[GH-ISSUE #1310] Ollama - The model ignored our prompt and didn't respond with the expected JSON #836

Closed
opened 2026-03-02 11:53:08 +03:00 by kerem · 3 comments
Owner

Originally created by @pixelpassport on GitHub (Apr 25, 2025).
Original GitHub issue: https://github.com/karakeep-app/karakeep/issues/1310

Describe the Bug

I really can't figure this one out. This setup was working previously with the same gemma3:1b model, the tags were great. Now I can't get the tagging to work at all. I did not update or change anything when it stopped working, though I have since changed to the 'latest' karakeep release tag. I have verified that ollama with gemma3:1b is working correctly inside the docker container, it is able to output JSON with no issues and has plenty of memory to spare.

Steps to Reproduce

Use any method to add a bookmark to karakeep. This also happens in the admin panel when I try to retag the bookmarks that have failed tagging.

Expected Behaviour

Previously it would take maybe 10 seconds and tags would be added to the bookmarks.

Screenshots or Additional Context

.env params:

OLLAMA_BASE_URL=http://localhost:11434
INFERENCE_TEXT_MODEL=gemma3:1b
INFERENCE_IMAGE_MODEL=llava-phi3:latest
INFERENCE_CONTEXT_LENGTH=2048
INFERENCE_JOB_TIMEOUT_SEC=90

docker compose log snippet:

ollama | time=2025-04-25T04:37:42.381Z level=WARN source=ggml.go:152 msg="key not found" key=general.alignment default=32
ollama | time=2025-04-25T04:37:42.406Z level=WARN source=ggml.go:152 msg="key not found" key=general.alignment default=32
ollama | time=2025-04-25T04:37:42.430Z level=WARN source=ggml.go:152 msg="key not found" key=general.alignment default=32
ollama | time=2025-04-25T04:37:42.431Z level=INFO source=server.go:105 msg="system memory" total="31.1 GiB" free="20.3 GiB" free_swap="768.7 MiB"
ollama | time=2025-04-25T04:37:42.431Z level=WARN source=ggml.go:152 msg="key not found" key=gemma3.vision.block_count default=0
ollama | time=2025-04-25T04:37:42.431Z level=INFO source=server.go:138 msg=offload library=cpu layers.requested=-1 layers.model=27 layers.offload=0 layers.split="" memory.available="[20.3 GiB]" memory.gpu_overhead="0 B" memory.required.full="1.3 GiB" memory.required.partial="0 B" memory.required.kv="71.0 MiB" memory.required.allocations="[1.3 GiB]" memory.weights.total="762.5 MiB" memory.weights.repeating="456.5 MiB" memory.weights.nonrepeating="306.0 MiB" memory.graph.full="514.2 MiB" memory.graph.partial="750.5 MiB"
ollama | time=2025-04-25T04:37:42.496Z level=WARN source=ggml.go:152 msg="key not found" key=general.alignment default=32
ollama | time=2025-04-25T04:37:42.498Z level=WARN source=ggml.go:152 msg="key not found" key=tokenizer.ggml.add_eot_token default=false
ollama | time=2025-04-25T04:37:42.500Z level=WARN source=ggml.go:152 msg="key not found" key=gemma3.vision.image_size default=0
ollama | time=2025-04-25T04:37:42.500Z level=WARN source=ggml.go:152 msg="key not found" key=gemma3.vision.patch_size default=0
ollama | time=2025-04-25T04:37:42.500Z level=WARN source=ggml.go:152 msg="key not found" key=gemma3.vision.num_channels default=0
ollama | time=2025-04-25T04:37:42.500Z level=WARN source=ggml.go:152 msg="key not found" key=gemma3.vision.block_count default=0
ollama | time=2025-04-25T04:37:42.500Z level=WARN source=ggml.go:152 msg="key not found" key=gemma3.vision.embedding_length default=0
ollama | time=2025-04-25T04:37:42.500Z level=WARN source=ggml.go:152 msg="key not found" key=gemma3.vision.attention.head_count default=0
ollama | time=2025-04-25T04:37:42.500Z level=WARN source=ggml.go:152 msg="key not found" key=gemma3.vision.image_size default=0
ollama | time=2025-04-25T04:37:42.500Z level=WARN source=ggml.go:152 msg="key not found" key=gemma3.vision.patch_size default=0
ollama | time=2025-04-25T04:37:42.500Z level=WARN source=ggml.go:152 msg="key not found" key=gemma3.vision.attention.layer_norm_epsilon default=0
ollama | time=2025-04-25T04:37:42.504Z level=WARN source=ggml.go:152 msg="key not found" key=gemma3.rope.freq_scale default=1
ollama | time=2025-04-25T04:37:42.504Z level=WARN source=ggml.go:152 msg="key not found" key=gemma3.mm_tokens_per_image default=256
ollama | time=2025-04-25T04:37:42.504Z level=INFO source=server.go:405 msg="starting llama server" cmd="/usr/bin/ollama runner --ollama-engine --model /root/.ollama/models/blobs/sha256-7cd4618c1faf8b7233c6c906dac1694b6a47684b37b8895d470ac688520b9c01 --ctx-size 4096 --batch-size 512 --threads 6 --no-mmap --parallel 4 --port 42413"
ollama | time=2025-04-25T04:37:42.504Z level=INFO source=sched.go:451 msg="loaded runners" count=1
ollama | time=2025-04-25T04:37:42.504Z level=INFO source=server.go:580 msg="waiting for llama runner to start responding"
ollama | time=2025-04-25T04:37:42.504Z level=INFO source=server.go:614 msg="waiting for server to become available" status="llm server error"
ollama | time=2025-04-25T04:37:42.511Z level=INFO source=runner.go:866 msg="starting ollama engine"
ollama | time=2025-04-25T04:37:42.512Z level=INFO source=runner.go:929 msg="Server listening on 127.0.0.1:42413"
ollama | time=2025-04-25T04:37:42.573Z level=WARN source=ggml.go:152 msg="key not found" key=general.alignment default=32
ollama | time=2025-04-25T04:37:42.573Z level=WARN source=ggml.go:152 msg="key not found" key=general.name default=""
ollama | time=2025-04-25T04:37:42.573Z level=WARN source=ggml.go:152 msg="key not found" key=general.description default=""
ollama | time=2025-04-25T04:37:42.573Z level=INFO source=ggml.go:72 msg="" architecture=gemma3 file_type=Q4_K_M name="" description="" num_tensors=340 num_key_values=32
ollama | load_backend: loaded CPU backend from /usr/lib/ollama/libggml-cpu-alderlake.so
ollama | time=2025-04-25T04:37:42.576Z level=INFO source=ggml.go:109 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX_VNNI=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 compiler=cgo(gcc)
ollama | time=2025-04-25T04:37:42.576Z level=INFO source=ggml.go:298 msg="model weights" buffer=CPU size="1.0 GiB"
ollama | time=2025-04-25T04:37:42.756Z level=INFO source=server.go:614 msg="waiting for server to become available" status="llm server loading model"
ollama | time=2025-04-25T04:37:42.800Z level=WARN source=ggml.go:152 msg="key not found" key=tokenizer.ggml.add_eot_token default=false
ollama | time=2025-04-25T04:37:42.801Z level=WARN source=ggml.go:152 msg="key not found" key=gemma3.vision.image_size default=0
ollama | time=2025-04-25T04:37:42.801Z level=WARN source=ggml.go:152 msg="key not found" key=gemma3.vision.patch_size default=0
ollama | time=2025-04-25T04:37:42.801Z level=WARN source=ggml.go:152 msg="key not found" key=gemma3.vision.num_channels default=0
ollama | time=2025-04-25T04:37:42.801Z level=WARN source=ggml.go:152 msg="key not found" key=gemma3.vision.block_count default=0
ollama | time=2025-04-25T04:37:42.801Z level=WARN source=ggml.go:152 msg="key not found" key=gemma3.vision.embedding_length default=0
ollama | time=2025-04-25T04:37:42.801Z level=WARN source=ggml.go:152 msg="key not found" key=gemma3.vision.attention.head_count default=0
ollama | time=2025-04-25T04:37:42.801Z level=WARN source=ggml.go:152 msg="key not found" key=gemma3.vision.image_size default=0
ollama | time=2025-04-25T04:37:42.801Z level=WARN source=ggml.go:152 msg="key not found" key=gemma3.vision.patch_size default=0
ollama | time=2025-04-25T04:37:42.801Z level=WARN source=ggml.go:152 msg="key not found" key=gemma3.vision.attention.layer_norm_epsilon default=0
ollama | time=2025-04-25T04:37:42.804Z level=WARN source=ggml.go:152 msg="key not found" key=gemma3.rope.freq_scale default=1
ollama | time=2025-04-25T04:37:42.804Z level=WARN source=ggml.go:152 msg="key not found" key=gemma3.mm_tokens_per_image default=256
ollama | time=2025-04-25T04:37:42.834Z level=INFO source=ggml.go:556 msg="compute graph" backend=CPU buffer_type=CPU size="36.2 MiB"
ollama | time=2025-04-25T04:37:43.006Z level=INFO source=server.go:619 msg="llama runner started in 0.50 seconds"
ollama | llama_model_loader: loaded meta data with 31 key-value pairs and 340 tensors from /root/.ollama/models/blobs/sha256-7cd4618c1faf8b7233c6c906dac1694b6a47684b37b8895d470ac688520b9c01 (version GGUF V3 (latest))
ollama | llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
ollama | llama_model_loader: - kv 0: gemma3.attention.head_count u32 = 4
ollama | llama_model_loader: - kv 1: gemma3.attention.head_count_kv u32 = 1
ollama | llama_model_loader: - kv 2: gemma3.attention.key_length u32 = 256
ollama | llama_model_loader: - kv 3: gemma3.attention.layer_norm_rms_epsilon f32 = 0.000001
ollama | llama_model_loader: - kv 4: gemma3.attention.sliding_window u32 = 512
ollama | llama_model_loader: - kv 5: gemma3.attention.value_length u32 = 256
ollama | llama_model_loader: - kv 6: gemma3.block_count u32 = 26
ollama | llama_model_loader: - kv 7: gemma3.context_length u32 = 32768
ollama | llama_model_loader: - kv 8: gemma3.embedding_length u32 = 1152
ollama | llama_model_loader: - kv 9: gemma3.feed_forward_length u32 = 6912
ollama | llama_model_loader: - kv 10: gemma3.final_logit_softcapping f32 = 30.000000
ollama | llama_model_loader: - kv 11: gemma3.rope.global.freq_base f32 = 1000000.000000
ollama | llama_model_loader: - kv 12: gemma3.rope.local.freq_base f32 = 10000.000000
ollama | llama_model_loader: - kv 13: general.architecture str = gemma3
ollama | llama_model_loader: - kv 14: tokenizer.chat_template str = {{ bos_token }}\n{%- if messages[0]['r...
ollama | llama_model_loader: - kv 15: tokenizer.ggml.add_bos_token bool = true
ollama | llama_model_loader: - kv 16: tokenizer.ggml.add_eos_token bool = false
ollama | llama_model_loader: - kv 17: tokenizer.ggml.add_padding_token bool = false
ollama | llama_model_loader: - kv 18: tokenizer.ggml.add_unknown_token bool = false
ollama | llama_model_loader: - kv 19: tokenizer.ggml.bos_token_id u32 = 2
ollama | llama_model_loader: - kv 20: tokenizer.ggml.eos_token_id u32 = 1
ollama | llama_model_loader: - kv 21: tokenizer.ggml.merges arr[str,514906] = ["\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n \n", ...
ollama | llama_model_loader: - kv 22: tokenizer.ggml.model str = llama
ollama | llama_model_loader: - kv 23: tokenizer.ggml.padding_token_id u32 = 0
ollama | llama_model_loader: - kv 24: tokenizer.ggml.pre str = default
ollama | llama_model_loader: - kv 25: tokenizer.ggml.scores arr[f32,262144] = [0.000000, 0.000000, 0.000000, 0.0000...
ollama | llama_model_loader: - kv 26: tokenizer.ggml.token_type arr[i32,262144] = [3, 3, 3, 2, 1, 1, 1, 1, 1, 1, 1, 1, ...
ollama | llama_model_loader: - kv 27: tokenizer.ggml.tokens arr[str,262144] = ["", "", "", "", ...
ollama | llama_model_loader: - kv 28: tokenizer.ggml.unknown_token_id u32 = 3
ollama | llama_model_loader: - kv 29: general.quantization_version u32 = 2
ollama | llama_model_loader: - kv 30: general.file_type u32 = 15
ollama | llama_model_loader: - type f32: 157 tensors
ollama | llama_model_loader: - type q5_0: 117 tensors
ollama | llama_model_loader: - type q8_0: 14 tensors
ollama | llama_model_loader: - type q4_K: 39 tensors
ollama | llama_model_loader: - type q6_K: 13 tensors
ollama | load: special_eos_id is not in special_eog_ids - the tokenizer config may be incorrect
ollama | load: special tokens cache size = 6
ollama | load: token to piece cache size = 1.9446 MB
ollama | ggml-alloc.c:819: GGML_ASSERT(talloc->buffer_id >= 0) failed
ollama | /usr/bin/ollama(+0x11021a8)[0x5630adf941a8]
ollama | /usr/bin/ollama(+0x1102526)[0x5630adf94526]
ollama | /usr/bin/ollama(+0x10ef8f5)[0x5630adf818f5]
ollama | /usr/bin/ollama(+0x10f101b)[0x5630adf8301b]
ollama | /usr/bin/ollama(+0x1116005)[0x5630adfa8005]
ollama | /usr/bin/ollama(+0x111645b)[0x5630adfa845b]
ollama | /usr/bin/ollama(+0x117071b)[0x5630ae00271b]
ollama | /usr/bin/ollama(+0x334801)[0x5630ad1c6801]
ollama | SIGABRT: abort
ollama | PC=0x7fae6709000b m=23 sigcode=18446744073709551610
ollama | signal arrived during cgo execution
ollama |
ollama | goroutine 6 gp=0xc000102e00 m=23 mp=0xc001b80808 [syscall]:
ollama | runtime.cgocall(0x5630ae002700, 0xc00011baf8)
ollama | runtime/cgocall.go:167 +0x4b fp=0xc00011bad0 sp=0xc00011ba98 pc=0x5630ad1bc14b
ollama | github.com/ollama/ollama/ml/backend/ggml._Cfunc_ggml_backend_sched_graph_compute_async(0x7fadf0000d40, 0x7fad74002e60)
ollama | _cgo_gotypes.go:516 +0x4a fp=0xc00011baf8 sp=0xc00011bad0 pc=0x5630ad5b96aa
ollama | github.com/ollama/ollama/ml/backend/ggml.(*Context).Compute.func1(...)
ollama | github.com/ollama/ollama/ml/backend/ggml/ggml.go:529
ollama | github.com/ollama/ollama/ml/backend/ggml.(*Context).Compute(0xc003a0a240, {0xc00366e390, 0x1, 0x0?})
ollama | github.com/ollama/ollama/ml/backend/ggml/ggml.go:529 +0x96 fp=0xc00011bb88 sp=0xc00011baf8 pc=0x5630ad5c2956
ollama | github.com/ollama/ollama/model.Forward({0x5630ae4c20b0, 0xc003a0a240}, {0x5630ae4b8a90, 0xc00344c000}, {0xc003671800, 0x200, 0x200}, {{0x5630ae4caab0, 0xc000010078}, {0x0, ...}, ...})
ollama | github.com/ollama/ollama/model/model.go:313 +0x2b8 fp=0xc00011bc70 sp=0xc00011bb88 pc=0x5630ad5f07d8
ollama | github.com/ollama/ollama/runner/ollamarunner.(*Server).processBatch(0xc0000f46c0)
ollama | github.com/ollama/ollama/runner/ollamarunner/runner.go:478 +0x476 fp=0xc00011bf98 sp=0xc00011bc70 pc=0x5630ad672ab6
ollama | github.com/ollama/ollama/runner/ollamarunner.(*Server).run(0xc0000f46c0, {0x5630ae4b9df0, 0xc0003fe960})
ollama | github.com/ollama/ollama/runner/ollamarunner/runner.go:364 +0x4e fp=0xc00011bfb8 sp=0xc00011bf98 pc=0x5630ad6725ee
ollama | github.com/ollama/ollama/runner/ollamarunner.Execute.gowrap2()
ollama | github.com/ollama/ollama/runner/ollamarunner/runner.go:906 +0x28 fp=0xc00011bfe0 sp=0xc00011bfb8 pc=0x5630ad6770e8
ollama | runtime.goexit({})
ollama | runtime/asm_amd64.s:1700 +0x1 fp=0xc00011bfe8 sp=0xc00011bfe0 pc=0x5630ad1c6b81
ollama | created by github.com/ollama/ollama/runner/ollamarunner.Execute in goroutine 1
ollama | github.com/ollama/ollama/runner/ollamarunner/runner.go:906 +0xb37
ollama |
ollama | goroutine 1 gp=0xc000002380 m=nil [IO wait]:
ollama | runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
ollama | runtime/proc.go:435 +0xce fp=0xc000117628 sp=0xc000117608 pc=0x5630ad1bf44e
ollama | runtime.netpollblock(0xc000117678?, 0xad158c06?, 0x30?)
ollama | runtime/netpoll.go:575 +0xf7 fp=0xc000117660 sp=0xc000117628 pc=0x5630ad184237
ollama | internal/poll.runtime_pollWait(0x7fae1e4fcde0, 0x72)
ollama | runtime/netpoll.go:351 +0x85 fp=0xc000117680 sp=0xc000117660 pc=0x5630ad1be665
ollama | internal/poll.(*pollDesc).wait(0xc000591380?, 0x900000036?, 0x0)
ollama | internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc0001176a8 sp=0xc000117680 pc=0x5630ad2459c7
ollama | internal/poll.(*pollDesc).waitRead(...)
ollama | internal/poll/fd_poll_runtime.go:89
ollama | internal/poll.(*FD).Accept(0xc000591380)
ollama | internal/poll/fd_unix.go:620 +0x295 fp=0xc000117750 sp=0xc0001176a8 pc=0x5630ad24ad95
ollama | net.(*netFD).accept(0xc000591380)
ollama | net/fd_unix.go:172 +0x29 fp=0xc000117808 sp=0xc000117750 pc=0x5630ad2bdba9
ollama | net.(*TCPListener).accept(0xc0000a9780)
ollama | net/tcpsock_posix.go:159 +0x1b fp=0xc000117858 sp=0xc000117808 pc=0x5630ad2d355b
ollama | net.(*TCPListener).Accept(0xc0000a9780)
ollama | net/tcpsock.go:380 +0x30 fp=0xc000117888 sp=0xc000117858 pc=0x5630ad2d2410
ollama | net/http.(*onceCloseListener).Accept(0xc000364090?)
ollama | :1 +0x24 fp=0xc0001178a0 sp=0xc000117888 pc=0x5630ad4e9a44
ollama | net/http.(*Server).Serve(0xc0001aa700, {0x5630ae4b7af8, 0xc0000a9780})
ollama | net/http/server.go:3424 +0x30c fp=0xc0001179d0 sp=0xc0001178a0 pc=0x5630ad4c130c
ollama | github.com/ollama/ollama/runner/ollamarunner.Execute({0xc0001aa030, 0xd, 0xd})
ollama | github.com/ollama/ollama/runner/ollamarunner/runner.go:930 +0xec9 fp=0xc000117d08 sp=0xc0001179d0 pc=0x5630ad676e49
ollama | github.com/ollama/ollama/runner.Execute({0xc0001aa010?, 0x0?, 0x0?})
ollama | github.com/ollama/ollama/runner/runner.go:20 +0xc9 fp=0xc000117d30 sp=0xc000117d08 pc=0x5630ad677ac9
ollama | github.com/ollama/ollama/cmd.NewCLI.func2(0xc000034e00?, {0x5630ae01e055?, 0x4?, 0x5630ae01e059?})
ollama | github.com/ollama/ollama/cmd/cmd.go:1365 +0x45 fp=0xc000117d58 sp=0xc000117d30 pc=0x5630addc6be5
ollama | github.com/spf13/cobra.(*Command).execute(0xc0000faf08, {0xc0000d75e0, 0xe, 0xe})
ollama | github.com/spf13/cobra@v1.7.0/command.go:940 +0x85c fp=0xc000117e78 sp=0xc000117d58 pc=0x5630ad3371fc
ollama | github.com/spf13/cobra.(*Command).ExecuteC(0xc0000d4908)
ollama | github.com/spf13/cobra@v1.7.0/command.go:1068 +0x3a5 fp=0xc000117f30 sp=0xc000117e78 pc=0x5630ad337a45
ollama | github.com/spf13/cobra.(*Command).Execute(...)
ollama | github.com/spf13/cobra@v1.7.0/command.go:992
ollama | github.com/spf13/cobra.(*Command).ExecuteContext(...)
ollama | github.com/spf13/cobra@v1.7.0/command.go:985
ollama | main.main()
ollama | github.com/ollama/ollama/main.go:12 +0x4d fp=0xc000117f50 sp=0xc000117f30 pc=0x5630addc6f4d
ollama | runtime.main()
ollama | runtime/proc.go:283 +0x29d fp=0xc000117fe0 sp=0xc000117f50 pc=0x5630ad18b83d
ollama | runtime.goexit({})
ollama | runtime/asm_amd64.s:1700 +0x1 fp=0xc000117fe8 sp=0xc000117fe0 pc=0x5630ad1c6b81
ollama |
ollama | goroutine 2 gp=0xc000002e00 m=nil [force gc (idle)]:
ollama | runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
ollama | runtime/proc.go:435 +0xce fp=0xc00007afa8 sp=0xc00007af88 pc=0x5630ad1bf44e
ollama | runtime.goparkunlock(...)
ollama | runtime/proc.go:441
ollama | runtime.forcegchelper()
ollama | runtime/proc.go:348 +0xb8 fp=0xc00007afe0 sp=0xc00007afa8 pc=0x5630ad18bb78
ollama | runtime.goexit({})
ollama | runtime/asm_amd64.s:1700 +0x1 fp=0xc00007afe8 sp=0xc00007afe0 pc=0x5630ad1c6b81
ollama | created by runtime.init.7 in goroutine 1
ollama | runtime/proc.go:336 +0x1a
ollama |
ollama | goroutine 3 gp=0xc000003340 m=nil [GC sweep wait]:
ollama | runtime.gopark(0x1?, 0x0?, 0x0?, 0x0?, 0x0?)
ollama | runtime/proc.go:435 +0xce fp=0xc00007b780 sp=0xc00007b760 pc=0x5630ad1bf44e
ollama | runtime.goparkunlock(...)
ollama | runtime/proc.go:441
ollama | runtime.bgsweep(0xc0000a6000)
ollama | runtime/mgcsweep.go:316 +0xdf fp=0xc00007b7c8 sp=0xc00007b780 pc=0x5630ad17623f
ollama | runtime.gcenable.gowrap1()
ollama | runtime/mgc.go:204 +0x25 fp=0xc00007b7e0 sp=0xc00007b7c8 pc=0x5630ad16a625
ollama | runtime.goexit({})
ollama | runtime/asm_amd64.s:1700 +0x1 fp=0xc00007b7e8 sp=0xc00007b7e0 pc=0x5630ad1c6b81
ollama | created by runtime.gcenable in goroutine 1
ollama | runtime/mgc.go:204 +0x66
ollama |
ollama | goroutine 4 gp=0xc000003500 m=nil [GC scavenge wait]:
ollama | runtime.gopark(0x10000?, 0x5630ae1d58c8?, 0x0?, 0x0?, 0x0?)
ollama | runtime/proc.go:435 +0xce fp=0xc00007bf78 sp=0xc00007bf58 pc=0x5630ad1bf44e
ollama | runtime.goparkunlock(...)
ollama | runtime/proc.go:441
ollama | runtime.(*scavengerState).park(0x5630aed20300)
ollama | runtime/mgcscavenge.go:425 +0x49 fp=0xc00007bfa8 sp=0xc00007bf78 pc=0x5630ad173c89
ollama | runtime.bgscavenge(0xc0000a6000)
ollama | runtime/mgcscavenge.go:658 +0x59 fp=0xc00007bfc8 sp=0xc00007bfa8 pc=0x5630ad174219
ollama | runtime.gcenable.gowrap2()
ollama | runtime/mgc.go:205 +0x25 fp=0xc00007bfe0 sp=0xc00007bfc8 pc=0x5630ad16a5c5
ollama | runtime.goexit({})
ollama | runtime/asm_amd64.s:1700 +0x1 fp=0xc00007bfe8 sp=0xc00007bfe0 pc=0x5630ad1c6b81
ollama | created by runtime.gcenable in goroutine 1
ollama | runtime/mgc.go:205 +0xa5
ollama |
ollama | goroutine 18 gp=0xc000186380 m=nil [finalizer wait]:
ollama | runtime.gopark(0x1b8?, 0xc000002380?, 0x1?, 0x23?, 0xc00007a688?)
ollama | runtime/proc.go:435 +0xce fp=0xc00007a630 sp=0xc00007a610 pc=0x5630ad1bf44e
ollama | runtime.runfinq()
ollama | runtime/mfinal.go:196 +0x107 fp=0xc00007a7e0 sp=0xc00007a630 pc=0x5630ad1695e7
ollama | runtime.goexit({})
ollama | runtime/asm_amd64.s:1700 +0x1 fp=0xc00007a7e8 sp=0xc00007a7e0 pc=0x5630ad1c6b81
ollama | created by runtime.createfing in goroutine 1
ollama | runtime/mfinal.go:166 +0x3d
ollama |
ollama | goroutine 19 gp=0xc000186e00 m=nil [chan receive]:
ollama | runtime.gopark(0xc00024d860?, 0xc0035b0048?, 0x60?, 0x67?, 0x5630ad2a48e8?)
ollama | runtime/proc.go:435 +0xce fp=0xc000076718 sp=0xc0000766f8 pc=0x5630ad1bf44e
ollama | runtime.chanrecv(0xc000182310, 0x0, 0x1)
ollama | runtime/chan.go:664 +0x445 fp=0xc000076790 sp=0xc000076718 pc=0x5630ad15b7e5
ollama | runtime.chanrecv1(0x0?, 0x0?)
ollama | runtime/chan.go:506 +0x12 fp=0xc0000767b8 sp=0xc000076790 pc=0x5630ad15b372
ollama | runtime.unique_runtime_registerUniqueMapCleanup.func2(...)
ollama | runtime/mgc.go:1796
ollama | runtime.unique_runtime_registerUniqueMapCleanup.gowrap1()
ollama | runtime/mgc.go:1799 +0x2f fp=0xc0000767e0 sp=0xc0000767b8 pc=0x5630ad16d7cf
ollama | runtime.goexit({})
ollama | runtime/asm_amd64.s:1700 +0x1 fp=0xc0000767e8 sp=0xc0000767e0 pc=0x5630ad1c6b81
ollama | created by unique.runtime_registerUniqueMapCleanup in goroutine 1
ollama | runtime/mgc.go:1794 +0x85
ollama |
ollama | goroutine 20 gp=0xc000187180 m=nil [GC worker (idle)]:
ollama | runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
ollama | runtime/proc.go:435 +0xce fp=0xc000076f38 sp=0xc000076f18 pc=0x5630ad1bf44e
ollama | runtime.gcBgMarkWorker(0xc000183730)
ollama | runtime/mgc.go:1423 +0xe9 fp=0xc000076fc8 sp=0xc000076f38 pc=0x5630ad16cae9
ollama | runtime.gcBgMarkStartWorkers.gowrap1()
ollama | runtime/mgc.go:1339 +0x25 fp=0xc000076fe0 sp=0xc000076fc8 pc=0x5630ad16c9c5
ollama | runtime.goexit({})
ollama | runtime/asm_amd64.s:1700 +0x1 fp=0xc000076fe8 sp=0xc000076fe0 pc=0x5630ad1c6b81
ollama | created by runtime.gcBgMarkStartWorkers in goroutine 1
ollama | runtime/mgc.go:1339 +0x105
ollama |
ollama | goroutine 21 gp=0xc000187340 m=nil [GC worker (idle)]:
ollama | runtime.gopark(0x925d7a23278?, 0x3?, 0x32?, 0x33?, 0x0?)
ollama | runtime/proc.go:435 +0xce fp=0xc000077738 sp=0xc000077718 pc=0x5630ad1bf44e
ollama | runtime.gcBgMarkWorker(0xc000183730)
ollama | runtime/mgc.go:1423 +0xe9 fp=0xc0000777c8 sp=0xc000077738 pc=0x5630ad16cae9
ollama | runtime.gcBgMarkStartWorkers.gowrap1()
ollama | runtime/mgc.go:1339 +0x25 fp=0xc0000777e0 sp=0xc0000777c8 pc=0x5630ad16c9c5
ollama | runtime.goexit({})
ollama | runtime/asm_amd64.s:1700 +0x1 fp=0xc0000777e8 sp=0xc0000777e0 pc=0x5630ad1c6b81
ollama | created by runtime.gcBgMarkStartWorkers in goroutine 1
ollama | runtime/mgc.go:1339 +0x105
ollama |
ollama | goroutine 22 gp=0xc000187500 m=nil [GC worker (idle)]:
ollama | runtime.gopark(0x925d798e990?, 0x1?, 0x36?, 0x5e?, 0x0?)
ollama | runtime/proc.go:435 +0xce fp=0xc000077f38 sp=0xc000077f18 pc=0x5630ad1bf44e
ollama | runtime.gcBgMarkWorker(0xc000183730)
ollama | runtime/mgc.go:1423 +0xe9 fp=0xc000077fc8 sp=0xc000077f38 pc=0x5630ad16cae9
ollama | runtime.gcBgMarkStartWorkers.gowrap1()
ollama | runtime/mgc.go:1339 +0x25 fp=0xc000077fe0 sp=0xc000077fc8 pc=0x5630ad16c9c5
ollama | runtime.goexit({})
ollama | runtime/asm_amd64.s:1700 +0x1 fp=0xc000077fe8 sp=0xc000077fe0 pc=0x5630ad1c6b81
ollama | created by runtime.gcBgMarkStartWorkers in goroutine 1
ollama | runtime/mgc.go:1339 +0x105
ollama |
ollama | goroutine 23 gp=0xc0001876c0 m=nil [GC worker (idle)]:
ollama | runtime.gopark(0x925d798eacc?, 0x1?, 0xc8?, 0x3c?, 0x0?)
ollama | runtime/proc.go:435 +0xce fp=0xc000078738 sp=0xc000078718 pc=0x5630ad1bf44e
ollama | runtime.gcBgMarkWorker(0xc000183730)
ollama | runtime/mgc.go:1423 +0xe9 fp=0xc0000787c8 sp=0xc000078738 pc=0x5630ad16cae9
ollama | runtime.gcBgMarkStartWorkers.gowrap1()
ollama | runtime/mgc.go:1339 +0x25 fp=0xc0000787e0 sp=0xc0000787c8 pc=0x5630ad16c9c5
ollama | runtime.goexit({})
ollama | runtime/asm_amd64.s:1700 +0x1 fp=0xc0000787e8 sp=0xc0000787e0 pc=0x5630ad1c6b81
ollama | created by runtime.gcBgMarkStartWorkers in goroutine 1
ollama | runtime/mgc.go:1339 +0x105
ollama |
ollama | goroutine 24 gp=0xc000187880 m=nil [GC worker (idle)]:
ollama | runtime.gopark(0x925d798eb85?, 0x1?, 0x95?, 0x4f?, 0x0?)
ollama | runtime/proc.go:435 +0xce fp=0xc000078f38 sp=0xc000078f18 pc=0x5630ad1bf44e
ollama | runtime.gcBgMarkWorker(0xc000183730)
ollama | runtime/mgc.go:1423 +0xe9 fp=0xc000078fc8 sp=0xc000078f38 pc=0x5630ad16cae9
ollama | runtime.gcBgMarkStartWorkers.gowrap1()
ollama | runtime/mgc.go:1339 +0x25 fp=0xc000078fe0 sp=0xc000078fc8 pc=0x5630ad16c9c5
ollama | runtime.goexit({})
ollama | runtime/asm_amd64.s:1700 +0x1 fp=0xc000078fe8 sp=0xc000078fe0 pc=0x5630ad1c6b81
ollama | created by runtime.gcBgMarkStartWorkers in goroutine 1
ollama | runtime/mgc.go:1339 +0x105
ollama |
ollama | goroutine 25 gp=0xc000187a40 m=nil [GC worker (idle)]:
ollama | runtime.gopark(0x925d798e8bc?, 0x3?, 0x25?, 0x33?, 0x0?)
ollama | runtime/proc.go:435 +0xce fp=0xc000079738 sp=0xc000079718 pc=0x5630ad1bf44e
ollama | runtime.gcBgMarkWorker(0xc000183730)
ollama | runtime/mgc.go:1423 +0xe9 fp=0xc0000797c8 sp=0xc000079738 pc=0x5630ad16cae9
ollama | runtime.gcBgMarkStartWorkers.gowrap1()
ollama | runtime/mgc.go:1339 +0x25 fp=0xc0000797e0 sp=0xc0000797c8 pc=0x5630ad16c9c5
ollama | runtime.goexit({})
ollama | runtime/asm_amd64.s:1700 +0x1 fp=0xc0000797e8 sp=0xc0000797e0 pc=0x5630ad1c6b81
ollama | created by runtime.gcBgMarkStartWorkers in goroutine 1
ollama | runtime/mgc.go:1339 +0x105
ollama |
ollama | goroutine 26 gp=0xc000187c00 m=nil [GC worker (idle)]:
ollama | runtime.gopark(0x5630aedceb40?, 0x1?, 0xed?, 0x4b?, 0x0?)
ollama | runtime/proc.go:435 +0xce fp=0xc000079f38 sp=0xc000079f18 pc=0x5630ad1bf44e
ollama | runtime.gcBgMarkWorker(0xc000183730)
ollama | runtime/mgc.go:1423 +0xe9 fp=0xc000079fc8 sp=0xc000079f38 pc=0x5630ad16cae9
ollama | runtime.gcBgMarkStartWorkers.gowrap1()
ollama | runtime/mgc.go:1339 +0x25 fp=0xc000079fe0 sp=0xc000079fc8 pc=0x5630ad16c9c5
ollama | runtime.goexit({})
ollama | runtime/asm_amd64.s:1700 +0x1 fp=0xc000079fe8 sp=0xc000079fe0 pc=0x5630ad1c6b81
ollama | created by runtime.gcBgMarkStartWorkers in goroutine 1
ollama | runtime/mgc.go:1339 +0x105
ollama |
ollama | goroutine 27 gp=0xc000187dc0 m=nil [GC worker (idle)]:
ollama | runtime.gopark(0x925d7a18b7d?, 0x3?, 0xf6?, 0xf9?, 0x0?)
ollama | runtime/proc.go:435 +0xce fp=0xc0004f6738 sp=0xc0004f6718 pc=0x5630ad1bf44e
ollama | runtime.gcBgMarkWorker(0xc000183730)
ollama | runtime/mgc.go:1423 +0xe9 fp=0xc0004f67c8 sp=0xc0004f6738 pc=0x5630ad16cae9
ollama | runtime.gcBgMarkStartWorkers.gowrap1()
ollama | runtime/mgc.go:1339 +0x25 fp=0xc0004f67e0 sp=0xc0004f67c8 pc=0x5630ad16c9c5
ollama | runtime.goexit({})
ollama | runtime/asm_amd64.s:1700 +0x1 fp=0xc0004f67e8 sp=0xc0004f67e0 pc=0x5630ad1c6b81
ollama | created by runtime.gcBgMarkStartWorkers in goroutine 1
ollama | runtime/mgc.go:1339 +0x105
ollama |
ollama | goroutine 28 gp=0xc0004fa000 m=nil [GC worker (idle)]:
ollama | runtime.gopark(0x925d7a2a22f?, 0x3?, 0x35?, 0x4b?, 0x0?)
ollama | runtime/proc.go:435 +0xce fp=0xc0004f6f38 sp=0xc0004f6f18 pc=0x5630ad1bf44e
ollama | runtime.gcBgMarkWorker(0xc000183730)
ollama | runtime/mgc.go:1423 +0xe9 fp=0xc0004f6fc8 sp=0xc0004f6f38 pc=0x5630ad16cae9
ollama | runtime.gcBgMarkStartWorkers.gowrap1()
ollama | runtime/mgc.go:1339 +0x25 fp=0xc0004f6fe0 sp=0xc0004f6fc8 pc=0x5630ad16c9c5
ollama | runtime.goexit({})
ollama | runtime/asm_amd64.s:1700 +0x1 fp=0xc0004f6fe8 sp=0xc0004f6fe0 pc=0x5630ad1c6b81
ollama | created by runtime.gcBgMarkStartWorkers in goroutine 1
ollama | runtime/mgc.go:1339 +0x105
ollama |
ollama | goroutine 29 gp=0xc0004fa1c0 m=nil [GC worker (idle)]:
ollama | runtime.gopark(0x925d798e9c6?, 0x3?, 0xa2?, 0x81?, 0x0?)
ollama | runtime/proc.go:435 +0xce fp=0xc0004f7738 sp=0xc0004f7718 pc=0x5630ad1bf44e
ollama | runtime.gcBgMarkWorker(0xc000183730)
ollama | runtime/mgc.go:1423 +0xe9 fp=0xc0004f77c8 sp=0xc0004f7738 pc=0x5630ad16cae9
ollama | runtime.gcBgMarkStartWorkers.gowrap1()
ollama | runtime/mgc.go:1339 +0x25 fp=0xc0004f77e0 sp=0xc0004f77c8 pc=0x5630ad16c9c5
ollama | runtime.goexit({})
ollama | runtime/asm_amd64.s:1700 +0x1 fp=0xc0004f77e8 sp=0xc0004f77e0 pc=0x5630ad1c6b81
ollama | created by runtime.gcBgMarkStartWorkers in goroutine 1
ollama | runtime/mgc.go:1339 +0x105
ollama |
ollama | goroutine 30 gp=0xc0004fa380 m=nil [GC worker (idle)]:
ollama | runtime.gopark(0x925d798e092?, 0x3?, 0x7c?, 0x25?, 0x0?)
ollama | runtime/proc.go:435 +0xce fp=0xc0004f7f38 sp=0xc0004f7f18 pc=0x5630ad1bf44e
ollama | runtime.gcBgMarkWorker(0xc000183730)
ollama | runtime/mgc.go:1423 +0xe9 fp=0xc0004f7fc8 sp=0xc0004f7f38 pc=0x5630ad16cae9
ollama | runtime.gcBgMarkStartWorkers.gowrap1()
ollama | runtime/mgc.go:1339 +0x25 fp=0xc0004f7fe0 sp=0xc0004f7fc8 pc=0x5630ad16c9c5
ollama | runtime.goexit({})
ollama | runtime/asm_amd64.s:1700 +0x1 fp=0xc0004f7fe8 sp=0xc0004f7fe0 pc=0x5630ad1c6b81
ollama | created by runtime.gcBgMarkStartWorkers in goroutine 1
ollama | runtime/mgc.go:1339 +0x105
ollama |
ollama | goroutine 31 gp=0xc0004fa540 m=nil [GC worker (idle)]:
ollama | runtime.gopark(0x925d7a45d26?, 0x3?, 0x1a?, 0x6c?, 0x0?)
ollama | runtime/proc.go:435 +0xce fp=0xc0004f8738 sp=0xc0004f8718 pc=0x5630ad1bf44e
ollama | runtime.gcBgMarkWorker(0xc000183730)
ollama | runtime/mgc.go:1423 +0xe9 fp=0xc0004f87c8 sp=0xc0004f8738 pc=0x5630ad16cae9
ollama | runtime.gcBgMarkStartWorkers.gowrap1()
ollama | runtime/mgc.go:1339 +0x25 fp=0xc0004f87e0 sp=0xc0004f87c8 pc=0x5630ad16c9c5
ollama | runtime.goexit({})
ollama | runtime/asm_amd64.s:1700 +0x1 fp=0xc0004f87e8 sp=0xc0004f87e0 pc=0x5630ad1c6b81
ollama | created by runtime.gcBgMarkStartWorkers in goroutine 1
ollama | runtime/mgc.go:1339 +0x105
ollama |
ollama | goroutine 32 gp=0xc0004fa700 m=nil [GC worker (idle)]:
ollama | runtime.gopark(0x925d798e330?, 0x3?, 0x79?, 0xe?, 0x0?)
ollama | runtime/proc.go:435 +0xce fp=0xc0004f8f38 sp=0xc0004f8f18 pc=0x5630ad1bf44e
ollama | runtime.gcBgMarkWorker(0xc000183730)
ollama | runtime/mgc.go:1423 +0xe9 fp=0xc0004f8fc8 sp=0xc0004f8f38 pc=0x5630ad16cae9
ollama | runtime.gcBgMarkStartWorkers.gowrap1()
ollama | runtime/mgc.go:1339 +0x25 fp=0xc0004f8fe0 sp=0xc0004f8fc8 pc=0x5630ad16c9c5
ollama | runtime.goexit({})
ollama | runtime/asm_amd64.s:1700 +0x1 fp=0xc0004f8fe8 sp=0xc0004f8fe0 pc=0x5630ad1c6b81
ollama | created by runtime.gcBgMarkStartWorkers in goroutine 1
ollama | runtime/mgc.go:1339 +0x105
ollama |
ollama | goroutine 33 gp=0xc0004fa8c0 m=nil [GC worker (idle)]:
ollama | runtime.gopark(0x925d798ea44?, 0x3?, 0x6b?, 0xea?, 0x0?)
ollama | runtime/proc.go:435 +0xce fp=0xc0004f9738 sp=0xc0004f9718 pc=0x5630ad1bf44e
ollama | runtime.gcBgMarkWorker(0xc000183730)
ollama | runtime/mgc.go:1423 +0xe9 fp=0xc0004f97c8 sp=0xc0004f9738 pc=0x5630ad16cae9
ollama | runtime.gcBgMarkStartWorkers.gowrap1()
ollama | runtime/mgc.go:1339 +0x25 fp=0xc0004f97e0 sp=0xc0004f97c8 pc=0x5630ad16c9c5
ollama | runtime.goexit({})
ollama | runtime/asm_amd64.s:1700 +0x1 fp=0xc0004f97e8 sp=0xc0004f97e0 pc=0x5630ad1c6b81
ollama | created by runtime.gcBgMarkStartWorkers in goroutine 1
ollama | runtime/mgc.go:1339 +0x105
ollama |
ollama | goroutine 34 gp=0xc0004faa80 m=nil [GC worker (idle)]:
ollama | runtime.gopark(0x925d798e2ba?, 0x3?, 0x2c?, 0x9?, 0x0?)
ollama | runtime/proc.go:435 +0xce fp=0xc0004f9f38 sp=0xc0004f9f18 pc=0x5630ad1bf44e
ollama | runtime.gcBgMarkWorker(0xc000183730)
ollama | runtime/mgc.go:1423 +0xe9 fp=0xc0004f9fc8 sp=0xc0004f9f38 pc=0x5630ad16cae9
ollama | runtime.gcBgMarkStartWorkers.gowrap1()
ollama | runtime/mgc.go:1339 +0x25 fp=0xc0004f9fe0 sp=0xc0004f9fc8 pc=0x5630ad16c9c5
ollama | runtime.goexit({})
ollama | runtime/asm_amd64.s:1700 +0x1 fp=0xc0004f9fe8 sp=0xc0004f9fe0 pc=0x5630ad1c6b81
ollama | created by runtime.gcBgMarkStartWorkers in goroutine 1
ollama | runtime/mgc.go:1339 +0x105
ollama |
ollama | goroutine 35 gp=0xc0004fac40 m=nil [GC worker (idle)]:
ollama | runtime.gopark(0x925d798e937?, 0x1?, 0x76?, 0x1a?, 0x0?)
ollama | runtime/proc.go:435 +0xce fp=0xc0004f2738 sp=0xc0004f2718 pc=0x5630ad1bf44e
ollama | runtime.gcBgMarkWorker(0xc000183730)
ollama | runtime/mgc.go:1423 +0xe9 fp=0xc0004f27c8 sp=0xc0004f2738 pc=0x5630ad16cae9
ollama | runtime.gcBgMarkStartWorkers.gowrap1()
ollama | runtime/mgc.go:1339 +0x25 fp=0xc0004f27e0 sp=0xc0004f27c8 pc=0x5630ad16c9c5
ollama | runtime.goexit({})
ollama | runtime/asm_amd64.s:1700 +0x1 fp=0xc0004f27e8 sp=0xc0004f27e0 pc=0x5630ad1c6b81
ollama | created by runtime.gcBgMarkStartWorkers in goroutine 1
ollama | runtime/mgc.go:1339 +0x105
ollama |
ollama | goroutine 470 gp=0xc000582fc0 m=nil [select]:
ollama | runtime.gopark(0xc000045a28?, 0x2?, 0x0?, 0x87?, 0xc000045894?)
ollama | runtime/proc.go:435 +0xce fp=0xc0000456a8 sp=0xc000045688 pc=0x5630ad1bf44e
ollama | runtime.selectgo(0xc000045a28, 0xc000045890, 0x328?, 0x0, 0x4?, 0x1)
ollama | runtime/select.go:351 +0x837 fp=0xc0000457e0 sp=0xc0000456a8 pc=0x5630ad19dd37
ollama | github.com/ollama/ollama/runner/ollamarunner.(*Server).completion(0xc0000f46c0, {0x5630ae4b7cd8, 0xc0031fe000}, 0xc0005a03c0)
ollama | github.com/ollama/ollama/runner/ollamarunner/runner.go:677 +0xb05 fp=0xc000045ac0 sp=0xc0000457e0 pc=0x5630ad674dc5
ollama | github.com/ollama/ollama/runner/ollamarunner.(*Server).completion-fm({0x5630ae4b7cd8?, 0xc0031fe000?}, 0xc00011bb40?)
ollama | :1 +0x36 fp=0xc000045af0 sp=0xc000045ac0 pc=0x5630ad677936
ollama | net/http.HandlerFunc.ServeHTTP(0xc0000c9680?, {0x5630ae4b7cd8?, 0xc0031fe000?}, 0xc00011bb60?)
ollama | net/http/server.go:2294 +0x29 fp=0xc000045b18 sp=0xc000045af0 pc=0x5630ad4bd949
ollama | net/http.(*ServeMux).ServeHTTP(0x5630ad163b05?, {0x5630ae4b7cd8, 0xc0031fe000}, 0xc0005a03c0)
ollama | net/http/server.go:2822 +0x1c4 fp=0xc000045b68 sp=0xc000045b18 pc=0x5630ad4bf844
ollama | net/http.serverHandler.ServeHTTP({0x5630ae4b43b0?}, {0x5630ae4b7cd8?, 0xc0031fe000?}, 0x1?)
ollama | net/http/server.go:3301 +0x8e fp=0xc000045b98 sp=0xc000045b68 pc=0x5630ad4dd2ce
ollama | net/http.(*conn).serve(0xc000364090, {0x5630ae4b9db8, 0xc0003e45d0})
ollama | net/http/server.go:2102 +0x625 fp=0xc000045fb8 sp=0xc000045b98 pc=0x5630ad4bbe45
ollama | net/http.(*Server).Serve.gowrap3()
ollama | net/http/server.go:3454 +0x28 fp=0xc000045fe0 sp=0xc000045fb8 pc=0x5630ad4c1708
ollama | runtime.goexit({})
ollama | runtime/asm_amd64.s:1700 +0x1 fp=0xc000045fe8 sp=0xc000045fe0 pc=0x5630ad1c6b81
ollama | created by net/http.(*Server).Serve in goroutine 1
ollama | net/http/server.go:3454 +0x485
ollama |
ollama | goroutine 356 gp=0xc000583340 m=nil [IO wait]:
ollama | runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0xb?)
ollama | runtime/proc.go:435 +0xce fp=0xc00304d5d8 sp=0xc00304d5b8 pc=0x5630ad1bf44e
ollama | runtime.netpollblock(0x5630ad1e27b8?, 0xad158c06?, 0x30?)
ollama | runtime/netpoll.go:575 +0xf7 fp=0xc00304d610 sp=0xc00304d5d8 pc=0x5630ad184237
ollama | internal/poll.runtime_pollWait(0x7fae1e4fcbb0, 0x72)
ollama | runtime/netpoll.go:351 +0x85 fp=0xc00304d630 sp=0xc00304d610 pc=0x5630ad1be665
ollama | internal/poll.(*pollDesc).wait(0xc003692300?, 0xc0038ae251?, 0x0)
ollama | internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc00304d658 sp=0xc00304d630 pc=0x5630ad2459c7
ollama | internal/poll.(*pollDesc).waitRead(...)
ollama | internal/poll/fd_poll_runtime.go:89
ollama | internal/poll.(*FD).Read(0xc003692300, {0xc0038ae251, 0x1, 0x1})
ollama | internal/poll/fd_unix.go:165 +0x27a fp=0xc00304d6f0 sp=0xc00304d658 pc=0x5630ad246cba
ollama | net.(*netFD).Read(0xc003692300, {0xc0038ae251?, 0xc003014058?, 0xc00304d770?})
ollama | net/fd_posix.go:55 +0x25 fp=0xc00304d738 sp=0xc00304d6f0 pc=0x5630ad2bbc05
ollama | net.(*conn).Read(0xc00007e090, {0xc0038ae251?, 0xc003015a40?, 0x5630ad544e20?})
ollama | net/net.go:194 +0x45 fp=0xc00304d780 sp=0xc00304d738 pc=0x5630ad2c9fc5
ollama | net/http.(*connReader).backgroundRead(0xc0038ae240)
ollama | net/http/server.go:690 +0x37 fp=0xc00304d7c8 sp=0xc00304d780 pc=0x5630ad4b5d17
ollama | net/http.(*connReader).startBackgroundRead.gowrap2()
ollama | net/http/server.go:686 +0x25 fp=0xc00304d7e0 sp=0xc00304d7c8 pc=0x5630ad4b5c45
ollama | runtime.goexit({})
ollama | runtime/asm_amd64.s:1700 +0x1 fp=0xc00304d7e8 sp=0xc00304d7e0 pc=0x5630ad1c6b81
ollama | created by net/http.(*connReader).startBackgroundRead in goroutine 470
ollama | net/http/server.go:686 +0xb6
ollama |
ollama | rax 0x0
ollama | rbx 0x7fadd8ff9700
ollama | rcx 0x7fae6709000b
ollama | rdx 0x0
ollama | rdi 0x2
ollama | rsi 0x7fadd8ff8930
ollama | rbp 0x5630ae1f335d
ollama | rsp 0x7fadd8ff8930
ollama | r8 0x0
ollama | r9 0x7fadd8ff8930
ollama | r10 0x8
ollama | r11 0x246
ollama | r12 0x5630ae2190ab
ollama | r13 0x333
ollama | r14 0x46f
ollama | r15 0x7fadf002a2a0
ollama | rip 0x7fae6709000b
ollama | rflags 0x246
ollama | cs 0x33
ollama | fs 0x0
ollama | gs 0x0
ollama | [GIN] 2025/04/25 - 04:37:43 | 200 | 984.934538ms | ::1 | POST "/api/chat"
ollama | time=2025-04-25T04:37:43.335Z level=ERROR source=server.go:449 msg="llama runner terminated" error="exit status 2"
web-1 | 2025-04-25T04:37:43.336Z warn: Got an exception from ollama, will still attempt to deserialize the response we got so far: Error: POST predict: Post "http://127.0.0.1:42413/completion": EOF
web-1 | 2025-04-25T04:37:43.336Z error: [inference][622] inference job failed: Error: [inference][622] The model ignored our prompt and didn't respond with the expected JSON: {}. Here's a sneak peak from the response:
web-1 | Error: [inference][622] The model ignored our prompt and didn't respond with the expected JSON: {}. Here's a sneak peak from the response:
web-1 | at inferTags (/app/apps/workers/openaiWorker.ts:6:4346)
web-1 | at process.processTicksAndRejections (node:internal/process/task_queues:105:5)
web-1 | at async Object.runOpenAI [as run] (/app/apps/workers/openaiWorker.ts:6:6868)
web-1 | at async Runner.runOnce (/app/apps/workers/node_modules/.pnpm/liteque@0.3.2_better-sqlite3@11.3.0/node_modules/liteque/dist/runner.js:2:2656)

Device Details

docker container on debian 12 server

Exact Karakeep Version

0.23.1

Have you checked the troubleshooting guide?

  • I have checked the troubleshooting guide and I haven't found a solution to my problem
Originally created by @pixelpassport on GitHub (Apr 25, 2025). Original GitHub issue: https://github.com/karakeep-app/karakeep/issues/1310 ### Describe the Bug I really can't figure this one out. This setup was working previously with the same gemma3:1b model, the tags were great. Now I can't get the tagging to work at all. I did not update or change anything when it stopped working, though I have since changed to the 'latest' karakeep release tag. I have verified that ollama with gemma3:1b is working correctly inside the docker container, it is able to output JSON with no issues and has plenty of memory to spare. ### Steps to Reproduce Use any method to add a bookmark to karakeep. This also happens in the admin panel when I try to retag the bookmarks that have failed tagging. ### Expected Behaviour Previously it would take maybe 10 seconds and tags would be added to the bookmarks. ### Screenshots or Additional Context .env params: OLLAMA_BASE_URL=http://localhost:11434 INFERENCE_TEXT_MODEL=gemma3:1b INFERENCE_IMAGE_MODEL=llava-phi3:latest INFERENCE_CONTEXT_LENGTH=2048 INFERENCE_JOB_TIMEOUT_SEC=90 docker compose log snippet: ollama | time=2025-04-25T04:37:42.381Z level=WARN source=ggml.go:152 msg="key not found" key=general.alignment default=32 ollama | time=2025-04-25T04:37:42.406Z level=WARN source=ggml.go:152 msg="key not found" key=general.alignment default=32 ollama | time=2025-04-25T04:37:42.430Z level=WARN source=ggml.go:152 msg="key not found" key=general.alignment default=32 ollama | time=2025-04-25T04:37:42.431Z level=INFO source=server.go:105 msg="system memory" total="31.1 GiB" free="20.3 GiB" free_swap="768.7 MiB" ollama | time=2025-04-25T04:37:42.431Z level=WARN source=ggml.go:152 msg="key not found" key=gemma3.vision.block_count default=0 ollama | time=2025-04-25T04:37:42.431Z level=INFO source=server.go:138 msg=offload library=cpu layers.requested=-1 layers.model=27 layers.offload=0 layers.split="" memory.available="[20.3 GiB]" memory.gpu_overhead="0 B" memory.required.full="1.3 GiB" memory.required.partial="0 B" memory.required.kv="71.0 MiB" memory.required.allocations="[1.3 GiB]" memory.weights.total="762.5 MiB" memory.weights.repeating="456.5 MiB" memory.weights.nonrepeating="306.0 MiB" memory.graph.full="514.2 MiB" memory.graph.partial="750.5 MiB" ollama | time=2025-04-25T04:37:42.496Z level=WARN source=ggml.go:152 msg="key not found" key=general.alignment default=32 ollama | time=2025-04-25T04:37:42.498Z level=WARN source=ggml.go:152 msg="key not found" key=tokenizer.ggml.add_eot_token default=false ollama | time=2025-04-25T04:37:42.500Z level=WARN source=ggml.go:152 msg="key not found" key=gemma3.vision.image_size default=0 ollama | time=2025-04-25T04:37:42.500Z level=WARN source=ggml.go:152 msg="key not found" key=gemma3.vision.patch_size default=0 ollama | time=2025-04-25T04:37:42.500Z level=WARN source=ggml.go:152 msg="key not found" key=gemma3.vision.num_channels default=0 ollama | time=2025-04-25T04:37:42.500Z level=WARN source=ggml.go:152 msg="key not found" key=gemma3.vision.block_count default=0 ollama | time=2025-04-25T04:37:42.500Z level=WARN source=ggml.go:152 msg="key not found" key=gemma3.vision.embedding_length default=0 ollama | time=2025-04-25T04:37:42.500Z level=WARN source=ggml.go:152 msg="key not found" key=gemma3.vision.attention.head_count default=0 ollama | time=2025-04-25T04:37:42.500Z level=WARN source=ggml.go:152 msg="key not found" key=gemma3.vision.image_size default=0 ollama | time=2025-04-25T04:37:42.500Z level=WARN source=ggml.go:152 msg="key not found" key=gemma3.vision.patch_size default=0 ollama | time=2025-04-25T04:37:42.500Z level=WARN source=ggml.go:152 msg="key not found" key=gemma3.vision.attention.layer_norm_epsilon default=0 ollama | time=2025-04-25T04:37:42.504Z level=WARN source=ggml.go:152 msg="key not found" key=gemma3.rope.freq_scale default=1 ollama | time=2025-04-25T04:37:42.504Z level=WARN source=ggml.go:152 msg="key not found" key=gemma3.mm_tokens_per_image default=256 ollama | time=2025-04-25T04:37:42.504Z level=INFO source=server.go:405 msg="starting llama server" cmd="/usr/bin/ollama runner --ollama-engine --model /root/.ollama/models/blobs/sha256-7cd4618c1faf8b7233c6c906dac1694b6a47684b37b8895d470ac688520b9c01 --ctx-size 4096 --batch-size 512 --threads 6 --no-mmap --parallel 4 --port 42413" ollama | time=2025-04-25T04:37:42.504Z level=INFO source=sched.go:451 msg="loaded runners" count=1 ollama | time=2025-04-25T04:37:42.504Z level=INFO source=server.go:580 msg="waiting for llama runner to start responding" ollama | time=2025-04-25T04:37:42.504Z level=INFO source=server.go:614 msg="waiting for server to become available" status="llm server error" ollama | time=2025-04-25T04:37:42.511Z level=INFO source=runner.go:866 msg="starting ollama engine" ollama | time=2025-04-25T04:37:42.512Z level=INFO source=runner.go:929 msg="Server listening on 127.0.0.1:42413" ollama | time=2025-04-25T04:37:42.573Z level=WARN source=ggml.go:152 msg="key not found" key=general.alignment default=32 ollama | time=2025-04-25T04:37:42.573Z level=WARN source=ggml.go:152 msg="key not found" key=general.name default="" ollama | time=2025-04-25T04:37:42.573Z level=WARN source=ggml.go:152 msg="key not found" key=general.description default="" ollama | time=2025-04-25T04:37:42.573Z level=INFO source=ggml.go:72 msg="" architecture=gemma3 file_type=Q4_K_M name="" description="" num_tensors=340 num_key_values=32 ollama | load_backend: loaded CPU backend from /usr/lib/ollama/libggml-cpu-alderlake.so ollama | time=2025-04-25T04:37:42.576Z level=INFO source=ggml.go:109 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX_VNNI=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 compiler=cgo(gcc) ollama | time=2025-04-25T04:37:42.576Z level=INFO source=ggml.go:298 msg="model weights" buffer=CPU size="1.0 GiB" ollama | time=2025-04-25T04:37:42.756Z level=INFO source=server.go:614 msg="waiting for server to become available" status="llm server loading model" ollama | time=2025-04-25T04:37:42.800Z level=WARN source=ggml.go:152 msg="key not found" key=tokenizer.ggml.add_eot_token default=false ollama | time=2025-04-25T04:37:42.801Z level=WARN source=ggml.go:152 msg="key not found" key=gemma3.vision.image_size default=0 ollama | time=2025-04-25T04:37:42.801Z level=WARN source=ggml.go:152 msg="key not found" key=gemma3.vision.patch_size default=0 ollama | time=2025-04-25T04:37:42.801Z level=WARN source=ggml.go:152 msg="key not found" key=gemma3.vision.num_channels default=0 ollama | time=2025-04-25T04:37:42.801Z level=WARN source=ggml.go:152 msg="key not found" key=gemma3.vision.block_count default=0 ollama | time=2025-04-25T04:37:42.801Z level=WARN source=ggml.go:152 msg="key not found" key=gemma3.vision.embedding_length default=0 ollama | time=2025-04-25T04:37:42.801Z level=WARN source=ggml.go:152 msg="key not found" key=gemma3.vision.attention.head_count default=0 ollama | time=2025-04-25T04:37:42.801Z level=WARN source=ggml.go:152 msg="key not found" key=gemma3.vision.image_size default=0 ollama | time=2025-04-25T04:37:42.801Z level=WARN source=ggml.go:152 msg="key not found" key=gemma3.vision.patch_size default=0 ollama | time=2025-04-25T04:37:42.801Z level=WARN source=ggml.go:152 msg="key not found" key=gemma3.vision.attention.layer_norm_epsilon default=0 ollama | time=2025-04-25T04:37:42.804Z level=WARN source=ggml.go:152 msg="key not found" key=gemma3.rope.freq_scale default=1 ollama | time=2025-04-25T04:37:42.804Z level=WARN source=ggml.go:152 msg="key not found" key=gemma3.mm_tokens_per_image default=256 ollama | time=2025-04-25T04:37:42.834Z level=INFO source=ggml.go:556 msg="compute graph" backend=CPU buffer_type=CPU size="36.2 MiB" ollama | time=2025-04-25T04:37:43.006Z level=INFO source=server.go:619 msg="llama runner started in 0.50 seconds" ollama | llama_model_loader: loaded meta data with 31 key-value pairs and 340 tensors from /root/.ollama/models/blobs/sha256-7cd4618c1faf8b7233c6c906dac1694b6a47684b37b8895d470ac688520b9c01 (version GGUF V3 (latest)) ollama | llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output. ollama | llama_model_loader: - kv 0: gemma3.attention.head_count u32 = 4 ollama | llama_model_loader: - kv 1: gemma3.attention.head_count_kv u32 = 1 ollama | llama_model_loader: - kv 2: gemma3.attention.key_length u32 = 256 ollama | llama_model_loader: - kv 3: gemma3.attention.layer_norm_rms_epsilon f32 = 0.000001 ollama | llama_model_loader: - kv 4: gemma3.attention.sliding_window u32 = 512 ollama | llama_model_loader: - kv 5: gemma3.attention.value_length u32 = 256 ollama | llama_model_loader: - kv 6: gemma3.block_count u32 = 26 ollama | llama_model_loader: - kv 7: gemma3.context_length u32 = 32768 ollama | llama_model_loader: - kv 8: gemma3.embedding_length u32 = 1152 ollama | llama_model_loader: - kv 9: gemma3.feed_forward_length u32 = 6912 ollama | llama_model_loader: - kv 10: gemma3.final_logit_softcapping f32 = 30.000000 ollama | llama_model_loader: - kv 11: gemma3.rope.global.freq_base f32 = 1000000.000000 ollama | llama_model_loader: - kv 12: gemma3.rope.local.freq_base f32 = 10000.000000 ollama | llama_model_loader: - kv 13: general.architecture str = gemma3 ollama | llama_model_loader: - kv 14: tokenizer.chat_template str = {{ bos_token }}\n{%- if messages[0]['r... ollama | llama_model_loader: - kv 15: tokenizer.ggml.add_bos_token bool = true ollama | llama_model_loader: - kv 16: tokenizer.ggml.add_eos_token bool = false ollama | llama_model_loader: - kv 17: tokenizer.ggml.add_padding_token bool = false ollama | llama_model_loader: - kv 18: tokenizer.ggml.add_unknown_token bool = false ollama | llama_model_loader: - kv 19: tokenizer.ggml.bos_token_id u32 = 2 ollama | llama_model_loader: - kv 20: tokenizer.ggml.eos_token_id u32 = 1 ollama | llama_model_loader: - kv 21: tokenizer.ggml.merges arr[str,514906] = ["\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n \n", ... ollama | llama_model_loader: - kv 22: tokenizer.ggml.model str = llama ollama | llama_model_loader: - kv 23: tokenizer.ggml.padding_token_id u32 = 0 ollama | llama_model_loader: - kv 24: tokenizer.ggml.pre str = default ollama | llama_model_loader: - kv 25: tokenizer.ggml.scores arr[f32,262144] = [0.000000, 0.000000, 0.000000, 0.0000... ollama | llama_model_loader: - kv 26: tokenizer.ggml.token_type arr[i32,262144] = [3, 3, 3, 2, 1, 1, 1, 1, 1, 1, 1, 1, ... ollama | llama_model_loader: - kv 27: tokenizer.ggml.tokens arr[str,262144] = ["<pad>", "<eos>", "<bos>", "<unk>", ... ollama | llama_model_loader: - kv 28: tokenizer.ggml.unknown_token_id u32 = 3 ollama | llama_model_loader: - kv 29: general.quantization_version u32 = 2 ollama | llama_model_loader: - kv 30: general.file_type u32 = 15 ollama | llama_model_loader: - type f32: 157 tensors ollama | llama_model_loader: - type q5_0: 117 tensors ollama | llama_model_loader: - type q8_0: 14 tensors ollama | llama_model_loader: - type q4_K: 39 tensors ollama | llama_model_loader: - type q6_K: 13 tensors ollama | load: special_eos_id is not in special_eog_ids - the tokenizer config may be incorrect ollama | load: special tokens cache size = 6 ollama | load: token to piece cache size = 1.9446 MB ollama | ggml-alloc.c:819: GGML_ASSERT(talloc->buffer_id >= 0) failed ollama | /usr/bin/ollama(+0x11021a8)[0x5630adf941a8] ollama | /usr/bin/ollama(+0x1102526)[0x5630adf94526] ollama | /usr/bin/ollama(+0x10ef8f5)[0x5630adf818f5] ollama | /usr/bin/ollama(+0x10f101b)[0x5630adf8301b] ollama | /usr/bin/ollama(+0x1116005)[0x5630adfa8005] ollama | /usr/bin/ollama(+0x111645b)[0x5630adfa845b] ollama | /usr/bin/ollama(+0x117071b)[0x5630ae00271b] ollama | /usr/bin/ollama(+0x334801)[0x5630ad1c6801] ollama | SIGABRT: abort ollama | PC=0x7fae6709000b m=23 sigcode=18446744073709551610 ollama | signal arrived during cgo execution ollama | ollama | goroutine 6 gp=0xc000102e00 m=23 mp=0xc001b80808 [syscall]: ollama | runtime.cgocall(0x5630ae002700, 0xc00011baf8) ollama | runtime/cgocall.go:167 +0x4b fp=0xc00011bad0 sp=0xc00011ba98 pc=0x5630ad1bc14b ollama | github.com/ollama/ollama/ml/backend/ggml._Cfunc_ggml_backend_sched_graph_compute_async(0x7fadf0000d40, 0x7fad74002e60) ollama | _cgo_gotypes.go:516 +0x4a fp=0xc00011baf8 sp=0xc00011bad0 pc=0x5630ad5b96aa ollama | github.com/ollama/ollama/ml/backend/ggml.(*Context).Compute.func1(...) ollama | github.com/ollama/ollama/ml/backend/ggml/ggml.go:529 ollama | github.com/ollama/ollama/ml/backend/ggml.(*Context).Compute(0xc003a0a240, {0xc00366e390, 0x1, 0x0?}) ollama | github.com/ollama/ollama/ml/backend/ggml/ggml.go:529 +0x96 fp=0xc00011bb88 sp=0xc00011baf8 pc=0x5630ad5c2956 ollama | github.com/ollama/ollama/model.Forward({0x5630ae4c20b0, 0xc003a0a240}, {0x5630ae4b8a90, 0xc00344c000}, {0xc003671800, 0x200, 0x200}, {{0x5630ae4caab0, 0xc000010078}, {0x0, ...}, ...}) ollama | github.com/ollama/ollama/model/model.go:313 +0x2b8 fp=0xc00011bc70 sp=0xc00011bb88 pc=0x5630ad5f07d8 ollama | github.com/ollama/ollama/runner/ollamarunner.(*Server).processBatch(0xc0000f46c0) ollama | github.com/ollama/ollama/runner/ollamarunner/runner.go:478 +0x476 fp=0xc00011bf98 sp=0xc00011bc70 pc=0x5630ad672ab6 ollama | github.com/ollama/ollama/runner/ollamarunner.(*Server).run(0xc0000f46c0, {0x5630ae4b9df0, 0xc0003fe960}) ollama | github.com/ollama/ollama/runner/ollamarunner/runner.go:364 +0x4e fp=0xc00011bfb8 sp=0xc00011bf98 pc=0x5630ad6725ee ollama | github.com/ollama/ollama/runner/ollamarunner.Execute.gowrap2() ollama | github.com/ollama/ollama/runner/ollamarunner/runner.go:906 +0x28 fp=0xc00011bfe0 sp=0xc00011bfb8 pc=0x5630ad6770e8 ollama | runtime.goexit({}) ollama | runtime/asm_amd64.s:1700 +0x1 fp=0xc00011bfe8 sp=0xc00011bfe0 pc=0x5630ad1c6b81 ollama | created by github.com/ollama/ollama/runner/ollamarunner.Execute in goroutine 1 ollama | github.com/ollama/ollama/runner/ollamarunner/runner.go:906 +0xb37 ollama | ollama | goroutine 1 gp=0xc000002380 m=nil [IO wait]: ollama | runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) ollama | runtime/proc.go:435 +0xce fp=0xc000117628 sp=0xc000117608 pc=0x5630ad1bf44e ollama | runtime.netpollblock(0xc000117678?, 0xad158c06?, 0x30?) ollama | runtime/netpoll.go:575 +0xf7 fp=0xc000117660 sp=0xc000117628 pc=0x5630ad184237 ollama | internal/poll.runtime_pollWait(0x7fae1e4fcde0, 0x72) ollama | runtime/netpoll.go:351 +0x85 fp=0xc000117680 sp=0xc000117660 pc=0x5630ad1be665 ollama | internal/poll.(*pollDesc).wait(0xc000591380?, 0x900000036?, 0x0) ollama | internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc0001176a8 sp=0xc000117680 pc=0x5630ad2459c7 ollama | internal/poll.(*pollDesc).waitRead(...) ollama | internal/poll/fd_poll_runtime.go:89 ollama | internal/poll.(*FD).Accept(0xc000591380) ollama | internal/poll/fd_unix.go:620 +0x295 fp=0xc000117750 sp=0xc0001176a8 pc=0x5630ad24ad95 ollama | net.(*netFD).accept(0xc000591380) ollama | net/fd_unix.go:172 +0x29 fp=0xc000117808 sp=0xc000117750 pc=0x5630ad2bdba9 ollama | net.(*TCPListener).accept(0xc0000a9780) ollama | net/tcpsock_posix.go:159 +0x1b fp=0xc000117858 sp=0xc000117808 pc=0x5630ad2d355b ollama | net.(*TCPListener).Accept(0xc0000a9780) ollama | net/tcpsock.go:380 +0x30 fp=0xc000117888 sp=0xc000117858 pc=0x5630ad2d2410 ollama | net/http.(*onceCloseListener).Accept(0xc000364090?) ollama | <autogenerated>:1 +0x24 fp=0xc0001178a0 sp=0xc000117888 pc=0x5630ad4e9a44 ollama | net/http.(*Server).Serve(0xc0001aa700, {0x5630ae4b7af8, 0xc0000a9780}) ollama | net/http/server.go:3424 +0x30c fp=0xc0001179d0 sp=0xc0001178a0 pc=0x5630ad4c130c ollama | github.com/ollama/ollama/runner/ollamarunner.Execute({0xc0001aa030, 0xd, 0xd}) ollama | github.com/ollama/ollama/runner/ollamarunner/runner.go:930 +0xec9 fp=0xc000117d08 sp=0xc0001179d0 pc=0x5630ad676e49 ollama | github.com/ollama/ollama/runner.Execute({0xc0001aa010?, 0x0?, 0x0?}) ollama | github.com/ollama/ollama/runner/runner.go:20 +0xc9 fp=0xc000117d30 sp=0xc000117d08 pc=0x5630ad677ac9 ollama | github.com/ollama/ollama/cmd.NewCLI.func2(0xc000034e00?, {0x5630ae01e055?, 0x4?, 0x5630ae01e059?}) ollama | github.com/ollama/ollama/cmd/cmd.go:1365 +0x45 fp=0xc000117d58 sp=0xc000117d30 pc=0x5630addc6be5 ollama | github.com/spf13/cobra.(*Command).execute(0xc0000faf08, {0xc0000d75e0, 0xe, 0xe}) ollama | github.com/spf13/cobra@v1.7.0/command.go:940 +0x85c fp=0xc000117e78 sp=0xc000117d58 pc=0x5630ad3371fc ollama | github.com/spf13/cobra.(*Command).ExecuteC(0xc0000d4908) ollama | github.com/spf13/cobra@v1.7.0/command.go:1068 +0x3a5 fp=0xc000117f30 sp=0xc000117e78 pc=0x5630ad337a45 ollama | github.com/spf13/cobra.(*Command).Execute(...) ollama | github.com/spf13/cobra@v1.7.0/command.go:992 ollama | github.com/spf13/cobra.(*Command).ExecuteContext(...) ollama | github.com/spf13/cobra@v1.7.0/command.go:985 ollama | main.main() ollama | github.com/ollama/ollama/main.go:12 +0x4d fp=0xc000117f50 sp=0xc000117f30 pc=0x5630addc6f4d ollama | runtime.main() ollama | runtime/proc.go:283 +0x29d fp=0xc000117fe0 sp=0xc000117f50 pc=0x5630ad18b83d ollama | runtime.goexit({}) ollama | runtime/asm_amd64.s:1700 +0x1 fp=0xc000117fe8 sp=0xc000117fe0 pc=0x5630ad1c6b81 ollama | ollama | goroutine 2 gp=0xc000002e00 m=nil [force gc (idle)]: ollama | runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) ollama | runtime/proc.go:435 +0xce fp=0xc00007afa8 sp=0xc00007af88 pc=0x5630ad1bf44e ollama | runtime.goparkunlock(...) ollama | runtime/proc.go:441 ollama | runtime.forcegchelper() ollama | runtime/proc.go:348 +0xb8 fp=0xc00007afe0 sp=0xc00007afa8 pc=0x5630ad18bb78 ollama | runtime.goexit({}) ollama | runtime/asm_amd64.s:1700 +0x1 fp=0xc00007afe8 sp=0xc00007afe0 pc=0x5630ad1c6b81 ollama | created by runtime.init.7 in goroutine 1 ollama | runtime/proc.go:336 +0x1a ollama | ollama | goroutine 3 gp=0xc000003340 m=nil [GC sweep wait]: ollama | runtime.gopark(0x1?, 0x0?, 0x0?, 0x0?, 0x0?) ollama | runtime/proc.go:435 +0xce fp=0xc00007b780 sp=0xc00007b760 pc=0x5630ad1bf44e ollama | runtime.goparkunlock(...) ollama | runtime/proc.go:441 ollama | runtime.bgsweep(0xc0000a6000) ollama | runtime/mgcsweep.go:316 +0xdf fp=0xc00007b7c8 sp=0xc00007b780 pc=0x5630ad17623f ollama | runtime.gcenable.gowrap1() ollama | runtime/mgc.go:204 +0x25 fp=0xc00007b7e0 sp=0xc00007b7c8 pc=0x5630ad16a625 ollama | runtime.goexit({}) ollama | runtime/asm_amd64.s:1700 +0x1 fp=0xc00007b7e8 sp=0xc00007b7e0 pc=0x5630ad1c6b81 ollama | created by runtime.gcenable in goroutine 1 ollama | runtime/mgc.go:204 +0x66 ollama | ollama | goroutine 4 gp=0xc000003500 m=nil [GC scavenge wait]: ollama | runtime.gopark(0x10000?, 0x5630ae1d58c8?, 0x0?, 0x0?, 0x0?) ollama | runtime/proc.go:435 +0xce fp=0xc00007bf78 sp=0xc00007bf58 pc=0x5630ad1bf44e ollama | runtime.goparkunlock(...) ollama | runtime/proc.go:441 ollama | runtime.(*scavengerState).park(0x5630aed20300) ollama | runtime/mgcscavenge.go:425 +0x49 fp=0xc00007bfa8 sp=0xc00007bf78 pc=0x5630ad173c89 ollama | runtime.bgscavenge(0xc0000a6000) ollama | runtime/mgcscavenge.go:658 +0x59 fp=0xc00007bfc8 sp=0xc00007bfa8 pc=0x5630ad174219 ollama | runtime.gcenable.gowrap2() ollama | runtime/mgc.go:205 +0x25 fp=0xc00007bfe0 sp=0xc00007bfc8 pc=0x5630ad16a5c5 ollama | runtime.goexit({}) ollama | runtime/asm_amd64.s:1700 +0x1 fp=0xc00007bfe8 sp=0xc00007bfe0 pc=0x5630ad1c6b81 ollama | created by runtime.gcenable in goroutine 1 ollama | runtime/mgc.go:205 +0xa5 ollama | ollama | goroutine 18 gp=0xc000186380 m=nil [finalizer wait]: ollama | runtime.gopark(0x1b8?, 0xc000002380?, 0x1?, 0x23?, 0xc00007a688?) ollama | runtime/proc.go:435 +0xce fp=0xc00007a630 sp=0xc00007a610 pc=0x5630ad1bf44e ollama | runtime.runfinq() ollama | runtime/mfinal.go:196 +0x107 fp=0xc00007a7e0 sp=0xc00007a630 pc=0x5630ad1695e7 ollama | runtime.goexit({}) ollama | runtime/asm_amd64.s:1700 +0x1 fp=0xc00007a7e8 sp=0xc00007a7e0 pc=0x5630ad1c6b81 ollama | created by runtime.createfing in goroutine 1 ollama | runtime/mfinal.go:166 +0x3d ollama | ollama | goroutine 19 gp=0xc000186e00 m=nil [chan receive]: ollama | runtime.gopark(0xc00024d860?, 0xc0035b0048?, 0x60?, 0x67?, 0x5630ad2a48e8?) ollama | runtime/proc.go:435 +0xce fp=0xc000076718 sp=0xc0000766f8 pc=0x5630ad1bf44e ollama | runtime.chanrecv(0xc000182310, 0x0, 0x1) ollama | runtime/chan.go:664 +0x445 fp=0xc000076790 sp=0xc000076718 pc=0x5630ad15b7e5 ollama | runtime.chanrecv1(0x0?, 0x0?) ollama | runtime/chan.go:506 +0x12 fp=0xc0000767b8 sp=0xc000076790 pc=0x5630ad15b372 ollama | runtime.unique_runtime_registerUniqueMapCleanup.func2(...) ollama | runtime/mgc.go:1796 ollama | runtime.unique_runtime_registerUniqueMapCleanup.gowrap1() ollama | runtime/mgc.go:1799 +0x2f fp=0xc0000767e0 sp=0xc0000767b8 pc=0x5630ad16d7cf ollama | runtime.goexit({}) ollama | runtime/asm_amd64.s:1700 +0x1 fp=0xc0000767e8 sp=0xc0000767e0 pc=0x5630ad1c6b81 ollama | created by unique.runtime_registerUniqueMapCleanup in goroutine 1 ollama | runtime/mgc.go:1794 +0x85 ollama | ollama | goroutine 20 gp=0xc000187180 m=nil [GC worker (idle)]: ollama | runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) ollama | runtime/proc.go:435 +0xce fp=0xc000076f38 sp=0xc000076f18 pc=0x5630ad1bf44e ollama | runtime.gcBgMarkWorker(0xc000183730) ollama | runtime/mgc.go:1423 +0xe9 fp=0xc000076fc8 sp=0xc000076f38 pc=0x5630ad16cae9 ollama | runtime.gcBgMarkStartWorkers.gowrap1() ollama | runtime/mgc.go:1339 +0x25 fp=0xc000076fe0 sp=0xc000076fc8 pc=0x5630ad16c9c5 ollama | runtime.goexit({}) ollama | runtime/asm_amd64.s:1700 +0x1 fp=0xc000076fe8 sp=0xc000076fe0 pc=0x5630ad1c6b81 ollama | created by runtime.gcBgMarkStartWorkers in goroutine 1 ollama | runtime/mgc.go:1339 +0x105 ollama | ollama | goroutine 21 gp=0xc000187340 m=nil [GC worker (idle)]: ollama | runtime.gopark(0x925d7a23278?, 0x3?, 0x32?, 0x33?, 0x0?) ollama | runtime/proc.go:435 +0xce fp=0xc000077738 sp=0xc000077718 pc=0x5630ad1bf44e ollama | runtime.gcBgMarkWorker(0xc000183730) ollama | runtime/mgc.go:1423 +0xe9 fp=0xc0000777c8 sp=0xc000077738 pc=0x5630ad16cae9 ollama | runtime.gcBgMarkStartWorkers.gowrap1() ollama | runtime/mgc.go:1339 +0x25 fp=0xc0000777e0 sp=0xc0000777c8 pc=0x5630ad16c9c5 ollama | runtime.goexit({}) ollama | runtime/asm_amd64.s:1700 +0x1 fp=0xc0000777e8 sp=0xc0000777e0 pc=0x5630ad1c6b81 ollama | created by runtime.gcBgMarkStartWorkers in goroutine 1 ollama | runtime/mgc.go:1339 +0x105 ollama | ollama | goroutine 22 gp=0xc000187500 m=nil [GC worker (idle)]: ollama | runtime.gopark(0x925d798e990?, 0x1?, 0x36?, 0x5e?, 0x0?) ollama | runtime/proc.go:435 +0xce fp=0xc000077f38 sp=0xc000077f18 pc=0x5630ad1bf44e ollama | runtime.gcBgMarkWorker(0xc000183730) ollama | runtime/mgc.go:1423 +0xe9 fp=0xc000077fc8 sp=0xc000077f38 pc=0x5630ad16cae9 ollama | runtime.gcBgMarkStartWorkers.gowrap1() ollama | runtime/mgc.go:1339 +0x25 fp=0xc000077fe0 sp=0xc000077fc8 pc=0x5630ad16c9c5 ollama | runtime.goexit({}) ollama | runtime/asm_amd64.s:1700 +0x1 fp=0xc000077fe8 sp=0xc000077fe0 pc=0x5630ad1c6b81 ollama | created by runtime.gcBgMarkStartWorkers in goroutine 1 ollama | runtime/mgc.go:1339 +0x105 ollama | ollama | goroutine 23 gp=0xc0001876c0 m=nil [GC worker (idle)]: ollama | runtime.gopark(0x925d798eacc?, 0x1?, 0xc8?, 0x3c?, 0x0?) ollama | runtime/proc.go:435 +0xce fp=0xc000078738 sp=0xc000078718 pc=0x5630ad1bf44e ollama | runtime.gcBgMarkWorker(0xc000183730) ollama | runtime/mgc.go:1423 +0xe9 fp=0xc0000787c8 sp=0xc000078738 pc=0x5630ad16cae9 ollama | runtime.gcBgMarkStartWorkers.gowrap1() ollama | runtime/mgc.go:1339 +0x25 fp=0xc0000787e0 sp=0xc0000787c8 pc=0x5630ad16c9c5 ollama | runtime.goexit({}) ollama | runtime/asm_amd64.s:1700 +0x1 fp=0xc0000787e8 sp=0xc0000787e0 pc=0x5630ad1c6b81 ollama | created by runtime.gcBgMarkStartWorkers in goroutine 1 ollama | runtime/mgc.go:1339 +0x105 ollama | ollama | goroutine 24 gp=0xc000187880 m=nil [GC worker (idle)]: ollama | runtime.gopark(0x925d798eb85?, 0x1?, 0x95?, 0x4f?, 0x0?) ollama | runtime/proc.go:435 +0xce fp=0xc000078f38 sp=0xc000078f18 pc=0x5630ad1bf44e ollama | runtime.gcBgMarkWorker(0xc000183730) ollama | runtime/mgc.go:1423 +0xe9 fp=0xc000078fc8 sp=0xc000078f38 pc=0x5630ad16cae9 ollama | runtime.gcBgMarkStartWorkers.gowrap1() ollama | runtime/mgc.go:1339 +0x25 fp=0xc000078fe0 sp=0xc000078fc8 pc=0x5630ad16c9c5 ollama | runtime.goexit({}) ollama | runtime/asm_amd64.s:1700 +0x1 fp=0xc000078fe8 sp=0xc000078fe0 pc=0x5630ad1c6b81 ollama | created by runtime.gcBgMarkStartWorkers in goroutine 1 ollama | runtime/mgc.go:1339 +0x105 ollama | ollama | goroutine 25 gp=0xc000187a40 m=nil [GC worker (idle)]: ollama | runtime.gopark(0x925d798e8bc?, 0x3?, 0x25?, 0x33?, 0x0?) ollama | runtime/proc.go:435 +0xce fp=0xc000079738 sp=0xc000079718 pc=0x5630ad1bf44e ollama | runtime.gcBgMarkWorker(0xc000183730) ollama | runtime/mgc.go:1423 +0xe9 fp=0xc0000797c8 sp=0xc000079738 pc=0x5630ad16cae9 ollama | runtime.gcBgMarkStartWorkers.gowrap1() ollama | runtime/mgc.go:1339 +0x25 fp=0xc0000797e0 sp=0xc0000797c8 pc=0x5630ad16c9c5 ollama | runtime.goexit({}) ollama | runtime/asm_amd64.s:1700 +0x1 fp=0xc0000797e8 sp=0xc0000797e0 pc=0x5630ad1c6b81 ollama | created by runtime.gcBgMarkStartWorkers in goroutine 1 ollama | runtime/mgc.go:1339 +0x105 ollama | ollama | goroutine 26 gp=0xc000187c00 m=nil [GC worker (idle)]: ollama | runtime.gopark(0x5630aedceb40?, 0x1?, 0xed?, 0x4b?, 0x0?) ollama | runtime/proc.go:435 +0xce fp=0xc000079f38 sp=0xc000079f18 pc=0x5630ad1bf44e ollama | runtime.gcBgMarkWorker(0xc000183730) ollama | runtime/mgc.go:1423 +0xe9 fp=0xc000079fc8 sp=0xc000079f38 pc=0x5630ad16cae9 ollama | runtime.gcBgMarkStartWorkers.gowrap1() ollama | runtime/mgc.go:1339 +0x25 fp=0xc000079fe0 sp=0xc000079fc8 pc=0x5630ad16c9c5 ollama | runtime.goexit({}) ollama | runtime/asm_amd64.s:1700 +0x1 fp=0xc000079fe8 sp=0xc000079fe0 pc=0x5630ad1c6b81 ollama | created by runtime.gcBgMarkStartWorkers in goroutine 1 ollama | runtime/mgc.go:1339 +0x105 ollama | ollama | goroutine 27 gp=0xc000187dc0 m=nil [GC worker (idle)]: ollama | runtime.gopark(0x925d7a18b7d?, 0x3?, 0xf6?, 0xf9?, 0x0?) ollama | runtime/proc.go:435 +0xce fp=0xc0004f6738 sp=0xc0004f6718 pc=0x5630ad1bf44e ollama | runtime.gcBgMarkWorker(0xc000183730) ollama | runtime/mgc.go:1423 +0xe9 fp=0xc0004f67c8 sp=0xc0004f6738 pc=0x5630ad16cae9 ollama | runtime.gcBgMarkStartWorkers.gowrap1() ollama | runtime/mgc.go:1339 +0x25 fp=0xc0004f67e0 sp=0xc0004f67c8 pc=0x5630ad16c9c5 ollama | runtime.goexit({}) ollama | runtime/asm_amd64.s:1700 +0x1 fp=0xc0004f67e8 sp=0xc0004f67e0 pc=0x5630ad1c6b81 ollama | created by runtime.gcBgMarkStartWorkers in goroutine 1 ollama | runtime/mgc.go:1339 +0x105 ollama | ollama | goroutine 28 gp=0xc0004fa000 m=nil [GC worker (idle)]: ollama | runtime.gopark(0x925d7a2a22f?, 0x3?, 0x35?, 0x4b?, 0x0?) ollama | runtime/proc.go:435 +0xce fp=0xc0004f6f38 sp=0xc0004f6f18 pc=0x5630ad1bf44e ollama | runtime.gcBgMarkWorker(0xc000183730) ollama | runtime/mgc.go:1423 +0xe9 fp=0xc0004f6fc8 sp=0xc0004f6f38 pc=0x5630ad16cae9 ollama | runtime.gcBgMarkStartWorkers.gowrap1() ollama | runtime/mgc.go:1339 +0x25 fp=0xc0004f6fe0 sp=0xc0004f6fc8 pc=0x5630ad16c9c5 ollama | runtime.goexit({}) ollama | runtime/asm_amd64.s:1700 +0x1 fp=0xc0004f6fe8 sp=0xc0004f6fe0 pc=0x5630ad1c6b81 ollama | created by runtime.gcBgMarkStartWorkers in goroutine 1 ollama | runtime/mgc.go:1339 +0x105 ollama | ollama | goroutine 29 gp=0xc0004fa1c0 m=nil [GC worker (idle)]: ollama | runtime.gopark(0x925d798e9c6?, 0x3?, 0xa2?, 0x81?, 0x0?) ollama | runtime/proc.go:435 +0xce fp=0xc0004f7738 sp=0xc0004f7718 pc=0x5630ad1bf44e ollama | runtime.gcBgMarkWorker(0xc000183730) ollama | runtime/mgc.go:1423 +0xe9 fp=0xc0004f77c8 sp=0xc0004f7738 pc=0x5630ad16cae9 ollama | runtime.gcBgMarkStartWorkers.gowrap1() ollama | runtime/mgc.go:1339 +0x25 fp=0xc0004f77e0 sp=0xc0004f77c8 pc=0x5630ad16c9c5 ollama | runtime.goexit({}) ollama | runtime/asm_amd64.s:1700 +0x1 fp=0xc0004f77e8 sp=0xc0004f77e0 pc=0x5630ad1c6b81 ollama | created by runtime.gcBgMarkStartWorkers in goroutine 1 ollama | runtime/mgc.go:1339 +0x105 ollama | ollama | goroutine 30 gp=0xc0004fa380 m=nil [GC worker (idle)]: ollama | runtime.gopark(0x925d798e092?, 0x3?, 0x7c?, 0x25?, 0x0?) ollama | runtime/proc.go:435 +0xce fp=0xc0004f7f38 sp=0xc0004f7f18 pc=0x5630ad1bf44e ollama | runtime.gcBgMarkWorker(0xc000183730) ollama | runtime/mgc.go:1423 +0xe9 fp=0xc0004f7fc8 sp=0xc0004f7f38 pc=0x5630ad16cae9 ollama | runtime.gcBgMarkStartWorkers.gowrap1() ollama | runtime/mgc.go:1339 +0x25 fp=0xc0004f7fe0 sp=0xc0004f7fc8 pc=0x5630ad16c9c5 ollama | runtime.goexit({}) ollama | runtime/asm_amd64.s:1700 +0x1 fp=0xc0004f7fe8 sp=0xc0004f7fe0 pc=0x5630ad1c6b81 ollama | created by runtime.gcBgMarkStartWorkers in goroutine 1 ollama | runtime/mgc.go:1339 +0x105 ollama | ollama | goroutine 31 gp=0xc0004fa540 m=nil [GC worker (idle)]: ollama | runtime.gopark(0x925d7a45d26?, 0x3?, 0x1a?, 0x6c?, 0x0?) ollama | runtime/proc.go:435 +0xce fp=0xc0004f8738 sp=0xc0004f8718 pc=0x5630ad1bf44e ollama | runtime.gcBgMarkWorker(0xc000183730) ollama | runtime/mgc.go:1423 +0xe9 fp=0xc0004f87c8 sp=0xc0004f8738 pc=0x5630ad16cae9 ollama | runtime.gcBgMarkStartWorkers.gowrap1() ollama | runtime/mgc.go:1339 +0x25 fp=0xc0004f87e0 sp=0xc0004f87c8 pc=0x5630ad16c9c5 ollama | runtime.goexit({}) ollama | runtime/asm_amd64.s:1700 +0x1 fp=0xc0004f87e8 sp=0xc0004f87e0 pc=0x5630ad1c6b81 ollama | created by runtime.gcBgMarkStartWorkers in goroutine 1 ollama | runtime/mgc.go:1339 +0x105 ollama | ollama | goroutine 32 gp=0xc0004fa700 m=nil [GC worker (idle)]: ollama | runtime.gopark(0x925d798e330?, 0x3?, 0x79?, 0xe?, 0x0?) ollama | runtime/proc.go:435 +0xce fp=0xc0004f8f38 sp=0xc0004f8f18 pc=0x5630ad1bf44e ollama | runtime.gcBgMarkWorker(0xc000183730) ollama | runtime/mgc.go:1423 +0xe9 fp=0xc0004f8fc8 sp=0xc0004f8f38 pc=0x5630ad16cae9 ollama | runtime.gcBgMarkStartWorkers.gowrap1() ollama | runtime/mgc.go:1339 +0x25 fp=0xc0004f8fe0 sp=0xc0004f8fc8 pc=0x5630ad16c9c5 ollama | runtime.goexit({}) ollama | runtime/asm_amd64.s:1700 +0x1 fp=0xc0004f8fe8 sp=0xc0004f8fe0 pc=0x5630ad1c6b81 ollama | created by runtime.gcBgMarkStartWorkers in goroutine 1 ollama | runtime/mgc.go:1339 +0x105 ollama | ollama | goroutine 33 gp=0xc0004fa8c0 m=nil [GC worker (idle)]: ollama | runtime.gopark(0x925d798ea44?, 0x3?, 0x6b?, 0xea?, 0x0?) ollama | runtime/proc.go:435 +0xce fp=0xc0004f9738 sp=0xc0004f9718 pc=0x5630ad1bf44e ollama | runtime.gcBgMarkWorker(0xc000183730) ollama | runtime/mgc.go:1423 +0xe9 fp=0xc0004f97c8 sp=0xc0004f9738 pc=0x5630ad16cae9 ollama | runtime.gcBgMarkStartWorkers.gowrap1() ollama | runtime/mgc.go:1339 +0x25 fp=0xc0004f97e0 sp=0xc0004f97c8 pc=0x5630ad16c9c5 ollama | runtime.goexit({}) ollama | runtime/asm_amd64.s:1700 +0x1 fp=0xc0004f97e8 sp=0xc0004f97e0 pc=0x5630ad1c6b81 ollama | created by runtime.gcBgMarkStartWorkers in goroutine 1 ollama | runtime/mgc.go:1339 +0x105 ollama | ollama | goroutine 34 gp=0xc0004faa80 m=nil [GC worker (idle)]: ollama | runtime.gopark(0x925d798e2ba?, 0x3?, 0x2c?, 0x9?, 0x0?) ollama | runtime/proc.go:435 +0xce fp=0xc0004f9f38 sp=0xc0004f9f18 pc=0x5630ad1bf44e ollama | runtime.gcBgMarkWorker(0xc000183730) ollama | runtime/mgc.go:1423 +0xe9 fp=0xc0004f9fc8 sp=0xc0004f9f38 pc=0x5630ad16cae9 ollama | runtime.gcBgMarkStartWorkers.gowrap1() ollama | runtime/mgc.go:1339 +0x25 fp=0xc0004f9fe0 sp=0xc0004f9fc8 pc=0x5630ad16c9c5 ollama | runtime.goexit({}) ollama | runtime/asm_amd64.s:1700 +0x1 fp=0xc0004f9fe8 sp=0xc0004f9fe0 pc=0x5630ad1c6b81 ollama | created by runtime.gcBgMarkStartWorkers in goroutine 1 ollama | runtime/mgc.go:1339 +0x105 ollama | ollama | goroutine 35 gp=0xc0004fac40 m=nil [GC worker (idle)]: ollama | runtime.gopark(0x925d798e937?, 0x1?, 0x76?, 0x1a?, 0x0?) ollama | runtime/proc.go:435 +0xce fp=0xc0004f2738 sp=0xc0004f2718 pc=0x5630ad1bf44e ollama | runtime.gcBgMarkWorker(0xc000183730) ollama | runtime/mgc.go:1423 +0xe9 fp=0xc0004f27c8 sp=0xc0004f2738 pc=0x5630ad16cae9 ollama | runtime.gcBgMarkStartWorkers.gowrap1() ollama | runtime/mgc.go:1339 +0x25 fp=0xc0004f27e0 sp=0xc0004f27c8 pc=0x5630ad16c9c5 ollama | runtime.goexit({}) ollama | runtime/asm_amd64.s:1700 +0x1 fp=0xc0004f27e8 sp=0xc0004f27e0 pc=0x5630ad1c6b81 ollama | created by runtime.gcBgMarkStartWorkers in goroutine 1 ollama | runtime/mgc.go:1339 +0x105 ollama | ollama | goroutine 470 gp=0xc000582fc0 m=nil [select]: ollama | runtime.gopark(0xc000045a28?, 0x2?, 0x0?, 0x87?, 0xc000045894?) ollama | runtime/proc.go:435 +0xce fp=0xc0000456a8 sp=0xc000045688 pc=0x5630ad1bf44e ollama | runtime.selectgo(0xc000045a28, 0xc000045890, 0x328?, 0x0, 0x4?, 0x1) ollama | runtime/select.go:351 +0x837 fp=0xc0000457e0 sp=0xc0000456a8 pc=0x5630ad19dd37 ollama | github.com/ollama/ollama/runner/ollamarunner.(*Server).completion(0xc0000f46c0, {0x5630ae4b7cd8, 0xc0031fe000}, 0xc0005a03c0) ollama | github.com/ollama/ollama/runner/ollamarunner/runner.go:677 +0xb05 fp=0xc000045ac0 sp=0xc0000457e0 pc=0x5630ad674dc5 ollama | github.com/ollama/ollama/runner/ollamarunner.(*Server).completion-fm({0x5630ae4b7cd8?, 0xc0031fe000?}, 0xc00011bb40?) ollama | <autogenerated>:1 +0x36 fp=0xc000045af0 sp=0xc000045ac0 pc=0x5630ad677936 ollama | net/http.HandlerFunc.ServeHTTP(0xc0000c9680?, {0x5630ae4b7cd8?, 0xc0031fe000?}, 0xc00011bb60?) ollama | net/http/server.go:2294 +0x29 fp=0xc000045b18 sp=0xc000045af0 pc=0x5630ad4bd949 ollama | net/http.(*ServeMux).ServeHTTP(0x5630ad163b05?, {0x5630ae4b7cd8, 0xc0031fe000}, 0xc0005a03c0) ollama | net/http/server.go:2822 +0x1c4 fp=0xc000045b68 sp=0xc000045b18 pc=0x5630ad4bf844 ollama | net/http.serverHandler.ServeHTTP({0x5630ae4b43b0?}, {0x5630ae4b7cd8?, 0xc0031fe000?}, 0x1?) ollama | net/http/server.go:3301 +0x8e fp=0xc000045b98 sp=0xc000045b68 pc=0x5630ad4dd2ce ollama | net/http.(*conn).serve(0xc000364090, {0x5630ae4b9db8, 0xc0003e45d0}) ollama | net/http/server.go:2102 +0x625 fp=0xc000045fb8 sp=0xc000045b98 pc=0x5630ad4bbe45 ollama | net/http.(*Server).Serve.gowrap3() ollama | net/http/server.go:3454 +0x28 fp=0xc000045fe0 sp=0xc000045fb8 pc=0x5630ad4c1708 ollama | runtime.goexit({}) ollama | runtime/asm_amd64.s:1700 +0x1 fp=0xc000045fe8 sp=0xc000045fe0 pc=0x5630ad1c6b81 ollama | created by net/http.(*Server).Serve in goroutine 1 ollama | net/http/server.go:3454 +0x485 ollama | ollama | goroutine 356 gp=0xc000583340 m=nil [IO wait]: ollama | runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0xb?) ollama | runtime/proc.go:435 +0xce fp=0xc00304d5d8 sp=0xc00304d5b8 pc=0x5630ad1bf44e ollama | runtime.netpollblock(0x5630ad1e27b8?, 0xad158c06?, 0x30?) ollama | runtime/netpoll.go:575 +0xf7 fp=0xc00304d610 sp=0xc00304d5d8 pc=0x5630ad184237 ollama | internal/poll.runtime_pollWait(0x7fae1e4fcbb0, 0x72) ollama | runtime/netpoll.go:351 +0x85 fp=0xc00304d630 sp=0xc00304d610 pc=0x5630ad1be665 ollama | internal/poll.(*pollDesc).wait(0xc003692300?, 0xc0038ae251?, 0x0) ollama | internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc00304d658 sp=0xc00304d630 pc=0x5630ad2459c7 ollama | internal/poll.(*pollDesc).waitRead(...) ollama | internal/poll/fd_poll_runtime.go:89 ollama | internal/poll.(*FD).Read(0xc003692300, {0xc0038ae251, 0x1, 0x1}) ollama | internal/poll/fd_unix.go:165 +0x27a fp=0xc00304d6f0 sp=0xc00304d658 pc=0x5630ad246cba ollama | net.(*netFD).Read(0xc003692300, {0xc0038ae251?, 0xc003014058?, 0xc00304d770?}) ollama | net/fd_posix.go:55 +0x25 fp=0xc00304d738 sp=0xc00304d6f0 pc=0x5630ad2bbc05 ollama | net.(*conn).Read(0xc00007e090, {0xc0038ae251?, 0xc003015a40?, 0x5630ad544e20?}) ollama | net/net.go:194 +0x45 fp=0xc00304d780 sp=0xc00304d738 pc=0x5630ad2c9fc5 ollama | net/http.(*connReader).backgroundRead(0xc0038ae240) ollama | net/http/server.go:690 +0x37 fp=0xc00304d7c8 sp=0xc00304d780 pc=0x5630ad4b5d17 ollama | net/http.(*connReader).startBackgroundRead.gowrap2() ollama | net/http/server.go:686 +0x25 fp=0xc00304d7e0 sp=0xc00304d7c8 pc=0x5630ad4b5c45 ollama | runtime.goexit({}) ollama | runtime/asm_amd64.s:1700 +0x1 fp=0xc00304d7e8 sp=0xc00304d7e0 pc=0x5630ad1c6b81 ollama | created by net/http.(*connReader).startBackgroundRead in goroutine 470 ollama | net/http/server.go:686 +0xb6 ollama | ollama | rax 0x0 ollama | rbx 0x7fadd8ff9700 ollama | rcx 0x7fae6709000b ollama | rdx 0x0 ollama | rdi 0x2 ollama | rsi 0x7fadd8ff8930 ollama | rbp 0x5630ae1f335d ollama | rsp 0x7fadd8ff8930 ollama | r8 0x0 ollama | r9 0x7fadd8ff8930 ollama | r10 0x8 ollama | r11 0x246 ollama | r12 0x5630ae2190ab ollama | r13 0x333 ollama | r14 0x46f ollama | r15 0x7fadf002a2a0 ollama | rip 0x7fae6709000b ollama | rflags 0x246 ollama | cs 0x33 ollama | fs 0x0 ollama | gs 0x0 ollama | [GIN] 2025/04/25 - 04:37:43 | 200 | 984.934538ms | ::1 | POST "/api/chat" ollama | time=2025-04-25T04:37:43.335Z level=ERROR source=server.go:449 msg="llama runner terminated" error="exit status 2" web-1 | 2025-04-25T04:37:43.336Z warn: Got an exception from ollama, will still attempt to deserialize the response we got so far: Error: POST predict: Post "http://127.0.0.1:42413/completion": EOF web-1 | 2025-04-25T04:37:43.336Z error: [inference][622] inference job failed: Error: [inference][622] The model ignored our prompt and didn't respond with the expected JSON: {}. Here's a sneak peak from the response: web-1 | Error: [inference][622] The model ignored our prompt and didn't respond with the expected JSON: {}. Here's a sneak peak from the response: web-1 | at inferTags (/app/apps/workers/openaiWorker.ts:6:4346) web-1 | at process.processTicksAndRejections (node:internal/process/task_queues:105:5) web-1 | at async Object.runOpenAI [as run] (/app/apps/workers/openaiWorker.ts:6:6868) web-1 | at async Runner.runOnce (/app/apps/workers/node_modules/.pnpm/liteque@0.3.2_better-sqlite3@11.3.0/node_modules/liteque/dist/runner.js:2:2656) ### Device Details docker container on debian 12 server ### Exact Karakeep Version 0.23.1 ### Have you checked the troubleshooting guide? - [x] I have checked the troubleshooting guide and I haven't found a solution to my problem
kerem 2026-03-02 11:53:08 +03:00
Author
Owner

@MohamedBassem commented on GitHub (Apr 25, 2025):

@pixelpassport This might be similar to https://github.com/karakeep-app/karakeep/issues/1160

Given that you're on latest, can you try setting:

INFERENCE_OUTPUT_SCHEMA=json

and if it didn't work, try

INFERENCE_OUTPUT_SCHEMA=plain

This was potentially the only relevant change that might have impacted the inference requests.

<!-- gh-comment-id:2829854750 --> @MohamedBassem commented on GitHub (Apr 25, 2025): @pixelpassport This might be similar to https://github.com/karakeep-app/karakeep/issues/1160 Given that you're on latest, can you try setting: ``` INFERENCE_OUTPUT_SCHEMA=json ``` and if it didn't work, try ``` INFERENCE_OUTPUT_SCHEMA=plain ``` This was potentially the only relevant change that might have impacted the inference requests.
Author
Owner

@pixelpassport commented on GitHub (Apr 25, 2025):

@MohamedBassem Thank you for the quick response. I tried both of these settings and got the same results.

I also tried clearing everything and setting it up from the beginning including ollama, and tried some other models that were also working for me originally. I would normally think its user error but the way it started failing as I was using the service throughout the day makes me think otherwise, I didn't change any settings or update anything until I was trying to troubleshoot the issue.

<!-- gh-comment-id:2830783588 --> @pixelpassport commented on GitHub (Apr 25, 2025): @MohamedBassem Thank you for the quick response. I tried both of these settings and got the same results. I also tried clearing everything and setting it up from the beginning including ollama, and tried some other models that were also working for me originally. I would normally think its user error but the way it started failing as I was using the service throughout the day makes me think otherwise, I didn't change any settings or update anything until I was trying to troubleshoot the issue.
Author
Owner

@pixelpassport commented on GitHub (May 5, 2025):

This seems like it actually was user error, my apologies. Apparently 2048 and even 1024 context length was too long for my hardware, I had to set it to 512 and it is now working as expected. There are not memory errors that I can see when having this issue, so it may be a limitation of the small models that I am running or something else, but I don't think it's a Karakeep issue.

<!-- gh-comment-id:2852766839 --> @pixelpassport commented on GitHub (May 5, 2025): This seems like it actually was user error, my apologies. Apparently 2048 and even 1024 context length was too long for my hardware, I had to set it to 512 and it is now working as expected. There are not memory errors that I can see when having this issue, so it may be a limitation of the small models that I am running or something else, but I don't think it's a Karakeep issue.
Sign in to join this conversation.
No milestone
No project
No assignees
1 participant
Notifications
Due date
The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set.

Reference
starred/karakeep#836
No description provided.