[GH-ISSUE #9500] crash on calling models #83874

Closed
opened 2026-05-09 19:17:29 -05:00 by GiteaMirror · 3 comments
Owner

Originally created by @furryaxw on GitHub (Mar 4, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/9500

What is the issue?

crashes on every call to the server

Relevant log output

2025/03/04 15:51:47 routes.go:1205: INFO server config env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://0.0.0.0:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/ollama OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:0 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://*] OLLAMA_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]"
time=2025-03-04T15:51:47.296Z level=INFO source=images.go:432 msg="total blobs: 4"
time=2025-03-04T15:51:47.296Z level=INFO source=images.go:439 msg="total unused blobs removed: 0"
time=2025-03-04T15:51:47.297Z level=INFO source=routes.go:1256 msg="Listening on [::]:11434 (version 0.5.12)"
time=2025-03-04T15:51:47.297Z level=INFO source=gpu.go:217 msg="looking for compatible GPUs"
time=2025-03-04T15:51:47.335Z level=INFO source=amd_linux.go:386 msg="amdgpu is supported" gpu=GPU-6f927101732c7315 gpu_type=gfx906
time=2025-03-04T15:51:47.336Z level=INFO source=types.go:130 msg="inference compute" id=GPU-6f927101732c7315 library=rocm variant="" compute=gfx906 driver=6.10 name=1002:66a1 total="16.0 GiB" available="16.0 GiB"
[GIN] 2025/03/04 - 15:51:52 | 200 |      89.166µs |       127.0.0.1 | HEAD     "/"
[GIN] 2025/03/04 - 15:51:52 | 200 |   86.907454ms |       127.0.0.1 | POST     "/api/show"
time=2025-03-04T15:51:52.574Z level=INFO source=sched.go:715 msg="new model will fit in available VRAM in single GPU, loading" model=/ollama/blobs/sha256-e729bfb34d8e05557eca33c39b6745a25f17b6e55dac5283296ff78704469c3f gpu=GPU-6f927101732c7315 parallel=4 available=17152217088 required="6.5 GiB"
time=2025-03-04T15:51:52.574Z level=INFO source=server.go:97 msg="system memory" total="46.9 GiB" free="45.5 GiB" free_swap="8.0 GiB"
time=2025-03-04T15:51:52.575Z level=INFO source=server.go:130 msg=offload library=rocm layers.requested=-1 layers.model=33 layers.offload=33 layers.split="" memory.available="[16.0 GiB]" memory.gpu_overhead="0 B" memory.required.full="6.5 GiB" memory.required.partial="6.5 GiB" memory.required.kv="1.0 GiB" memory.required.allocations="[6.5 GiB]" memory.weights.total="4.9 GiB" memory.weights.repeating="4.5 GiB" memory.weights.nonrepeating="411.0 MiB" memory.graph.full="560.0 MiB" memory.graph.partial="677.5 MiB"
time=2025-03-04T15:51:52.576Z level=INFO source=server.go:380 msg="starting llama server" cmd="/usr/bin/ollama runner --model /ollama/blobs/sha256-e729bfb34d8e05557eca33c39b6745a25f17b6e55dac5283296ff78704469c3f --ctx-size 8192 --batch-size 512 --n-gpu-layers 33 --threads 16 --parallel 4 --port 40381"
time=2025-03-04T15:51:52.577Z level=INFO source=sched.go:450 msg="loaded runners" count=1
time=2025-03-04T15:51:52.577Z level=INFO source=server.go:557 msg="waiting for llama runner to start responding"
time=2025-03-04T15:51:52.578Z level=INFO source=server.go:591 msg="waiting for server to become available" status="llm server error"
time=2025-03-04T15:51:52.619Z level=INFO source=runner.go:932 msg="starting go runner"
ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
  Device 0: AMD Radeon (TM) Pro VII, compute capability 9.0, VMM: no
load_backend: loaded ROCm backend from /usr/lib/ollama/rocm/libggml-hip.so
load_backend: loaded CPU backend from /usr/lib/ollama/libggml-cpu-sandybridge.so
time=2025-03-04T15:51:54.299Z level=INFO source=runner.go:935 msg=system info="CPU : LLAMAFILE = 1 | CPU : LLAMAFILE = 1 | ROCm : PEER_MAX_BATCH_SIZE = 128 | CPU : SSE3 = 1 | SSSE3 = 1 | AVX = 1 | LLAMAFILE = 1 | cgo(gcc)" threads=16
time=2025-03-04T15:51:54.299Z level=INFO source=runner.go:993 msg="Server listening on 127.0.0.1:40381"
llama_load_model_from_file: using device ROCm0 (AMD Radeon (TM) Pro VII) - 15926 MiB free
time=2025-03-04T15:51:54.336Z level=INFO source=server.go:591 msg="waiting for server to become available" status="llm server loading model"
llama_model_loader: loaded meta data with 29 key-value pairs and 292 tensors from /ollama/blobs/sha256-e729bfb34d8e05557eca33c39b6745a25f17b6e55dac5283296ff78704469c3f (version GGUF V3 (latest))
llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
llama_model_loader: - kv   0:                       general.architecture str              = llama
llama_model_loader: - kv   1:                               general.type str              = model
llama_model_loader: - kv   2:                               general.name str              = Llama3.1 8B Chinese Furry 1.6.5t
llama_model_loader: - kv   3:                           general.finetune str              = Chinese-Furry-1.6.5t
llama_model_loader: - kv   4:                           general.basename str              = Llama3.1
llama_model_loader: - kv   5:                         general.size_label str              = 8B
llama_model_loader: - kv   6:                          llama.block_count u32              = 32
llama_model_loader: - kv   7:                       llama.context_length u32              = 131072
llama_model_loader: - kv   8:                     llama.embedding_length u32              = 4096
llama_model_loader: - kv   9:                  llama.feed_forward_length u32              = 14336
llama_model_loader: - kv  10:                 llama.attention.head_count u32              = 32
llama_model_loader: - kv  11:              llama.attention.head_count_kv u32              = 8
llama_model_loader: - kv  12:                       llama.rope.freq_base f32              = 500000.000000
llama_model_loader: - kv  13:     llama.attention.layer_norm_rms_epsilon f32              = 0.000010
llama_model_loader: - kv  14:                 llama.attention.key_length u32              = 128
llama_model_loader: - kv  15:               llama.attention.value_length u32              = 128
llama_model_loader: - kv  16:                          general.file_type u32              = 15
llama_model_loader: - kv  17:                           llama.vocab_size u32              = 128256
llama_model_loader: - kv  18:                 llama.rope.dimension_count u32              = 128
llama_model_loader: - kv  19:                       tokenizer.ggml.model str              = gpt2
llama_model_loader: - kv  20:                         tokenizer.ggml.pre str              = smaug-bpe
llama_model_loader: - kv  21:                      tokenizer.ggml.tokens arr[str,128256]  = ["!", "\"", "#", "$", "%", "&", "'", ...
llama_model_loader: - kv  22:                  tokenizer.ggml.token_type arr[i32,128256]  = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv  23:                      tokenizer.ggml.merges arr[str,280147]  = ["Ġ Ġ", "Ġ ĠĠĠ", "ĠĠ ĠĠ", "...
llama_model_loader: - kv  24:                tokenizer.ggml.bos_token_id u32              = 128000
llama_model_loader: - kv  25:                tokenizer.ggml.eos_token_id u32              = 128009
llama_model_loader: - kv  26:            tokenizer.ggml.padding_token_id u32              = 128009
llama_model_loader: - kv  27:                    tokenizer.chat_template str              = {% set loop_messages = messages %}{% ...
llama_model_loader: - kv  28:               general.quantization_version u32              = 2
llama_model_loader: - type  f32:   66 tensors
llama_model_loader: - type q4_K:  193 tensors
llama_model_loader: - type q6_K:   33 tensors
llm_load_vocab: special tokens cache size = 256
llm_load_vocab: token to piece cache size = 0.7999 MB
llm_load_print_meta: format           = GGUF V3 (latest)
llm_load_print_meta: arch             = llama
llm_load_print_meta: vocab type       = BPE
llm_load_print_meta: n_vocab          = 128256
llm_load_print_meta: n_merges         = 280147
llm_load_print_meta: vocab_only       = 0
llm_load_print_meta: n_ctx_train      = 131072
llm_load_print_meta: n_embd           = 4096
llm_load_print_meta: n_layer          = 32
llm_load_print_meta: n_head           = 32
llm_load_print_meta: n_head_kv        = 8
llm_load_print_meta: n_rot            = 128
llm_load_print_meta: n_swa            = 0
llm_load_print_meta: n_embd_head_k    = 128
llm_load_print_meta: n_embd_head_v    = 128
llm_load_print_meta: n_gqa            = 4
llm_load_print_meta: n_embd_k_gqa     = 1024
llm_load_print_meta: n_embd_v_gqa     = 1024
llm_load_print_meta: f_norm_eps       = 0.0e+00
llm_load_print_meta: f_norm_rms_eps   = 1.0e-05
llm_load_print_meta: f_clamp_kqv      = 0.0e+00
llm_load_print_meta: f_max_alibi_bias = 0.0e+00
llm_load_print_meta: f_logit_scale    = 0.0e+00
llm_load_print_meta: n_ff             = 14336
llm_load_print_meta: n_expert         = 0
llm_load_print_meta: n_expert_used    = 0
llm_load_print_meta: causal attn      = 1
llm_load_print_meta: pooling type     = 0
llm_load_print_meta: rope type        = 0
llm_load_print_meta: rope scaling     = linear
llm_load_print_meta: freq_base_train  = 500000.0
llm_load_print_meta: freq_scale_train = 1
llm_load_print_meta: n_ctx_orig_yarn  = 131072
llm_load_print_meta: rope_finetuned   = unknown
llm_load_print_meta: ssm_d_conv       = 0
llm_load_print_meta: ssm_d_inner      = 0
llm_load_print_meta: ssm_d_state      = 0
llm_load_print_meta: ssm_dt_rank      = 0
llm_load_print_meta: ssm_dt_b_c_rms   = 0
llm_load_print_meta: model type       = 8B
llm_load_print_meta: model ftype      = Q4_K - Medium
llm_load_print_meta: model params     = 8.03 B
llm_load_print_meta: model size       = 4.58 GiB (4.89 BPW)
llm_load_print_meta: general.name     = Llama3.1 8B Chinese Furry 1.6.5t
llm_load_print_meta: BOS token        = 128000 '<|begin_of_text|>'
llm_load_print_meta: EOS token        = 128009 '<|eot_id|>'
llm_load_print_meta: EOT token        = 128009 '<|eot_id|>'
llm_load_print_meta: EOM token        = 128008 '<|eom_id|>'
llm_load_print_meta: PAD token        = 128009 '<|eot_id|>'
llm_load_print_meta: LF token         = 128 'Ä'
llm_load_print_meta: EOG token        = 128008 '<|eom_id|>'
llm_load_print_meta: EOG token        = 128009 '<|eot_id|>'
llm_load_print_meta: max token length = 256
llm_load_tensors: offloading 32 repeating layers to GPU
llm_load_tensors: offloading output layer to GPU
llm_load_tensors: offloaded 33/33 layers to GPU
llm_load_tensors:        ROCm0 model buffer size =  4403.49 MiB
llm_load_tensors:   CPU_Mapped model buffer size =   281.81 MiB
llama_new_context_with_model: n_seq_max     = 4
llama_new_context_with_model: n_ctx         = 8192
llama_new_context_with_model: n_ctx_per_seq = 2048
llama_new_context_with_model: n_batch       = 2048
llama_new_context_with_model: n_ubatch      = 512
llama_new_context_with_model: flash_attn    = 0
llama_new_context_with_model: freq_base     = 500000.0
llama_new_context_with_model: freq_scale    = 1
llama_new_context_with_model: n_ctx_per_seq (2048) < n_ctx_train (131072) -- the full capacity of the model will not be utilized
llama_kv_cache_init: kv_size = 8192, offload = 1, type_k = 'f16', type_v = 'f16', n_layer = 32, can_shift = 1
llama_kv_cache_init:      ROCm0 KV buffer size =  1024.00 MiB
llama_new_context_with_model: KV self size  = 1024.00 MiB, K (f16):  512.00 MiB, V (f16):  512.00 MiB
llama_new_context_with_model:  ROCm_Host  output buffer size =     2.02 MiB
llama_new_context_with_model:      ROCm0 compute buffer size =   560.00 MiB
llama_new_context_with_model:  ROCm_Host compute buffer size =    24.01 MiB
llama_new_context_with_model: graph nodes  = 1030
llama_new_context_with_model: graph splits = 2
time=2025-03-04T15:51:58.360Z level=INFO source=server.go:596 msg="llama runner started in 5.78 seconds"
[GIN] 2025/03/04 - 15:51:58 | 200 |  5.886295765s |       127.0.0.1 | POST     "/api/generate"
SIGILL: illegal instruction
PC=0x7f7fdc968f27 m=4 sigcode=2
signal arrived during cgo execution
instruction bytes: 0xc4 0xe2 0x79 0x13 0xc0 0xc5 0xf0 0x57 0xc9 0xc5 0xf8 0x2e 0xc1 0x75 0x6 0xf

goroutine 46 gp=0xc000504540 m=4 mp=0xc0000b1508 [syscall]:
runtime.cgocall(0x563cf527ace0, 0xc0000beba0)
        runtime/cgocall.go:167 +0x4b fp=0xc0000beb78 sp=0xc0000beb40 pc=0x563cf4665acb
github.com/ollama/ollama/llama._Cfunc_llama_decode(0x7f7dd58bf120, {0xa, 0x7f7dd639f910, 0x0, 0x0, 0x7f7dd5ba43c0, 0x7f7dd5ae67b0, 0x7f7dd5b1bd20, 0x7f7dd5959200})
        _cgo_gotypes.go:545 +0x4f fp=0xc0000beba0 sp=0xc0000beb78 pc=0x563cf4a1b56f
github.com/ollama/ollama/llama.(*Context).Decode.func1(0x563cf4a3a48b?, 0x7f7dd58bf120?)
        github.com/ollama/ollama/llama/llama.go:163 +0xf5 fp=0xc0000bec90 sp=0xc0000beba0 pc=0x563cf4a1e295
github.com/ollama/ollama/llama.(*Context).Decode(0xc000495578?, 0x0?)
        github.com/ollama/ollama/llama/llama.go:163 +0x13 fp=0xc0000becd8 sp=0xc0000bec90 pc=0x563cf4a1e113
github.com/ollama/ollama/runner/llamarunner.(*Server).processBatch(0xc0000d8000, 0xc00046c120, 0xc000495720)
        github.com/ollama/ollama/runner/llamarunner/runner.go:435 +0x23f fp=0xc0000beee0 sp=0xc0000becd8 pc=0x563cf4a3927f
github.com/ollama/ollama/runner/llamarunner.(*Server).run(0xc0000d8000, {0x563cf58cd920, 0xc0000ae050})
        github.com/ollama/ollama/runner/llamarunner/runner.go:343 +0x1d5 fp=0xc0000befb8 sp=0xc0000beee0 pc=0x563cf4a38cb5
github.com/ollama/ollama/runner/llamarunner.Execute.gowrap2()
        github.com/ollama/ollama/runner/llamarunner/runner.go:973 +0x28 fp=0xc0000befe0 sp=0xc0000befb8 pc=0x563cf4a3db48
runtime.goexit({})
        runtime/asm_amd64.s:1700 +0x1 fp=0xc0000befe8 sp=0xc0000befe0 pc=0x563cf46745a1
created by github.com/ollama/ollama/runner/llamarunner.Execute in goroutine 1
        github.com/ollama/ollama/runner/llamarunner/runner.go:973 +0xdb5

goroutine 1 gp=0xc0000061c0 m=nil [IO wait]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
        runtime/proc.go:424 +0xce fp=0xc0000495c0 sp=0xc0000495a0 pc=0x563cf466c1ce
runtime.netpollblock(0xc000465f80?, 0xf4602fe6?, 0x3c?)
        runtime/netpoll.go:575 +0xf7 fp=0xc0000495f8 sp=0xc0000495c0 pc=0x563cf462fe37
internal/poll.runtime_pollWait(0x7f801d782df0, 0x72)
        runtime/netpoll.go:351 +0x85 fp=0xc000049618 sp=0xc0000495f8 pc=0x563cf466b4c5
internal/poll.(*pollDesc).wait(0xc000020080?, 0x2c?, 0x0)
        internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc000049640 sp=0xc000049618 pc=0x563cf46f3707
internal/poll.(*pollDesc).waitRead(...)
        internal/poll/fd_poll_runtime.go:89
internal/poll.(*FD).Accept(0xc000020080)
        internal/poll/fd_unix.go:620 +0x295 fp=0xc0000496e8 sp=0xc000049640 pc=0x563cf46f8ad5
net.(*netFD).accept(0xc000020080)
        net/fd_unix.go:172 +0x29 fp=0xc0000497a0 sp=0xc0000496e8 pc=0x563cf4761bc9
net.(*TCPListener).accept(0xc000133440)
        net/tcpsock_posix.go:159 +0x1e fp=0xc0000497f0 sp=0xc0000497a0 pc=0x563cf477783e
net.(*TCPListener).Accept(0xc000133440)
        net/tcpsock.go:372 +0x30 fp=0xc000049820 sp=0xc0000497f0 pc=0x563cf47766f0
net/http.(*onceCloseListener).Accept(0xc000460000?)
        <autogenerated>:1 +0x24 fp=0xc000049838 sp=0xc000049820 pc=0x563cf49c0964
net/http.(*Server).Serve(0xc00001a3c0, {0x563cf58cb4f8, 0xc000133440})
        net/http/server.go:3330 +0x30c fp=0xc000049968 sp=0xc000049838 pc=0x563cf49988ec
github.com/ollama/ollama/runner/llamarunner.Execute({0xc000136020, 0xe, 0xe})
        github.com/ollama/ollama/runner/llamarunner/runner.go:994 +0x1174 fp=0xc000049d08 sp=0xc000049968 pc=0x563cf4a3d834
github.com/ollama/ollama/runner.Execute({0xc000136010?, 0x0?, 0x0?})
        github.com/ollama/ollama/runner/runner.go:22 +0xd4 fp=0xc000049d30 sp=0xc000049d08 pc=0x563cf4c6dc54
github.com/ollama/ollama/cmd.NewCLI.func2(0xc000137500?, {0x563cf5468050?, 0x4?, 0x563cf5468054?})
        github.com/ollama/ollama/cmd/cmd.go:1280 +0x45 fp=0xc000049d58 sp=0xc000049d30 pc=0x563cf527a245
github.com/spf13/cobra.(*Command).execute(0xc0005f1b08, {0xc0005a77a0, 0xe, 0xe})
        github.com/spf13/cobra@v1.7.0/command.go:940 +0x862 fp=0xc000049e78 sp=0xc000049d58 pc=0x563cf47da902
github.com/spf13/cobra.(*Command).ExecuteC(0xc000595508)
        github.com/spf13/cobra@v1.7.0/command.go:1068 +0x3a5 fp=0xc000049f30 sp=0xc000049e78 pc=0x563cf47db145
github.com/spf13/cobra.(*Command).Execute(...)
        github.com/spf13/cobra@v1.7.0/command.go:992
github.com/spf13/cobra.(*Command).ExecuteContext(...)
        github.com/spf13/cobra@v1.7.0/command.go:985
main.main()
        github.com/ollama/ollama/main.go:12 +0x4d fp=0xc000049f50 sp=0xc000049f30 pc=0x563cf527a5cd
runtime.main()
        runtime/proc.go:272 +0x29d fp=0xc000049fe0 sp=0xc000049f50 pc=0x563cf46374dd
runtime.goexit({})
        runtime/asm_amd64.s:1700 +0x1 fp=0xc000049fe8 sp=0xc000049fe0 pc=0x563cf46745a1

goroutine 2 gp=0xc000006c40 m=nil [force gc (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
        runtime/proc.go:424 +0xce fp=0xc0000aafa8 sp=0xc0000aaf88 pc=0x563cf466c1ce
runtime.goparkunlock(...)
        runtime/proc.go:430
runtime.forcegchelper()
        runtime/proc.go:337 +0xb8 fp=0xc0000aafe0 sp=0xc0000aafa8 pc=0x563cf4637818
runtime.goexit({})
        runtime/asm_amd64.s:1700 +0x1 fp=0xc0000aafe8 sp=0xc0000aafe0 pc=0x563cf46745a1
created by runtime.init.7 in goroutine 1
        runtime/proc.go:325 +0x1a

goroutine 3 gp=0xc000007180 m=nil [GC sweep wait]:
runtime.gopark(0x1?, 0x0?, 0x0?, 0x0?, 0x0?)
        runtime/proc.go:424 +0xce fp=0xc0000ab780 sp=0xc0000ab760 pc=0x563cf466c1ce
runtime.goparkunlock(...)
        runtime/proc.go:430
runtime.bgsweep(0xc0000d8000)
        runtime/mgcsweep.go:317 +0xdf fp=0xc0000ab7c8 sp=0xc0000ab780 pc=0x563cf4621ebf
runtime.gcenable.gowrap1()
        runtime/mgc.go:204 +0x25 fp=0xc0000ab7e0 sp=0xc0000ab7c8 pc=0x563cf4616505
runtime.goexit({})
        runtime/asm_amd64.s:1700 +0x1 fp=0xc0000ab7e8 sp=0xc0000ab7e0 pc=0x563cf46745a1
created by runtime.gcenable in goroutine 1
        runtime/mgc.go:204 +0x66

goroutine 4 gp=0xc000007340 m=nil [GC scavenge wait]:
runtime.gopark(0x10000?, 0x563cf561b6f8?, 0x0?, 0x0?, 0x0?)
        runtime/proc.go:424 +0xce fp=0xc0000abf78 sp=0xc0000abf58 pc=0x563cf466c1ce
runtime.goparkunlock(...)
        runtime/proc.go:430
runtime.(*scavengerState).park(0x563cf60c2080)
        runtime/mgcscavenge.go:425 +0x49 fp=0xc0000abfa8 sp=0xc0000abf78 pc=0x563cf461f889
runtime.bgscavenge(0xc0000d8000)
        runtime/mgcscavenge.go:658 +0x59 fp=0xc0000abfc8 sp=0xc0000abfa8 pc=0x563cf461fe19
runtime.gcenable.gowrap2()
        runtime/mgc.go:205 +0x25 fp=0xc0000abfe0 sp=0xc0000abfc8 pc=0x563cf46164a5
runtime.goexit({})
        runtime/asm_amd64.s:1700 +0x1 fp=0xc0000abfe8 sp=0xc0000abfe0 pc=0x563cf46745a1
created by runtime.gcenable in goroutine 1
        runtime/mgc.go:205 +0xa5

goroutine 18 gp=0xc000104700 m=nil [finalizer wait]:
runtime.gopark(0xc0000aa648?, 0x563cf460ca05?, 0xb0?, 0x1?, 0xc0000061c0?)
        runtime/proc.go:424 +0xce fp=0xc0000aa620 sp=0xc0000aa600 pc=0x563cf466c1ce
runtime.runfinq()
        runtime/mfinal.go:193 +0x107 fp=0xc0000aa7e0 sp=0xc0000aa620 pc=0x563cf4615587
runtime.goexit({})
        runtime/asm_amd64.s:1700 +0x1 fp=0xc0000aa7e8 sp=0xc0000aa7e0 pc=0x563cf46745a1
created by runtime.createfing in goroutine 1
        runtime/mfinal.go:163 +0x3d

goroutine 19 gp=0xc00027e000 m=nil [chan receive]:
runtime.gopark(0xc0000a6760?, 0x563cf4749245?, 0x60?, 0xc9?, 0x563cf58e0280?)
        runtime/proc.go:424 +0xce fp=0xc0000a6718 sp=0xc0000a66f8 pc=0x563cf466c1ce
runtime.chanrecv(0xc000112310, 0x0, 0x1)
        runtime/chan.go:639 +0x41c fp=0xc0000a6790 sp=0xc0000a6718 pc=0x563cf4605bfc
runtime.chanrecv1(0x0?, 0x0?)
        runtime/chan.go:489 +0x12 fp=0xc0000a67b8 sp=0xc0000a6790 pc=0x563cf46057b2
runtime.unique_runtime_registerUniqueMapCleanup.func1(...)
        runtime/mgc.go:1781
runtime.unique_runtime_registerUniqueMapCleanup.gowrap1()
        runtime/mgc.go:1784 +0x2f fp=0xc0000a67e0 sp=0xc0000a67b8 pc=0x563cf461956f
runtime.goexit({})
        runtime/asm_amd64.s:1700 +0x1 fp=0xc0000a67e8 sp=0xc0000a67e0 pc=0x563cf46745a1
created by unique.runtime_registerUniqueMapCleanup in goroutine 1
        runtime/mgc.go:1779 +0x96

goroutine 20 gp=0xc00027e380 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
        runtime/proc.go:424 +0xce fp=0xc0000a6f38 sp=0xc0000a6f18 pc=0x563cf466c1ce
runtime.gcBgMarkWorker(0xc000113730)
        runtime/mgc.go:1412 +0xe9 fp=0xc0000a6fc8 sp=0xc0000a6f38 pc=0x563cf4618869
runtime.gcBgMarkStartWorkers.gowrap1()
        runtime/mgc.go:1328 +0x25 fp=0xc0000a6fe0 sp=0xc0000a6fc8 pc=0x563cf4618745
runtime.goexit({})
        runtime/asm_amd64.s:1700 +0x1 fp=0xc0000a6fe8 sp=0xc0000a6fe0 pc=0x563cf46745a1
created by runtime.gcBgMarkStartWorkers in goroutine 1
        runtime/mgc.go:1328 +0x105

goroutine 21 gp=0xc00027e540 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
        runtime/proc.go:424 +0xce fp=0xc0000a7738 sp=0xc0000a7718 pc=0x563cf466c1ce
runtime.gcBgMarkWorker(0xc000113730)
        runtime/mgc.go:1412 +0xe9 fp=0xc0000a77c8 sp=0xc0000a7738 pc=0x563cf4618869
runtime.gcBgMarkStartWorkers.gowrap1()
        runtime/mgc.go:1328 +0x25 fp=0xc0000a77e0 sp=0xc0000a77c8 pc=0x563cf4618745
runtime.goexit({})
        runtime/asm_amd64.s:1700 +0x1 fp=0xc0000a77e8 sp=0xc0000a77e0 pc=0x563cf46745a1
created by runtime.gcBgMarkStartWorkers in goroutine 1
        runtime/mgc.go:1328 +0x105

goroutine 34 gp=0xc000484000 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
        runtime/proc.go:424 +0xce fp=0xc00048a738 sp=0xc00048a718 pc=0x563cf466c1ce
runtime.gcBgMarkWorker(0xc000113730)
        runtime/mgc.go:1412 +0xe9 fp=0xc00048a7c8 sp=0xc00048a738 pc=0x563cf4618869
runtime.gcBgMarkStartWorkers.gowrap1()
        runtime/mgc.go:1328 +0x25 fp=0xc00048a7e0 sp=0xc00048a7c8 pc=0x563cf4618745
runtime.goexit({})
        runtime/asm_amd64.s:1700 +0x1 fp=0xc00048a7e8 sp=0xc00048a7e0 pc=0x563cf46745a1
created by runtime.gcBgMarkStartWorkers in goroutine 1
        runtime/mgc.go:1328 +0x105

goroutine 35 gp=0xc0004841c0 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
        runtime/proc.go:424 +0xce fp=0xc00048af38 sp=0xc00048af18 pc=0x563cf466c1ce
runtime.gcBgMarkWorker(0xc000113730)
        runtime/mgc.go:1412 +0xe9 fp=0xc00048afc8 sp=0xc00048af38 pc=0x563cf4618869
runtime.gcBgMarkStartWorkers.gowrap1()
        runtime/mgc.go:1328 +0x25 fp=0xc00048afe0 sp=0xc00048afc8 pc=0x563cf4618745
runtime.goexit({})
        runtime/asm_amd64.s:1700 +0x1 fp=0xc00048afe8 sp=0xc00048afe0 pc=0x563cf46745a1
created by runtime.gcBgMarkStartWorkers in goroutine 1
        runtime/mgc.go:1328 +0x105

goroutine 36 gp=0xc000484380 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
        runtime/proc.go:424 +0xce fp=0xc00048b738 sp=0xc00048b718 pc=0x563cf466c1ce
runtime.gcBgMarkWorker(0xc000113730)
        runtime/mgc.go:1412 +0xe9 fp=0xc00048b7c8 sp=0xc00048b738 pc=0x563cf4618869
runtime.gcBgMarkStartWorkers.gowrap1()
        runtime/mgc.go:1328 +0x25 fp=0xc00048b7e0 sp=0xc00048b7c8 pc=0x563cf4618745
runtime.goexit({})
        runtime/asm_amd64.s:1700 +0x1 fp=0xc00048b7e8 sp=0xc00048b7e0 pc=0x563cf46745a1
created by runtime.gcBgMarkStartWorkers in goroutine 1
        runtime/mgc.go:1328 +0x105

goroutine 5 gp=0xc000007880 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
        runtime/proc.go:424 +0xce fp=0xc0000ac738 sp=0xc0000ac718 pc=0x563cf466c1ce
runtime.gcBgMarkWorker(0xc000113730)
        runtime/mgc.go:1412 +0xe9 fp=0xc0000ac7c8 sp=0xc0000ac738 pc=0x563cf4618869
runtime.gcBgMarkStartWorkers.gowrap1()
        runtime/mgc.go:1328 +0x25 fp=0xc0000ac7e0 sp=0xc0000ac7c8 pc=0x563cf4618745
runtime.goexit({})
        runtime/asm_amd64.s:1700 +0x1 fp=0xc0000ac7e8 sp=0xc0000ac7e0 pc=0x563cf46745a1
created by runtime.gcBgMarkStartWorkers in goroutine 1
        runtime/mgc.go:1328 +0x105

goroutine 22 gp=0xc00027e700 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
        runtime/proc.go:424 +0xce fp=0xc0000a7f38 sp=0xc0000a7f18 pc=0x563cf466c1ce
runtime.gcBgMarkWorker(0xc000113730)
        runtime/mgc.go:1412 +0xe9 fp=0xc0000a7fc8 sp=0xc0000a7f38 pc=0x563cf4618869
runtime.gcBgMarkStartWorkers.gowrap1()
        runtime/mgc.go:1328 +0x25 fp=0xc0000a7fe0 sp=0xc0000a7fc8 pc=0x563cf4618745
runtime.goexit({})
        runtime/asm_amd64.s:1700 +0x1 fp=0xc0000a7fe8 sp=0xc0000a7fe0 pc=0x563cf46745a1
created by runtime.gcBgMarkStartWorkers in goroutine 1
        runtime/mgc.go:1328 +0x105

goroutine 23 gp=0xc00027e8c0 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
        runtime/proc.go:424 +0xce fp=0xc0000a8738 sp=0xc0000a8718 pc=0x563cf466c1ce
runtime.gcBgMarkWorker(0xc000113730)
        runtime/mgc.go:1412 +0xe9 fp=0xc0000a87c8 sp=0xc0000a8738 pc=0x563cf4618869
runtime.gcBgMarkStartWorkers.gowrap1()
        runtime/mgc.go:1328 +0x25 fp=0xc0000a87e0 sp=0xc0000a87c8 pc=0x563cf4618745
runtime.goexit({})
        runtime/asm_amd64.s:1700 +0x1 fp=0xc0000a87e8 sp=0xc0000a87e0 pc=0x563cf46745a1
created by runtime.gcBgMarkStartWorkers in goroutine 1
        runtime/mgc.go:1328 +0x105

goroutine 24 gp=0xc00027ea80 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
        runtime/proc.go:424 +0xce fp=0xc0000a8f38 sp=0xc0000a8f18 pc=0x563cf466c1ce
runtime.gcBgMarkWorker(0xc000113730)
        runtime/mgc.go:1412 +0xe9 fp=0xc0000a8fc8 sp=0xc0000a8f38 pc=0x563cf4618869
runtime.gcBgMarkStartWorkers.gowrap1()
        runtime/mgc.go:1328 +0x25 fp=0xc0000a8fe0 sp=0xc0000a8fc8 pc=0x563cf4618745
runtime.goexit({})
        runtime/asm_amd64.s:1700 +0x1 fp=0xc0000a8fe8 sp=0xc0000a8fe0 pc=0x563cf46745a1
created by runtime.gcBgMarkStartWorkers in goroutine 1
        runtime/mgc.go:1328 +0x105

goroutine 25 gp=0xc00027ec40 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
        runtime/proc.go:424 +0xce fp=0xc0000a9738 sp=0xc0000a9718 pc=0x563cf466c1ce
runtime.gcBgMarkWorker(0xc000113730)
        runtime/mgc.go:1412 +0xe9 fp=0xc0000a97c8 sp=0xc0000a9738 pc=0x563cf4618869
runtime.gcBgMarkStartWorkers.gowrap1()
        runtime/mgc.go:1328 +0x25 fp=0xc0000a97e0 sp=0xc0000a97c8 pc=0x563cf4618745
runtime.goexit({})
        runtime/asm_amd64.s:1700 +0x1 fp=0xc0000a97e8 sp=0xc0000a97e0 pc=0x563cf46745a1
created by runtime.gcBgMarkStartWorkers in goroutine 1
        runtime/mgc.go:1328 +0x105

goroutine 37 gp=0xc000484540 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
        runtime/proc.go:424 +0xce fp=0xc00048bf38 sp=0xc00048bf18 pc=0x563cf466c1ce
runtime.gcBgMarkWorker(0xc000113730)
        runtime/mgc.go:1412 +0xe9 fp=0xc00048bfc8 sp=0xc00048bf38 pc=0x563cf4618869
runtime.gcBgMarkStartWorkers.gowrap1()
        runtime/mgc.go:1328 +0x25 fp=0xc00048bfe0 sp=0xc00048bfc8 pc=0x563cf4618745
runtime.goexit({})
        runtime/asm_amd64.s:1700 +0x1 fp=0xc00048bfe8 sp=0xc00048bfe0 pc=0x563cf46745a1
created by runtime.gcBgMarkStartWorkers in goroutine 1
        runtime/mgc.go:1328 +0x105

goroutine 38 gp=0xc000484700 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
        runtime/proc.go:424 +0xce fp=0xc00048c738 sp=0xc00048c718 pc=0x563cf466c1ce
runtime.gcBgMarkWorker(0xc000113730)
        runtime/mgc.go:1412 +0xe9 fp=0xc00048c7c8 sp=0xc00048c738 pc=0x563cf4618869
runtime.gcBgMarkStartWorkers.gowrap1()
        runtime/mgc.go:1328 +0x25 fp=0xc00048c7e0 sp=0xc00048c7c8 pc=0x563cf4618745
runtime.goexit({})
        runtime/asm_amd64.s:1700 +0x1 fp=0xc00048c7e8 sp=0xc00048c7e0 pc=0x563cf46745a1
created by runtime.gcBgMarkStartWorkers in goroutine 1
        runtime/mgc.go:1328 +0x105

goroutine 39 gp=0xc0004848c0 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
        runtime/proc.go:424 +0xce fp=0xc00048cf38 sp=0xc00048cf18 pc=0x563cf466c1ce
runtime.gcBgMarkWorker(0xc000113730)
        runtime/mgc.go:1412 +0xe9 fp=0xc00048cfc8 sp=0xc00048cf38 pc=0x563cf4618869
runtime.gcBgMarkStartWorkers.gowrap1()
        runtime/mgc.go:1328 +0x25 fp=0xc00048cfe0 sp=0xc00048cfc8 pc=0x563cf4618745
runtime.goexit({})
        runtime/asm_amd64.s:1700 +0x1 fp=0xc00048cfe8 sp=0xc00048cfe0 pc=0x563cf46745a1
created by runtime.gcBgMarkStartWorkers in goroutine 1
        runtime/mgc.go:1328 +0x105

goroutine 40 gp=0xc000484a80 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
        runtime/proc.go:424 +0xce fp=0xc00048d738 sp=0xc00048d718 pc=0x563cf466c1ce
runtime.gcBgMarkWorker(0xc000113730)
        runtime/mgc.go:1412 +0xe9 fp=0xc00048d7c8 sp=0xc00048d738 pc=0x563cf4618869
runtime.gcBgMarkStartWorkers.gowrap1()
        runtime/mgc.go:1328 +0x25 fp=0xc00048d7e0 sp=0xc00048d7c8 pc=0x563cf4618745
runtime.goexit({})
        runtime/asm_amd64.s:1700 +0x1 fp=0xc00048d7e8 sp=0xc00048d7e0 pc=0x563cf46745a1
created by runtime.gcBgMarkStartWorkers in goroutine 1
        runtime/mgc.go:1328 +0x105

goroutine 6 gp=0xc000007a40 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
        runtime/proc.go:424 +0xce fp=0xc0000acf38 sp=0xc0000acf18 pc=0x563cf466c1ce
runtime.gcBgMarkWorker(0xc000113730)
        runtime/mgc.go:1412 +0xe9 fp=0xc0000acfc8 sp=0xc0000acf38 pc=0x563cf4618869
runtime.gcBgMarkStartWorkers.gowrap1()
        runtime/mgc.go:1328 +0x25 fp=0xc0000acfe0 sp=0xc0000acfc8 pc=0x563cf4618745
runtime.goexit({})
        runtime/asm_amd64.s:1700 +0x1 fp=0xc0000acfe8 sp=0xc0000acfe0 pc=0x563cf46745a1
created by runtime.gcBgMarkStartWorkers in goroutine 1
        runtime/mgc.go:1328 +0x105

goroutine 26 gp=0xc00027ee00 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
        runtime/proc.go:424 +0xce fp=0xc0000a9f38 sp=0xc0000a9f18 pc=0x563cf466c1ce
runtime.gcBgMarkWorker(0xc000113730)
        runtime/mgc.go:1412 +0xe9 fp=0xc0000a9fc8 sp=0xc0000a9f38 pc=0x563cf4618869
runtime.gcBgMarkStartWorkers.gowrap1()
        runtime/mgc.go:1328 +0x25 fp=0xc0000a9fe0 sp=0xc0000a9fc8 pc=0x563cf4618745
runtime.goexit({})
        runtime/asm_amd64.s:1700 +0x1 fp=0xc0000a9fe8 sp=0xc0000a9fe0 pc=0x563cf46745a1
created by runtime.gcBgMarkStartWorkers in goroutine 1
        runtime/mgc.go:1328 +0x105

goroutine 27 gp=0xc00027efc0 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
        runtime/proc.go:424 +0xce fp=0xc000486738 sp=0xc000486718 pc=0x563cf466c1ce
runtime.gcBgMarkWorker(0xc000113730)
        runtime/mgc.go:1412 +0xe9 fp=0xc0004867c8 sp=0xc000486738 pc=0x563cf4618869
runtime.gcBgMarkStartWorkers.gowrap1()
        runtime/mgc.go:1328 +0x25 fp=0xc0004867e0 sp=0xc0004867c8 pc=0x563cf4618745
runtime.goexit({})
        runtime/asm_amd64.s:1700 +0x1 fp=0xc0004867e8 sp=0xc0004867e0 pc=0x563cf46745a1
created by runtime.gcBgMarkStartWorkers in goroutine 1
        runtime/mgc.go:1328 +0x105

goroutine 28 gp=0xc00027f180 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
        runtime/proc.go:424 +0xce fp=0xc000486f38 sp=0xc000486f18 pc=0x563cf466c1ce
runtime.gcBgMarkWorker(0xc000113730)
        runtime/mgc.go:1412 +0xe9 fp=0xc000486fc8 sp=0xc000486f38 pc=0x563cf4618869
runtime.gcBgMarkStartWorkers.gowrap1()
        runtime/mgc.go:1328 +0x25 fp=0xc000486fe0 sp=0xc000486fc8 pc=0x563cf4618745
runtime.goexit({})
        runtime/asm_amd64.s:1700 +0x1 fp=0xc000486fe8 sp=0xc000486fe0 pc=0x563cf46745a1
created by runtime.gcBgMarkStartWorkers in goroutine 1
        runtime/mgc.go:1328 +0x105

goroutine 29 gp=0xc00027f340 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
        runtime/proc.go:424 +0xce fp=0xc000487738 sp=0xc000487718 pc=0x563cf466c1ce
runtime.gcBgMarkWorker(0xc000113730)
        runtime/mgc.go:1412 +0xe9 fp=0xc0004877c8 sp=0xc000487738 pc=0x563cf4618869
runtime.gcBgMarkStartWorkers.gowrap1()
        runtime/mgc.go:1328 +0x25 fp=0xc0004877e0 sp=0xc0004877c8 pc=0x563cf4618745
runtime.goexit({})
        runtime/asm_amd64.s:1700 +0x1 fp=0xc0004877e8 sp=0xc0004877e0 pc=0x563cf46745a1
created by runtime.gcBgMarkStartWorkers in goroutine 1
        runtime/mgc.go:1328 +0x105

goroutine 30 gp=0xc00027f500 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
        runtime/proc.go:424 +0xce fp=0xc000487f38 sp=0xc000487f18 pc=0x563cf466c1ce
runtime.gcBgMarkWorker(0xc000113730)
        runtime/mgc.go:1412 +0xe9 fp=0xc000487fc8 sp=0xc000487f38 pc=0x563cf4618869
runtime.gcBgMarkStartWorkers.gowrap1()
        runtime/mgc.go:1328 +0x25 fp=0xc000487fe0 sp=0xc000487fc8 pc=0x563cf4618745
runtime.goexit({})
        runtime/asm_amd64.s:1700 +0x1 fp=0xc000487fe8 sp=0xc000487fe0 pc=0x563cf46745a1
created by runtime.gcBgMarkStartWorkers in goroutine 1
        runtime/mgc.go:1328 +0x105

goroutine 31 gp=0xc00027f6c0 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
        runtime/proc.go:424 +0xce fp=0xc000488738 sp=0xc000488718 pc=0x563cf466c1ce
runtime.gcBgMarkWorker(0xc000113730)
        runtime/mgc.go:1412 +0xe9 fp=0xc0004887c8 sp=0xc000488738 pc=0x563cf4618869
runtime.gcBgMarkStartWorkers.gowrap1()
        runtime/mgc.go:1328 +0x25 fp=0xc0004887e0 sp=0xc0004887c8 pc=0x563cf4618745
runtime.goexit({})
        runtime/asm_amd64.s:1700 +0x1 fp=0xc0004887e8 sp=0xc0004887e0 pc=0x563cf46745a1
created by runtime.gcBgMarkStartWorkers in goroutine 1
        runtime/mgc.go:1328 +0x105

goroutine 32 gp=0xc00027f880 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
        runtime/proc.go:424 +0xce fp=0xc000488f38 sp=0xc000488f18 pc=0x563cf466c1ce
runtime.gcBgMarkWorker(0xc000113730)
        runtime/mgc.go:1412 +0xe9 fp=0xc000488fc8 sp=0xc000488f38 pc=0x563cf4618869
runtime.gcBgMarkStartWorkers.gowrap1()
        runtime/mgc.go:1328 +0x25 fp=0xc000488fe0 sp=0xc000488fc8 pc=0x563cf4618745
runtime.goexit({})
        runtime/asm_amd64.s:1700 +0x1 fp=0xc000488fe8 sp=0xc000488fe0 pc=0x563cf46745a1
created by runtime.gcBgMarkStartWorkers in goroutine 1
        runtime/mgc.go:1328 +0x105

goroutine 41 gp=0xc000484c40 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
        runtime/proc.go:424 +0xce fp=0xc00048df38 sp=0xc00048df18 pc=0x563cf466c1ce
runtime.gcBgMarkWorker(0xc000113730)
        runtime/mgc.go:1412 +0xe9 fp=0xc00048dfc8 sp=0xc00048df38 pc=0x563cf4618869
runtime.gcBgMarkStartWorkers.gowrap1()
        runtime/mgc.go:1328 +0x25 fp=0xc00048dfe0 sp=0xc00048dfc8 pc=0x563cf4618745
runtime.goexit({})
        runtime/asm_amd64.s:1700 +0x1 fp=0xc00048dfe8 sp=0xc00048dfe0 pc=0x563cf46745a1
created by runtime.gcBgMarkStartWorkers in goroutine 1
        runtime/mgc.go:1328 +0x105

goroutine 42 gp=0xc000484e00 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
        runtime/proc.go:424 +0xce fp=0xc000492738 sp=0xc000492718 pc=0x563cf466c1ce
runtime.gcBgMarkWorker(0xc000113730)
        runtime/mgc.go:1412 +0xe9 fp=0xc0004927c8 sp=0xc000492738 pc=0x563cf4618869
runtime.gcBgMarkStartWorkers.gowrap1()
        runtime/mgc.go:1328 +0x25 fp=0xc0004927e0 sp=0xc0004927c8 pc=0x563cf4618745
runtime.goexit({})
        runtime/asm_amd64.s:1700 +0x1 fp=0xc0004927e8 sp=0xc0004927e0 pc=0x563cf46745a1
created by runtime.gcBgMarkStartWorkers in goroutine 1
        runtime/mgc.go:1328 +0x105

goroutine 43 gp=0xc000484fc0 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
        runtime/proc.go:424 +0xce fp=0xc000492f38 sp=0xc000492f18 pc=0x563cf466c1ce
runtime.gcBgMarkWorker(0xc000113730)
        runtime/mgc.go:1412 +0xe9 fp=0xc000492fc8 sp=0xc000492f38 pc=0x563cf4618869
runtime.gcBgMarkStartWorkers.gowrap1()
        runtime/mgc.go:1328 +0x25 fp=0xc000492fe0 sp=0xc000492fc8 pc=0x563cf4618745
runtime.goexit({})
        runtime/asm_amd64.s:1700 +0x1 fp=0xc000492fe8 sp=0xc000492fe0 pc=0x563cf46745a1
created by runtime.gcBgMarkStartWorkers in goroutine 1
        runtime/mgc.go:1328 +0x105

goroutine 7 gp=0xc000007c00 m=nil [GC worker (idle)]:
runtime.gopark(0x1867defd493?, 0x0?, 0x0?, 0x0?, 0x0?)
        runtime/proc.go:424 +0xce fp=0xc0000ad738 sp=0xc0000ad718 pc=0x563cf466c1ce
runtime.gcBgMarkWorker(0xc000113730)
        runtime/mgc.go:1412 +0xe9 fp=0xc0000ad7c8 sp=0xc0000ad738 pc=0x563cf4618869
runtime.gcBgMarkStartWorkers.gowrap1()
        runtime/mgc.go:1328 +0x25 fp=0xc0000ad7e0 sp=0xc0000ad7c8 pc=0x563cf4618745
runtime.goexit({})
        runtime/asm_amd64.s:1700 +0x1 fp=0xc0000ad7e8 sp=0xc0000ad7e0 pc=0x563cf46745a1
created by runtime.gcBgMarkStartWorkers in goroutine 1
        runtime/mgc.go:1328 +0x105

goroutine 44 gp=0xc000485180 m=nil [GC worker (idle)]:
runtime.gopark(0x563cf61706e0?, 0x1?, 0xc?, 0xd0?, 0x0?)
        runtime/proc.go:424 +0xce fp=0xc000493738 sp=0xc000493718 pc=0x563cf466c1ce
runtime.gcBgMarkWorker(0xc000113730)
        runtime/mgc.go:1412 +0xe9 fp=0xc0004937c8 sp=0xc000493738 pc=0x563cf4618869
runtime.gcBgMarkStartWorkers.gowrap1()
        runtime/mgc.go:1328 +0x25 fp=0xc0004937e0 sp=0xc0004937c8 pc=0x563cf4618745
runtime.goexit({})
        runtime/asm_amd64.s:1700 +0x1 fp=0xc0004937e8 sp=0xc0004937e0 pc=0x563cf46745a1
created by runtime.gcBgMarkStartWorkers in goroutine 1
        runtime/mgc.go:1328 +0x105

goroutine 33 gp=0xc00027fa40 m=nil [GC worker (idle)]:
runtime.gopark(0x563cf61706e0?, 0x1?, 0x82?, 0x21?, 0x0?)
        runtime/proc.go:424 +0xce fp=0xc000489738 sp=0xc000489718 pc=0x563cf466c1ce
runtime.gcBgMarkWorker(0xc000113730)
        runtime/mgc.go:1412 +0xe9 fp=0xc0004897c8 sp=0xc000489738 pc=0x563cf4618869
runtime.gcBgMarkStartWorkers.gowrap1()
        runtime/mgc.go:1328 +0x25 fp=0xc0004897e0 sp=0xc0004897c8 pc=0x563cf4618745
runtime.goexit({})
        runtime/asm_amd64.s:1700 +0x1 fp=0xc0004897e8 sp=0xc0004897e0 pc=0x563cf46745a1
created by runtime.gcBgMarkStartWorkers in goroutine 1
        runtime/mgc.go:1328 +0x105

goroutine 8 gp=0xc000007dc0 m=nil [GC worker (idle)]:
runtime.gopark(0x1867def25e4?, 0x1?, 0x58?, 0x5b?, 0x0?)
        runtime/proc.go:424 +0xce fp=0xc0000adf38 sp=0xc0000adf18 pc=0x563cf466c1ce
runtime.gcBgMarkWorker(0xc000113730)
        runtime/mgc.go:1412 +0xe9 fp=0xc0000adfc8 sp=0xc0000adf38 pc=0x563cf4618869
runtime.gcBgMarkStartWorkers.gowrap1()
        runtime/mgc.go:1328 +0x25 fp=0xc0000adfe0 sp=0xc0000adfc8 pc=0x563cf4618745
runtime.goexit({})
        runtime/asm_amd64.s:1700 +0x1 fp=0xc0000adfe8 sp=0xc0000adfe0 pc=0x563cf46745a1
created by runtime.gcBgMarkStartWorkers in goroutine 1
        runtime/mgc.go:1328 +0x105

goroutine 9 gp=0xc0000e8000 m=nil [GC worker (idle)]:
runtime.gopark(0x563cf61706e0?, 0x1?, 0xb9?, 0x31?, 0x0?)
        runtime/proc.go:424 +0xce fp=0xc00048e738 sp=0xc00048e718 pc=0x563cf466c1ce
runtime.gcBgMarkWorker(0xc000113730)
        runtime/mgc.go:1412 +0xe9 fp=0xc00048e7c8 sp=0xc00048e738 pc=0x563cf4618869
runtime.gcBgMarkStartWorkers.gowrap1()
        runtime/mgc.go:1328 +0x25 fp=0xc00048e7e0 sp=0xc00048e7c8 pc=0x563cf4618745
runtime.goexit({})
        runtime/asm_amd64.s:1700 +0x1 fp=0xc00048e7e8 sp=0xc00048e7e0 pc=0x563cf46745a1
created by runtime.gcBgMarkStartWorkers in goroutine 1
        runtime/mgc.go:1328 +0x105

goroutine 10 gp=0xc0000e81c0 m=nil [GC worker (idle)]:
runtime.gopark(0x563cf61706e0?, 0x1?, 0xfa?, 0x39?, 0x0?)
        runtime/proc.go:424 +0xce fp=0xc00048ef38 sp=0xc00048ef18 pc=0x563cf466c1ce
runtime.gcBgMarkWorker(0xc000113730)
        runtime/mgc.go:1412 +0xe9 fp=0xc00048efc8 sp=0xc00048ef38 pc=0x563cf4618869
runtime.gcBgMarkStartWorkers.gowrap1()
        runtime/mgc.go:1328 +0x25 fp=0xc00048efe0 sp=0xc00048efc8 pc=0x563cf4618745
runtime.goexit({})
        runtime/asm_amd64.s:1700 +0x1 fp=0xc00048efe8 sp=0xc00048efe0 pc=0x563cf46745a1
created by runtime.gcBgMarkStartWorkers in goroutine 1
        runtime/mgc.go:1328 +0x105

goroutine 11 gp=0xc0000e8380 m=nil [GC worker (idle)]:
runtime.gopark(0x563cf61706e0?, 0x1?, 0xaf?, 0xe2?, 0x0?)
        runtime/proc.go:424 +0xce fp=0xc00048f738 sp=0xc00048f718 pc=0x563cf466c1ce
runtime.gcBgMarkWorker(0xc000113730)
        runtime/mgc.go:1412 +0xe9 fp=0xc00048f7c8 sp=0xc00048f738 pc=0x563cf4618869
runtime.gcBgMarkStartWorkers.gowrap1()
        runtime/mgc.go:1328 +0x25 fp=0xc00048f7e0 sp=0xc00048f7c8 pc=0x563cf4618745
runtime.goexit({})
        runtime/asm_amd64.s:1700 +0x1 fp=0xc00048f7e8 sp=0xc00048f7e0 pc=0x563cf46745a1
created by runtime.gcBgMarkStartWorkers in goroutine 1
        runtime/mgc.go:1328 +0x105

goroutine 50 gp=0xc000604380 m=nil [select]:
runtime.gopark(0xc0003cba68?, 0x2?, 0x8e?, 0x55?, 0xc0003cb834?)
        runtime/proc.go:424 +0xce fp=0xc0003cb6a0 sp=0xc0003cb680 pc=0x563cf466c1ce
runtime.selectgo(0xc0003cba68, 0xc0003cb830, 0xa?, 0x0, 0x1?, 0x1)
        runtime/select.go:335 +0x7a5 fp=0xc0003cb7c8 sp=0xc0003cb6a0 pc=0x563cf46494c5
github.com/ollama/ollama/runner/llamarunner.(*Server).completion(0xc0000d8000, {0x563cf58cb708, 0xc00022c620}, 0xc0005eca00)
        github.com/ollama/ollama/runner/llamarunner/runner.go:688 +0xa86 fp=0xc0003cbac0 sp=0xc0003cb7c8 pc=0x563cf4a3afa6
github.com/ollama/ollama/runner/llamarunner.(*Server).completion-fm({0x563cf58cb708?, 0xc00022c620?}, 0x563cf49a26c7?)
        <autogenerated>:1 +0x36 fp=0xc0003cbaf0 sp=0xc0003cbac0 pc=0x563cf4a3e076
net/http.HandlerFunc.ServeHTTP(0xc0000ee000?, {0x563cf58cb708?, 0xc00022c620?}, 0x0?)
        net/http/server.go:2220 +0x29 fp=0xc0003cbb18 sp=0xc0003cbaf0 pc=0x563cf4994ee9
net/http.(*ServeMux).ServeHTTP(0x563cf460ca05?, {0x563cf58cb708, 0xc00022c620}, 0xc0005eca00)
        net/http/server.go:2747 +0x1ca fp=0xc0003cbb68 sp=0xc0003cbb18 pc=0x563cf4996dea
net/http.serverHandler.ServeHTTP({0x563cf58c80d0?}, {0x563cf58cb708?, 0xc00022c620?}, 0x6?)
        net/http/server.go:3210 +0x8e fp=0xc0003cbb98 sp=0xc0003cbb68 pc=0x563cf49b434e
net/http.(*conn).serve(0xc000460000, {0x563cf58cd8e8, 0xc00001c300})
        net/http/server.go:2092 +0x5d0 fp=0xc0003cbfb8 sp=0xc0003cbb98 pc=0x563cf4993890
net/http.(*Server).Serve.gowrap3()
        net/http/server.go:3360 +0x28 fp=0xc0003cbfe0 sp=0xc0003cbfb8 pc=0x563cf4998ce8
runtime.goexit({})
        runtime/asm_amd64.s:1700 +0x1 fp=0xc0003cbfe8 sp=0xc0003cbfe0 pc=0x563cf46745a1
created by net/http.(*Server).Serve in goroutine 1
        net/http/server.go:3360 +0x485

goroutine 85 gp=0xc000604c40 m=nil [IO wait]:
runtime.gopark(0x563cf4610ee5?, 0x0?, 0x0?, 0x0?, 0xb?)
        runtime/proc.go:424 +0xce fp=0xc0002485a8 sp=0xc000248588 pc=0x563cf466c1ce
runtime.netpollblock(0x563cf468f6b8?, 0xf4602fe6?, 0x3c?)
        runtime/netpoll.go:575 +0xf7 fp=0xc0002485e0 sp=0xc0002485a8 pc=0x563cf462fe37
internal/poll.runtime_pollWait(0x7f801d782cd8, 0x72)
        runtime/netpoll.go:351 +0x85 fp=0xc000248600 sp=0xc0002485e0 pc=0x563cf466b4c5
internal/poll.(*pollDesc).wait(0xc00045e000?, 0xc00045a101?, 0x0)
        internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc000248628 sp=0xc000248600 pc=0x563cf46f3707
internal/poll.(*pollDesc).waitRead(...)
        internal/poll/fd_poll_runtime.go:89
internal/poll.(*FD).Read(0xc00045e000, {0xc00045a101, 0x1, 0x1})
        internal/poll/fd_unix.go:165 +0x27a fp=0xc0002486c0 sp=0xc000248628 pc=0x563cf46f49fa
net.(*netFD).Read(0xc00045e000, {0xc00045a101?, 0xc000248748?, 0x563cf466de50?})
        net/fd_posix.go:55 +0x25 fp=0xc000248708 sp=0xc0002486c0 pc=0x563cf475fc05
net.(*conn).Read(0xc00045c008, {0xc00045a101?, 0x0?, 0x563cf616e480?})
        net/net.go:189 +0x45 fp=0xc000248750 sp=0xc000248708 pc=0x563cf476e205
net.(*TCPConn).Read(0x563cf601ff60?, {0xc00045a101?, 0x0?, 0x0?})
        <autogenerated>:1 +0x25 fp=0xc000248780 sp=0xc000248750 pc=0x563cf4781405
net/http.(*connReader).backgroundRead(0xc00045a0f0)
        net/http/server.go:690 +0x37 fp=0xc0002487c8 sp=0xc000248780 pc=0x563cf498e217
net/http.(*connReader).startBackgroundRead.gowrap2()
        net/http/server.go:686 +0x25 fp=0xc0002487e0 sp=0xc0002487c8 pc=0x563cf498e145
runtime.goexit({})
        runtime/asm_amd64.s:1700 +0x1 fp=0xc0002487e8 sp=0xc0002487e0 pc=0x563cf46745a1
created by net/http.(*connReader).startBackgroundRead in goroutine 50
        net/http/server.go:686 +0xb6

rax    0x3c00
rbx    0x7f801dfb8310
rcx    0x7f80083ade70
rdx    0x7f80080008e0
rdi    0x11
rsi    0x7f80083ade20
rbp    0x0
rsp    0x7f801dfb7a30
r8     0x0
r9     0x7f80083af500
r10    0x0
r11    0x9c9afa8d5a4b8f9e
r12    0x0
r13    0x563d110ae400
r14    0x7f801dfb86e8
r15    0x20
rip    0x7f7fdc968f27
rflags 0x10202
cs     0x33
fs     0x0
gs     0x0
[GIN] 2025/03/04 - 15:52:01 | 200 |  251.491877ms |       127.0.0.1 | POST     "/api/chat"

OS

Linux

GPU

Intel

CPU

AMD

Ollama version

0.5.12

Originally created by @furryaxw on GitHub (Mar 4, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/9500 ### What is the issue? crashes on every call to the server ### Relevant log output ```shell 2025/03/04 15:51:47 routes.go:1205: INFO server config env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://0.0.0.0:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/ollama OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:0 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://*] OLLAMA_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]" time=2025-03-04T15:51:47.296Z level=INFO source=images.go:432 msg="total blobs: 4" time=2025-03-04T15:51:47.296Z level=INFO source=images.go:439 msg="total unused blobs removed: 0" time=2025-03-04T15:51:47.297Z level=INFO source=routes.go:1256 msg="Listening on [::]:11434 (version 0.5.12)" time=2025-03-04T15:51:47.297Z level=INFO source=gpu.go:217 msg="looking for compatible GPUs" time=2025-03-04T15:51:47.335Z level=INFO source=amd_linux.go:386 msg="amdgpu is supported" gpu=GPU-6f927101732c7315 gpu_type=gfx906 time=2025-03-04T15:51:47.336Z level=INFO source=types.go:130 msg="inference compute" id=GPU-6f927101732c7315 library=rocm variant="" compute=gfx906 driver=6.10 name=1002:66a1 total="16.0 GiB" available="16.0 GiB" [GIN] 2025/03/04 - 15:51:52 | 200 | 89.166µs | 127.0.0.1 | HEAD "/" [GIN] 2025/03/04 - 15:51:52 | 200 | 86.907454ms | 127.0.0.1 | POST "/api/show" time=2025-03-04T15:51:52.574Z level=INFO source=sched.go:715 msg="new model will fit in available VRAM in single GPU, loading" model=/ollama/blobs/sha256-e729bfb34d8e05557eca33c39b6745a25f17b6e55dac5283296ff78704469c3f gpu=GPU-6f927101732c7315 parallel=4 available=17152217088 required="6.5 GiB" time=2025-03-04T15:51:52.574Z level=INFO source=server.go:97 msg="system memory" total="46.9 GiB" free="45.5 GiB" free_swap="8.0 GiB" time=2025-03-04T15:51:52.575Z level=INFO source=server.go:130 msg=offload library=rocm layers.requested=-1 layers.model=33 layers.offload=33 layers.split="" memory.available="[16.0 GiB]" memory.gpu_overhead="0 B" memory.required.full="6.5 GiB" memory.required.partial="6.5 GiB" memory.required.kv="1.0 GiB" memory.required.allocations="[6.5 GiB]" memory.weights.total="4.9 GiB" memory.weights.repeating="4.5 GiB" memory.weights.nonrepeating="411.0 MiB" memory.graph.full="560.0 MiB" memory.graph.partial="677.5 MiB" time=2025-03-04T15:51:52.576Z level=INFO source=server.go:380 msg="starting llama server" cmd="/usr/bin/ollama runner --model /ollama/blobs/sha256-e729bfb34d8e05557eca33c39b6745a25f17b6e55dac5283296ff78704469c3f --ctx-size 8192 --batch-size 512 --n-gpu-layers 33 --threads 16 --parallel 4 --port 40381" time=2025-03-04T15:51:52.577Z level=INFO source=sched.go:450 msg="loaded runners" count=1 time=2025-03-04T15:51:52.577Z level=INFO source=server.go:557 msg="waiting for llama runner to start responding" time=2025-03-04T15:51:52.578Z level=INFO source=server.go:591 msg="waiting for server to become available" status="llm server error" time=2025-03-04T15:51:52.619Z level=INFO source=runner.go:932 msg="starting go runner" ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no ggml_cuda_init: found 1 ROCm devices: Device 0: AMD Radeon (TM) Pro VII, compute capability 9.0, VMM: no load_backend: loaded ROCm backend from /usr/lib/ollama/rocm/libggml-hip.so load_backend: loaded CPU backend from /usr/lib/ollama/libggml-cpu-sandybridge.so time=2025-03-04T15:51:54.299Z level=INFO source=runner.go:935 msg=system info="CPU : LLAMAFILE = 1 | CPU : LLAMAFILE = 1 | ROCm : PEER_MAX_BATCH_SIZE = 128 | CPU : SSE3 = 1 | SSSE3 = 1 | AVX = 1 | LLAMAFILE = 1 | cgo(gcc)" threads=16 time=2025-03-04T15:51:54.299Z level=INFO source=runner.go:993 msg="Server listening on 127.0.0.1:40381" llama_load_model_from_file: using device ROCm0 (AMD Radeon (TM) Pro VII) - 15926 MiB free time=2025-03-04T15:51:54.336Z level=INFO source=server.go:591 msg="waiting for server to become available" status="llm server loading model" llama_model_loader: loaded meta data with 29 key-value pairs and 292 tensors from /ollama/blobs/sha256-e729bfb34d8e05557eca33c39b6745a25f17b6e55dac5283296ff78704469c3f (version GGUF V3 (latest)) llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output. llama_model_loader: - kv 0: general.architecture str = llama llama_model_loader: - kv 1: general.type str = model llama_model_loader: - kv 2: general.name str = Llama3.1 8B Chinese Furry 1.6.5t llama_model_loader: - kv 3: general.finetune str = Chinese-Furry-1.6.5t llama_model_loader: - kv 4: general.basename str = Llama3.1 llama_model_loader: - kv 5: general.size_label str = 8B llama_model_loader: - kv 6: llama.block_count u32 = 32 llama_model_loader: - kv 7: llama.context_length u32 = 131072 llama_model_loader: - kv 8: llama.embedding_length u32 = 4096 llama_model_loader: - kv 9: llama.feed_forward_length u32 = 14336 llama_model_loader: - kv 10: llama.attention.head_count u32 = 32 llama_model_loader: - kv 11: llama.attention.head_count_kv u32 = 8 llama_model_loader: - kv 12: llama.rope.freq_base f32 = 500000.000000 llama_model_loader: - kv 13: llama.attention.layer_norm_rms_epsilon f32 = 0.000010 llama_model_loader: - kv 14: llama.attention.key_length u32 = 128 llama_model_loader: - kv 15: llama.attention.value_length u32 = 128 llama_model_loader: - kv 16: general.file_type u32 = 15 llama_model_loader: - kv 17: llama.vocab_size u32 = 128256 llama_model_loader: - kv 18: llama.rope.dimension_count u32 = 128 llama_model_loader: - kv 19: tokenizer.ggml.model str = gpt2 llama_model_loader: - kv 20: tokenizer.ggml.pre str = smaug-bpe llama_model_loader: - kv 21: tokenizer.ggml.tokens arr[str,128256] = ["!", "\"", "#", "$", "%", "&", "'", ... llama_model_loader: - kv 22: tokenizer.ggml.token_type arr[i32,128256] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... llama_model_loader: - kv 23: tokenizer.ggml.merges arr[str,280147] = ["Ġ Ġ", "Ġ ĠĠĠ", "ĠĠ ĠĠ", "... llama_model_loader: - kv 24: tokenizer.ggml.bos_token_id u32 = 128000 llama_model_loader: - kv 25: tokenizer.ggml.eos_token_id u32 = 128009 llama_model_loader: - kv 26: tokenizer.ggml.padding_token_id u32 = 128009 llama_model_loader: - kv 27: tokenizer.chat_template str = {% set loop_messages = messages %}{% ... llama_model_loader: - kv 28: general.quantization_version u32 = 2 llama_model_loader: - type f32: 66 tensors llama_model_loader: - type q4_K: 193 tensors llama_model_loader: - type q6_K: 33 tensors llm_load_vocab: special tokens cache size = 256 llm_load_vocab: token to piece cache size = 0.7999 MB llm_load_print_meta: format = GGUF V3 (latest) llm_load_print_meta: arch = llama llm_load_print_meta: vocab type = BPE llm_load_print_meta: n_vocab = 128256 llm_load_print_meta: n_merges = 280147 llm_load_print_meta: vocab_only = 0 llm_load_print_meta: n_ctx_train = 131072 llm_load_print_meta: n_embd = 4096 llm_load_print_meta: n_layer = 32 llm_load_print_meta: n_head = 32 llm_load_print_meta: n_head_kv = 8 llm_load_print_meta: n_rot = 128 llm_load_print_meta: n_swa = 0 llm_load_print_meta: n_embd_head_k = 128 llm_load_print_meta: n_embd_head_v = 128 llm_load_print_meta: n_gqa = 4 llm_load_print_meta: n_embd_k_gqa = 1024 llm_load_print_meta: n_embd_v_gqa = 1024 llm_load_print_meta: f_norm_eps = 0.0e+00 llm_load_print_meta: f_norm_rms_eps = 1.0e-05 llm_load_print_meta: f_clamp_kqv = 0.0e+00 llm_load_print_meta: f_max_alibi_bias = 0.0e+00 llm_load_print_meta: f_logit_scale = 0.0e+00 llm_load_print_meta: n_ff = 14336 llm_load_print_meta: n_expert = 0 llm_load_print_meta: n_expert_used = 0 llm_load_print_meta: causal attn = 1 llm_load_print_meta: pooling type = 0 llm_load_print_meta: rope type = 0 llm_load_print_meta: rope scaling = linear llm_load_print_meta: freq_base_train = 500000.0 llm_load_print_meta: freq_scale_train = 1 llm_load_print_meta: n_ctx_orig_yarn = 131072 llm_load_print_meta: rope_finetuned = unknown llm_load_print_meta: ssm_d_conv = 0 llm_load_print_meta: ssm_d_inner = 0 llm_load_print_meta: ssm_d_state = 0 llm_load_print_meta: ssm_dt_rank = 0 llm_load_print_meta: ssm_dt_b_c_rms = 0 llm_load_print_meta: model type = 8B llm_load_print_meta: model ftype = Q4_K - Medium llm_load_print_meta: model params = 8.03 B llm_load_print_meta: model size = 4.58 GiB (4.89 BPW) llm_load_print_meta: general.name = Llama3.1 8B Chinese Furry 1.6.5t llm_load_print_meta: BOS token = 128000 '<|begin_of_text|>' llm_load_print_meta: EOS token = 128009 '<|eot_id|>' llm_load_print_meta: EOT token = 128009 '<|eot_id|>' llm_load_print_meta: EOM token = 128008 '<|eom_id|>' llm_load_print_meta: PAD token = 128009 '<|eot_id|>' llm_load_print_meta: LF token = 128 'Ä' llm_load_print_meta: EOG token = 128008 '<|eom_id|>' llm_load_print_meta: EOG token = 128009 '<|eot_id|>' llm_load_print_meta: max token length = 256 llm_load_tensors: offloading 32 repeating layers to GPU llm_load_tensors: offloading output layer to GPU llm_load_tensors: offloaded 33/33 layers to GPU llm_load_tensors: ROCm0 model buffer size = 4403.49 MiB llm_load_tensors: CPU_Mapped model buffer size = 281.81 MiB llama_new_context_with_model: n_seq_max = 4 llama_new_context_with_model: n_ctx = 8192 llama_new_context_with_model: n_ctx_per_seq = 2048 llama_new_context_with_model: n_batch = 2048 llama_new_context_with_model: n_ubatch = 512 llama_new_context_with_model: flash_attn = 0 llama_new_context_with_model: freq_base = 500000.0 llama_new_context_with_model: freq_scale = 1 llama_new_context_with_model: n_ctx_per_seq (2048) < n_ctx_train (131072) -- the full capacity of the model will not be utilized llama_kv_cache_init: kv_size = 8192, offload = 1, type_k = 'f16', type_v = 'f16', n_layer = 32, can_shift = 1 llama_kv_cache_init: ROCm0 KV buffer size = 1024.00 MiB llama_new_context_with_model: KV self size = 1024.00 MiB, K (f16): 512.00 MiB, V (f16): 512.00 MiB llama_new_context_with_model: ROCm_Host output buffer size = 2.02 MiB llama_new_context_with_model: ROCm0 compute buffer size = 560.00 MiB llama_new_context_with_model: ROCm_Host compute buffer size = 24.01 MiB llama_new_context_with_model: graph nodes = 1030 llama_new_context_with_model: graph splits = 2 time=2025-03-04T15:51:58.360Z level=INFO source=server.go:596 msg="llama runner started in 5.78 seconds" [GIN] 2025/03/04 - 15:51:58 | 200 | 5.886295765s | 127.0.0.1 | POST "/api/generate" SIGILL: illegal instruction PC=0x7f7fdc968f27 m=4 sigcode=2 signal arrived during cgo execution instruction bytes: 0xc4 0xe2 0x79 0x13 0xc0 0xc5 0xf0 0x57 0xc9 0xc5 0xf8 0x2e 0xc1 0x75 0x6 0xf goroutine 46 gp=0xc000504540 m=4 mp=0xc0000b1508 [syscall]: runtime.cgocall(0x563cf527ace0, 0xc0000beba0) runtime/cgocall.go:167 +0x4b fp=0xc0000beb78 sp=0xc0000beb40 pc=0x563cf4665acb github.com/ollama/ollama/llama._Cfunc_llama_decode(0x7f7dd58bf120, {0xa, 0x7f7dd639f910, 0x0, 0x0, 0x7f7dd5ba43c0, 0x7f7dd5ae67b0, 0x7f7dd5b1bd20, 0x7f7dd5959200}) _cgo_gotypes.go:545 +0x4f fp=0xc0000beba0 sp=0xc0000beb78 pc=0x563cf4a1b56f github.com/ollama/ollama/llama.(*Context).Decode.func1(0x563cf4a3a48b?, 0x7f7dd58bf120?) github.com/ollama/ollama/llama/llama.go:163 +0xf5 fp=0xc0000bec90 sp=0xc0000beba0 pc=0x563cf4a1e295 github.com/ollama/ollama/llama.(*Context).Decode(0xc000495578?, 0x0?) github.com/ollama/ollama/llama/llama.go:163 +0x13 fp=0xc0000becd8 sp=0xc0000bec90 pc=0x563cf4a1e113 github.com/ollama/ollama/runner/llamarunner.(*Server).processBatch(0xc0000d8000, 0xc00046c120, 0xc000495720) github.com/ollama/ollama/runner/llamarunner/runner.go:435 +0x23f fp=0xc0000beee0 sp=0xc0000becd8 pc=0x563cf4a3927f github.com/ollama/ollama/runner/llamarunner.(*Server).run(0xc0000d8000, {0x563cf58cd920, 0xc0000ae050}) github.com/ollama/ollama/runner/llamarunner/runner.go:343 +0x1d5 fp=0xc0000befb8 sp=0xc0000beee0 pc=0x563cf4a38cb5 github.com/ollama/ollama/runner/llamarunner.Execute.gowrap2() github.com/ollama/ollama/runner/llamarunner/runner.go:973 +0x28 fp=0xc0000befe0 sp=0xc0000befb8 pc=0x563cf4a3db48 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0000befe8 sp=0xc0000befe0 pc=0x563cf46745a1 created by github.com/ollama/ollama/runner/llamarunner.Execute in goroutine 1 github.com/ollama/ollama/runner/llamarunner/runner.go:973 +0xdb5 goroutine 1 gp=0xc0000061c0 m=nil [IO wait]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xce fp=0xc0000495c0 sp=0xc0000495a0 pc=0x563cf466c1ce runtime.netpollblock(0xc000465f80?, 0xf4602fe6?, 0x3c?) runtime/netpoll.go:575 +0xf7 fp=0xc0000495f8 sp=0xc0000495c0 pc=0x563cf462fe37 internal/poll.runtime_pollWait(0x7f801d782df0, 0x72) runtime/netpoll.go:351 +0x85 fp=0xc000049618 sp=0xc0000495f8 pc=0x563cf466b4c5 internal/poll.(*pollDesc).wait(0xc000020080?, 0x2c?, 0x0) internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc000049640 sp=0xc000049618 pc=0x563cf46f3707 internal/poll.(*pollDesc).waitRead(...) internal/poll/fd_poll_runtime.go:89 internal/poll.(*FD).Accept(0xc000020080) internal/poll/fd_unix.go:620 +0x295 fp=0xc0000496e8 sp=0xc000049640 pc=0x563cf46f8ad5 net.(*netFD).accept(0xc000020080) net/fd_unix.go:172 +0x29 fp=0xc0000497a0 sp=0xc0000496e8 pc=0x563cf4761bc9 net.(*TCPListener).accept(0xc000133440) net/tcpsock_posix.go:159 +0x1e fp=0xc0000497f0 sp=0xc0000497a0 pc=0x563cf477783e net.(*TCPListener).Accept(0xc000133440) net/tcpsock.go:372 +0x30 fp=0xc000049820 sp=0xc0000497f0 pc=0x563cf47766f0 net/http.(*onceCloseListener).Accept(0xc000460000?) <autogenerated>:1 +0x24 fp=0xc000049838 sp=0xc000049820 pc=0x563cf49c0964 net/http.(*Server).Serve(0xc00001a3c0, {0x563cf58cb4f8, 0xc000133440}) net/http/server.go:3330 +0x30c fp=0xc000049968 sp=0xc000049838 pc=0x563cf49988ec github.com/ollama/ollama/runner/llamarunner.Execute({0xc000136020, 0xe, 0xe}) github.com/ollama/ollama/runner/llamarunner/runner.go:994 +0x1174 fp=0xc000049d08 sp=0xc000049968 pc=0x563cf4a3d834 github.com/ollama/ollama/runner.Execute({0xc000136010?, 0x0?, 0x0?}) github.com/ollama/ollama/runner/runner.go:22 +0xd4 fp=0xc000049d30 sp=0xc000049d08 pc=0x563cf4c6dc54 github.com/ollama/ollama/cmd.NewCLI.func2(0xc000137500?, {0x563cf5468050?, 0x4?, 0x563cf5468054?}) github.com/ollama/ollama/cmd/cmd.go:1280 +0x45 fp=0xc000049d58 sp=0xc000049d30 pc=0x563cf527a245 github.com/spf13/cobra.(*Command).execute(0xc0005f1b08, {0xc0005a77a0, 0xe, 0xe}) github.com/spf13/cobra@v1.7.0/command.go:940 +0x862 fp=0xc000049e78 sp=0xc000049d58 pc=0x563cf47da902 github.com/spf13/cobra.(*Command).ExecuteC(0xc000595508) github.com/spf13/cobra@v1.7.0/command.go:1068 +0x3a5 fp=0xc000049f30 sp=0xc000049e78 pc=0x563cf47db145 github.com/spf13/cobra.(*Command).Execute(...) github.com/spf13/cobra@v1.7.0/command.go:992 github.com/spf13/cobra.(*Command).ExecuteContext(...) github.com/spf13/cobra@v1.7.0/command.go:985 main.main() github.com/ollama/ollama/main.go:12 +0x4d fp=0xc000049f50 sp=0xc000049f30 pc=0x563cf527a5cd runtime.main() runtime/proc.go:272 +0x29d fp=0xc000049fe0 sp=0xc000049f50 pc=0x563cf46374dd runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000049fe8 sp=0xc000049fe0 pc=0x563cf46745a1 goroutine 2 gp=0xc000006c40 m=nil [force gc (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xce fp=0xc0000aafa8 sp=0xc0000aaf88 pc=0x563cf466c1ce runtime.goparkunlock(...) runtime/proc.go:430 runtime.forcegchelper() runtime/proc.go:337 +0xb8 fp=0xc0000aafe0 sp=0xc0000aafa8 pc=0x563cf4637818 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0000aafe8 sp=0xc0000aafe0 pc=0x563cf46745a1 created by runtime.init.7 in goroutine 1 runtime/proc.go:325 +0x1a goroutine 3 gp=0xc000007180 m=nil [GC sweep wait]: runtime.gopark(0x1?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xce fp=0xc0000ab780 sp=0xc0000ab760 pc=0x563cf466c1ce runtime.goparkunlock(...) runtime/proc.go:430 runtime.bgsweep(0xc0000d8000) runtime/mgcsweep.go:317 +0xdf fp=0xc0000ab7c8 sp=0xc0000ab780 pc=0x563cf4621ebf runtime.gcenable.gowrap1() runtime/mgc.go:204 +0x25 fp=0xc0000ab7e0 sp=0xc0000ab7c8 pc=0x563cf4616505 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0000ab7e8 sp=0xc0000ab7e0 pc=0x563cf46745a1 created by runtime.gcenable in goroutine 1 runtime/mgc.go:204 +0x66 goroutine 4 gp=0xc000007340 m=nil [GC scavenge wait]: runtime.gopark(0x10000?, 0x563cf561b6f8?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xce fp=0xc0000abf78 sp=0xc0000abf58 pc=0x563cf466c1ce runtime.goparkunlock(...) runtime/proc.go:430 runtime.(*scavengerState).park(0x563cf60c2080) runtime/mgcscavenge.go:425 +0x49 fp=0xc0000abfa8 sp=0xc0000abf78 pc=0x563cf461f889 runtime.bgscavenge(0xc0000d8000) runtime/mgcscavenge.go:658 +0x59 fp=0xc0000abfc8 sp=0xc0000abfa8 pc=0x563cf461fe19 runtime.gcenable.gowrap2() runtime/mgc.go:205 +0x25 fp=0xc0000abfe0 sp=0xc0000abfc8 pc=0x563cf46164a5 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0000abfe8 sp=0xc0000abfe0 pc=0x563cf46745a1 created by runtime.gcenable in goroutine 1 runtime/mgc.go:205 +0xa5 goroutine 18 gp=0xc000104700 m=nil [finalizer wait]: runtime.gopark(0xc0000aa648?, 0x563cf460ca05?, 0xb0?, 0x1?, 0xc0000061c0?) runtime/proc.go:424 +0xce fp=0xc0000aa620 sp=0xc0000aa600 pc=0x563cf466c1ce runtime.runfinq() runtime/mfinal.go:193 +0x107 fp=0xc0000aa7e0 sp=0xc0000aa620 pc=0x563cf4615587 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0000aa7e8 sp=0xc0000aa7e0 pc=0x563cf46745a1 created by runtime.createfing in goroutine 1 runtime/mfinal.go:163 +0x3d goroutine 19 gp=0xc00027e000 m=nil [chan receive]: runtime.gopark(0xc0000a6760?, 0x563cf4749245?, 0x60?, 0xc9?, 0x563cf58e0280?) runtime/proc.go:424 +0xce fp=0xc0000a6718 sp=0xc0000a66f8 pc=0x563cf466c1ce runtime.chanrecv(0xc000112310, 0x0, 0x1) runtime/chan.go:639 +0x41c fp=0xc0000a6790 sp=0xc0000a6718 pc=0x563cf4605bfc runtime.chanrecv1(0x0?, 0x0?) runtime/chan.go:489 +0x12 fp=0xc0000a67b8 sp=0xc0000a6790 pc=0x563cf46057b2 runtime.unique_runtime_registerUniqueMapCleanup.func1(...) runtime/mgc.go:1781 runtime.unique_runtime_registerUniqueMapCleanup.gowrap1() runtime/mgc.go:1784 +0x2f fp=0xc0000a67e0 sp=0xc0000a67b8 pc=0x563cf461956f runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0000a67e8 sp=0xc0000a67e0 pc=0x563cf46745a1 created by unique.runtime_registerUniqueMapCleanup in goroutine 1 runtime/mgc.go:1779 +0x96 goroutine 20 gp=0xc00027e380 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xce fp=0xc0000a6f38 sp=0xc0000a6f18 pc=0x563cf466c1ce runtime.gcBgMarkWorker(0xc000113730) runtime/mgc.go:1412 +0xe9 fp=0xc0000a6fc8 sp=0xc0000a6f38 pc=0x563cf4618869 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x25 fp=0xc0000a6fe0 sp=0xc0000a6fc8 pc=0x563cf4618745 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0000a6fe8 sp=0xc0000a6fe0 pc=0x563cf46745a1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1328 +0x105 goroutine 21 gp=0xc00027e540 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xce fp=0xc0000a7738 sp=0xc0000a7718 pc=0x563cf466c1ce runtime.gcBgMarkWorker(0xc000113730) runtime/mgc.go:1412 +0xe9 fp=0xc0000a77c8 sp=0xc0000a7738 pc=0x563cf4618869 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x25 fp=0xc0000a77e0 sp=0xc0000a77c8 pc=0x563cf4618745 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0000a77e8 sp=0xc0000a77e0 pc=0x563cf46745a1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1328 +0x105 goroutine 34 gp=0xc000484000 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xce fp=0xc00048a738 sp=0xc00048a718 pc=0x563cf466c1ce runtime.gcBgMarkWorker(0xc000113730) runtime/mgc.go:1412 +0xe9 fp=0xc00048a7c8 sp=0xc00048a738 pc=0x563cf4618869 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x25 fp=0xc00048a7e0 sp=0xc00048a7c8 pc=0x563cf4618745 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc00048a7e8 sp=0xc00048a7e0 pc=0x563cf46745a1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1328 +0x105 goroutine 35 gp=0xc0004841c0 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xce fp=0xc00048af38 sp=0xc00048af18 pc=0x563cf466c1ce runtime.gcBgMarkWorker(0xc000113730) runtime/mgc.go:1412 +0xe9 fp=0xc00048afc8 sp=0xc00048af38 pc=0x563cf4618869 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x25 fp=0xc00048afe0 sp=0xc00048afc8 pc=0x563cf4618745 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc00048afe8 sp=0xc00048afe0 pc=0x563cf46745a1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1328 +0x105 goroutine 36 gp=0xc000484380 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xce fp=0xc00048b738 sp=0xc00048b718 pc=0x563cf466c1ce runtime.gcBgMarkWorker(0xc000113730) runtime/mgc.go:1412 +0xe9 fp=0xc00048b7c8 sp=0xc00048b738 pc=0x563cf4618869 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x25 fp=0xc00048b7e0 sp=0xc00048b7c8 pc=0x563cf4618745 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc00048b7e8 sp=0xc00048b7e0 pc=0x563cf46745a1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1328 +0x105 goroutine 5 gp=0xc000007880 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xce fp=0xc0000ac738 sp=0xc0000ac718 pc=0x563cf466c1ce runtime.gcBgMarkWorker(0xc000113730) runtime/mgc.go:1412 +0xe9 fp=0xc0000ac7c8 sp=0xc0000ac738 pc=0x563cf4618869 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x25 fp=0xc0000ac7e0 sp=0xc0000ac7c8 pc=0x563cf4618745 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0000ac7e8 sp=0xc0000ac7e0 pc=0x563cf46745a1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1328 +0x105 goroutine 22 gp=0xc00027e700 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xce fp=0xc0000a7f38 sp=0xc0000a7f18 pc=0x563cf466c1ce runtime.gcBgMarkWorker(0xc000113730) runtime/mgc.go:1412 +0xe9 fp=0xc0000a7fc8 sp=0xc0000a7f38 pc=0x563cf4618869 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x25 fp=0xc0000a7fe0 sp=0xc0000a7fc8 pc=0x563cf4618745 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0000a7fe8 sp=0xc0000a7fe0 pc=0x563cf46745a1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1328 +0x105 goroutine 23 gp=0xc00027e8c0 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xce fp=0xc0000a8738 sp=0xc0000a8718 pc=0x563cf466c1ce runtime.gcBgMarkWorker(0xc000113730) runtime/mgc.go:1412 +0xe9 fp=0xc0000a87c8 sp=0xc0000a8738 pc=0x563cf4618869 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x25 fp=0xc0000a87e0 sp=0xc0000a87c8 pc=0x563cf4618745 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0000a87e8 sp=0xc0000a87e0 pc=0x563cf46745a1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1328 +0x105 goroutine 24 gp=0xc00027ea80 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xce fp=0xc0000a8f38 sp=0xc0000a8f18 pc=0x563cf466c1ce runtime.gcBgMarkWorker(0xc000113730) runtime/mgc.go:1412 +0xe9 fp=0xc0000a8fc8 sp=0xc0000a8f38 pc=0x563cf4618869 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x25 fp=0xc0000a8fe0 sp=0xc0000a8fc8 pc=0x563cf4618745 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0000a8fe8 sp=0xc0000a8fe0 pc=0x563cf46745a1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1328 +0x105 goroutine 25 gp=0xc00027ec40 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xce fp=0xc0000a9738 sp=0xc0000a9718 pc=0x563cf466c1ce runtime.gcBgMarkWorker(0xc000113730) runtime/mgc.go:1412 +0xe9 fp=0xc0000a97c8 sp=0xc0000a9738 pc=0x563cf4618869 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x25 fp=0xc0000a97e0 sp=0xc0000a97c8 pc=0x563cf4618745 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0000a97e8 sp=0xc0000a97e0 pc=0x563cf46745a1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1328 +0x105 goroutine 37 gp=0xc000484540 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xce fp=0xc00048bf38 sp=0xc00048bf18 pc=0x563cf466c1ce runtime.gcBgMarkWorker(0xc000113730) runtime/mgc.go:1412 +0xe9 fp=0xc00048bfc8 sp=0xc00048bf38 pc=0x563cf4618869 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x25 fp=0xc00048bfe0 sp=0xc00048bfc8 pc=0x563cf4618745 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc00048bfe8 sp=0xc00048bfe0 pc=0x563cf46745a1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1328 +0x105 goroutine 38 gp=0xc000484700 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xce fp=0xc00048c738 sp=0xc00048c718 pc=0x563cf466c1ce runtime.gcBgMarkWorker(0xc000113730) runtime/mgc.go:1412 +0xe9 fp=0xc00048c7c8 sp=0xc00048c738 pc=0x563cf4618869 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x25 fp=0xc00048c7e0 sp=0xc00048c7c8 pc=0x563cf4618745 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc00048c7e8 sp=0xc00048c7e0 pc=0x563cf46745a1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1328 +0x105 goroutine 39 gp=0xc0004848c0 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xce fp=0xc00048cf38 sp=0xc00048cf18 pc=0x563cf466c1ce runtime.gcBgMarkWorker(0xc000113730) runtime/mgc.go:1412 +0xe9 fp=0xc00048cfc8 sp=0xc00048cf38 pc=0x563cf4618869 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x25 fp=0xc00048cfe0 sp=0xc00048cfc8 pc=0x563cf4618745 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc00048cfe8 sp=0xc00048cfe0 pc=0x563cf46745a1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1328 +0x105 goroutine 40 gp=0xc000484a80 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xce fp=0xc00048d738 sp=0xc00048d718 pc=0x563cf466c1ce runtime.gcBgMarkWorker(0xc000113730) runtime/mgc.go:1412 +0xe9 fp=0xc00048d7c8 sp=0xc00048d738 pc=0x563cf4618869 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x25 fp=0xc00048d7e0 sp=0xc00048d7c8 pc=0x563cf4618745 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc00048d7e8 sp=0xc00048d7e0 pc=0x563cf46745a1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1328 +0x105 goroutine 6 gp=0xc000007a40 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xce fp=0xc0000acf38 sp=0xc0000acf18 pc=0x563cf466c1ce runtime.gcBgMarkWorker(0xc000113730) runtime/mgc.go:1412 +0xe9 fp=0xc0000acfc8 sp=0xc0000acf38 pc=0x563cf4618869 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x25 fp=0xc0000acfe0 sp=0xc0000acfc8 pc=0x563cf4618745 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0000acfe8 sp=0xc0000acfe0 pc=0x563cf46745a1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1328 +0x105 goroutine 26 gp=0xc00027ee00 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xce fp=0xc0000a9f38 sp=0xc0000a9f18 pc=0x563cf466c1ce runtime.gcBgMarkWorker(0xc000113730) runtime/mgc.go:1412 +0xe9 fp=0xc0000a9fc8 sp=0xc0000a9f38 pc=0x563cf4618869 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x25 fp=0xc0000a9fe0 sp=0xc0000a9fc8 pc=0x563cf4618745 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0000a9fe8 sp=0xc0000a9fe0 pc=0x563cf46745a1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1328 +0x105 goroutine 27 gp=0xc00027efc0 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xce fp=0xc000486738 sp=0xc000486718 pc=0x563cf466c1ce runtime.gcBgMarkWorker(0xc000113730) runtime/mgc.go:1412 +0xe9 fp=0xc0004867c8 sp=0xc000486738 pc=0x563cf4618869 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x25 fp=0xc0004867e0 sp=0xc0004867c8 pc=0x563cf4618745 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0004867e8 sp=0xc0004867e0 pc=0x563cf46745a1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1328 +0x105 goroutine 28 gp=0xc00027f180 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xce fp=0xc000486f38 sp=0xc000486f18 pc=0x563cf466c1ce runtime.gcBgMarkWorker(0xc000113730) runtime/mgc.go:1412 +0xe9 fp=0xc000486fc8 sp=0xc000486f38 pc=0x563cf4618869 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x25 fp=0xc000486fe0 sp=0xc000486fc8 pc=0x563cf4618745 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000486fe8 sp=0xc000486fe0 pc=0x563cf46745a1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1328 +0x105 goroutine 29 gp=0xc00027f340 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xce fp=0xc000487738 sp=0xc000487718 pc=0x563cf466c1ce runtime.gcBgMarkWorker(0xc000113730) runtime/mgc.go:1412 +0xe9 fp=0xc0004877c8 sp=0xc000487738 pc=0x563cf4618869 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x25 fp=0xc0004877e0 sp=0xc0004877c8 pc=0x563cf4618745 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0004877e8 sp=0xc0004877e0 pc=0x563cf46745a1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1328 +0x105 goroutine 30 gp=0xc00027f500 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xce fp=0xc000487f38 sp=0xc000487f18 pc=0x563cf466c1ce runtime.gcBgMarkWorker(0xc000113730) runtime/mgc.go:1412 +0xe9 fp=0xc000487fc8 sp=0xc000487f38 pc=0x563cf4618869 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x25 fp=0xc000487fe0 sp=0xc000487fc8 pc=0x563cf4618745 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000487fe8 sp=0xc000487fe0 pc=0x563cf46745a1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1328 +0x105 goroutine 31 gp=0xc00027f6c0 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xce fp=0xc000488738 sp=0xc000488718 pc=0x563cf466c1ce runtime.gcBgMarkWorker(0xc000113730) runtime/mgc.go:1412 +0xe9 fp=0xc0004887c8 sp=0xc000488738 pc=0x563cf4618869 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x25 fp=0xc0004887e0 sp=0xc0004887c8 pc=0x563cf4618745 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0004887e8 sp=0xc0004887e0 pc=0x563cf46745a1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1328 +0x105 goroutine 32 gp=0xc00027f880 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xce fp=0xc000488f38 sp=0xc000488f18 pc=0x563cf466c1ce runtime.gcBgMarkWorker(0xc000113730) runtime/mgc.go:1412 +0xe9 fp=0xc000488fc8 sp=0xc000488f38 pc=0x563cf4618869 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x25 fp=0xc000488fe0 sp=0xc000488fc8 pc=0x563cf4618745 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000488fe8 sp=0xc000488fe0 pc=0x563cf46745a1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1328 +0x105 goroutine 41 gp=0xc000484c40 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xce fp=0xc00048df38 sp=0xc00048df18 pc=0x563cf466c1ce runtime.gcBgMarkWorker(0xc000113730) runtime/mgc.go:1412 +0xe9 fp=0xc00048dfc8 sp=0xc00048df38 pc=0x563cf4618869 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x25 fp=0xc00048dfe0 sp=0xc00048dfc8 pc=0x563cf4618745 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc00048dfe8 sp=0xc00048dfe0 pc=0x563cf46745a1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1328 +0x105 goroutine 42 gp=0xc000484e00 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xce fp=0xc000492738 sp=0xc000492718 pc=0x563cf466c1ce runtime.gcBgMarkWorker(0xc000113730) runtime/mgc.go:1412 +0xe9 fp=0xc0004927c8 sp=0xc000492738 pc=0x563cf4618869 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x25 fp=0xc0004927e0 sp=0xc0004927c8 pc=0x563cf4618745 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0004927e8 sp=0xc0004927e0 pc=0x563cf46745a1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1328 +0x105 goroutine 43 gp=0xc000484fc0 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xce fp=0xc000492f38 sp=0xc000492f18 pc=0x563cf466c1ce runtime.gcBgMarkWorker(0xc000113730) runtime/mgc.go:1412 +0xe9 fp=0xc000492fc8 sp=0xc000492f38 pc=0x563cf4618869 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x25 fp=0xc000492fe0 sp=0xc000492fc8 pc=0x563cf4618745 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000492fe8 sp=0xc000492fe0 pc=0x563cf46745a1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1328 +0x105 goroutine 7 gp=0xc000007c00 m=nil [GC worker (idle)]: runtime.gopark(0x1867defd493?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xce fp=0xc0000ad738 sp=0xc0000ad718 pc=0x563cf466c1ce runtime.gcBgMarkWorker(0xc000113730) runtime/mgc.go:1412 +0xe9 fp=0xc0000ad7c8 sp=0xc0000ad738 pc=0x563cf4618869 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x25 fp=0xc0000ad7e0 sp=0xc0000ad7c8 pc=0x563cf4618745 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0000ad7e8 sp=0xc0000ad7e0 pc=0x563cf46745a1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1328 +0x105 goroutine 44 gp=0xc000485180 m=nil [GC worker (idle)]: runtime.gopark(0x563cf61706e0?, 0x1?, 0xc?, 0xd0?, 0x0?) runtime/proc.go:424 +0xce fp=0xc000493738 sp=0xc000493718 pc=0x563cf466c1ce runtime.gcBgMarkWorker(0xc000113730) runtime/mgc.go:1412 +0xe9 fp=0xc0004937c8 sp=0xc000493738 pc=0x563cf4618869 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x25 fp=0xc0004937e0 sp=0xc0004937c8 pc=0x563cf4618745 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0004937e8 sp=0xc0004937e0 pc=0x563cf46745a1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1328 +0x105 goroutine 33 gp=0xc00027fa40 m=nil [GC worker (idle)]: runtime.gopark(0x563cf61706e0?, 0x1?, 0x82?, 0x21?, 0x0?) runtime/proc.go:424 +0xce fp=0xc000489738 sp=0xc000489718 pc=0x563cf466c1ce runtime.gcBgMarkWorker(0xc000113730) runtime/mgc.go:1412 +0xe9 fp=0xc0004897c8 sp=0xc000489738 pc=0x563cf4618869 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x25 fp=0xc0004897e0 sp=0xc0004897c8 pc=0x563cf4618745 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0004897e8 sp=0xc0004897e0 pc=0x563cf46745a1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1328 +0x105 goroutine 8 gp=0xc000007dc0 m=nil [GC worker (idle)]: runtime.gopark(0x1867def25e4?, 0x1?, 0x58?, 0x5b?, 0x0?) runtime/proc.go:424 +0xce fp=0xc0000adf38 sp=0xc0000adf18 pc=0x563cf466c1ce runtime.gcBgMarkWorker(0xc000113730) runtime/mgc.go:1412 +0xe9 fp=0xc0000adfc8 sp=0xc0000adf38 pc=0x563cf4618869 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x25 fp=0xc0000adfe0 sp=0xc0000adfc8 pc=0x563cf4618745 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0000adfe8 sp=0xc0000adfe0 pc=0x563cf46745a1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1328 +0x105 goroutine 9 gp=0xc0000e8000 m=nil [GC worker (idle)]: runtime.gopark(0x563cf61706e0?, 0x1?, 0xb9?, 0x31?, 0x0?) runtime/proc.go:424 +0xce fp=0xc00048e738 sp=0xc00048e718 pc=0x563cf466c1ce runtime.gcBgMarkWorker(0xc000113730) runtime/mgc.go:1412 +0xe9 fp=0xc00048e7c8 sp=0xc00048e738 pc=0x563cf4618869 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x25 fp=0xc00048e7e0 sp=0xc00048e7c8 pc=0x563cf4618745 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc00048e7e8 sp=0xc00048e7e0 pc=0x563cf46745a1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1328 +0x105 goroutine 10 gp=0xc0000e81c0 m=nil [GC worker (idle)]: runtime.gopark(0x563cf61706e0?, 0x1?, 0xfa?, 0x39?, 0x0?) runtime/proc.go:424 +0xce fp=0xc00048ef38 sp=0xc00048ef18 pc=0x563cf466c1ce runtime.gcBgMarkWorker(0xc000113730) runtime/mgc.go:1412 +0xe9 fp=0xc00048efc8 sp=0xc00048ef38 pc=0x563cf4618869 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x25 fp=0xc00048efe0 sp=0xc00048efc8 pc=0x563cf4618745 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc00048efe8 sp=0xc00048efe0 pc=0x563cf46745a1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1328 +0x105 goroutine 11 gp=0xc0000e8380 m=nil [GC worker (idle)]: runtime.gopark(0x563cf61706e0?, 0x1?, 0xaf?, 0xe2?, 0x0?) runtime/proc.go:424 +0xce fp=0xc00048f738 sp=0xc00048f718 pc=0x563cf466c1ce runtime.gcBgMarkWorker(0xc000113730) runtime/mgc.go:1412 +0xe9 fp=0xc00048f7c8 sp=0xc00048f738 pc=0x563cf4618869 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x25 fp=0xc00048f7e0 sp=0xc00048f7c8 pc=0x563cf4618745 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc00048f7e8 sp=0xc00048f7e0 pc=0x563cf46745a1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1328 +0x105 goroutine 50 gp=0xc000604380 m=nil [select]: runtime.gopark(0xc0003cba68?, 0x2?, 0x8e?, 0x55?, 0xc0003cb834?) runtime/proc.go:424 +0xce fp=0xc0003cb6a0 sp=0xc0003cb680 pc=0x563cf466c1ce runtime.selectgo(0xc0003cba68, 0xc0003cb830, 0xa?, 0x0, 0x1?, 0x1) runtime/select.go:335 +0x7a5 fp=0xc0003cb7c8 sp=0xc0003cb6a0 pc=0x563cf46494c5 github.com/ollama/ollama/runner/llamarunner.(*Server).completion(0xc0000d8000, {0x563cf58cb708, 0xc00022c620}, 0xc0005eca00) github.com/ollama/ollama/runner/llamarunner/runner.go:688 +0xa86 fp=0xc0003cbac0 sp=0xc0003cb7c8 pc=0x563cf4a3afa6 github.com/ollama/ollama/runner/llamarunner.(*Server).completion-fm({0x563cf58cb708?, 0xc00022c620?}, 0x563cf49a26c7?) <autogenerated>:1 +0x36 fp=0xc0003cbaf0 sp=0xc0003cbac0 pc=0x563cf4a3e076 net/http.HandlerFunc.ServeHTTP(0xc0000ee000?, {0x563cf58cb708?, 0xc00022c620?}, 0x0?) net/http/server.go:2220 +0x29 fp=0xc0003cbb18 sp=0xc0003cbaf0 pc=0x563cf4994ee9 net/http.(*ServeMux).ServeHTTP(0x563cf460ca05?, {0x563cf58cb708, 0xc00022c620}, 0xc0005eca00) net/http/server.go:2747 +0x1ca fp=0xc0003cbb68 sp=0xc0003cbb18 pc=0x563cf4996dea net/http.serverHandler.ServeHTTP({0x563cf58c80d0?}, {0x563cf58cb708?, 0xc00022c620?}, 0x6?) net/http/server.go:3210 +0x8e fp=0xc0003cbb98 sp=0xc0003cbb68 pc=0x563cf49b434e net/http.(*conn).serve(0xc000460000, {0x563cf58cd8e8, 0xc00001c300}) net/http/server.go:2092 +0x5d0 fp=0xc0003cbfb8 sp=0xc0003cbb98 pc=0x563cf4993890 net/http.(*Server).Serve.gowrap3() net/http/server.go:3360 +0x28 fp=0xc0003cbfe0 sp=0xc0003cbfb8 pc=0x563cf4998ce8 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0003cbfe8 sp=0xc0003cbfe0 pc=0x563cf46745a1 created by net/http.(*Server).Serve in goroutine 1 net/http/server.go:3360 +0x485 goroutine 85 gp=0xc000604c40 m=nil [IO wait]: runtime.gopark(0x563cf4610ee5?, 0x0?, 0x0?, 0x0?, 0xb?) runtime/proc.go:424 +0xce fp=0xc0002485a8 sp=0xc000248588 pc=0x563cf466c1ce runtime.netpollblock(0x563cf468f6b8?, 0xf4602fe6?, 0x3c?) runtime/netpoll.go:575 +0xf7 fp=0xc0002485e0 sp=0xc0002485a8 pc=0x563cf462fe37 internal/poll.runtime_pollWait(0x7f801d782cd8, 0x72) runtime/netpoll.go:351 +0x85 fp=0xc000248600 sp=0xc0002485e0 pc=0x563cf466b4c5 internal/poll.(*pollDesc).wait(0xc00045e000?, 0xc00045a101?, 0x0) internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc000248628 sp=0xc000248600 pc=0x563cf46f3707 internal/poll.(*pollDesc).waitRead(...) internal/poll/fd_poll_runtime.go:89 internal/poll.(*FD).Read(0xc00045e000, {0xc00045a101, 0x1, 0x1}) internal/poll/fd_unix.go:165 +0x27a fp=0xc0002486c0 sp=0xc000248628 pc=0x563cf46f49fa net.(*netFD).Read(0xc00045e000, {0xc00045a101?, 0xc000248748?, 0x563cf466de50?}) net/fd_posix.go:55 +0x25 fp=0xc000248708 sp=0xc0002486c0 pc=0x563cf475fc05 net.(*conn).Read(0xc00045c008, {0xc00045a101?, 0x0?, 0x563cf616e480?}) net/net.go:189 +0x45 fp=0xc000248750 sp=0xc000248708 pc=0x563cf476e205 net.(*TCPConn).Read(0x563cf601ff60?, {0xc00045a101?, 0x0?, 0x0?}) <autogenerated>:1 +0x25 fp=0xc000248780 sp=0xc000248750 pc=0x563cf4781405 net/http.(*connReader).backgroundRead(0xc00045a0f0) net/http/server.go:690 +0x37 fp=0xc0002487c8 sp=0xc000248780 pc=0x563cf498e217 net/http.(*connReader).startBackgroundRead.gowrap2() net/http/server.go:686 +0x25 fp=0xc0002487e0 sp=0xc0002487c8 pc=0x563cf498e145 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0002487e8 sp=0xc0002487e0 pc=0x563cf46745a1 created by net/http.(*connReader).startBackgroundRead in goroutine 50 net/http/server.go:686 +0xb6 rax 0x3c00 rbx 0x7f801dfb8310 rcx 0x7f80083ade70 rdx 0x7f80080008e0 rdi 0x11 rsi 0x7f80083ade20 rbp 0x0 rsp 0x7f801dfb7a30 r8 0x0 r9 0x7f80083af500 r10 0x0 r11 0x9c9afa8d5a4b8f9e r12 0x0 r13 0x563d110ae400 r14 0x7f801dfb86e8 r15 0x20 rip 0x7f7fdc968f27 rflags 0x10202 cs 0x33 fs 0x0 gs 0x0 [GIN] 2025/03/04 - 15:52:01 | 200 | 251.491877ms | 127.0.0.1 | POST "/api/chat" ``` ### OS Linux ### GPU Intel ### CPU AMD ### Ollama version 0.5.12
GiteaMirror added the bug label 2026-05-09 19:17:29 -05:00
Author
Owner

@rick-github commented on GitHub (Mar 4, 2025):

ollama tried to execute an instruction that is apparently not supported on your CPU;

   0:	c4 e2 79 13 c0       	vcvtph2ps %xmm0,%xmm0
   5:	c5 f0 57 c9          	vxorps %xmm1,%xmm1,%xmm1
   9:	c5 f8 2e c1          	vucomiss %xmm1,%xmm0
   d:	75 06                	jne    0x15
   f:	0f                   	.byte 0xf

What CPU do you have?

<!-- gh-comment-id:2698321742 --> @rick-github commented on GitHub (Mar 4, 2025): ollama tried to execute an instruction that is apparently not supported on your CPU; ``` 0: c4 e2 79 13 c0 vcvtph2ps %xmm0,%xmm0 5: c5 f0 57 c9 vxorps %xmm1,%xmm1,%xmm1 9: c5 f8 2e c1 vucomiss %xmm1,%xmm0 d: 75 06 jne 0x15 f: 0f .byte 0xf ``` What CPU do you have?
Author
Owner

@furryaxw commented on GitHub (Mar 4, 2025):

ollama tried to execute an instruction that is apparently not supported on your CPU;

   0:	c4 e2 79 13 c0       	vcvtph2ps %xmm0,%xmm0
   5:	c5 f0 57 c9          	vxorps %xmm1,%xmm1,%xmm1
   9:	c5 f8 2e c1          	vucomiss %xmm1,%xmm0
   d:	75 06                	jne    0x15
   f:	0f                   	.byte 0xf

What CPU do you have?

E5-2689 (x79)

<!-- gh-comment-id:2698365609 --> @furryaxw commented on GitHub (Mar 4, 2025): > ollama tried to execute an instruction that is apparently not supported on your CPU; > > ``` > 0: c4 e2 79 13 c0 vcvtph2ps %xmm0,%xmm0 > 5: c5 f0 57 c9 vxorps %xmm1,%xmm1,%xmm1 > 9: c5 f8 2e c1 vucomiss %xmm1,%xmm0 > d: 75 06 jne 0x15 > f: 0f .byte 0xf > ``` > > What CPU do you have? E5-2689 (x79)
Author
Owner

@rick-github commented on GitHub (Mar 4, 2025):

Likely an issue with the ROCm library: https://github.com/ROCm/rocBLAS/issues/1422#issuecomment-2089026056

PR https://github.com/ollama/ollama/pull/9304 upgrades to 6.3 which should resolve this. Try the pre-release and see if that works.

<!-- gh-comment-id:2698478036 --> @rick-github commented on GitHub (Mar 4, 2025): Likely an issue with the ROCm library: https://github.com/ROCm/rocBLAS/issues/1422#issuecomment-2089026056 PR https://github.com/ollama/ollama/pull/9304 upgrades to 6.3 which should resolve this. Try the [pre-release](https://github.com/ollama/ollama/releases/tag/v0.5.13) and see if that works.
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#83874