEBUG source=sched.go:529 msg="finished setting up" runner.name=registry.ollama.ai/library/nemotron-3-nano:30b-a3b-q8_0 runner.inference="[{ID:0 Library:Metal}]" runner.size="32.7 GiB" runner.vram="32.7 GiB" runner.parallel=1 runner.pid=37058 runner.model=/Users/cgk/.ollama/models/blobs/sha256-9c57f6ad9b291e7a7ea07b62711c60fcdf652a72e47efdd466ec953544a1c5eb runner.num_ctx=32000 time=2025-12-16T18:33:43.582-05:00 level=DEBUG source=server.go:1509 msg="completion request" images=0 prompt=37460 format="" time=2025-12-16T18:33:43.618-05:00 level=DEBUG source=cache.go:104 msg="loading cache slot" id=0 cache=0 prompt=8248 used=0 remaining=8248 ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_scale_f32_4', name = 'kernel_scale_f32_4' ggml_metal_library_compile_pipeline: loaded kernel_scale_f32_4 0x107623d70 | th_max = 1024 | th_width = 32 ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_rms_norm_mul_f32_4', name = 'kernel_rms_norm_mul_f32_4' ggml_metal_library_compile_pipeline: loaded kernel_rms_norm_mul_f32_4 0x107624570 | th_max = 1024 | th_width = 32 ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_get_rows_f32', name = 'kernel_get_rows_f32' ggml_metal_library_compile_pipeline: loaded kernel_get_rows_f32 0x107624d70 | th_max = 1024 | th_width = 32 ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_mul_mm_q8_0_f32', name = 'kernel_mul_mm_q8_0_f32_bci=0_bco=0' ggml_metal_library_compile_pipeline: loaded kernel_mul_mm_q8_0_f32_bci=0_bco=0 0x107625870 | th_max = 1024 | th_width = 32 ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_concat', name = 'kernel_concat' ggml_metal_library_compile_pipeline: loaded kernel_concat 0x107625b70 | th_max = 1024 | th_width = 32 ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_cpy_f32_f32', name = 'kernel_cpy_f32_f32' ggml_metal_library_compile_pipeline: loaded kernel_cpy_f32_f32 0x107625e70 | th_max = 1024 | th_width = 32 ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_ssm_conv_f32_f32_batched_4', name = 'kernel_ssm_conv_f32_f32_batched_4_ssm_conv_bs=256' ggml_metal_library_compile_pipeline: loaded kernel_ssm_conv_f32_f32_batched_4_ssm_conv_bs=256 0x107626470 | th_max = 1024 | th_width = 32 ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_add_row_c4_fuse_1', name = 'kernel_add_row_c4_fuse_1' ggml_metal_library_compile_pipeline: loaded kernel_add_row_c4_fuse_1 0x107626770 | th_max = 1024 | th_width = 32 ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_silu_f32_4', name = 'kernel_silu_f32_4' ggml_metal_library_compile_pipeline: loaded kernel_silu_f32_4 0x91ed9c000 | th_max = 1024 | th_width = 32 ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_ssm_scan_f32', name = 'kernel_ssm_scan_f32_nsg=4' ggml_metal_library_compile_pipeline: loaded kernel_ssm_scan_f32_nsg=4 0x91ed9c300 | th_max = 1024 | th_width = 32 ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_mul_fuse_1', name = 'kernel_mul_fuse_1' ggml_metal_library_compile_pipeline: loaded kernel_mul_fuse_1 0x91ed9c600 | th_max = 1024 | th_width = 32 ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_add_fuse_1', name = 'kernel_add_fuse_1' ggml_metal_library_compile_pipeline: loaded kernel_add_fuse_1 0x91ed9c900 | th_max = 1024 | th_width = 32 ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_swiglu_f32', name = 'kernel_swiglu_f32' ggml_metal_library_compile_pipeline: loaded kernel_swiglu_f32 0x91ed9cc00 | th_max = 1024 | th_width = 32 ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_mul_mm_f32_f32', name = 'kernel_mul_mm_f32_f32_bci=0_bco=0' ggml_metal_library_compile_pipeline: loaded kernel_mul_mm_f32_f32_bci=0_bco=0 0x91ed9cf00 | th_max = 1024 | th_width = 32 ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_sigmoid_f32_4', name = 'kernel_sigmoid_f32_4' ggml_metal_library_compile_pipeline: loaded kernel_sigmoid_f32_4 0x91ed9d200 | th_max = 1024 | th_width = 32 ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_argsort_f32_i32_desc', name = 'kernel_argsort_f32_i32_desc' ggml_metal_library_compile_pipeline: loaded kernel_argsort_f32_i32_desc 0x91ed9d500 | th_max = 1024 | th_width = 32 ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_argsort_merge_f32_i32_desc', name = 'kernel_argsort_merge_f32_i32_desc' ggml_metal_library_compile_pipeline: loaded kernel_argsort_merge_f32_i32_desc 0x91ed9d800 | th_max = 1024 | th_width = 32 ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_sum_rows_f32', name = 'kernel_sum_rows_f32' ggml_metal_library_compile_pipeline: loaded kernel_sum_rows_f32 0x91ed9db00 | th_max = 1024 | th_width = 32 ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_clamp_f32_4', name = 'kernel_clamp_f32_4' ggml_metal_library_compile_pipeline: loaded kernel_clamp_f32_4 0x91ed9de00 | th_max = 1024 | th_width = 32 ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_mul_mm_id_map0_ne20_6', name = 'kernel_mul_mm_id_map0_ne20_6_ne02=128' ggml_metal_library_compile_pipeline: loaded kernel_mul_mm_id_map0_ne20_6_ne02=128 0x91ed9e100 | th_max = 1024 | th_width = 32 ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_mul_mm_id_q8_0_f32', name = 'kernel_mul_mm_id_q8_0_f32_bci=0' ggml_metal_library_compile_pipeline: loaded kernel_mul_mm_id_q8_0_f32_bci=0 0x91ed9e400 | th_max = 1024 | th_width = 32 ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_div_fuse_1', name = 'kernel_div_fuse_1' ggml_metal_library_compile_pipeline: loaded kernel_div_fuse_1 0x91ed9e700 | th_max = 1024 | th_width = 32 ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_relu_f32_4', name = 'kernel_relu_f32_4' ggml_metal_library_compile_pipeline: loaded kernel_relu_f32_4 0x91ed9ea00 | th_max = 1024 | th_width = 32 ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_sqr_f32_4', name = 'kernel_sqr_f32_4' ggml_metal_library_compile_pipeline: loaded kernel_sqr_f32_4 0x91ed9ed00 | th_max = 1024 | th_width = 32 ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_add_fuse_5', name = 'kernel_add_fuse_5' ggml_metal_library_compile_pipeline: loaded kernel_add_fuse_5 0x91ed9f000 | th_max = 1024 | th_width = 32 ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_add_fuse_2', name = 'kernel_add_fuse_2' ggml_metal_library_compile_pipeline: loaded kernel_add_fuse_2 0x91ed9f300 | th_max = 1024 | th_width = 32 ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_set_rows_f16_i64', name = 'kernel_set_rows_f16_i64' ggml_metal_library_compile_pipeline: loaded kernel_set_rows_f16_i64 0x91ed9f600 | th_max = 1024 | th_width = 32 ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_cpy_f32_f16', name = 'kernel_cpy_f32_f16' ggml_metal_library_compile_pipeline: loaded kernel_cpy_f32_f16 0x91ed9f900 | th_max = 1024 | th_width = 32 ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_flash_attn_ext_blk', name = 'kernel_flash_attn_ext_blk_nqptg=8_ncpsg=64' ggml_metal_library_compile_pipeline: loaded kernel_flash_attn_ext_blk_nqptg=8_ncpsg=64 0x91ed9fc00 | th_max = 1024 | th_width = 32 ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_flash_attn_ext_f16_dk128_dv128', name = 'kernel_flash_attn_ext_f16_dk128_dv128_mask=1_sinks=0_bias=0_scap=0_kvpad=0_bcm=0_ns10=256_ns20=256_nsg=4' ggml_metal_library_compile_pipeline: loaded kernel_flash_attn_ext_f16_dk128_dv128_mask=1_sinks=0_bias=0_scap=0_kvpad=0_bcm=0_ns10=256_ns20=256_nsg=4 0x91edbc000 | th_max = 1024 | th_width = 32 [GIN] 2025/12/16 - 18:33:48 | 200 | 17.125µs | 127.0.0.1 | HEAD "/" [GIN] 2025/12/16 - 18:33:48 | 200 | 14.708µs | 127.0.0.1 | GET "/api/ps" ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_mul_mm_q8_0_f32', name = 'kernel_mul_mm_q8_0_f32_bci=0_bco=1' ggml_metal_library_compile_pipeline: loaded kernel_mul_mm_q8_0_f32_bci=0_bco=1 0x91edbc300 | th_max = 1024 | th_width = 32 ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_ssm_conv_f32_f32_batched_4', name = 'kernel_ssm_conv_f32_f32_batched_4_ssm_conv_bs=64' ggml_metal_library_compile_pipeline: loaded kernel_ssm_conv_f32_f32_batched_4_ssm_conv_bs=64 0x91edbc600 | th_max = 1024 | th_width = 32 ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_mul_mm_f32_f32', name = 'kernel_mul_mm_f32_f32_bci=0_bco=1' ggml_metal_library_compile_pipeline: loaded kernel_mul_mm_f32_f32_bci=0_bco=1 0x91edbc900 | th_max = 1024 | th_width = 32 ggml_metal_library_compile_pipeline: compiling pipeline: base = 'kernel_mul_mv_q8_0_f32', name = 'kernel_mul_mv_q8_0_f32_nsg=4' ggml_metal_library_compile_pipeline: loaded kernel_mul_mv_q8_0_f32_nsg=4 0x91edbcc00 | th_max = 1024 | th_width = 32 Assertion failed: (found), function llama_sampler_dist_apply, file llama-sampling.cpp, line 660. SIGABRT: abort PC=0x1970db5b0 m=12 sigcode=0 signal arrived during cgo execution goroutine 13 gp=0x14000504a80 m=12 mp=0x14000326008 [syscall]: runtime.cgocall(0x105762e1c, 0x14000099c48) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/cgocall.go:167 +0x44 fp=0x14000099c00 sp=0x14000099bc0 pc=0x104bdfb64 github.com/ollama/ollama/llama._Cfunc_common_sampler_csample(0x10761efd0, 0x107617850, 0x37) _cgo_gotypes.go:417 +0x34 fp=0x14000099c40 sp=0x14000099c00 pc=0x104f42734 github.com/ollama/ollama/runner/llamarunner.(*Server).processBatch.(*SamplingContext).Sample.func1(...) /Users/runner/work/ollama/ollama/llama/llama.go:678 github.com/ollama/ollama/llama.(*SamplingContext).Sample(...) /Users/runner/work/ollama/ollama/llama/llama.go:678 github.com/ollama/ollama/runner/llamarunner.(*Server).processBatch(0x140004a6140, 0x1400059ca00, 0x14000099f18) /Users/runner/work/ollama/ollama/runner/llamarunner/runner.go:539 +0x510 fp=0x14000099ed0 sp=0x14000099c40 pc=0x104fe8920 github.com/ollama/ollama/runner/llamarunner.(*Server).run(0x140004a6140, {0x106297170, 0x140006a23c0}) /Users/runner/work/ollama/ollama/runner/llamarunner/runner.go:387 +0x164 fp=0x14000099fa0 sp=0x14000099ed0 pc=0x104fe82a4 github.com/ollama/ollama/runner/llamarunner.Execute.gowrap1() /Users/runner/work/ollama/ollama/runner/llamarunner/runner.go:981 +0x30 fp=0x14000099fd0 sp=0x14000099fa0 pc=0x104fec7b0 runtime.goexit({}) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x14000099fd0 sp=0x14000099fd0 pc=0x104beb354 created by github.com/ollama/ollama/runner/llamarunner.Execute in goroutine 1 /Users/runner/work/ollama/ollama/runner/llamarunner/runner.go:981 +0x44c goroutine 1 gp=0x140000021c0 m=nil [IO wait]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x140003a9720 sp=0x140003a9700 pc=0x104be3088 runtime.netpollblock(0x140005177b8?, 0x4c676c0?, 0x1?) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/netpoll.go:575 +0x158 fp=0x140003a9760 sp=0x140003a9720 pc=0x104ba8c98 internal/poll.runtime_pollWait(0x13242d950, 0x72) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/netpoll.go:351 +0xa0 fp=0x140003a9790 sp=0x140003a9760 pc=0x104be2240 internal/poll.(*pollDesc).wait(0x14000052b00?, 0x104c69928?, 0x0) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/internal/poll/fd_poll_runtime.go:84 +0x28 fp=0x140003a97c0 sp=0x140003a9790 pc=0x104c62ed8 internal/poll.(*pollDesc).waitRead(...) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/internal/poll/fd_poll_runtime.go:89 internal/poll.(*FD).Accept(0x14000052b00) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/internal/poll/fd_unix.go:620 +0x24c fp=0x140003a9870 sp=0x140003a97c0 pc=0x104c677ac net.(*netFD).accept(0x14000052b00) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/net/fd_unix.go:172 +0x28 fp=0x140003a9930 sp=0x140003a9870 pc=0x104cd7538 net.(*TCPListener).accept(0x140005ac540) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/net/tcpsock_posix.go:159 +0x24 fp=0x140003a9980 sp=0x140003a9930 pc=0x104ceb794 net.(*TCPListener).Accept(0x140005ac540) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/net/tcpsock.go:380 +0x2c fp=0x140003a99c0 sp=0x140003a9980 pc=0x104cea77c net/http.(*onceCloseListener).Accept(0x140004ae090?) <autogenerated>:1 +0x30 fp=0x140003a99e0 sp=0x140003a99c0 pc=0x104ec5b40 net/http.(*Server).Serve(0x1400011e200, {0x106294b20, 0x140005ac540}) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/net/http/server.go:3424 +0x290 fp=0x140003a9b10 sp=0x140003a99e0 pc=0x104e9f280 github.com/ollama/ollama/runner/llamarunner.Execute({0x14000032260, 0x4, 0x4}) /Users/runner/work/ollama/ollama/runner/llamarunner/runner.go:1002 +0x7ac fp=0x140003a9ce0 sp=0x140003a9b10 pc=0x104fec58c github.com/ollama/ollama/runner.Execute({0x14000032250?, 0x0?, 0x0?}) /Users/runner/work/ollama/ollama/runner/runner.go:22 +0x130 fp=0x140003a9d10 sp=0x140003a9ce0 pc=0x105071530 github.com/ollama/ollama/cmd.NewCLI.func2(0x14000203200?, {0x105d9d152?, 0x4?, 0x105d9d156?}) /Users/runner/work/ollama/ollama/cmd/cmd.go:1841 +0x54 fp=0x140003a9d40 sp=0x140003a9d10 pc=0x105710a44 github.com/spf13/cobra.(*Command).execute(0x140005afb08, {0x140005307c0, 0x4, 0x4}) /Users/runner/go/pkg/mod/github.com/spf13/cobra@v1.7.0/command.go:940 +0x648 fp=0x140003a9e60 sp=0x140003a9d40 pc=0x104d45ad8 github.com/spf13/cobra.(*Command).ExecuteC(0x140004a0c08) /Users/runner/go/pkg/mod/github.com/spf13/cobra@v1.7.0/command.go:1068 +0x320 fp=0x140003a9f20 sp=0x140003a9e60 pc=0x104d46220 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=0x140003a9f40 sp=0x140003a9f20 pc=0x105711594 runtime.main() /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:283 +0x284 fp=0x140003a9fd0 sp=0x140003a9f40 pc=0x104baf804 runtime.goexit({}) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x140003a9fd0 sp=0x140003a9fd0 pc=0x104beb354 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=0x14000084f90 sp=0x14000084f70 pc=0x104be3088 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=0x14000084fd0 sp=0x14000084f90 pc=0x104bafb58 runtime.goexit({}) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x14000084fd0 sp=0x14000084fd0 pc=0x104beb354 created by runtime.init.7 in goroutine 1 /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:336 +0x24 goroutine 3 gp=0x14000003180 m=nil [GC sweep wait]: runtime.gopark(0x1?, 0x0?, 0x0?, 0x0?, 0x0?) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x14000085760 sp=0x14000085740 pc=0x104be3088 runtime.goparkunlock(...) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:441 runtime.bgsweep(0x140000ae000) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgcsweep.go:316 +0x108 fp=0x140000857b0 sp=0x14000085760 pc=0x104b9ac38 runtime.gcenable.gowrap1() /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:204 +0x28 fp=0x140000857d0 sp=0x140000857b0 pc=0x104b8ea38 runtime.goexit({}) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x140000857d0 sp=0x140000857d0 pc=0x104beb354 created by runtime.gcenable in goroutine 1 /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:204 +0x6c goroutine 4 gp=0x14000003340 m=nil [GC scavenge wait]: runtime.gopark(0x10000?, 0x105f65b00?, 0x0?, 0x0?, 0x0?) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x14000085f60 sp=0x14000085f40 pc=0x104be3088 runtime.goparkunlock(...) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:441 runtime.(*scavengerState).park(0x106bb0280) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgcscavenge.go:425 +0x5c fp=0x14000085f90 sp=0x14000085f60 pc=0x104b986cc runtime.bgscavenge(0x140000ae000) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgcscavenge.go:658 +0xac fp=0x14000085fb0 sp=0x14000085f90 pc=0x104b98c6c runtime.gcenable.gowrap2() /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:205 +0x28 fp=0x14000085fd0 sp=0x14000085fb0 pc=0x104b8e9d8 runtime.goexit({}) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x14000085fd0 sp=0x14000085fd0 pc=0x104beb354 created by runtime.gcenable in goroutine 1 /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:205 +0xac goroutine 5 gp=0x14000003c00 m=nil [finalizer wait]: runtime.gopark(0x0?, 0x106281048?, 0x30?, 0xe0?, 0x1000000010?) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x14000084590 sp=0x14000084570 pc=0x104be3088 runtime.runfinq() /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mfinal.go:196 +0x108 fp=0x140000847d0 sp=0x14000084590 pc=0x104b8da38 runtime.goexit({}) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x140000847d0 sp=0x140000847d0 pc=0x104beb354 created by runtime.createfing in goroutine 1 /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mfinal.go:166 +0x80 goroutine 6 gp=0x140001ee700 m=nil [chan receive]: runtime.gopark(0x14000189a40?, 0x1400038a018?, 0x48?, 0x67?, 0x104cab708?) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x140000866f0 sp=0x140000866d0 pc=0x104be3088 runtime.chanrecv(0x14000044380, 0x0, 0x1) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/chan.go:664 +0x42c fp=0x14000086770 sp=0x140000866f0 pc=0x104b7fdac runtime.chanrecv1(0x0?, 0x0?) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/chan.go:506 +0x14 fp=0x140000867a0 sp=0x14000086770 pc=0x104b7f944 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=0x140000867d0 sp=0x140000867a0 pc=0x104b91c5c runtime.goexit({}) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x140000867d0 sp=0x140000867d0 pc=0x104beb354 created by unique.runtime_registerUniqueMapCleanup in goroutine 1 /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1794 +0x78 goroutine 7 gp=0x140001eea80 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=0x14000086f10 sp=0x14000086ef0 pc=0x104be3088 runtime.gcBgMarkWorker(0x140000457a0) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1423 +0xdc fp=0x14000086fb0 sp=0x14000086f10 pc=0x104b90ecc runtime.gcBgMarkStartWorkers.gowrap1() /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x28 fp=0x14000086fd0 sp=0x14000086fb0 pc=0x104b90db8 runtime.goexit({}) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x14000086fd0 sp=0x14000086fd0 pc=0x104beb354 created by runtime.gcBgMarkStartWorkers in goroutine 1 /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x140 goroutine 18 gp=0x14000504000 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x14000080710 sp=0x140000806f0 pc=0x104be3088 runtime.gcBgMarkWorker(0x140000457a0) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1423 +0xdc fp=0x140000807b0 sp=0x14000080710 pc=0x104b90ecc runtime.gcBgMarkStartWorkers.gowrap1() /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x28 fp=0x140000807d0 sp=0x140000807b0 pc=0x104b90db8 runtime.goexit({}) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x140000807d0 sp=0x140000807d0 pc=0x104beb354 created by runtime.gcBgMarkStartWorkers in goroutine 1 /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x140 goroutine 34 gp=0x14000102380 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x1400011a710 sp=0x1400011a6f0 pc=0x104be3088 runtime.gcBgMarkWorker(0x140000457a0) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1423 +0xdc fp=0x1400011a7b0 sp=0x1400011a710 pc=0x104b90ecc runtime.gcBgMarkStartWorkers.gowrap1() /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x28 fp=0x1400011a7d0 sp=0x1400011a7b0 pc=0x104b90db8 runtime.goexit({}) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x1400011a7d0 sp=0x1400011a7d0 pc=0x104beb354 created by runtime.gcBgMarkStartWorkers in goroutine 1 /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x140 goroutine 8 gp=0x140001eec40 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=0x14000087710 sp=0x140000876f0 pc=0x104be3088 runtime.gcBgMarkWorker(0x140000457a0) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1423 +0xdc fp=0x140000877b0 sp=0x14000087710 pc=0x104b90ecc runtime.gcBgMarkStartWorkers.gowrap1() /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x28 fp=0x140000877d0 sp=0x140000877b0 pc=0x104b90db8 runtime.goexit({}) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x140000877d0 sp=0x140000877d0 pc=0x104beb354 created by runtime.gcBgMarkStartWorkers in goroutine 1 /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x140 goroutine 9 gp=0x140001eee00 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=0x14000087f10 sp=0x14000087ef0 pc=0x104be3088 runtime.gcBgMarkWorker(0x140000457a0) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1423 +0xdc fp=0x14000087fb0 sp=0x14000087f10 pc=0x104b90ecc runtime.gcBgMarkStartWorkers.gowrap1() /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x28 fp=0x14000087fd0 sp=0x14000087fb0 pc=0x104b90db8 runtime.goexit({}) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x14000087fd0 sp=0x14000087fd0 pc=0x104beb354 created by runtime.gcBgMarkStartWorkers in goroutine 1 /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x140 goroutine 35 gp=0x14000102540 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x1400011af10 sp=0x1400011aef0 pc=0x104be3088 runtime.gcBgMarkWorker(0x140000457a0) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1423 +0xdc fp=0x1400011afb0 sp=0x1400011af10 pc=0x104b90ecc runtime.gcBgMarkStartWorkers.gowrap1() /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x28 fp=0x1400011afd0 sp=0x1400011afb0 pc=0x104b90db8 runtime.goexit({}) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x1400011afd0 sp=0x1400011afd0 pc=0x104beb354 created by runtime.gcBgMarkStartWorkers in goroutine 1 /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x140 goroutine 10 gp=0x140001eefc0 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=0x14000116710 sp=0x140001166f0 pc=0x104be3088 runtime.gcBgMarkWorker(0x140000457a0) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1423 +0xdc fp=0x140001167b0 sp=0x14000116710 pc=0x104b90ecc runtime.gcBgMarkStartWorkers.gowrap1() /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x28 fp=0x140001167d0 sp=0x140001167b0 pc=0x104b90db8 runtime.goexit({}) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x140001167d0 sp=0x140001167d0 pc=0x104beb354 created by runtime.gcBgMarkStartWorkers in goroutine 1 /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x140 goroutine 19 gp=0x140005041c0 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x14000080f10 sp=0x14000080ef0 pc=0x104be3088 runtime.gcBgMarkWorker(0x140000457a0) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1423 +0xdc fp=0x14000080fb0 sp=0x14000080f10 pc=0x104b90ecc runtime.gcBgMarkStartWorkers.gowrap1() /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x28 fp=0x14000080fd0 sp=0x14000080fb0 pc=0x104b90db8 runtime.goexit({}) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x14000080fd0 sp=0x14000080fd0 pc=0x104beb354 created by runtime.gcBgMarkStartWorkers in goroutine 1 /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x140 goroutine 36 gp=0x14000102700 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x1400011b710 sp=0x1400011b6f0 pc=0x104be3088 runtime.gcBgMarkWorker(0x140000457a0) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1423 +0xdc fp=0x1400011b7b0 sp=0x1400011b710 pc=0x104b90ecc runtime.gcBgMarkStartWorkers.gowrap1() /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x28 fp=0x1400011b7d0 sp=0x1400011b7b0 pc=0x104b90db8 runtime.goexit({}) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x1400011b7d0 sp=0x1400011b7d0 pc=0x104beb354 created by runtime.gcBgMarkStartWorkers in goroutine 1 /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x140 goroutine 37 gp=0x140001028c0 m=nil [GC worker (idle)]: runtime.gopark(0x106be1ee0?, 0x1?, 0xb7?, 0x96?, 0x0?) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x1400011bf10 sp=0x1400011bef0 pc=0x104be3088 runtime.gcBgMarkWorker(0x140000457a0) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1423 +0xdc fp=0x1400011bfb0 sp=0x1400011bf10 pc=0x104b90ecc runtime.gcBgMarkStartWorkers.gowrap1() /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x28 fp=0x1400011bfd0 sp=0x1400011bfb0 pc=0x104b90db8 runtime.goexit({}) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x1400011bfd0 sp=0x1400011bfd0 pc=0x104beb354 created by runtime.gcBgMarkStartWorkers in goroutine 1 /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x140 goroutine 38 gp=0x14000102a80 m=nil [GC worker (idle)]: runtime.gopark(0x142eee86827ad?, 0x1?, 0xc6?, 0x55?, 0x0?) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x1400011c710 sp=0x1400011c6f0 pc=0x104be3088 runtime.gcBgMarkWorker(0x140000457a0) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1423 +0xdc fp=0x1400011c7b0 sp=0x1400011c710 pc=0x104b90ecc runtime.gcBgMarkStartWorkers.gowrap1() /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x28 fp=0x1400011c7d0 sp=0x1400011c7b0 pc=0x104b90db8 runtime.goexit({}) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x1400011c7d0 sp=0x1400011c7d0 pc=0x104beb354 created by runtime.gcBgMarkStartWorkers in goroutine 1 /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x140 goroutine 39 gp=0x14000102c40 m=nil [GC worker (idle)]: runtime.gopark(0x106be1ee0?, 0x1?, 0x59?, 0x83?, 0x0?) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x1400011cf10 sp=0x1400011cef0 pc=0x104be3088 runtime.gcBgMarkWorker(0x140000457a0) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1423 +0xdc fp=0x1400011cfb0 sp=0x1400011cf10 pc=0x104b90ecc runtime.gcBgMarkStartWorkers.gowrap1() /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x28 fp=0x1400011cfd0 sp=0x1400011cfb0 pc=0x104b90db8 runtime.goexit({}) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x1400011cfd0 sp=0x1400011cfd0 pc=0x104beb354 created by runtime.gcBgMarkStartWorkers in goroutine 1 /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x140 goroutine 11 gp=0x140001ef180 m=nil [GC worker (idle)]: runtime.gopark(0x142eee86811de?, 0x1?, 0x5d?, 0x3d?, 0x0?) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x14000116f10 sp=0x14000116ef0 pc=0x104be3088 runtime.gcBgMarkWorker(0x140000457a0) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1423 +0xdc fp=0x14000116fb0 sp=0x14000116f10 pc=0x104b90ecc runtime.gcBgMarkStartWorkers.gowrap1() /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x28 fp=0x14000116fd0 sp=0x14000116fb0 pc=0x104b90db8 runtime.goexit({}) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x14000116fd0 sp=0x14000116fd0 pc=0x104beb354 created by runtime.gcBgMarkStartWorkers in goroutine 1 /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x140 goroutine 20 gp=0x14000504380 m=nil [GC worker (idle)]: runtime.gopark(0x142eee86810ba?, 0x1?, 0x6d?, 0xe1?, 0x0?) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x14000081710 sp=0x140000816f0 pc=0x104be3088 runtime.gcBgMarkWorker(0x140000457a0) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1423 +0xdc fp=0x140000817b0 sp=0x14000081710 pc=0x104b90ecc runtime.gcBgMarkStartWorkers.gowrap1() /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x28 fp=0x140000817d0 sp=0x140000817b0 pc=0x104b90db8 runtime.goexit({}) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x140000817d0 sp=0x140000817d0 pc=0x104beb354 created by runtime.gcBgMarkStartWorkers in goroutine 1 /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x140 goroutine 12 gp=0x140001ef340 m=nil [GC worker (idle)]: runtime.gopark(0x142eee8681355?, 0x3?, 0xb6?, 0x3c?, 0x0?) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x14000117710 sp=0x140001176f0 pc=0x104be3088 runtime.gcBgMarkWorker(0x140000457a0) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1423 +0xdc fp=0x140001177b0 sp=0x14000117710 pc=0x104b90ecc runtime.gcBgMarkStartWorkers.gowrap1() /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x28 fp=0x140001177d0 sp=0x140001177b0 pc=0x104b90db8 runtime.goexit({}) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x140001177d0 sp=0x140001177d0 pc=0x104beb354 created by runtime.gcBgMarkStartWorkers in goroutine 1 /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x140 goroutine 40 gp=0x14000102e00 m=nil [GC worker (idle)]: runtime.gopark(0x106be1ee0?, 0x3?, 0x8c?, 0xb2?, 0x0?) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x1400011d710 sp=0x1400011d6f0 pc=0x104be3088 runtime.gcBgMarkWorker(0x140000457a0) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1423 +0xdc fp=0x1400011d7b0 sp=0x1400011d710 pc=0x104b90ecc runtime.gcBgMarkStartWorkers.gowrap1() /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x28 fp=0x1400011d7d0 sp=0x1400011d7b0 pc=0x104b90db8 runtime.goexit({}) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x1400011d7d0 sp=0x1400011d7d0 pc=0x104beb354 created by runtime.gcBgMarkStartWorkers in goroutine 1 /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/mgc.go:1339 +0x140 goroutine 14 gp=0x14000504c40 m=nil [select]: runtime.gopark(0x1400004ba60?, 0x2?, 0xa?, 0x0?, 0x1400004b864?) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x1400004b6b0 sp=0x1400004b690 pc=0x104be3088 runtime.selectgo(0x1400004ba60, 0x1400004b860, 0x2038?, 0x0, 0x1?, 0x1) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/select.go:351 +0x6c4 fp=0x1400004b7e0 sp=0x1400004b6b0 pc=0x104bc2e74 github.com/ollama/ollama/runner/llamarunner.(*Server).completion(0x140004a6140, {0x106294d00, 0x1400051ee00}, 0x14000154500) /Users/runner/work/ollama/ollama/runner/llamarunner/runner.go:716 +0xa1c fp=0x1400004baa0 sp=0x1400004b7e0 pc=0x104fe9f7c github.com/ollama/ollama/runner/llamarunner.(*Server).completion-fm({0x106294d00?, 0x1400051ee00?}, 0x1400004bb28?) <autogenerated>:1 +0x40 fp=0x1400004bad0 sp=0x1400004baa0 pc=0x104fecba0 net/http.HandlerFunc.ServeHTTP(0x1400053a300?, {0x106294d00?, 0x1400051ee00?}, 0x1400004bb10?) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/net/http/server.go:2294 +0x38 fp=0x1400004bb00 sp=0x1400004bad0 pc=0x104e9bca8 net/http.(*ServeMux).ServeHTTP(0x10?, {0x106294d00, 0x1400051ee00}, 0x14000154500) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/net/http/server.go:2822 +0x1b4 fp=0x1400004bb50 sp=0x1400004bb00 pc=0x104e9d834 net/http.serverHandler.ServeHTTP({0x1062912f0?}, {0x106294d00?, 0x1400051ee00?}, 0x1?) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/net/http/server.go:3301 +0xbc fp=0x1400004bb80 sp=0x1400004bb50 pc=0x104eb951c net/http.(*conn).serve(0x140004ae090, {0x106297138, 0x140000ffb00}) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/net/http/server.go:2102 +0x52c fp=0x1400004bfa0 sp=0x1400004bb80 pc=0x104e9a44c net/http.(*Server).Serve.gowrap3() /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/net/http/server.go:3454 +0x30 fp=0x1400004bfd0 sp=0x1400004bfa0 pc=0x104e9f610 runtime.goexit({}) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x1400004bfd0 sp=0x1400004bfd0 pc=0x104beb354 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 46 gp=0x14000504fc0 m=nil [IO wait]: runtime.gopark(0xffffffffffffffff?, 0xffffffffffffffff?, 0x23?, 0x0?, 0x104c06b70?) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/proc.go:435 +0xc8 fp=0x14000152580 sp=0x14000152560 pc=0x104be3088 runtime.netpollblock(0x0?, 0x0?, 0x0?) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/netpoll.go:575 +0x158 fp=0x140001525c0 sp=0x14000152580 pc=0x104ba8c98 internal/poll.runtime_pollWait(0x13242d838, 0x72) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/netpoll.go:351 +0xa0 fp=0x140001525f0 sp=0x140001525c0 pc=0x104be2240 internal/poll.(*pollDesc).wait(0x14000052b80?, 0x140000ffc01?, 0x0) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/internal/poll/fd_poll_runtime.go:84 +0x28 fp=0x14000152620 sp=0x140001525f0 pc=0x104c62ed8 internal/poll.(*pollDesc).waitRead(...) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/internal/poll/fd_poll_runtime.go:89 internal/poll.(*FD).Read(0x14000052b80, {0x140000ffc01, 0x1, 0x1}) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/internal/poll/fd_unix.go:165 +0x1fc fp=0x140001526c0 sp=0x14000152620 pc=0x104c6418c net.(*netFD).Read(0x14000052b80, {0x140000ffc01?, 0x14000152758?, 0x104e94ec4?}) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/net/fd_posix.go:55 +0x28 fp=0x14000152710 sp=0x140001526c0 pc=0x104cd5b08 net.(*conn).Read(0x14000526098, {0x140000ffc01?, 0x0?, 0x0?}) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/net/net.go:194 +0x34 fp=0x14000152760 sp=0x14000152710 pc=0x104ce29d4 net/http.(*connReader).backgroundRead(0x140000ffbf0) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/net/http/server.go:690 +0x40 fp=0x140001527b0 sp=0x14000152760 pc=0x104e94dc0 net/http.(*connReader).startBackgroundRead.gowrap2() /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/net/http/server.go:686 +0x28 fp=0x140001527d0 sp=0x140001527b0 pc=0x104e94ca8 runtime.goexit({}) /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/runtime/asm_arm64.s:1223 +0x4 fp=0x140001527d0 sp=0x140001527d0 pc=0x104beb354 created by net/http.(*connReader).startBackgroundRead in goroutine 14 /Users/runner/hostedtoolcache/go/1.24.1/arm64/src/net/http/server.go:686 +0xc4 r0 0x0 r1 0x0 r2 0x0 r3 0x0 r4 0x0 r5 0x2e r6 0x91b400000 r7 0x0 r8 0x502f0da86a09699e r9 0x502f0da91ef6599e r10 0x2 r11 0x10000000000 r12 0xfffffffd r13 0x0 r14 0x0 r15 0x0 r16 0x148 r17 0x2055f4990 r18 0x0 r19 0x6 r20 0x330f r21 0x174ff30e0 r22 0x1665e8000 r23 0x105f96bfc r24 0x201631000 r25 0x14000067c90 r26 0x14000099b08 r27 0x818 r28 0x14000582540 r29 0x174ff2ba0 lr 0x197115888 sp 0x174ff2b80 pc 0x1970db5b0 fault 0x1970db5b0 time=2025-12-16T18:33:51.700-05:00 level=ERROR source=server.go:1583 msg="post predict" error="Post \"http://127.0.0.1:52036/completion\": EOF" [GIN] 2025/12/16 - 18:33:51 | 500 | 10.776447958s | 192.168.99.177 | POST "/api/chat" time=2025-12-16T18:33:51.700-05:00 level=DEBUG source=sched.go:537 msg="context for request finished" time=2025-12-16T18:33:51.700-05:00 level=DEBUG source=sched.go:290 msg="runner with non-zero duration has gone idle, adding timer" runner.name=registry.ollama.ai/library/nemotron-3-nano:30b-a3b-q8_0 runner.inference="[{ID:0 Library:Metal}]" runner.size="32.7 GiB" runner.vram="32.7 GiB" runner.parallel=1 runner.pid=37058 runner.model=/Users/cgk/.ollama/models/blobs/sha256-9c57f6ad9b291e7a7ea07b62711c60fcdf652a72e47efdd466ec953544a1c5eb runner.num_ctx=32000 duration=5m0s time=2025-12-16T18:33:51.700-05:00 level=DEBUG source=sched.go:308 msg="after processing request finished event" runner.name=registry.ollama.ai/library/nemotron-3-nano:30b-a3b-q8_0 runner.inference="[{ID:0 Library:Metal}]" runner.size="32.7 GiB" runner.vram="32.7 GiB" runner.parallel=1 runner.pid=37058 runner.model=/Users/cgk/.ollama/models/blobs/sha256-9c57f6ad9b291e7a7ea07b62711c60fcdf652a72e47efdd466ec953544a1c5eb runner.num_ctx=32000 refCount=0 ``` ### OS macOS ### GPU Apple ### CPU Apple ### Ollama version 0.13.4
GiteaMirror added the bug label 2026-04-22 18:24:39 -05:00
Author
Owner

@ParthSareen commented on GitHub (Dec 17, 2025):

Hi @chigkim could you share your specs for VRAM in addition to how much context length you are loading for the model? ollama ps would also be helpful after doing ollama run.

<!-- gh-comment-id:3666942063 --> @ParthSareen commented on GitHub (Dec 17, 2025): Hi @chigkim could you share your specs for VRAM in addition to how much context length you are loading for the model? `ollama ps` would also be helpful after doing `ollama run`.
Author
Owner

@chigkim commented on GitHub (Dec 17, 2025):

I have M3Max with 64GB, and I set iogpu.wired_limit_mb=59392.
My prompt is about 8237 tokens for mistral-small3.2:24b, 8164 tokens for gemma3:27b, 7170 tokens for qwen3-next:80b, and , 7084 tokens for gpt-oss:20b.
I assume it's less than 10k tokens for nemotron, so I tried 16k, 32k for num_ctx.
Here's the output for ollama ps.
nemotron-3-nano:30b-a3b-q8_0 a98df31bcc4a 35 GB 100% GPU 32000 4 minutes from now
Plenty of room for memory and context.

<!-- gh-comment-id:3667096419 --> @chigkim commented on GitHub (Dec 17, 2025): I have M3Max with 64GB, and I set iogpu.wired_limit_mb=59392. My prompt is about 8237 tokens for mistral-small3.2:24b, 8164 tokens for gemma3:27b, 7170 tokens for qwen3-next:80b, and , 7084 tokens for gpt-oss:20b. I assume it's less than 10k tokens for nemotron, so I tried 16k, 32k for num_ctx. Here's the output for `ollama ps`. nemotron-3-nano:30b-a3b-q8_0 a98df31bcc4a 35 GB 100% GPU 32000 4 minutes from now Plenty of room for memory and context.
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#34664