github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-08 00:51:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #8292] qwn qvq-72b-preview crash #5307

New Issue
Closed
opened 2026-04-12 16:29:51 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-12 16:29:51 -05:00
Owner
Copy Link

Originally created by @ghmole on GitHub (Jan 3, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/8292

What is the issue?

time=2025-01-03T08:27:01.902Z level=WARN source=runner.go:129 msg="truncating input prompt" limit=2048 prompt=2101 keep=4 new=2048
llama_model_loader: loaded meta data with 40 key-value pairs and 963 tensors from /data/models/ollama/models/blobs/sha256-49ecab6afc82486151830989cb79d3bf58b88197c714197968c7fd2f4523afe3 (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 = qwen2vl
llama_model_loader: - kv 1: general.type str = model
llama_model_loader: - kv 2: general.name str = QVQ 72B Preview
llama_model_loader: - kv 3: general.finetune str = Preview
llama_model_loader: - kv 4: general.basename str = QVQ
llama_model_loader: - kv 5: general.size_label str = 72B
llama_model_loader: - kv 6: general.license str = other
llama_model_loader: - kv 7: general.license.name str = qwen
llama_model_loader: - kv 8: general.license.link str = https://huggingface.co/Qwen/QVQ-72B-P...
llama_model_loader: - kv 9: general.base_model.count u32 = 1
llama_model_loader: - kv 10: general.base_model.0.name str = Qwen2 VL 72B
llama_model_loader: - kv 11: general.base_model.0.organization str = Qwen
llama_model_loader: - kv 12: general.base_model.0.repo_url str = https://huggingface.co/Qwen/Qwen2-VL-72B
llama_model_loader: - kv 13: general.tags arr[str,2] = ["chat", "image-text-to-text"]
llama_model_loader: - kv 14: general.languages arr[str,1] = ["en"]
llama_model_loader: - kv 15: qwen2vl.block_count u32 = 80
llama_model_loader: - kv 16: qwen2vl.context_length u32 = 128000
llama_model_loader: - kv 17: qwen2vl.embedding_length u32 = 8192
llama_model_loader: - kv 18: qwen2vl.feed_forward_length u32 = 29568
llama_model_loader: - kv 19: qwen2vl.attention.head_count u32 = 64
llama_model_loader: - kv 20: qwen2vl.attention.head_count_kv u32 = 8
llama_model_loader: - kv 21: qwen2vl.rope.freq_base f32 = 1000000.000000
llama_model_loader: - kv 22: qwen2vl.attention.layer_norm_rms_epsilon f32 = 0.000001
llama_model_loader: - kv 23: general.file_type u32 = 15
llama_model_loader: - kv 24: qwen2vl.rope.dimension_sections arr[i32,4] = [16, 24, 24, 0]
llama_model_loader: - kv 25: tokenizer.ggml.model str = gpt2
llama_model_loader: - kv 26: tokenizer.ggml.pre str = qwen2
llama_model_loader: - kv 27: tokenizer.ggml.tokens arr[str,152064] = ["!", """, "#", "$", "%", "&", "'", ...
llama_model_loader: - kv 28: tokenizer.ggml.token_type arr[i32,152064] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv 29: tokenizer.ggml.merges arr[str,151387] = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
llama_model_loader: - kv 30: tokenizer.ggml.eos_token_id u32 = 151645
llama_model_loader: - kv 31: tokenizer.ggml.padding_token_id u32 = 151643
llama_model_loader: - kv 32: tokenizer.ggml.bos_token_id u32 = 151643
llama_model_loader: - kv 33: tokenizer.ggml.add_bos_token bool = false
llama_model_loader: - kv 34: tokenizer.chat_template str = {% set image_count = namespace(value=...
llama_model_loader: - kv 35: general.quantization_version u32 = 2
llama_model_loader: - kv 36: quantize.imatrix.file str = /models_out/QVQ-72B-Preview-GGUF/QVQ-...
llama_model_loader: - kv 37: quantize.imatrix.dataset str = /training_dir/calibration_datav3.txt
llama_model_loader: - kv 38: quantize.imatrix.entries_count i32 = 560
llama_model_loader: - kv 39: quantize.imatrix.chunks_count i32 = 128
llama_model_loader: - type f32: 401 tensors
llama_model_loader: - type q5_0: 40 tensors
llama_model_loader: - type q8_0: 42 tensors
llama_model_loader: - type q4_K: 400 tensors
llama_model_loader: - type q5_K: 40 tensors
llama_model_loader: - type q6_K: 40 tensors
llm_load_vocab: special tokens cache size = 22
llm_load_vocab: token to piece cache size = 0.9310 MB
llm_load_print_meta: format = GGUF V3 (latest)
llm_load_print_meta: arch = qwen2vl
llm_load_print_meta: vocab type = BPE
llm_load_print_meta: n_vocab = 152064
llm_load_print_meta: n_merges = 151387
llm_load_print_meta: vocab_only = 1
llm_load_print_meta: model type = ?B
llm_load_print_meta: model ftype = all F32
llm_load_print_meta: model params = 72.71 B
llm_load_print_meta: model size = 45.01 GiB (5.32 BPW)
llm_load_print_meta: general.name = QVQ 72B Preview
llm_load_print_meta: BOS token = 151643 '<|endoftext|>'
llm_load_print_meta: EOS token = 151645 '<|im_end|>'
llm_load_print_meta: EOT token = 151645 '<|im_end|>'
llm_load_print_meta: PAD token = 151643 '<|endoftext|>'
llm_load_print_meta: LF token = 148848 'ÄĬ'
llm_load_print_meta: FIM PRE token = 151659 '<|fim_prefix|>'
llm_load_print_meta: FIM SUF token = 151661 '<|fim_suffix|>'
llm_load_print_meta: FIM MID token = 151660 '<|fim_middle|>'
llm_load_print_meta: FIM PAD token = 151662 '<|fim_pad|>'
llm_load_print_meta: FIM REP token = 151663 '<|repo_name|>'
llm_load_print_meta: FIM SEP token = 151664 '<|file_sep|>'
llm_load_print_meta: EOG token = 151643 '<|endoftext|>'
llm_load_print_meta: EOG token = 151645 '<|im_end|>'
llm_load_print_meta: EOG token = 151662 '<|fim_pad|>'
llm_load_print_meta: EOG token = 151663 '<|repo_name|>'
llm_load_print_meta: EOG token = 151664 '<|file_sep|>'
llm_load_print_meta: max token length = 256
llama_model_load: vocab only - skipping tensors
[GIN] 2025/01/03 - 08:27:29 | 200 | 27.344406312s | 192.168.100.232 | POST "/api/chat"
[GIN] 2025/01/03 - 08:27:44 | 200 | 30.190356335s | 192.168.100.232 | POST "/api/chat"
time=2025-01-03T08:27:47.970Z level=WARN source=runner.go:129 msg="truncating input prompt" limit=2048 prompt=2158 keep=4 new=2048
llama/ggml-cuda/rope.cu:449: GGML_ASSERT(sections.v[0] > 0 || sections.v[1] > 0 || sections.v[2] > 0) failed
Could not attach to process. If your uid matches the uid of the target
process, check the setting of /proc/sys/kernel/yama/ptrace_scope, or try
again as the root user. For more details, see /etc/sysctl.d/10-ptrace.conf
ptrace: Inappropriate ioctl for device.
No stack.
The program is not being run.
SIGABRT: abort
PC=0xffff84acf200 m=0 sigcode=18446744073709551610
signal arrived during cgo execution

goroutine 37 gp=0x40001868c0 m=0 mp=0xaaaadf40dec0 [syscall]:
runtime.cgocall(0xaaaadeec27d0, 0x4000330b68)
runtime/cgocall.go:167 +0x44 fp=0x4000330b30 sp=0x4000330af0 pc=0xaaaadecbb834
github.com/ollama/ollama/llama._Cfunc_llama_decode(0xffff149d0a20, {0x7, 0xffff14981d30, 0x0, 0x0, 0xffff149e0490, 0xffff149ebfa0, 0xffff1497c8a0, 0xffff14b109a0})
_cgo_gotypes.go:564 +0x34 fp=0x4000330b60 sp=0x4000330b30 pc=0xaaaaded5e464
github.com/ollama/ollama/llama.(*Context).Decode.func1(0x4000330c98?, 0xaaaadeebd650?)
github.com/ollama/ollama/llama/llama.go:207 +0xc8 fp=0x4000330c50 sp=0x4000330b60 pc=0xaaaaded60218
github.com/ollama/ollama/llama.(*Context).Decode(0x40002fe600?, 0x40001aa100?)
github.com/ollama/ollama/llama/llama.go:207 +0x1c fp=0x4000330ca0 sp=0x4000330c50 pc=0xaaaaded600ac
github.com/ollama/ollama/llama/runner.(*Server).processBatch(0x40001be1b0, 0x40001a84e0, 0x4000330f10)
github.com/ollama/ollama/llama/runner/runner.go:434 +0x200 fp=0x4000330ec0 sp=0x4000330ca0 pc=0xaaaadeebd660
github.com/ollama/ollama/llama/runner.(*Server).run(0x40001be1b0, {0xaaaadf230b20, 0x4000202050})
github.com/ollama/ollama/llama/runner/runner.go:342 +0x17c fp=0x4000330fa0 sp=0x4000330ec0 pc=0xaaaadeebd15c
github.com/ollama/ollama/llama/runner.Execute.gowrap2()
github.com/ollama/ollama/llama/runner/runner.go:984 +0x30 fp=0x4000330fd0 sp=0x4000330fa0 pc=0xaaaadeec14f0
runtime.goexit({})
runtime/asm_arm64.s:1223 +0x4 fp=0x4000330fd0 sp=0x4000330fd0 pc=0xaaaadecc94a4
created by github.com/ollama/ollama/llama/runner.Execute in goroutine 1
github.com/ollama/ollama/llama/runner/runner.go:984 +0xba8

goroutine 1 gp=0x40000021c0 m=nil [IO wait]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
runtime/proc.go:424 +0xc8 fp=0x40001f3750 sp=0x40001f3730 pc=0xaaaadecc17d8
runtime.netpollblock(0x7000000000?, 0x6?, 0x0?)
runtime/netpoll.go:575 +0x158 fp=0x40001f3790 sp=0x40001f3750 pc=0xaaaadec855a8
internal/poll.runtime_pollWait(0xffff2a0ebde0, 0x72)
runtime/netpoll.go:351 +0xa0 fp=0x40001f37c0 sp=0x40001f3790 pc=0xaaaadecc0a80
internal/poll.(*pollDesc).wait(0x40001fa100?, 0x0?, 0x0)
internal/poll/fd_poll_runtime.go:84 +0x28 fp=0x40001f37f0 sp=0x40001f37c0 pc=0xaaaaded154b8
internal/poll.(*pollDesc).waitRead(...)
internal/poll/fd_poll_runtime.go:89
internal/poll.(*FD).Accept(0x40001fa100)
internal/poll/fd_unix.go:620 +0x24c fp=0x40001f38a0 sp=0x40001f37f0 pc=0xaaaaded1687c
net.(*netFD).accept(0x40001fa100)
net/fd_unix.go:172 +0x28 fp=0x40001f3960 sp=0x40001f38a0 pc=0xaaaaded86448
net.(*TCPListener).accept(0x40001a66c0)
net/tcpsock_posix.go:159 +0x28 fp=0x40001f39b0 sp=0x40001f3960 pc=0xaaaaded96598
net.(*TCPListener).Accept(0x40001a66c0)
net/tcpsock.go:372 +0x2c fp=0x40001f39f0 sp=0x40001f39b0 pc=0xaaaaded958ec
net/http.(*onceCloseListener).Accept(0x40001be2d0?)
:1 +0x30 fp=0x40001f3a10 sp=0x40001f39f0 pc=0xaaaadee9c770
net/http.(*Server).Serve(0x40001f84b0, {0xaaaadf230538, 0x40001a66c0})
net/http/server.go:3330 +0x294 fp=0x40001f3b40 sp=0x40001f3a10 pc=0xaaaadee8ec84
github.com/ollama/ollama/llama/runner.Execute({0x40001aa010?, 0x0?, 0x4000052738?})
github.com/ollama/ollama/llama/runner/runner.go:1005 +0xebc fp=0x40001f3ee0 sp=0x40001f3b40 pc=0xaaaadeec122c
main.main()
github.com/ollama/ollama/cmd/runner/main.go:11 +0x54 fp=0x40001f3f40 sp=0x40001f3ee0 pc=0xaaaadeec2104
runtime.main()
runtime/proc.go:272 +0x288 fp=0x40001f3fd0 sp=0x40001f3f40 pc=0xaaaadec8c9c8
runtime.goexit({})
runtime/asm_arm64.s:1223 +0x4 fp=0x40001f3fd0 sp=0x40001f3fd0 pc=0xaaaadecc94a4

goroutine 2 gp=0x4000002c40 m=nil [force gc (idle), 2 minutes]:
runtime.gopark(0x3b630cd8c2e?, 0x0?, 0x0?, 0x0?, 0x0?)
runtime/proc.go:424 +0xc8 fp=0x4000052f90 sp=0x4000052f70 pc=0xaaaadecc17d8
runtime.goparkunlock(...)
runtime/proc.go:430
runtime.forcegchelper()
runtime/proc.go:337 +0xb8 fp=0x4000052fd0 sp=0x4000052f90 pc=0xaaaadec8cd28
runtime.goexit({})
runtime/asm_arm64.s:1223 +0x4 fp=0x4000052fd0 sp=0x4000052fd0 pc=0xaaaadecc94a4
created by runtime.init.7 in goroutine 1
runtime/proc.go:325 +0x24

goroutine 18 gp=0x4000104380 m=nil [GC sweep wait]:
runtime.gopark(0x1?, 0x0?, 0x0?, 0x0?, 0x0?)
runtime/proc.go:424 +0xc8 fp=0x400004e760 sp=0x400004e740 pc=0xaaaadecc17d8
runtime.goparkunlock(...)
runtime/proc.go:430
runtime.bgsweep(0x4000112000)
runtime/mgcsweep.go:317 +0x108 fp=0x400004e7b0 sp=0x400004e760 pc=0xaaaadec77368
runtime.gcenable.gowrap1()
runtime/mgc.go:204 +0x28 fp=0x400004e7d0 sp=0x400004e7b0 pc=0xaaaadec6b4f8
runtime.goexit({})
runtime/asm_arm64.s:1223 +0x4 fp=0x400004e7d0 sp=0x400004e7d0 pc=0xaaaadecc94a4
created by runtime.gcenable in goroutine 1
runtime/mgc.go:204 +0x6c

goroutine 19 gp=0x4000104540 m=nil [GC scavenge wait]:
runtime.gopark(0x3ba00e6b?, 0x3b9aca00?, 0x0?, 0x0?, 0x0?)
runtime/proc.go:424 +0xc8 fp=0x400004ef60 sp=0x400004ef40 pc=0xaaaadecc17d8
runtime.goparkunlock(...)
runtime/proc.go:430
runtime.(*scavengerState).park(0xaaaadf40d3a0)
runtime/mgcscavenge.go:425 +0x5c fp=0x400004ef90 sp=0x400004ef60 pc=0xaaaadec74d2c
runtime.bgscavenge(0x4000112000)
runtime/mgcscavenge.go:658 +0xac fp=0x400004efb0 sp=0x400004ef90 pc=0xaaaadec752bc
runtime.gcenable.gowrap2()
runtime/mgc.go:205 +0x28 fp=0x400004efd0 sp=0x400004efb0 pc=0xaaaadec6b498
runtime.goexit({})
runtime/asm_arm64.s:1223 +0x4 fp=0x400004efd0 sp=0x400004efd0 pc=0xaaaadecc94a4
created by runtime.gcenable in goroutine 1
runtime/mgc.go:205 +0xac

goroutine 34 gp=0x4000186380 m=nil [finalizer wait]:
runtime.gopark(0x0?, 0xaaaadf22bb38?, 0x0?, 0x40?, 0x1000000010?)
runtime/proc.go:424 +0xc8 fp=0x4000052580 sp=0x4000052560 pc=0xaaaadecc17d8
runtime.runfinq()
runtime/mfinal.go:193 +0x108 fp=0x40000527d0 sp=0x4000052580 pc=0xaaaadec6a5f8
runtime.goexit({})
runtime/asm_arm64.s:1223 +0x4 fp=0x40000527d0 sp=0x40000527d0 pc=0xaaaadecc94a4
created by runtime.createfing in goroutine 1
runtime/mfinal.go:163 +0x80

goroutine 35 gp=0x4000186540 m=nil [chan receive]:
runtime.gopark(0x40001d4748?, 0xaaaaded694ac?, 0x70?, 0x42?, 0xaaaadf234920?)
runtime/proc.go:424 +0xc8 fp=0x40001d46f0 sp=0x40001d46d0 pc=0xaaaadecc17d8
runtime.chanrecv(0x40001800e0, 0x0, 0x1)
runtime/chan.go:639 +0x414 fp=0x40001d4770 sp=0x40001d46f0 pc=0xaaaadec5b534
runtime.chanrecv1(0x0?, 0x0?)
runtime/chan.go:489 +0x14 fp=0x40001d47a0 sp=0x40001d4770 pc=0xaaaadec5b114
runtime.unique_runtime_registerUniqueMapCleanup.func1(...)
runtime/mgc.go:1781
runtime.unique_runtime_registerUniqueMapCleanup.gowrap1()
runtime/mgc.go:1784 +0x3c fp=0x40001d47d0 sp=0x40001d47a0 pc=0xaaaadec6e3ac
runtime.goexit({})
runtime/asm_arm64.s:1223 +0x4 fp=0x40001d47d0 sp=0x40001d47d0 pc=0xaaaadecc94a4
created by unique.runtime_registerUniqueMapCleanup in goroutine 1
runtime/mgc.go:1779 +0xa0

goroutine 455 gp=0x4000186700 m=nil [GC worker (idle), 2 minutes]:
runtime.gopark(0x4000316d18?, 0x4000316d14?, 0x58?, 0xb7?, 0xaaaadee85e34?)
runtime/proc.go:424 +0xc8 fp=0x400030b710 sp=0x400030b6f0 pc=0xaaaadecc17d8
runtime.gcBgMarkWorker(0x40002957a0)
runtime/mgc.go:1412 +0xdc fp=0x400030b7b0 sp=0x400030b710 pc=0xaaaadec6d61c
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1328 +0x28 fp=0x400030b7d0 sp=0x400030b7b0 pc=0xaaaadec6d508
runtime.goexit({})
runtime/asm_arm64.s:1223 +0x4 fp=0x400030b7d0 sp=0x400030b7d0 pc=0xaaaadecc94a4
created by runtime.gcBgMarkStartWorkers in goroutine 37
runtime/mgc.go:1328 +0x140

goroutine 457 gp=0x400016a700 m=nil [GC worker (idle), 2 minutes]:
runtime.gopark(0x400008c0d8?, 0x400008c0d4?, 0x58?, 0x27?, 0xaaaadee85e34?)
runtime/proc.go:424 +0xc8 fp=0x4000172710 sp=0x40001726f0 pc=0xaaaadecc17d8
runtime.gcBgMarkWorker(0x40002957a0)
runtime/mgc.go:1412 +0xdc fp=0x40001727b0 sp=0x4000172710 pc=0xaaaadec6d61c
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1328 +0x28 fp=0x40001727d0 sp=0x40001727b0 pc=0xaaaadec6d508
runtime.goexit({})
runtime/asm_arm64.s:1223 +0x4 fp=0x40001727d0 sp=0x40001727d0 pc=0xaaaadecc94a4
created by runtime.gcBgMarkStartWorkers in goroutine 37
runtime/mgc.go:1328 +0x140

goroutine 458 gp=0x400016ac40 m=nil [GC worker (idle), 2 minutes]:
runtime.gopark(0x400008c0d8?, 0x400008c0d4?, 0x58?, 0x3f?, 0xaaaadee85e34?)
runtime/proc.go:424 +0xc8 fp=0x4000173f10 sp=0x4000173ef0 pc=0xaaaadecc17d8
runtime.gcBgMarkWorker(0x40002957a0)
runtime/mgc.go:1412 +0xdc fp=0x4000173fb0 sp=0x4000173f10 pc=0xaaaadec6d61c
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1328 +0x28 fp=0x4000173fd0 sp=0x4000173fb0 pc=0xaaaadec6d508
runtime.goexit({})
runtime/asm_arm64.s:1223 +0x4 fp=0x4000173fd0 sp=0x4000173fd0 pc=0xaaaadecc94a4
created by runtime.gcBgMarkStartWorkers in goroutine 37
runtime/mgc.go:1328 +0x140

goroutine 460 gp=0x400016b340 m=nil [GC worker (idle), 2 minutes]:
runtime.gopark(0x400008c0d8?, 0x400008c0d4?, 0x58?, 0xdf?, 0xaaaadee85e34?)
runtime/proc.go:424 +0xc8 fp=0x400016df10 sp=0x400016def0 pc=0xaaaadecc17d8
runtime.gcBgMarkWorker(0x40002957a0)
runtime/mgc.go:1412 +0xdc fp=0x400016dfb0 sp=0x400016df10 pc=0xaaaadec6d61c
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1328 +0x28 fp=0x400016dfd0 sp=0x400016dfb0 pc=0xaaaadec6d508
runtime.goexit({})
runtime/asm_arm64.s:1223 +0x4 fp=0x400016dfd0 sp=0x400016dfd0 pc=0xaaaadecc94a4
created by runtime.gcBgMarkStartWorkers in goroutine 37
runtime/mgc.go:1328 +0x140

goroutine 459 gp=0x400016b6c0 m=nil [GC worker (idle), 2 minutes]:
runtime.gopark(0x400008c0d8?, 0x400008c0d4?, 0x58?, 0xef?, 0xaaaadee85e34?)
runtime/proc.go:424 +0xc8 fp=0x400016ef10 sp=0x400016eef0 pc=0xaaaadecc17d8
runtime.gcBgMarkWorker(0x40002957a0)
runtime/mgc.go:1412 +0xdc fp=0x400016efb0 sp=0x400016ef10 pc=0xaaaadec6d61c
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1328 +0x28 fp=0x400016efd0 sp=0x400016efb0 pc=0xaaaadec6d508
runtime.goexit({})
runtime/asm_arm64.s:1223 +0x4 fp=0x400016efd0 sp=0x400016efd0 pc=0xaaaadecc94a4
created by runtime.gcBgMarkStartWorkers in goroutine 37
runtime/mgc.go:1328 +0x140

goroutine 461 gp=0x400016b880 m=nil [GC worker (idle), 2 minutes]:
runtime.gopark(0x400008c0d8?, 0x400008c0d4?, 0x58?, 0xf7?, 0xaaaadee85e34?)
runtime/proc.go:424 +0xc8 fp=0x400016f710 sp=0x400016f6f0 pc=0xaaaadecc17d8
runtime.gcBgMarkWorker(0x40002957a0)
runtime/mgc.go:1412 +0xdc fp=0x400016f7b0 sp=0x400016f710 pc=0xaaaadec6d61c
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1328 +0x28 fp=0x400016f7d0 sp=0x400016f7b0 pc=0xaaaadec6d508
runtime.goexit({})
runtime/asm_arm64.s:1223 +0x4 fp=0x400016f7d0 sp=0x400016f7d0 pc=0xaaaadecc94a4
created by runtime.gcBgMarkStartWorkers in goroutine 37
runtime/mgc.go:1328 +0x140

goroutine 456 gp=0x400016bc00 m=nil [GC worker (idle), 2 minutes]:
runtime.gopark(0x4000245b90?, 0xaaaadf1147a0?, 0x58?, 0xe7?, 0xaaaadee85e34?)
runtime/proc.go:424 +0xc8 fp=0x400030e710 sp=0x400030e6f0 pc=0xaaaadecc17d8
runtime.gcBgMarkWorker(0x40002957a0)
runtime/mgc.go:1412 +0xdc fp=0x400030e7b0 sp=0x400030e710 pc=0xaaaadec6d61c
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1328 +0x28 fp=0x400030e7d0 sp=0x400030e7b0 pc=0xaaaadec6d508
runtime.goexit({})
runtime/asm_arm64.s:1223 +0x4 fp=0x400030e7d0 sp=0x400030e7d0 pc=0xaaaadecc94a4
created by runtime.gcBgMarkStartWorkers in goroutine 37
runtime/mgc.go:1328 +0x140

goroutine 347 gp=0x40003221c0 m=nil [IO wait]:
runtime.gopark(0x40001d7628?, 0xaaaaded2b684?, 0x88?, 0x75?, 0xaaaaded2d6c0?)
runtime/proc.go:424 +0xc8 fp=0x40001d7550 sp=0x40001d7530 pc=0xaaaadecc17d8
runtime.netpollblock(0x0?, 0xffffffff?, 0xff?)
runtime/netpoll.go:575 +0x158 fp=0x40001d7590 sp=0x40001d7550 pc=0xaaaadec855a8
internal/poll.runtime_pollWait(0xffff2a0ebbb0, 0x72)
runtime/netpoll.go:351 +0xa0 fp=0x40001d75c0 sp=0x40001d7590 pc=0xaaaadecc0a80
internal/poll.(*pollDesc).wait(0x40002fe480?, 0x400035a491?, 0x0)
internal/poll/fd_poll_runtime.go:84 +0x28 fp=0x40001d75f0 sp=0x40001d75c0 pc=0xaaaaded154b8
internal/poll.(*pollDesc).waitRead(...)
internal/poll/fd_poll_runtime.go:89
internal/poll.(*FD).Read(0x40002fe480, {0x400035a491, 0x1, 0x1})
internal/poll/fd_unix.go:165 +0x1fc fp=0x40001d7690 sp=0x40001d75f0 pc=0xaaaaded15fcc
net.(*netFD).Read(0x40002fe480, {0x400035a491?, 0x40001d7738?, 0xaaaadee8609c?})
net/fd_posix.go:55 +0x28 fp=0x40001d76e0 sp=0x40001d7690 pc=0xaaaaded85628
net.(*conn).Read(0x400019c058, {0x400035a491?, 0x0?, 0x400035a728?})
net/net.go:189 +0x34 fp=0x40001d7730 sp=0x40001d76e0 pc=0xaaaaded8ea44
net.(*TCPConn).Read(0x400035a720?, {0x400035a491?, 0x0?, 0x0?})
:1 +0x2c fp=0x40001d7760 sp=0x40001d7730 pc=0xaaaaded9b67c
net/http.(*connReader).backgroundRead(0x400035a480)
net/http/server.go:690 +0x40 fp=0x40001d77b0 sp=0x40001d7760 pc=0xaaaadee85d30
net/http.(*connReader).startBackgroundRead.gowrap2()
net/http/server.go:686 +0x28 fp=0x40001d77d0 sp=0x40001d77b0 pc=0xaaaadee85c18
runtime.goexit({})
runtime/asm_arm64.s:1223 +0x4 fp=0x40001d77d0 sp=0x40001d77d0 pc=0xaaaadecc94a4
created by net/http.(*connReader).startBackgroundRead in goroutine 345
net/http/server.go:686 +0xc4

goroutine 462 gp=0x40002a0380 m=nil [GC worker (idle), 2 minutes]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
runtime/proc.go:424 +0xc8 fp=0x400030bf10 sp=0x400030bef0 pc=0xaaaadecc17d8
runtime.gcBgMarkWorker(0x40002957a0)
runtime/mgc.go:1412 +0xdc fp=0x400030bfb0 sp=0x400030bf10 pc=0xaaaadec6d61c
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1328 +0x28 fp=0x400030bfd0 sp=0x400030bfb0 pc=0xaaaadec6d508
runtime.goexit({})
runtime/asm_arm64.s:1223 +0x4 fp=0x400030bfd0 sp=0x400030bfd0 pc=0xaaaadecc94a4
created by runtime.gcBgMarkStartWorkers in goroutine 37
runtime/mgc.go:1328 +0x140

goroutine 463 gp=0x40002a0540 m=nil [GC worker (idle), 2 minutes]:
runtime.gopark(0x3b630d97a67?, 0x0?, 0x0?, 0x0?, 0x0?)
runtime/proc.go:424 +0xc8 fp=0x400030c710 sp=0x400030c6f0 pc=0xaaaadecc17d8
runtime.gcBgMarkWorker(0x40002957a0)
runtime/mgc.go:1412 +0xdc fp=0x400030c7b0 sp=0x400030c710 pc=0xaaaadec6d61c
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1328 +0x28 fp=0x400030c7d0 sp=0x400030c7b0 pc=0xaaaadec6d508
runtime.goexit({})
runtime/asm_arm64.s:1223 +0x4 fp=0x400030c7d0 sp=0x400030c7d0 pc=0xaaaadecc94a4
created by runtime.gcBgMarkStartWorkers in goroutine 37
runtime/mgc.go:1328 +0x140

goroutine 464 gp=0x40002a0700 m=nil [GC worker (idle)]:
runtime.gopark(0x3b630da0ac7?, 0x1?, 0x3c?, 0x28?, 0x0?)
runtime/proc.go:424 +0xc8 fp=0x400030cf10 sp=0x400030cef0 pc=0xaaaadecc17d8
runtime.gcBgMarkWorker(0x40002957a0)
runtime/mgc.go:1412 +0xdc fp=0x400030cfb0 sp=0x400030cf10 pc=0xaaaadec6d61c
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1328 +0x28 fp=0x400030cfd0 sp=0x400030cfb0 pc=0xaaaadec6d508
runtime.goexit({})
runtime/asm_arm64.s:1223 +0x4 fp=0x400030cfd0 sp=0x400030cfd0 pc=0xaaaadecc94a4
created by runtime.gcBgMarkStartWorkers in goroutine 37
runtime/mgc.go:1328 +0x140

goroutine 465 gp=0x40002a08c0 m=nil [GC worker (idle), 2 minutes]:
runtime.gopark(0x39a2c50720b?, 0x0?, 0x0?, 0x0?, 0x0?)
runtime/proc.go:424 +0xc8 fp=0x400030d710 sp=0x400030d6f0 pc=0xaaaadecc17d8
runtime.gcBgMarkWorker(0x40002957a0)
runtime/mgc.go:1412 +0xdc fp=0x400030d7b0 sp=0x400030d710 pc=0xaaaadec6d61c
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1328 +0x28 fp=0x400030d7d0 sp=0x400030d7b0 pc=0xaaaadec6d508
runtime.goexit({})
runtime/asm_arm64.s:1223 +0x4 fp=0x400030d7d0 sp=0x400030d7d0 pc=0xaaaadecc94a4
created by runtime.gcBgMarkStartWorkers in goroutine 37
runtime/mgc.go:1328 +0x140

goroutine 482 gp=0x40002a0a80 m=nil [GC worker (idle)]:
runtime.gopark(0x3b630d9a007?, 0x0?, 0x0?, 0x0?, 0x0?)
runtime/proc.go:424 +0xc8 fp=0x400030df10 sp=0x400030def0 pc=0xaaaadecc17d8
runtime.gcBgMarkWorker(0x40002957a0)
runtime/mgc.go:1412 +0xdc fp=0x400030dfb0 sp=0x400030df10 pc=0xaaaadec6d61c
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1328 +0x28 fp=0x400030dfd0 sp=0x400030dfb0 pc=0xaaaadec6d508
runtime.goexit({})
runtime/asm_arm64.s:1223 +0x4 fp=0x400030dfd0 sp=0x400030dfd0 pc=0xaaaadecc94a4
created by runtime.gcBgMarkStartWorkers in goroutine 37
runtime/mgc.go:1328 +0x140

goroutine 483 gp=0x40002a0c40 m=nil [select]:
runtime.gopark(0x40001f5a50?, 0x2?, 0xe8?, 0x56?, 0x40001f580c?)
runtime/proc.go:424 +0xc8 fp=0x40001f5660 sp=0x40001f5640 pc=0xaaaadecc17d8
runtime.selectgo(0x40001f5a50, 0x40001f5808, 0x400011c300?, 0x0, 0x1?, 0x1)
runtime/select.go:335 +0x67c fp=0x40001f5790 sp=0x40001f5660 pc=0xaaaadec9fc5c
github.com/ollama/ollama/llama/runner.(*Server).completion(0x40001be1b0, {0xaaaadf2306b8, 0x40001d81c0}, 0x40001ee140)
github.com/ollama/ollama/llama/runner/runner.go:696 +0x8e8 fp=0x40001f5aa0 sp=0x40001f5790 pc=0xaaaadeebef48
github.com/ollama/ollama/llama/runner.(*Server).completion-fm({0xaaaadf2306b8?, 0x40001d81c0?}, 0x40001f5b28?)
:1 +0x40 fp=0x40001f5ad0 sp=0x40001f5aa0 pc=0xaaaadeec1d00
net/http.HandlerFunc.ServeHTTP(0x40001d80e0?, {0xaaaadf2306b8?, 0x40001d81c0?}, 0x40001f5b10?)
net/http/server.go:2220 +0x38 fp=0x40001f5b00 sp=0x40001f5ad0 pc=0xaaaadee8beb8
net/http.(*ServeMux).ServeHTTP(0x10?, {0xaaaadf2306b8, 0x40001d81c0}, 0x40001ee140)
net/http/server.go:2747 +0x1b4 fp=0x40001f5b50 sp=0x40001f5b00 pc=0xaaaadee8dab4
net/http.serverHandler.ServeHTTP({0xaaaadf22f770?}, {0xaaaadf2306b8?, 0x40001d81c0?}, 0x6?)
net/http/server.go:3210 +0xbc fp=0x40001f5b80 sp=0x40001f5b50 pc=0xaaaadee949fc
net/http.(*conn).serve(0x4000376000, {0xaaaadf230ae8, 0x40001a4f60})
net/http/server.go:2092 +0x4fc fp=0x40001f5fa0 sp=0x40001f5b80 pc=0xaaaadee8ad3c
net/http.(*Server).Serve.gowrap3()
net/http/server.go:3360 +0x30 fp=0x40001f5fd0 sp=0x40001f5fa0 pc=0xaaaadee8f010
runtime.goexit({})
runtime/asm_arm64.s:1223 +0x4 fp=0x40001f5fd0 sp=0x40001f5fd0 pc=0xaaaadecc94a4
created by net/http.(*Server).Serve in goroutine 1
net/http/server.go:3360 +0x3dc

goroutine 345 gp=0x40002a0e00 m=nil [select]:
runtime.gopark(0x40000fda50?, 0x2?, 0x88?, 0xd7?, 0x40000fd80c?)
runtime/proc.go:424 +0xc8 fp=0x40000fd660 sp=0x40000fd640 pc=0xaaaadecc17d8
runtime.selectgo(0x40000fda50, 0x40000fd808, 0x717?, 0x0, 0x1?, 0x1)
runtime/select.go:335 +0x67c fp=0x40000fd790 sp=0x40000fd660 pc=0xaaaadec9fc5c
github.com/ollama/ollama/llama/runner.(*Server).completion(0x40001be1b0, {0xaaaadf2306b8, 0x40001d8380}, 0x40001ee500)
github.com/ollama/ollama/llama/runner/runner.go:696 +0x8e8 fp=0x40000fdaa0 sp=0x40000fd790 pc=0xaaaadeebef48
github.com/ollama/ollama/llama/runner.(*Server).completion-fm({0xaaaadf2306b8?, 0x40001d8380?}, 0x40000fdb28?)
:1 +0x40 fp=0x40000fdad0 sp=0x40000fdaa0 pc=0xaaaadeec1d00
net/http.HandlerFunc.ServeHTTP(0x40001d80e0?, {0xaaaadf2306b8?, 0x40001d8380?}, 0x40000fdb10?)
net/http/server.go:2220 +0x38 fp=0x40000fdb00 sp=0x40000fdad0 pc=0xaaaadee8beb8
net/http.(*ServeMux).ServeHTTP(0x10?, {0xaaaadf2306b8, 0x40001d8380}, 0x40001ee500)
net/http/server.go:2747 +0x1b4 fp=0x40000fdb50 sp=0x40000fdb00 pc=0xaaaadee8dab4
net/http.serverHandler.ServeHTTP({0xaaaadf22f770?}, {0xaaaadf2306b8?, 0x40001d8380?}, 0x6?)
net/http/server.go:3210 +0xbc fp=0x40000fdb80 sp=0x40000fdb50 pc=0xaaaadee949fc
net/http.(*conn).serve(0x40001be2d0, {0xaaaadf230ae8, 0x40001a4f60})
net/http/server.go:2092 +0x4fc fp=0x40000fdfa0 sp=0x40000fdb80 pc=0xaaaadee8ad3c
net/http.(*Server).Serve.gowrap3()
net/http/server.go:3360 +0x30 fp=0x40000fdfd0 sp=0x40000fdfa0 pc=0xaaaadee8f010
runtime.goexit({})
runtime/asm_arm64.s:1223 +0x4 fp=0x40000fdfd0 sp=0x40000fdfd0 pc=0xaaaadecc94a4
created by net/http.(*Server).Serve in goroutine 1
net/http/server.go:3360 +0x3dc

goroutine 344 gp=0x40002a0fc0 m=nil [IO wait]:
runtime.gopark(0x10?, 0x10?, 0xa8?, 0x5?, 0xaaaadec65fe4?)
runtime/proc.go:424 +0xc8 fp=0x4000310550 sp=0x4000310530 pc=0xaaaadecc17d8
runtime.netpollblock(0x0?, 0xffffffff?, 0xff?)
runtime/netpoll.go:575 +0x158 fp=0x4000310590 sp=0x4000310550 pc=0xaaaadec855a8
internal/poll.runtime_pollWait(0xffff2a0ebcc8, 0x72)
runtime/netpoll.go:351 +0xa0 fp=0x40003105c0 sp=0x4000310590 pc=0xaaaadecc0a80
internal/poll.(*pollDesc).wait(0x40002fe700?, 0x4000284131?, 0x0)
internal/poll/fd_poll_runtime.go:84 +0x28 fp=0x40003105f0 sp=0x40003105c0 pc=0xaaaaded154b8
internal/poll.(*pollDesc).waitRead(...)
internal/poll/fd_poll_runtime.go:89
internal/poll.(*FD).Read(0x40002fe700, {0x4000284131, 0x1, 0x1})
internal/poll/fd_unix.go:165 +0x1fc fp=0x4000310690 sp=0x40003105f0 pc=0xaaaaded15fcc
net.(*netFD).Read(0x40002fe700, {0x4000284131?, 0x0?, 0x0?})
net/fd_posix.go:55 +0x28 fp=0x40003106e0 sp=0x4000310690 pc=0xaaaaded85628
net.(*conn).Read(0x4000056000, {0x4000284131?, 0x0?, 0x4000284128?})
net/net.go:189 +0x34 fp=0x4000310730 sp=0x40003106e0 pc=0xaaaaded8ea44
net.(*TCPConn).Read(0xaaaadf3ce0c0?, {0x4000284131?, 0x0?, 0x0?})
:1 +0x2c fp=0x4000310760 sp=0x4000310730 pc=0xaaaaded9b67c
net/http.(*connReader).backgroundRead(0x4000284120)
net/http/server.go:690 +0x40 fp=0x40003107b0 sp=0x4000310760 pc=0xaaaadee85d30
net/http.(*connReader).startBackgroundRead.gowrap2()
net/http/server.go:686 +0x28 fp=0x40003107d0 sp=0x40003107b0 pc=0xaaaadee85c18
runtime.goexit({})
runtime/asm_arm64.s:1223 +0x4 fp=0x40003107d0 sp=0x40003107d0 pc=0xaaaadecc94a4
created by net/http.(*connReader).startBackgroundRead in goroutine 483
net/http/server.go:686 +0xc4

r0 0x0
r1 0xb4
r2 0x6
r3 0xffff72450840
r4 0xffff8bd7cb58
r5 0xffff72451000
r6 0xffff72450840
r7 0x0
r8 0x83
r9 0xffffd291be75
r10 0x0
r11 0xa
r12 0xb4
r13 0x1
r14 0x150
r15 0xaaab074260a8
r16 0x1
r17 0xffff84a7704c
r18 0xe0
r19 0xb4
r20 0xffff72450840
r21 0x6
r22 0x1c1
r23 0xffffd291c1e8
r24 0xffffd291c208
r25 0x0
r26 0xffff148bf2b0
r27 0x0
r28 0xffff14c87550
r29 0xffffd291bef0
lr 0xffff84acf1ec
sp 0xffffd291bef0
pc 0xffff84acf200
fault 0x0

OS

Linux

GPU

Nvidia

CPU

Other

Ollama version

0.5.4

Originally created by @ghmole on GitHub (Jan 3, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/8292 ### What is the issue? time=2025-01-03T08:27:01.902Z level=WARN source=runner.go:129 msg="truncating input prompt" limit=2048 prompt=2101 keep=4 new=2048 llama_model_loader: loaded meta data with 40 key-value pairs and 963 tensors from /data/models/ollama/models/blobs/sha256-49ecab6afc82486151830989cb79d3bf58b88197c714197968c7fd2f4523afe3 (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 = qwen2vl llama_model_loader: - kv 1: general.type str = model llama_model_loader: - kv 2: general.name str = QVQ 72B Preview llama_model_loader: - kv 3: general.finetune str = Preview llama_model_loader: - kv 4: general.basename str = QVQ llama_model_loader: - kv 5: general.size_label str = 72B llama_model_loader: - kv 6: general.license str = other llama_model_loader: - kv 7: general.license.name str = qwen llama_model_loader: - kv 8: general.license.link str = https://huggingface.co/Qwen/QVQ-72B-P... llama_model_loader: - kv 9: general.base_model.count u32 = 1 llama_model_loader: - kv 10: general.base_model.0.name str = Qwen2 VL 72B llama_model_loader: - kv 11: general.base_model.0.organization str = Qwen llama_model_loader: - kv 12: general.base_model.0.repo_url str = https://huggingface.co/Qwen/Qwen2-VL-72B llama_model_loader: - kv 13: general.tags arr[str,2] = ["chat", "image-text-to-text"] llama_model_loader: - kv 14: general.languages arr[str,1] = ["en"] llama_model_loader: - kv 15: qwen2vl.block_count u32 = 80 llama_model_loader: - kv 16: qwen2vl.context_length u32 = 128000 llama_model_loader: - kv 17: qwen2vl.embedding_length u32 = 8192 llama_model_loader: - kv 18: qwen2vl.feed_forward_length u32 = 29568 llama_model_loader: - kv 19: qwen2vl.attention.head_count u32 = 64 llama_model_loader: - kv 20: qwen2vl.attention.head_count_kv u32 = 8 llama_model_loader: - kv 21: qwen2vl.rope.freq_base f32 = 1000000.000000 llama_model_loader: - kv 22: qwen2vl.attention.layer_norm_rms_epsilon f32 = 0.000001 llama_model_loader: - kv 23: general.file_type u32 = 15 llama_model_loader: - kv 24: qwen2vl.rope.dimension_sections arr[i32,4] = [16, 24, 24, 0] llama_model_loader: - kv 25: tokenizer.ggml.model str = gpt2 llama_model_loader: - kv 26: tokenizer.ggml.pre str = qwen2 llama_model_loader: - kv 27: tokenizer.ggml.tokens arr[str,152064] = ["!", "\"", "#", "$", "%", "&", "'", ... llama_model_loader: - kv 28: tokenizer.ggml.token_type arr[i32,152064] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... llama_model_loader: - kv 29: tokenizer.ggml.merges arr[str,151387] = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",... llama_model_loader: - kv 30: tokenizer.ggml.eos_token_id u32 = 151645 llama_model_loader: - kv 31: tokenizer.ggml.padding_token_id u32 = 151643 llama_model_loader: - kv 32: tokenizer.ggml.bos_token_id u32 = 151643 llama_model_loader: - kv 33: tokenizer.ggml.add_bos_token bool = false llama_model_loader: - kv 34: tokenizer.chat_template str = {% set image_count = namespace(value=... llama_model_loader: - kv 35: general.quantization_version u32 = 2 llama_model_loader: - kv 36: quantize.imatrix.file str = /models_out/QVQ-72B-Preview-GGUF/QVQ-... llama_model_loader: - kv 37: quantize.imatrix.dataset str = /training_dir/calibration_datav3.txt llama_model_loader: - kv 38: quantize.imatrix.entries_count i32 = 560 llama_model_loader: - kv 39: quantize.imatrix.chunks_count i32 = 128 llama_model_loader: - type f32: 401 tensors llama_model_loader: - type q5_0: 40 tensors llama_model_loader: - type q8_0: 42 tensors llama_model_loader: - type q4_K: 400 tensors llama_model_loader: - type q5_K: 40 tensors llama_model_loader: - type q6_K: 40 tensors llm_load_vocab: special tokens cache size = 22 llm_load_vocab: token to piece cache size = 0.9310 MB llm_load_print_meta: format = GGUF V3 (latest) llm_load_print_meta: arch = qwen2vl llm_load_print_meta: vocab type = BPE llm_load_print_meta: n_vocab = 152064 llm_load_print_meta: n_merges = 151387 llm_load_print_meta: vocab_only = 1 llm_load_print_meta: model type = ?B llm_load_print_meta: model ftype = all F32 llm_load_print_meta: model params = 72.71 B llm_load_print_meta: model size = 45.01 GiB (5.32 BPW) llm_load_print_meta: general.name = QVQ 72B Preview llm_load_print_meta: BOS token = 151643 '<|endoftext|>' llm_load_print_meta: EOS token = 151645 '<|im_end|>' llm_load_print_meta: EOT token = 151645 '<|im_end|>' llm_load_print_meta: PAD token = 151643 '<|endoftext|>' llm_load_print_meta: LF token = 148848 'ÄĬ' llm_load_print_meta: FIM PRE token = 151659 '<|fim_prefix|>' llm_load_print_meta: FIM SUF token = 151661 '<|fim_suffix|>' llm_load_print_meta: FIM MID token = 151660 '<|fim_middle|>' llm_load_print_meta: FIM PAD token = 151662 '<|fim_pad|>' llm_load_print_meta: FIM REP token = 151663 '<|repo_name|>' llm_load_print_meta: FIM SEP token = 151664 '<|file_sep|>' llm_load_print_meta: EOG token = 151643 '<|endoftext|>' llm_load_print_meta: EOG token = 151645 '<|im_end|>' llm_load_print_meta: EOG token = 151662 '<|fim_pad|>' llm_load_print_meta: EOG token = 151663 '<|repo_name|>' llm_load_print_meta: EOG token = 151664 '<|file_sep|>' llm_load_print_meta: max token length = 256 llama_model_load: vocab only - skipping tensors [GIN] 2025/01/03 - 08:27:29 | 200 | 27.344406312s | 192.168.100.232 | POST "/api/chat" [GIN] 2025/01/03 - 08:27:44 | 200 | 30.190356335s | 192.168.100.232 | POST "/api/chat" time=2025-01-03T08:27:47.970Z level=WARN source=runner.go:129 msg="truncating input prompt" limit=2048 prompt=2158 keep=4 new=2048 llama/ggml-cuda/rope.cu:449: GGML_ASSERT(sections.v[0] > 0 || sections.v[1] > 0 || sections.v[2] > 0) failed Could not attach to process. If your uid matches the uid of the target process, check the setting of /proc/sys/kernel/yama/ptrace_scope, or try again as the root user. For more details, see /etc/sysctl.d/10-ptrace.conf ptrace: Inappropriate ioctl for device. No stack. The program is not being run. SIGABRT: abort PC=0xffff84acf200 m=0 sigcode=18446744073709551610 signal arrived during cgo execution goroutine 37 gp=0x40001868c0 m=0 mp=0xaaaadf40dec0 [syscall]: runtime.cgocall(0xaaaadeec27d0, 0x4000330b68) runtime/cgocall.go:167 +0x44 fp=0x4000330b30 sp=0x4000330af0 pc=0xaaaadecbb834 github.com/ollama/ollama/llama._Cfunc_llama_decode(0xffff149d0a20, {0x7, 0xffff14981d30, 0x0, 0x0, 0xffff149e0490, 0xffff149ebfa0, 0xffff1497c8a0, 0xffff14b109a0}) _cgo_gotypes.go:564 +0x34 fp=0x4000330b60 sp=0x4000330b30 pc=0xaaaaded5e464 github.com/ollama/ollama/llama.(*Context).Decode.func1(0x4000330c98?, 0xaaaadeebd650?) github.com/ollama/ollama/llama/llama.go:207 +0xc8 fp=0x4000330c50 sp=0x4000330b60 pc=0xaaaaded60218 github.com/ollama/ollama/llama.(*Context).Decode(0x40002fe600?, 0x40001aa100?) github.com/ollama/ollama/llama/llama.go:207 +0x1c fp=0x4000330ca0 sp=0x4000330c50 pc=0xaaaaded600ac github.com/ollama/ollama/llama/runner.(*Server).processBatch(0x40001be1b0, 0x40001a84e0, 0x4000330f10) github.com/ollama/ollama/llama/runner/runner.go:434 +0x200 fp=0x4000330ec0 sp=0x4000330ca0 pc=0xaaaadeebd660 github.com/ollama/ollama/llama/runner.(*Server).run(0x40001be1b0, {0xaaaadf230b20, 0x4000202050}) github.com/ollama/ollama/llama/runner/runner.go:342 +0x17c fp=0x4000330fa0 sp=0x4000330ec0 pc=0xaaaadeebd15c github.com/ollama/ollama/llama/runner.Execute.gowrap2() github.com/ollama/ollama/llama/runner/runner.go:984 +0x30 fp=0x4000330fd0 sp=0x4000330fa0 pc=0xaaaadeec14f0 runtime.goexit({}) runtime/asm_arm64.s:1223 +0x4 fp=0x4000330fd0 sp=0x4000330fd0 pc=0xaaaadecc94a4 created by github.com/ollama/ollama/llama/runner.Execute in goroutine 1 github.com/ollama/ollama/llama/runner/runner.go:984 +0xba8 goroutine 1 gp=0x40000021c0 m=nil [IO wait]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xc8 fp=0x40001f3750 sp=0x40001f3730 pc=0xaaaadecc17d8 runtime.netpollblock(0x7000000000?, 0x6?, 0x0?) runtime/netpoll.go:575 +0x158 fp=0x40001f3790 sp=0x40001f3750 pc=0xaaaadec855a8 internal/poll.runtime_pollWait(0xffff2a0ebde0, 0x72) runtime/netpoll.go:351 +0xa0 fp=0x40001f37c0 sp=0x40001f3790 pc=0xaaaadecc0a80 internal/poll.(*pollDesc).wait(0x40001fa100?, 0x0?, 0x0) internal/poll/fd_poll_runtime.go:84 +0x28 fp=0x40001f37f0 sp=0x40001f37c0 pc=0xaaaaded154b8 internal/poll.(*pollDesc).waitRead(...) internal/poll/fd_poll_runtime.go:89 internal/poll.(*FD).Accept(0x40001fa100) internal/poll/fd_unix.go:620 +0x24c fp=0x40001f38a0 sp=0x40001f37f0 pc=0xaaaaded1687c net.(*netFD).accept(0x40001fa100) net/fd_unix.go:172 +0x28 fp=0x40001f3960 sp=0x40001f38a0 pc=0xaaaaded86448 net.(*TCPListener).accept(0x40001a66c0) net/tcpsock_posix.go:159 +0x28 fp=0x40001f39b0 sp=0x40001f3960 pc=0xaaaaded96598 net.(*TCPListener).Accept(0x40001a66c0) net/tcpsock.go:372 +0x2c fp=0x40001f39f0 sp=0x40001f39b0 pc=0xaaaaded958ec net/http.(*onceCloseListener).Accept(0x40001be2d0?) <autogenerated>:1 +0x30 fp=0x40001f3a10 sp=0x40001f39f0 pc=0xaaaadee9c770 net/http.(*Server).Serve(0x40001f84b0, {0xaaaadf230538, 0x40001a66c0}) net/http/server.go:3330 +0x294 fp=0x40001f3b40 sp=0x40001f3a10 pc=0xaaaadee8ec84 github.com/ollama/ollama/llama/runner.Execute({0x40001aa010?, 0x0?, 0x4000052738?}) github.com/ollama/ollama/llama/runner/runner.go:1005 +0xebc fp=0x40001f3ee0 sp=0x40001f3b40 pc=0xaaaadeec122c main.main() github.com/ollama/ollama/cmd/runner/main.go:11 +0x54 fp=0x40001f3f40 sp=0x40001f3ee0 pc=0xaaaadeec2104 runtime.main() runtime/proc.go:272 +0x288 fp=0x40001f3fd0 sp=0x40001f3f40 pc=0xaaaadec8c9c8 runtime.goexit({}) runtime/asm_arm64.s:1223 +0x4 fp=0x40001f3fd0 sp=0x40001f3fd0 pc=0xaaaadecc94a4 goroutine 2 gp=0x4000002c40 m=nil [force gc (idle), 2 minutes]: runtime.gopark(0x3b630cd8c2e?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xc8 fp=0x4000052f90 sp=0x4000052f70 pc=0xaaaadecc17d8 runtime.goparkunlock(...) runtime/proc.go:430 runtime.forcegchelper() runtime/proc.go:337 +0xb8 fp=0x4000052fd0 sp=0x4000052f90 pc=0xaaaadec8cd28 runtime.goexit({}) runtime/asm_arm64.s:1223 +0x4 fp=0x4000052fd0 sp=0x4000052fd0 pc=0xaaaadecc94a4 created by runtime.init.7 in goroutine 1 runtime/proc.go:325 +0x24 goroutine 18 gp=0x4000104380 m=nil [GC sweep wait]: runtime.gopark(0x1?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xc8 fp=0x400004e760 sp=0x400004e740 pc=0xaaaadecc17d8 runtime.goparkunlock(...) runtime/proc.go:430 runtime.bgsweep(0x4000112000) runtime/mgcsweep.go:317 +0x108 fp=0x400004e7b0 sp=0x400004e760 pc=0xaaaadec77368 runtime.gcenable.gowrap1() runtime/mgc.go:204 +0x28 fp=0x400004e7d0 sp=0x400004e7b0 pc=0xaaaadec6b4f8 runtime.goexit({}) runtime/asm_arm64.s:1223 +0x4 fp=0x400004e7d0 sp=0x400004e7d0 pc=0xaaaadecc94a4 created by runtime.gcenable in goroutine 1 runtime/mgc.go:204 +0x6c goroutine 19 gp=0x4000104540 m=nil [GC scavenge wait]: runtime.gopark(0x3ba00e6b?, 0x3b9aca00?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xc8 fp=0x400004ef60 sp=0x400004ef40 pc=0xaaaadecc17d8 runtime.goparkunlock(...) runtime/proc.go:430 runtime.(*scavengerState).park(0xaaaadf40d3a0) runtime/mgcscavenge.go:425 +0x5c fp=0x400004ef90 sp=0x400004ef60 pc=0xaaaadec74d2c runtime.bgscavenge(0x4000112000) runtime/mgcscavenge.go:658 +0xac fp=0x400004efb0 sp=0x400004ef90 pc=0xaaaadec752bc runtime.gcenable.gowrap2() runtime/mgc.go:205 +0x28 fp=0x400004efd0 sp=0x400004efb0 pc=0xaaaadec6b498 runtime.goexit({}) runtime/asm_arm64.s:1223 +0x4 fp=0x400004efd0 sp=0x400004efd0 pc=0xaaaadecc94a4 created by runtime.gcenable in goroutine 1 runtime/mgc.go:205 +0xac goroutine 34 gp=0x4000186380 m=nil [finalizer wait]: runtime.gopark(0x0?, 0xaaaadf22bb38?, 0x0?, 0x40?, 0x1000000010?) runtime/proc.go:424 +0xc8 fp=0x4000052580 sp=0x4000052560 pc=0xaaaadecc17d8 runtime.runfinq() runtime/mfinal.go:193 +0x108 fp=0x40000527d0 sp=0x4000052580 pc=0xaaaadec6a5f8 runtime.goexit({}) runtime/asm_arm64.s:1223 +0x4 fp=0x40000527d0 sp=0x40000527d0 pc=0xaaaadecc94a4 created by runtime.createfing in goroutine 1 runtime/mfinal.go:163 +0x80 goroutine 35 gp=0x4000186540 m=nil [chan receive]: runtime.gopark(0x40001d4748?, 0xaaaaded694ac?, 0x70?, 0x42?, 0xaaaadf234920?) runtime/proc.go:424 +0xc8 fp=0x40001d46f0 sp=0x40001d46d0 pc=0xaaaadecc17d8 runtime.chanrecv(0x40001800e0, 0x0, 0x1) runtime/chan.go:639 +0x414 fp=0x40001d4770 sp=0x40001d46f0 pc=0xaaaadec5b534 runtime.chanrecv1(0x0?, 0x0?) runtime/chan.go:489 +0x14 fp=0x40001d47a0 sp=0x40001d4770 pc=0xaaaadec5b114 runtime.unique_runtime_registerUniqueMapCleanup.func1(...) runtime/mgc.go:1781 runtime.unique_runtime_registerUniqueMapCleanup.gowrap1() runtime/mgc.go:1784 +0x3c fp=0x40001d47d0 sp=0x40001d47a0 pc=0xaaaadec6e3ac runtime.goexit({}) runtime/asm_arm64.s:1223 +0x4 fp=0x40001d47d0 sp=0x40001d47d0 pc=0xaaaadecc94a4 created by unique.runtime_registerUniqueMapCleanup in goroutine 1 runtime/mgc.go:1779 +0xa0 goroutine 455 gp=0x4000186700 m=nil [GC worker (idle), 2 minutes]: runtime.gopark(0x4000316d18?, 0x4000316d14?, 0x58?, 0xb7?, 0xaaaadee85e34?) runtime/proc.go:424 +0xc8 fp=0x400030b710 sp=0x400030b6f0 pc=0xaaaadecc17d8 runtime.gcBgMarkWorker(0x40002957a0) runtime/mgc.go:1412 +0xdc fp=0x400030b7b0 sp=0x400030b710 pc=0xaaaadec6d61c runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x28 fp=0x400030b7d0 sp=0x400030b7b0 pc=0xaaaadec6d508 runtime.goexit({}) runtime/asm_arm64.s:1223 +0x4 fp=0x400030b7d0 sp=0x400030b7d0 pc=0xaaaadecc94a4 created by runtime.gcBgMarkStartWorkers in goroutine 37 runtime/mgc.go:1328 +0x140 goroutine 457 gp=0x400016a700 m=nil [GC worker (idle), 2 minutes]: runtime.gopark(0x400008c0d8?, 0x400008c0d4?, 0x58?, 0x27?, 0xaaaadee85e34?) runtime/proc.go:424 +0xc8 fp=0x4000172710 sp=0x40001726f0 pc=0xaaaadecc17d8 runtime.gcBgMarkWorker(0x40002957a0) runtime/mgc.go:1412 +0xdc fp=0x40001727b0 sp=0x4000172710 pc=0xaaaadec6d61c runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x28 fp=0x40001727d0 sp=0x40001727b0 pc=0xaaaadec6d508 runtime.goexit({}) runtime/asm_arm64.s:1223 +0x4 fp=0x40001727d0 sp=0x40001727d0 pc=0xaaaadecc94a4 created by runtime.gcBgMarkStartWorkers in goroutine 37 runtime/mgc.go:1328 +0x140 goroutine 458 gp=0x400016ac40 m=nil [GC worker (idle), 2 minutes]: runtime.gopark(0x400008c0d8?, 0x400008c0d4?, 0x58?, 0x3f?, 0xaaaadee85e34?) runtime/proc.go:424 +0xc8 fp=0x4000173f10 sp=0x4000173ef0 pc=0xaaaadecc17d8 runtime.gcBgMarkWorker(0x40002957a0) runtime/mgc.go:1412 +0xdc fp=0x4000173fb0 sp=0x4000173f10 pc=0xaaaadec6d61c runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x28 fp=0x4000173fd0 sp=0x4000173fb0 pc=0xaaaadec6d508 runtime.goexit({}) runtime/asm_arm64.s:1223 +0x4 fp=0x4000173fd0 sp=0x4000173fd0 pc=0xaaaadecc94a4 created by runtime.gcBgMarkStartWorkers in goroutine 37 runtime/mgc.go:1328 +0x140 goroutine 460 gp=0x400016b340 m=nil [GC worker (idle), 2 minutes]: runtime.gopark(0x400008c0d8?, 0x400008c0d4?, 0x58?, 0xdf?, 0xaaaadee85e34?) runtime/proc.go:424 +0xc8 fp=0x400016df10 sp=0x400016def0 pc=0xaaaadecc17d8 runtime.gcBgMarkWorker(0x40002957a0) runtime/mgc.go:1412 +0xdc fp=0x400016dfb0 sp=0x400016df10 pc=0xaaaadec6d61c runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x28 fp=0x400016dfd0 sp=0x400016dfb0 pc=0xaaaadec6d508 runtime.goexit({}) runtime/asm_arm64.s:1223 +0x4 fp=0x400016dfd0 sp=0x400016dfd0 pc=0xaaaadecc94a4 created by runtime.gcBgMarkStartWorkers in goroutine 37 runtime/mgc.go:1328 +0x140 goroutine 459 gp=0x400016b6c0 m=nil [GC worker (idle), 2 minutes]: runtime.gopark(0x400008c0d8?, 0x400008c0d4?, 0x58?, 0xef?, 0xaaaadee85e34?) runtime/proc.go:424 +0xc8 fp=0x400016ef10 sp=0x400016eef0 pc=0xaaaadecc17d8 runtime.gcBgMarkWorker(0x40002957a0) runtime/mgc.go:1412 +0xdc fp=0x400016efb0 sp=0x400016ef10 pc=0xaaaadec6d61c runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x28 fp=0x400016efd0 sp=0x400016efb0 pc=0xaaaadec6d508 runtime.goexit({}) runtime/asm_arm64.s:1223 +0x4 fp=0x400016efd0 sp=0x400016efd0 pc=0xaaaadecc94a4 created by runtime.gcBgMarkStartWorkers in goroutine 37 runtime/mgc.go:1328 +0x140 goroutine 461 gp=0x400016b880 m=nil [GC worker (idle), 2 minutes]: runtime.gopark(0x400008c0d8?, 0x400008c0d4?, 0x58?, 0xf7?, 0xaaaadee85e34?) runtime/proc.go:424 +0xc8 fp=0x400016f710 sp=0x400016f6f0 pc=0xaaaadecc17d8 runtime.gcBgMarkWorker(0x40002957a0) runtime/mgc.go:1412 +0xdc fp=0x400016f7b0 sp=0x400016f710 pc=0xaaaadec6d61c runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x28 fp=0x400016f7d0 sp=0x400016f7b0 pc=0xaaaadec6d508 runtime.goexit({}) runtime/asm_arm64.s:1223 +0x4 fp=0x400016f7d0 sp=0x400016f7d0 pc=0xaaaadecc94a4 created by runtime.gcBgMarkStartWorkers in goroutine 37 runtime/mgc.go:1328 +0x140 goroutine 456 gp=0x400016bc00 m=nil [GC worker (idle), 2 minutes]: runtime.gopark(0x4000245b90?, 0xaaaadf1147a0?, 0x58?, 0xe7?, 0xaaaadee85e34?) runtime/proc.go:424 +0xc8 fp=0x400030e710 sp=0x400030e6f0 pc=0xaaaadecc17d8 runtime.gcBgMarkWorker(0x40002957a0) runtime/mgc.go:1412 +0xdc fp=0x400030e7b0 sp=0x400030e710 pc=0xaaaadec6d61c runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x28 fp=0x400030e7d0 sp=0x400030e7b0 pc=0xaaaadec6d508 runtime.goexit({}) runtime/asm_arm64.s:1223 +0x4 fp=0x400030e7d0 sp=0x400030e7d0 pc=0xaaaadecc94a4 created by runtime.gcBgMarkStartWorkers in goroutine 37 runtime/mgc.go:1328 +0x140 goroutine 347 gp=0x40003221c0 m=nil [IO wait]: runtime.gopark(0x40001d7628?, 0xaaaaded2b684?, 0x88?, 0x75?, 0xaaaaded2d6c0?) runtime/proc.go:424 +0xc8 fp=0x40001d7550 sp=0x40001d7530 pc=0xaaaadecc17d8 runtime.netpollblock(0x0?, 0xffffffff?, 0xff?) runtime/netpoll.go:575 +0x158 fp=0x40001d7590 sp=0x40001d7550 pc=0xaaaadec855a8 internal/poll.runtime_pollWait(0xffff2a0ebbb0, 0x72) runtime/netpoll.go:351 +0xa0 fp=0x40001d75c0 sp=0x40001d7590 pc=0xaaaadecc0a80 internal/poll.(*pollDesc).wait(0x40002fe480?, 0x400035a491?, 0x0) internal/poll/fd_poll_runtime.go:84 +0x28 fp=0x40001d75f0 sp=0x40001d75c0 pc=0xaaaaded154b8 internal/poll.(*pollDesc).waitRead(...) internal/poll/fd_poll_runtime.go:89 internal/poll.(*FD).Read(0x40002fe480, {0x400035a491, 0x1, 0x1}) internal/poll/fd_unix.go:165 +0x1fc fp=0x40001d7690 sp=0x40001d75f0 pc=0xaaaaded15fcc net.(*netFD).Read(0x40002fe480, {0x400035a491?, 0x40001d7738?, 0xaaaadee8609c?}) net/fd_posix.go:55 +0x28 fp=0x40001d76e0 sp=0x40001d7690 pc=0xaaaaded85628 net.(*conn).Read(0x400019c058, {0x400035a491?, 0x0?, 0x400035a728?}) net/net.go:189 +0x34 fp=0x40001d7730 sp=0x40001d76e0 pc=0xaaaaded8ea44 net.(*TCPConn).Read(0x400035a720?, {0x400035a491?, 0x0?, 0x0?}) <autogenerated>:1 +0x2c fp=0x40001d7760 sp=0x40001d7730 pc=0xaaaaded9b67c net/http.(*connReader).backgroundRead(0x400035a480) net/http/server.go:690 +0x40 fp=0x40001d77b0 sp=0x40001d7760 pc=0xaaaadee85d30 net/http.(*connReader).startBackgroundRead.gowrap2() net/http/server.go:686 +0x28 fp=0x40001d77d0 sp=0x40001d77b0 pc=0xaaaadee85c18 runtime.goexit({}) runtime/asm_arm64.s:1223 +0x4 fp=0x40001d77d0 sp=0x40001d77d0 pc=0xaaaadecc94a4 created by net/http.(*connReader).startBackgroundRead in goroutine 345 net/http/server.go:686 +0xc4 goroutine 462 gp=0x40002a0380 m=nil [GC worker (idle), 2 minutes]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xc8 fp=0x400030bf10 sp=0x400030bef0 pc=0xaaaadecc17d8 runtime.gcBgMarkWorker(0x40002957a0) runtime/mgc.go:1412 +0xdc fp=0x400030bfb0 sp=0x400030bf10 pc=0xaaaadec6d61c runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x28 fp=0x400030bfd0 sp=0x400030bfb0 pc=0xaaaadec6d508 runtime.goexit({}) runtime/asm_arm64.s:1223 +0x4 fp=0x400030bfd0 sp=0x400030bfd0 pc=0xaaaadecc94a4 created by runtime.gcBgMarkStartWorkers in goroutine 37 runtime/mgc.go:1328 +0x140 goroutine 463 gp=0x40002a0540 m=nil [GC worker (idle), 2 minutes]: runtime.gopark(0x3b630d97a67?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xc8 fp=0x400030c710 sp=0x400030c6f0 pc=0xaaaadecc17d8 runtime.gcBgMarkWorker(0x40002957a0) runtime/mgc.go:1412 +0xdc fp=0x400030c7b0 sp=0x400030c710 pc=0xaaaadec6d61c runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x28 fp=0x400030c7d0 sp=0x400030c7b0 pc=0xaaaadec6d508 runtime.goexit({}) runtime/asm_arm64.s:1223 +0x4 fp=0x400030c7d0 sp=0x400030c7d0 pc=0xaaaadecc94a4 created by runtime.gcBgMarkStartWorkers in goroutine 37 runtime/mgc.go:1328 +0x140 goroutine 464 gp=0x40002a0700 m=nil [GC worker (idle)]: runtime.gopark(0x3b630da0ac7?, 0x1?, 0x3c?, 0x28?, 0x0?) runtime/proc.go:424 +0xc8 fp=0x400030cf10 sp=0x400030cef0 pc=0xaaaadecc17d8 runtime.gcBgMarkWorker(0x40002957a0) runtime/mgc.go:1412 +0xdc fp=0x400030cfb0 sp=0x400030cf10 pc=0xaaaadec6d61c runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x28 fp=0x400030cfd0 sp=0x400030cfb0 pc=0xaaaadec6d508 runtime.goexit({}) runtime/asm_arm64.s:1223 +0x4 fp=0x400030cfd0 sp=0x400030cfd0 pc=0xaaaadecc94a4 created by runtime.gcBgMarkStartWorkers in goroutine 37 runtime/mgc.go:1328 +0x140 goroutine 465 gp=0x40002a08c0 m=nil [GC worker (idle), 2 minutes]: runtime.gopark(0x39a2c50720b?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xc8 fp=0x400030d710 sp=0x400030d6f0 pc=0xaaaadecc17d8 runtime.gcBgMarkWorker(0x40002957a0) runtime/mgc.go:1412 +0xdc fp=0x400030d7b0 sp=0x400030d710 pc=0xaaaadec6d61c runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x28 fp=0x400030d7d0 sp=0x400030d7b0 pc=0xaaaadec6d508 runtime.goexit({}) runtime/asm_arm64.s:1223 +0x4 fp=0x400030d7d0 sp=0x400030d7d0 pc=0xaaaadecc94a4 created by runtime.gcBgMarkStartWorkers in goroutine 37 runtime/mgc.go:1328 +0x140 goroutine 482 gp=0x40002a0a80 m=nil [GC worker (idle)]: runtime.gopark(0x3b630d9a007?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xc8 fp=0x400030df10 sp=0x400030def0 pc=0xaaaadecc17d8 runtime.gcBgMarkWorker(0x40002957a0) runtime/mgc.go:1412 +0xdc fp=0x400030dfb0 sp=0x400030df10 pc=0xaaaadec6d61c runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x28 fp=0x400030dfd0 sp=0x400030dfb0 pc=0xaaaadec6d508 runtime.goexit({}) runtime/asm_arm64.s:1223 +0x4 fp=0x400030dfd0 sp=0x400030dfd0 pc=0xaaaadecc94a4 created by runtime.gcBgMarkStartWorkers in goroutine 37 runtime/mgc.go:1328 +0x140 goroutine 483 gp=0x40002a0c40 m=nil [select]: runtime.gopark(0x40001f5a50?, 0x2?, 0xe8?, 0x56?, 0x40001f580c?) runtime/proc.go:424 +0xc8 fp=0x40001f5660 sp=0x40001f5640 pc=0xaaaadecc17d8 runtime.selectgo(0x40001f5a50, 0x40001f5808, 0x400011c300?, 0x0, 0x1?, 0x1) runtime/select.go:335 +0x67c fp=0x40001f5790 sp=0x40001f5660 pc=0xaaaadec9fc5c github.com/ollama/ollama/llama/runner.(*Server).completion(0x40001be1b0, {0xaaaadf2306b8, 0x40001d81c0}, 0x40001ee140) github.com/ollama/ollama/llama/runner/runner.go:696 +0x8e8 fp=0x40001f5aa0 sp=0x40001f5790 pc=0xaaaadeebef48 github.com/ollama/ollama/llama/runner.(*Server).completion-fm({0xaaaadf2306b8?, 0x40001d81c0?}, 0x40001f5b28?) <autogenerated>:1 +0x40 fp=0x40001f5ad0 sp=0x40001f5aa0 pc=0xaaaadeec1d00 net/http.HandlerFunc.ServeHTTP(0x40001d80e0?, {0xaaaadf2306b8?, 0x40001d81c0?}, 0x40001f5b10?) net/http/server.go:2220 +0x38 fp=0x40001f5b00 sp=0x40001f5ad0 pc=0xaaaadee8beb8 net/http.(*ServeMux).ServeHTTP(0x10?, {0xaaaadf2306b8, 0x40001d81c0}, 0x40001ee140) net/http/server.go:2747 +0x1b4 fp=0x40001f5b50 sp=0x40001f5b00 pc=0xaaaadee8dab4 net/http.serverHandler.ServeHTTP({0xaaaadf22f770?}, {0xaaaadf2306b8?, 0x40001d81c0?}, 0x6?) net/http/server.go:3210 +0xbc fp=0x40001f5b80 sp=0x40001f5b50 pc=0xaaaadee949fc net/http.(*conn).serve(0x4000376000, {0xaaaadf230ae8, 0x40001a4f60}) net/http/server.go:2092 +0x4fc fp=0x40001f5fa0 sp=0x40001f5b80 pc=0xaaaadee8ad3c net/http.(*Server).Serve.gowrap3() net/http/server.go:3360 +0x30 fp=0x40001f5fd0 sp=0x40001f5fa0 pc=0xaaaadee8f010 runtime.goexit({}) runtime/asm_arm64.s:1223 +0x4 fp=0x40001f5fd0 sp=0x40001f5fd0 pc=0xaaaadecc94a4 created by net/http.(*Server).Serve in goroutine 1 net/http/server.go:3360 +0x3dc goroutine 345 gp=0x40002a0e00 m=nil [select]: runtime.gopark(0x40000fda50?, 0x2?, 0x88?, 0xd7?, 0x40000fd80c?) runtime/proc.go:424 +0xc8 fp=0x40000fd660 sp=0x40000fd640 pc=0xaaaadecc17d8 runtime.selectgo(0x40000fda50, 0x40000fd808, 0x717?, 0x0, 0x1?, 0x1) runtime/select.go:335 +0x67c fp=0x40000fd790 sp=0x40000fd660 pc=0xaaaadec9fc5c github.com/ollama/ollama/llama/runner.(*Server).completion(0x40001be1b0, {0xaaaadf2306b8, 0x40001d8380}, 0x40001ee500) github.com/ollama/ollama/llama/runner/runner.go:696 +0x8e8 fp=0x40000fdaa0 sp=0x40000fd790 pc=0xaaaadeebef48 github.com/ollama/ollama/llama/runner.(*Server).completion-fm({0xaaaadf2306b8?, 0x40001d8380?}, 0x40000fdb28?) <autogenerated>:1 +0x40 fp=0x40000fdad0 sp=0x40000fdaa0 pc=0xaaaadeec1d00 net/http.HandlerFunc.ServeHTTP(0x40001d80e0?, {0xaaaadf2306b8?, 0x40001d8380?}, 0x40000fdb10?) net/http/server.go:2220 +0x38 fp=0x40000fdb00 sp=0x40000fdad0 pc=0xaaaadee8beb8 net/http.(*ServeMux).ServeHTTP(0x10?, {0xaaaadf2306b8, 0x40001d8380}, 0x40001ee500) net/http/server.go:2747 +0x1b4 fp=0x40000fdb50 sp=0x40000fdb00 pc=0xaaaadee8dab4 net/http.serverHandler.ServeHTTP({0xaaaadf22f770?}, {0xaaaadf2306b8?, 0x40001d8380?}, 0x6?) net/http/server.go:3210 +0xbc fp=0x40000fdb80 sp=0x40000fdb50 pc=0xaaaadee949fc net/http.(*conn).serve(0x40001be2d0, {0xaaaadf230ae8, 0x40001a4f60}) net/http/server.go:2092 +0x4fc fp=0x40000fdfa0 sp=0x40000fdb80 pc=0xaaaadee8ad3c net/http.(*Server).Serve.gowrap3() net/http/server.go:3360 +0x30 fp=0x40000fdfd0 sp=0x40000fdfa0 pc=0xaaaadee8f010 runtime.goexit({}) runtime/asm_arm64.s:1223 +0x4 fp=0x40000fdfd0 sp=0x40000fdfd0 pc=0xaaaadecc94a4 created by net/http.(*Server).Serve in goroutine 1 net/http/server.go:3360 +0x3dc goroutine 344 gp=0x40002a0fc0 m=nil [IO wait]: runtime.gopark(0x10?, 0x10?, 0xa8?, 0x5?, 0xaaaadec65fe4?) runtime/proc.go:424 +0xc8 fp=0x4000310550 sp=0x4000310530 pc=0xaaaadecc17d8 runtime.netpollblock(0x0?, 0xffffffff?, 0xff?) runtime/netpoll.go:575 +0x158 fp=0x4000310590 sp=0x4000310550 pc=0xaaaadec855a8 internal/poll.runtime_pollWait(0xffff2a0ebcc8, 0x72) runtime/netpoll.go:351 +0xa0 fp=0x40003105c0 sp=0x4000310590 pc=0xaaaadecc0a80 internal/poll.(*pollDesc).wait(0x40002fe700?, 0x4000284131?, 0x0) internal/poll/fd_poll_runtime.go:84 +0x28 fp=0x40003105f0 sp=0x40003105c0 pc=0xaaaaded154b8 internal/poll.(*pollDesc).waitRead(...) internal/poll/fd_poll_runtime.go:89 internal/poll.(*FD).Read(0x40002fe700, {0x4000284131, 0x1, 0x1}) internal/poll/fd_unix.go:165 +0x1fc fp=0x4000310690 sp=0x40003105f0 pc=0xaaaaded15fcc net.(*netFD).Read(0x40002fe700, {0x4000284131?, 0x0?, 0x0?}) net/fd_posix.go:55 +0x28 fp=0x40003106e0 sp=0x4000310690 pc=0xaaaaded85628 net.(*conn).Read(0x4000056000, {0x4000284131?, 0x0?, 0x4000284128?}) net/net.go:189 +0x34 fp=0x4000310730 sp=0x40003106e0 pc=0xaaaaded8ea44 net.(*TCPConn).Read(0xaaaadf3ce0c0?, {0x4000284131?, 0x0?, 0x0?}) <autogenerated>:1 +0x2c fp=0x4000310760 sp=0x4000310730 pc=0xaaaaded9b67c net/http.(*connReader).backgroundRead(0x4000284120) net/http/server.go:690 +0x40 fp=0x40003107b0 sp=0x4000310760 pc=0xaaaadee85d30 net/http.(*connReader).startBackgroundRead.gowrap2() net/http/server.go:686 +0x28 fp=0x40003107d0 sp=0x40003107b0 pc=0xaaaadee85c18 runtime.goexit({}) runtime/asm_arm64.s:1223 +0x4 fp=0x40003107d0 sp=0x40003107d0 pc=0xaaaadecc94a4 created by net/http.(*connReader).startBackgroundRead in goroutine 483 net/http/server.go:686 +0xc4 r0 0x0 r1 0xb4 r2 0x6 r3 0xffff72450840 r4 0xffff8bd7cb58 r5 0xffff72451000 r6 0xffff72450840 r7 0x0 r8 0x83 r9 0xffffd291be75 r10 0x0 r11 0xa r12 0xb4 r13 0x1 r14 0x150 r15 0xaaab074260a8 r16 0x1 r17 0xffff84a7704c r18 0xe0 r19 0xb4 r20 0xffff72450840 r21 0x6 r22 0x1c1 r23 0xffffd291c1e8 r24 0xffffd291c208 r25 0x0 r26 0xffff148bf2b0 r27 0x0 r28 0xffff14c87550 r29 0xffffd291bef0 lr 0xffff84acf1ec sp 0xffffd291bef0 pc 0xffff84acf200 fault 0x0 ### OS Linux ### GPU Nvidia ### CPU Other ### Ollama version 0.5.4
GiteaMirror added the bug label 2026-04-12 16:29:51 -05:00
GiteaMirror commented 2026-04-12 16:29:53 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Jan 3, 2025):

Full log. Where did the model come from? How was it imported?

<!-- gh-comment-id:2568864801 --> @rick-github commented on GitHub (Jan 3, 2025): Full log. Where did the model come from? How was it imported?
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#5307
Delete Branch "%!s()"

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