github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 16:11:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #12194] Ollama not running on GPU #33870

New Issue
Closed
opened 2026-04-22 16:59:43 -05:00 by GiteaMirror · 8 comments
GiteaMirror commented 2026-04-22 16:59:43 -05:00
Owner
Copy Link

Originally created by @jingzhang94 on GitHub (Sep 5, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/12194

What is the issue?

I'm using Nvidia V100 and Cuda v12.8 on Ubuntu 24.04
When I install Ollama v0.11.10, and run qwen3:4b model, it keeps loading and never started to let me type prompts. However the GPU is not utilized at all.
Now I have downgraded to v0.6.7, it throw message as below

Adding ollama user to render group...
Adding ollama user to video group...
Adding current user to ollama group...
Creating ollama systemd service...
Enabling and starting ollama service...
Created symlink /etc/systemd/system/default.target.wants/ollama.service → /etc/systemd/system/ollama.service.
NVIDIA GPU installed.
zhangj99@iZuf6bi9mf5aqzrm5qyr47Z:$ ollama list
NAME ID SIZE MODIFIED
qwen3:4b e55aed6fe643 2.5 GB 5 hours ago
qwen3:8b 500a1f067a9f 5.2 GB 9 hours ago
zhangj99@iZuf6bi9mf5aqzrm5qyr47Z:$ ollama run qwen3:4b
Error: llama runner process has terminated: exit status 2

nvidia-smi
+-----------------------------------------------------------------------------------------+
| NVIDIA-SMI 570.133.20 Driver Version: 570.133.20 CUDA Version: 12.8 |
|-----------------------------------------+------------------------+----------------------+
| GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. |
| | | MIG M. |
|=========================================+========================+======================|
| 0 Tesla V100-SXM2-16GB On | 00000000:00:07.0 Off | 0 |
| N/A 34C P0 38W / 300W | 3MiB / 16384MiB | 0% Default |
| | | N/A |
+-----------------------------------------+------------------------+----------------------+

+-----------------------------------------------------------------------------------------+
| Processes: |
| GPU GI CI PID Type Process name GPU Memory |
| ID ID Usage |
|=========================================================================================|
| No running processes found |
+-----------------------------------------------------------------------------------------+

Relevant log output

v0.11.10:
ep 05 16:56:59 iZuf6bi9mf5aqzrm5qyr47Z systemd[1]: Started ollama.service - Ollama Service.
Sep 05 16:56:59 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: time=2025-09-05T16:56:59.768+08:00 level=INFO source=routes.go:1331 msg="server config" env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:4096 OLLAMA_DEBUG:INFO OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/home/zhangj99/.ollama/models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NEW_ESTIMATES:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:1 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://* vscode-file://*] OLLAMA_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]"
Sep 05 16:56:59 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: time=2025-09-05T16:56:59.778+08:00 level=INFO source=images.go:477 msg="total blobs: 8"
Sep 05 16:56:59 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: time=2025-09-05T16:56:59.778+08:00 level=INFO source=images.go:484 msg="total unused blobs removed: 0"
Sep 05 16:56:59 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: time=2025-09-05T16:56:59.785+08:00 level=INFO source=routes.go:1384 msg="Listening on 127.0.0.1:11434 (version 0.11.10)"
Sep 05 16:56:59 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: time=2025-09-05T16:56:59.790+08:00 level=INFO source=gpu.go:217 msg="looking for compatible GPUs"
Sep 05 16:57:01 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: time=2025-09-05T16:57:01.157+08:00 level=INFO source=types.go:131 msg="inference compute" id=GPU-897caf43-6646-3de4-3d9d-1e22730db58f library=cuda variant=v12 compute=7.0 driver=12.8 name="Tesla V100-SXM2-16GB" total="15.8 GiB" available="15.5 GiB"
Sep 05 16:57:01 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: time=2025-09-05T16:57:01.157+08:00 level=INFO source=routes.go:1425 msg="entering low vram mode" "total vram"="15.8 GiB" threshold="20.0 GiB"
Sep 05 17:00:17 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: [GIN] 2025/09/05 - 17:00:17 | 200 |     960.574µs |       127.0.0.1 | HEAD     "/"
Sep 05 17:00:17 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: [GIN] 2025/09/05 - 17:00:17 | 200 |   89.488243ms |       127.0.0.1 | POST     "/api/show"
Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: llama_model_loader: loaded meta data with 33 key-value pairs and 398 tensors from /home/zhangj99/.ollama/models/blobs/sha256-3e4cb14174460404e7a233e531675303b2fbf7749c02f91864fe311ab6344e4f (version GGUF V3 (latest))
Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: llama_model_loader: - kv   0:                       general.architecture str              = qwen3
Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: llama_model_loader: - kv   1:                           general.basename str              = Qwen3
Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: llama_model_loader: - kv   2:                          general.file_type u32              = 15
Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: llama_model_loader: - kv   3:                           general.finetune str              = Thinking
Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: llama_model_loader: - kv   4:                            general.license str              = apache-2.0
Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: llama_model_loader: - kv   5:                       general.license.link str              = https://huggingface.co/Qwen/Qwen3-4B-...
Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: llama_model_loader: - kv   6:                               general.name str              = Qwen3 4B Thinking 2507
Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: llama_model_loader: - kv   7:                    general.parameter_count u64              = 4022468096
Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: llama_model_loader: - kv   8:               general.quantization_version u32              = 2
Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: llama_model_loader: - kv   9:                         general.size_label str              = 4B
Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: llama_model_loader: - kv  10:                               general.tags arr[str,1]       = ["text-generation"]
Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: llama_model_loader: - kv  11:                               general.type str              = model
Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: llama_model_loader: - kv  12:                            general.version str              = 2507
Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: llama_model_loader: - kv  13:                 qwen3.attention.head_count u32              = 32
Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: llama_model_loader: - kv  14:              qwen3.attention.head_count_kv u32              = 8
Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: llama_model_loader: - kv  15:                 qwen3.attention.key_length u32              = 128
Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: llama_model_loader: - kv  16:     qwen3.attention.layer_norm_rms_epsilon f32              = 0.000001
Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: llama_model_loader: - kv  17:               qwen3.attention.value_length u32              = 128
Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: llama_model_loader: - kv  18:                          qwen3.block_count u32              = 36
Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: llama_model_loader: - kv  19:                       qwen3.context_length u32              = 262144
Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: llama_model_loader: - kv  20:                     qwen3.embedding_length u32              = 2560
Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: llama_model_loader: - kv  21:                  qwen3.feed_forward_length u32              = 9728
Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: llama_model_loader: - kv  22:                       qwen3.rope.freq_base f32              = 5000000.000000
Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: llama_model_loader: - kv  23:                    tokenizer.chat_template str              = {%- if tools %}\n    {{- '<|im_start|>...
Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: llama_model_loader: - kv  24:               tokenizer.ggml.add_bos_token bool             = false
Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: llama_model_loader: - kv  25:                tokenizer.ggml.bos_token_id u32              = 151643
Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: llama_model_loader: - kv  26:                tokenizer.ggml.eos_token_id u32              = 151645
Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: llama_model_loader: - kv  27:                      tokenizer.ggml.merges arr[str,151387]  = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: llama_model_loader: - kv  28:                       tokenizer.ggml.model str              = gpt2
Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: llama_model_loader: - kv  29:            tokenizer.ggml.padding_token_id u32              = 151643
Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: llama_model_loader: - kv  30:                         tokenizer.ggml.pre str              = qwen2
Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: llama_model_loader: - kv  31:                  tokenizer.ggml.token_type arr[i32,151936]  = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: llama_model_loader: - kv  32:                      tokenizer.ggml.tokens arr[str,151936]  = ["!", "\"", "#", "$", "%", "&", "'", ...
Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: llama_model_loader: - type  f32:  145 tensors
Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: llama_model_loader: - type q4_K:  216 tensors
Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: llama_model_loader: - type q6_K:   37 tensors
Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: print_info: file format = GGUF V3 (latest)
Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: print_info: file type   = Q4_K - Medium
Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: print_info: file size   = 2.32 GiB (4.95 BPW)
Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: load: printing all EOG tokens:
Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: load:   - 151643 ('<|endoftext|>')
Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: load:   - 151645 ('<|im_end|>')
Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: load:   - 151662 ('<|fim_pad|>')
Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: load:   - 151663 ('<|repo_name|>')
Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: load:   - 151664 ('<|file_sep|>')
Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: load: special tokens cache size = 26
Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: load: token to piece cache size = 0.9311 MB
Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: print_info: arch             = qwen3
Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: print_info: vocab_only       = 1
Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: print_info: model type       = ?B
Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: print_info: model params     = 4.02 B
Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: print_info: general.name     = Qwen3 4B Thinking 2507
Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: print_info: vocab type       = BPE
Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: print_info: n_vocab          = 151936
Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: print_info: n_merges         = 151387
Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: print_info: BOS token        = 151643 '<|endoftext|>'
Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: print_info: EOS token        = 151645 '<|im_end|>'
Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: print_info: EOT token        = 151645 '<|im_end|>'
Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: print_info: PAD token        = 151643 '<|endoftext|>'
Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: print_info: LF token         = 198 'Ċ'
Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: print_info: FIM PRE token    = 151659 '<|fim_prefix|>'
Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: print_info: FIM SUF token    = 151661 '<|fim_suffix|>'
Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: print_info: FIM MID token    = 151660 '<|fim_middle|>'
Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: print_info: FIM PAD token    = 151662 '<|fim_pad|>'
Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: print_info: FIM REP token    = 151663 '<|repo_name|>'
Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: print_info: FIM SEP token    = 151664 '<|file_sep|>'
Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: print_info: EOG token        = 151643 '<|endoftext|>'
Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: print_info: EOG token        = 151645 '<|im_end|>'
Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: print_info: EOG token        = 151662 '<|fim_pad|>'
Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: print_info: EOG token        = 151663 '<|repo_name|>'
Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: print_info: EOG token        = 151664 '<|file_sep|>'
Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: print_info: max token length = 256
Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: llama_model_load: vocab only - skipping tensors
Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: time=2025-09-05T17:00:18.886+08:00 level=INFO source=server.go:398 msg="starting runner" cmd="/usr/local/bin/ollama runner --model /home/zhangj99/.ollama/models/blobs/sha256-3e4cb14174460404e7a233e531675303b2fbf7749c02f91864fe311ab6344e4f --port 38697"
Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: time=2025-09-05T17:00:18.909+08:00 level=INFO source=runner.go:864 msg="starting go runner"
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: time=2025-09-05T17:00:19.097+08:00 level=INFO source=server.go:503 msg="system memory" total="31.0 GiB" free="29.0 GiB" free_swap="0 B"
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: time=2025-09-05T17:00:19.098+08:00 level=INFO source=memory.go:36 msg="new model will fit in available VRAM across minimum required GPUs, loading" model=/home/zhangj99/.ollama/models/blobs/sha256-3e4cb14174460404e7a233e531675303b2fbf7749c02f91864fe311ab6344e4f library=cuda parallel=1 required="3.8 GiB" gpus=1
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: time=2025-09-05T17:00:19.098+08:00 level=INFO source=server.go:543 msg=offload library=cuda layers.requested=-1 layers.model=37 layers.offload=37 layers.split=[37] memory.available="[15.5 GiB]" memory.gpu_overhead="0 B" memory.required.full="3.8 GiB" memory.required.partial="3.8 GiB" memory.required.kv="576.0 MiB" memory.required.allocations="[3.8 GiB]" memory.weights.total="2.3 GiB" memory.weights.repeating="2.0 GiB" memory.weights.nonrepeating="304.3 MiB" memory.graph.full="384.0 MiB" memory.graph.partial="384.0 MiB"
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: ggml_cuda_init: found 1 CUDA devices:
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]:   Device 0: Tesla V100-SXM2-16GB, compute capability 7.0, VMM: yes, ID: GPU-897caf43-6646-3de4-3d9d-1e22730db58f
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: load_backend: loaded CUDA backend from /usr/local/lib/ollama/libggml-cuda.so
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: SIGILL: illegal instruction
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: PC=0x74b79c0b34d6 m=0 sigcode=2
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: signal arrived during cgo execution
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: instruction bytes: 0xc5 0xf9 0x6e 0xfa 0xc5 0xc2 0x5c 0x35 0xe 0x99 0xa 0x0 0xc5 0xf9 0x7e 0xf2
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: goroutine 1 gp=0xc000002380 m=0 mp=0x5f09ab54dd60 [syscall]:
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.cgocall(0x5f09aa4ee7c0, 0xc000515710)
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]:         runtime/cgocall.go:167 +0x4b fp=0xc0005156e8 sp=0xc0005156b0 pc=0x5f09a97fc3eb
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: github.com/ollama/ollama/ml/backend/ggml/ggml/src._Cfunc_ggml_backend_load_all_from_path(0x5f09dfbbd3f0)
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]:         _cgo_gotypes.go:195 +0x3e fp=0xc000515710 sp=0xc0005156e8 pc=0x5f09a9ba967e
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: github.com/ollama/ollama/ml/backend/ggml/ggml/src.init.func1.1({0xc00003a074, 0x15})
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]:         github.com/ollama/ollama/ml/backend/ggml/ggml/src/ggml.go:97 +0xf5 fp=0xc0005157a8 sp=0xc000515710 pc=0x5f09a9ba9115
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: github.com/ollama/ollama/ml/backend/ggml/ggml/src.init.func1()
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]:         github.com/ollama/ollama/ml/backend/ggml/ggml/src/ggml.go:98 +0x526 fp=0xc000515a38 sp=0xc0005157a8 pc=0x5f09a9ba8f66
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: github.com/ollama/ollama/ml/backend/ggml/ggml/src.init.OnceFunc.func2()
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]:         sync/oncefunc.go:27 +0x62 fp=0xc000515a80 sp=0xc000515a38 pc=0x5f09a9ba8962
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: sync.(*Once).doSlow(0x0?, 0x0?)
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]:         sync/once.go:78 +0xab fp=0xc000515ad8 sp=0xc000515a80 pc=0x5f09a98114ab
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: sync.(*Once).Do(0x0?, 0x0?)
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]:         sync/once.go:69 +0x19 fp=0xc000515af8 sp=0xc000515ad8 pc=0x5f09a98113d9
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: github.com/ollama/ollama/ml/backend/ggml/ggml/src.init.OnceFunc.func3()
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]:         sync/oncefunc.go:32 +0x2d fp=0xc000515b28 sp=0xc000515af8 pc=0x5f09a9ba88cd
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: github.com/ollama/ollama/llama.BackendInit()
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]:         github.com/ollama/ollama/llama/llama.go:61 +0x16 fp=0xc000515b38 sp=0xc000515b28 pc=0x5f09a9badc36
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: github.com/ollama/ollama/runner/llamarunner.Execute({0xc000034260, 0x4, 0x4})
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]:         github.com/ollama/ollama/runner/llamarunner/runner.go:866 +0x395 fp=0xc000515d08 sp=0xc000515b38 pc=0x5f09a9c79415
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: github.com/ollama/ollama/runner.Execute({0xc000034250?, 0x0?, 0x0?})
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]:         github.com/ollama/ollama/runner/runner.go:22 +0xd4 fp=0xc000515d30 sp=0xc000515d08 pc=0x5f09a9d08074
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: github.com/ollama/ollama/cmd.NewCLI.func2(0xc0001f3400?, {0x5f09aa7c1084?, 0x4?, 0x5f09aa7c1088?})
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]:         github.com/ollama/ollama/cmd/cmd.go:1583 +0x45 fp=0xc000515d58 sp=0xc000515d30 pc=0x5f09aa46bce5
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: github.com/spf13/cobra.(*Command).execute(0xc0004caf08, {0xc000412500, 0x4, 0x4})
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]:         github.com/spf13/cobra@v1.7.0/command.go:940 +0x85c fp=0xc000515e78 sp=0xc000515d58 pc=0x5f09a997789c
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: github.com/spf13/cobra.(*Command).ExecuteC(0xc00013b208)
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]:         github.com/spf13/cobra@v1.7.0/command.go:1068 +0x3a5 fp=0xc000515f30 sp=0xc000515e78 pc=0x5f09a99780e5
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: github.com/spf13/cobra.(*Command).Execute(...)
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]:         github.com/spf13/cobra@v1.7.0/command.go:992
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: github.com/spf13/cobra.(*Command).ExecuteContext(...)
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]:         github.com/spf13/cobra@v1.7.0/command.go:985
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: main.main()
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]:         github.com/ollama/ollama/main.go:12 +0x4d fp=0xc000515f50 sp=0xc000515f30 pc=0x5f09aa46c7cd
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.main()
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]:         runtime/proc.go:283 +0x29d fp=0xc000515fe0 sp=0xc000515f50 pc=0x5f09a97cb9dd
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.goexit({})
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc000515fe8 sp=0xc000515fe0 pc=0x5f09a9806fa1
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: goroutine 2 gp=0xc000002e00 m=nil [force gc (idle)]:
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]:         runtime/proc.go:435 +0xce fp=0xc000070fa8 sp=0xc000070f88 pc=0x5f09a97ff86e
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.goparkunlock(...)
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]:         runtime/proc.go:441
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.forcegchelper()
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]:         runtime/proc.go:348 +0xb8 fp=0xc000070fe0 sp=0xc000070fa8 pc=0x5f09a97cbd18
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.goexit({})
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc000070fe8 sp=0xc000070fe0 pc=0x5f09a9806fa1
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: created by runtime.init.7 in goroutine 1
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]:         runtime/proc.go:336 +0x1a
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: goroutine 3 gp=0xc000003340 m=nil [GC sweep wait]:
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.gopark(0x1?, 0x0?, 0x0?, 0x0?, 0x0?)
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]:         runtime/proc.go:435 +0xce fp=0xc000071780 sp=0xc000071760 pc=0x5f09a97ff86e
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.goparkunlock(...)
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]:         runtime/proc.go:441
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.bgsweep(0xc00009c000)
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]:         runtime/mgcsweep.go:316 +0xdf fp=0xc0000717c8 sp=0xc000071780 pc=0x5f09a97b64bf
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.gcenable.gowrap1()
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]:         runtime/mgc.go:204 +0x25 fp=0xc0000717e0 sp=0xc0000717c8 pc=0x5f09a97aa8a5
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.goexit({})
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0000717e8 sp=0xc0000717e0 pc=0x5f09a9806fa1
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: created by runtime.gcenable in goroutine 1
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]:         runtime/mgc.go:204 +0x66
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: goroutine 4 gp=0xc000003500 m=nil [GC scavenge wait]:
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.gopark(0x10000?, 0x5f09aa985380?, 0x0?, 0x0?, 0x0?)
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]:         runtime/proc.go:435 +0xce fp=0xc000071f78 sp=0xc000071f58 pc=0x5f09a97ff86e
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.goparkunlock(...)
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]:         runtime/proc.go:441
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.(*scavengerState).park(0x5f09ab54af40)
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]:         runtime/mgcscavenge.go:425 +0x49 fp=0xc000071fa8 sp=0xc000071f78 pc=0x5f09a97b3f09
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.bgscavenge(0xc00009c000)
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]:         runtime/mgcscavenge.go:658 +0x59 fp=0xc000071fc8 sp=0xc000071fa8 pc=0x5f09a97b4499
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.gcenable.gowrap2()
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]:         runtime/mgc.go:205 +0x25 fp=0xc000071fe0 sp=0xc000071fc8 pc=0x5f09a97aa845
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.goexit({})
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc000071fe8 sp=0xc000071fe0 pc=0x5f09a9806fa1
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: created by runtime.gcenable in goroutine 1
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]:         runtime/mgc.go:205 +0xa5
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: goroutine 5 gp=0xc000003dc0 m=nil [finalizer wait]:
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.gopark(0x1b8?, 0xc000002380?, 0x1?, 0x23?, 0xc000070688?)
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]:         runtime/proc.go:435 +0xce fp=0xc000070630 sp=0xc000070610 pc=0x5f09a97ff86e
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.runfinq()
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]:         runtime/mfinal.go:196 +0x107 fp=0xc0000707e0 sp=0xc000070630 pc=0x5f09a97a9867
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.goexit({})
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0000707e8 sp=0xc0000707e0 pc=0x5f09a9806fa1
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: created by runtime.createfing in goroutine 1
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]:         runtime/mfinal.go:166 +0x3d
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: goroutine 6 gp=0xc0001d08c0 m=nil [chan receive]:
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.gopark(0xc000225900?, 0xc000590018?, 0x60?, 0x27?, 0x5f09a98e4e88?)
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]:         runtime/proc.go:435 +0xce fp=0xc000072718 sp=0xc0000726f8 pc=0x5f09a97ff86e
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.chanrecv(0xc0000a6310, 0x0, 0x1)
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]:         runtime/chan.go:664 +0x445 fp=0xc000072790 sp=0xc000072718 pc=0x5f09a979b245
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.chanrecv1(0x0?, 0x0?)
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]:         runtime/chan.go:506 +0x12 fp=0xc0000727b8 sp=0xc000072790 pc=0x5f09a979add2
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.unique_runtime_registerUniqueMapCleanup.func2(...)
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]:         runtime/mgc.go:1796
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.unique_runtime_registerUniqueMapCleanup.gowrap1()
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]:         runtime/mgc.go:1799 +0x2f fp=0xc0000727e0 sp=0xc0000727b8 pc=0x5f09a97ada4f
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.goexit({})
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0000727e8 sp=0xc0000727e0 pc=0x5f09a9806fa1
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: created by unique.runtime_registerUniqueMapCleanup in goroutine 1
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]:         runtime/mgc.go:1794 +0x85
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: goroutine 7 gp=0xc0001d0c40 m=nil [GC worker (idle)]:
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]:         runtime/proc.go:435 +0xce fp=0xc000072f38 sp=0xc000072f18 pc=0x5f09a97ff86e
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.gcBgMarkWorker(0xc0000a7730)
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]:         runtime/mgc.go:1423 +0xe9 fp=0xc000072fc8 sp=0xc000072f38 pc=0x5f09a97acd69
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.gcBgMarkStartWorkers.gowrap1()
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]:         runtime/mgc.go:1339 +0x25 fp=0xc000072fe0 sp=0xc000072fc8 pc=0x5f09a97acc45
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.goexit({})
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc000072fe8 sp=0xc000072fe0 pc=0x5f09a9806fa1
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: created by runtime.gcBgMarkStartWorkers in goroutine 1
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]:         runtime/mgc.go:1339 +0x105
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: goroutine 18 gp=0xc000102380 m=nil [GC worker (idle)]:
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]:         runtime/proc.go:435 +0xce fp=0xc00006c738 sp=0xc00006c718 pc=0x5f09a97ff86e
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.gcBgMarkWorker(0xc0000a7730)
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]:         runtime/mgc.go:1423 +0xe9 fp=0xc00006c7c8 sp=0xc00006c738 pc=0x5f09a97acd69
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.gcBgMarkStartWorkers.gowrap1()
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]:         runtime/mgc.go:1339 +0x25 fp=0xc00006c7e0 sp=0xc00006c7c8 pc=0x5f09a97acc45
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.goexit({})
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc00006c7e8 sp=0xc00006c7e0 pc=0x5f09a9806fa1
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: created by runtime.gcBgMarkStartWorkers in goroutine 1
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]:         runtime/mgc.go:1339 +0x105
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: goroutine 34 gp=0xc000504000 m=nil [GC worker (idle)]:
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.gopark(0x4c40a32673?, 0x0?, 0x0?, 0x0?, 0x0?)
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]:         runtime/proc.go:435 +0xce fp=0xc00050a738 sp=0xc00050a718 pc=0x5f09a97ff86e
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.gcBgMarkWorker(0xc0000a7730)
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]:         runtime/mgc.go:1423 +0xe9 fp=0xc00050a7c8 sp=0xc00050a738 pc=0x5f09a97acd69
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.gcBgMarkStartWorkers.gowrap1()
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]:         runtime/mgc.go:1339 +0x25 fp=0xc00050a7e0 sp=0xc00050a7c8 pc=0x5f09a97acc45
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.goexit({})
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc00050a7e8 sp=0xc00050a7e0 pc=0x5f09a9806fa1
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: created by runtime.gcBgMarkStartWorkers in goroutine 1
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]:         runtime/mgc.go:1339 +0x105
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: goroutine 8 gp=0xc0001d0e00 m=nil [GC worker (idle)]:
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.gopark(0x4c40a0e2c6?, 0x0?, 0x0?, 0x0?, 0x0?)
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]:         runtime/proc.go:435 +0xce fp=0xc000073738 sp=0xc000073718 pc=0x5f09a97ff86e
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.gcBgMarkWorker(0xc0000a7730)
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]:         runtime/mgc.go:1423 +0xe9 fp=0xc0000737c8 sp=0xc000073738 pc=0x5f09a97acd69
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.gcBgMarkStartWorkers.gowrap1()
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]:         runtime/mgc.go:1339 +0x25 fp=0xc0000737e0 sp=0xc0000737c8 pc=0x5f09a97acc45
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.goexit({})
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0000737e8 sp=0xc0000737e0 pc=0x5f09a9806fa1
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: created by runtime.gcBgMarkStartWorkers in goroutine 1
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]:         runtime/mgc.go:1339 +0x105
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: goroutine 19 gp=0xc000102540 m=nil [GC worker (idle)]:
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.gopark(0x4c409e61f1?, 0x0?, 0x0?, 0x0?, 0x0?)
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]:         runtime/proc.go:435 +0xce fp=0xc00006cf38 sp=0xc00006cf18 pc=0x5f09a97ff86e
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.gcBgMarkWorker(0xc0000a7730)
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]:         runtime/mgc.go:1423 +0xe9 fp=0xc00006cfc8 sp=0xc00006cf38 pc=0x5f09a97acd69
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.gcBgMarkStartWorkers.gowrap1()
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]:         runtime/mgc.go:1339 +0x25 fp=0xc00006cfe0 sp=0xc00006cfc8 pc=0x5f09a97acc45
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.goexit({})
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc00006cfe8 sp=0xc00006cfe0 pc=0x5f09a9806fa1
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: created by runtime.gcBgMarkStartWorkers in goroutine 1
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]:         runtime/mgc.go:1339 +0x105
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: goroutine 9 gp=0xc0001d0fc0 m=nil [GC worker (idle)]:
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.gopark(0x4c40a13639?, 0x3?, 0xc?, 0x71?, 0x0?)
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]:         runtime/proc.go:435 +0xce fp=0xc000073f38 sp=0xc000073f18 pc=0x5f09a97ff86e
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.gcBgMarkWorker(0xc0000a7730)
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]:         runtime/mgc.go:1423 +0xe9 fp=0xc000073fc8 sp=0xc000073f38 pc=0x5f09a97acd69
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.gcBgMarkStartWorkers.gowrap1()
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]:         runtime/mgc.go:1339 +0x25 fp=0xc000073fe0 sp=0xc000073fc8 pc=0x5f09a97acc45
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.goexit({})
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc000073fe8 sp=0xc000073fe0 pc=0x5f09a9806fa1
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: created by runtime.gcBgMarkStartWorkers in goroutine 1
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]:         runtime/mgc.go:1339 +0x105
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: goroutine 20 gp=0xc000102700 m=nil [GC worker (idle)]:
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.gopark(0x4c40a0f489?, 0x3?, 0x8c?, 0x3?, 0x0?)
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]:         runtime/proc.go:435 +0xce fp=0xc00006d738 sp=0xc00006d718 pc=0x5f09a97ff86e
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.gcBgMarkWorker(0xc0000a7730)
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]:         runtime/mgc.go:1423 +0xe9 fp=0xc00006d7c8 sp=0xc00006d738 pc=0x5f09a97acd69
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.gcBgMarkStartWorkers.gowrap1()
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]:         runtime/mgc.go:1339 +0x25 fp=0xc00006d7e0 sp=0xc00006d7c8 pc=0x5f09a97acc45
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.goexit({})
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc00006d7e8 sp=0xc00006d7e0 pc=0x5f09a9806fa1
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: created by runtime.gcBgMarkStartWorkers in goroutine 1
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]:         runtime/mgc.go:1339 +0x105
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: goroutine 21 gp=0xc0001028c0 m=nil [GC worker (idle)]:
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.gopark(0x5f09ab5fac00?, 0x1?, 0x7a?, 0x9c?, 0x0?)
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]:         runtime/proc.go:435 +0xce fp=0xc00006df38 sp=0xc00006df18 pc=0x5f09a97ff86e
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.gcBgMarkWorker(0xc0000a7730)
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]:         runtime/mgc.go:1423 +0xe9 fp=0xc00006dfc8 sp=0xc00006df38 pc=0x5f09a97acd69
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.gcBgMarkStartWorkers.gowrap1()
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]:         runtime/mgc.go:1339 +0x25 fp=0xc00006dfe0 sp=0xc00006dfc8 pc=0x5f09a97acc45
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.goexit({})
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc00006dfe8 sp=0xc00006dfe0 pc=0x5f09a9806fa1
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: created by runtime.gcBgMarkStartWorkers in goroutine 1
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]:         runtime/mgc.go:1339 +0x105
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: rax    0x0
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: rbx    0x74b79c1bfe20
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: rcx    0x0
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: rdx    0x3f000000
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: rdi    0x0
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: rsi    0x138ce200
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: rbp    0x74b79c1dfe20
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: rsp    0x7ffd72abd940
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: r8     0x0
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: r9     0x0
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: r10    0x0
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: r11    0x0
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: r12    0x74b79c17bc40
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: r13    0x0
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: r14    0x5f09ab5729e0
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: r15    0x74b79c15b7c0
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: rip    0x74b79c0b34d6
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: rflags 0x10206
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: cs     0x33
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: fs     0x0
Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: gs     0x0
Sep 05 17:06:43 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: time=2025-09-05T17:06:43.313+08:00 level=INFO source=sched.go:441 msg="Load failed" model=/home/zhangj99/.ollama/models/blobs/sha256-3e4cb14174460404e7a233e531675303b2fbf7749c02f91864fe311ab6344e4f error="context canceled"
Sep 05 17:06:43 iZuf6bi9mf5aqzrm5qyr47Z systemd[1]: Stopping ollama.service - Ollama Service...
Sep 05 17:06:43 iZuf6bi9mf5aqzrm5qyr47Z systemd[1]: ollama.service: Deactivated successfully.
Sep 05 17:06:43 iZuf6bi9mf5aqzrm5qyr47Z systemd[1]: Stopped ollama.service - Ollama Service.
Sep 05 17:06:43 iZuf6bi9mf5aqzrm5qyr47Z systemd[1]: ollama.service: Consumed 4.756s CPU time, 381.1M memory peak, 0B memory swap peak.


v0.6.7:
Sep 05 21:18:08 iZuf6bi9mf5aqzrm5qyr47Z systemd[1]: Started ollama.service - Ollama Service.
Sep 05 21:18:08 iZuf6bi9mf5aqzrm5qyr47Z ollama[23038]: 2025/09/05 21:18:08 routes.go:1233: INFO server config env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:4096 OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/usr/share/ollama/.ollama/models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:0 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://* vscode-file://*] OLLAMA_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]"
Sep 05 21:18:08 iZuf6bi9mf5aqzrm5qyr47Z ollama[23038]: time=2025-09-05T21:18:08.510+08:00 level=INFO source=images.go:458 msg="total blobs: 0"
Sep 05 21:18:08 iZuf6bi9mf5aqzrm5qyr47Z ollama[23038]: time=2025-09-05T21:18:08.510+08:00 level=INFO source=images.go:465 msg="total unused blobs removed: 0"
Sep 05 21:18:08 iZuf6bi9mf5aqzrm5qyr47Z ollama[23038]: time=2025-09-05T21:18:08.510+08:00 level=INFO source=routes.go:1300 msg="Listening on 127.0.0.1:11434 (version 0.6.7)"
Sep 05 21:18:08 iZuf6bi9mf5aqzrm5qyr47Z ollama[23038]: time=2025-09-05T21:18:08.510+08:00 level=INFO source=gpu.go:217 msg="looking for compatible GPUs"
Sep 05 21:18:08 iZuf6bi9mf5aqzrm5qyr47Z ollama[23038]: time=2025-09-05T21:18:08.759+08:00 level=INFO source=types.go:130 msg="inference compute" id=GPU-897caf43-6646-3de4-3d9d-1e22730db58f library=cuda variant=v12 compute=7.0 driver=12.8 name="Tesla V100-SXM2-16GB" total="15.8 GiB" available="15.5 GiB"
Sep 05 21:19:40 iZuf6bi9mf5aqzrm5qyr47Z systemd[1]: Stopping ollama.service - Ollama Service...
Sep 05 21:19:40 iZuf6bi9mf5aqzrm5qyr47Z systemd[1]: ollama.service: Deactivated successfully.
Sep 05 21:19:40 iZuf6bi9mf5aqzrm5qyr47Z systemd[1]: Stopped ollama.service - Ollama Service.

OS

Linux

GPU

Nvidia

CPU

Intel

Ollama version

No response

Originally created by @jingzhang94 on GitHub (Sep 5, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/12194 ### What is the issue? I'm using Nvidia V100 and Cuda v12.8 on Ubuntu 24.04 When I install Ollama v0.11.10, and run qwen3:4b model, it keeps loading and never started to let me type prompts. However the GPU is not utilized at all. Now I have downgraded to v0.6.7, it throw message as below >>> Adding ollama user to render group... >>> Adding ollama user to video group... >>> Adding current user to ollama group... >>> Creating ollama systemd service... >>> Enabling and starting ollama service... Created symlink /etc/systemd/system/default.target.wants/ollama.service → /etc/systemd/system/ollama.service. >> NVIDIA GPU installed. zhangj99@iZuf6bi9mf5aqzrm5qyr47Z:~$ ollama list NAME ID SIZE MODIFIED qwen3:4b e55aed6fe643 2.5 GB 5 hours ago qwen3:8b 500a1f067a9f 5.2 GB 9 hours ago zhangj99@iZuf6bi9mf5aqzrm5qyr47Z:~$ ollama run qwen3:4b Error: llama runner process has terminated: exit status 2 nvidia-smi +-----------------------------------------------------------------------------------------+ | NVIDIA-SMI 570.133.20 Driver Version: 570.133.20 CUDA Version: 12.8 | |-----------------------------------------+------------------------+----------------------+ | GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC | | Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. | | | | MIG M. | |=========================================+========================+======================| | 0 Tesla V100-SXM2-16GB On | 00000000:00:07.0 Off | 0 | | N/A 34C P0 38W / 300W | 3MiB / 16384MiB | 0% Default | | | | N/A | +-----------------------------------------+------------------------+----------------------+ +-----------------------------------------------------------------------------------------+ | Processes: | | GPU GI CI PID Type Process name GPU Memory | | ID ID Usage | |=========================================================================================| | No running processes found | +-----------------------------------------------------------------------------------------+ ### Relevant log output ```shell v0.11.10: ep 05 16:56:59 iZuf6bi9mf5aqzrm5qyr47Z systemd[1]: Started ollama.service - Ollama Service. Sep 05 16:56:59 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: time=2025-09-05T16:56:59.768+08:00 level=INFO source=routes.go:1331 msg="server config" env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:4096 OLLAMA_DEBUG:INFO OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/home/zhangj99/.ollama/models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NEW_ESTIMATES:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:1 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://* vscode-file://*] OLLAMA_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]" Sep 05 16:56:59 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: time=2025-09-05T16:56:59.778+08:00 level=INFO source=images.go:477 msg="total blobs: 8" Sep 05 16:56:59 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: time=2025-09-05T16:56:59.778+08:00 level=INFO source=images.go:484 msg="total unused blobs removed: 0" Sep 05 16:56:59 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: time=2025-09-05T16:56:59.785+08:00 level=INFO source=routes.go:1384 msg="Listening on 127.0.0.1:11434 (version 0.11.10)" Sep 05 16:56:59 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: time=2025-09-05T16:56:59.790+08:00 level=INFO source=gpu.go:217 msg="looking for compatible GPUs" Sep 05 16:57:01 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: time=2025-09-05T16:57:01.157+08:00 level=INFO source=types.go:131 msg="inference compute" id=GPU-897caf43-6646-3de4-3d9d-1e22730db58f library=cuda variant=v12 compute=7.0 driver=12.8 name="Tesla V100-SXM2-16GB" total="15.8 GiB" available="15.5 GiB" Sep 05 16:57:01 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: time=2025-09-05T16:57:01.157+08:00 level=INFO source=routes.go:1425 msg="entering low vram mode" "total vram"="15.8 GiB" threshold="20.0 GiB" Sep 05 17:00:17 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: [GIN] 2025/09/05 - 17:00:17 | 200 | 960.574µs | 127.0.0.1 | HEAD "/" Sep 05 17:00:17 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: [GIN] 2025/09/05 - 17:00:17 | 200 | 89.488243ms | 127.0.0.1 | POST "/api/show" Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: llama_model_loader: loaded meta data with 33 key-value pairs and 398 tensors from /home/zhangj99/.ollama/models/blobs/sha256-3e4cb14174460404e7a233e531675303b2fbf7749c02f91864fe311ab6344e4f (version GGUF V3 (latest)) Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output. Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: llama_model_loader: - kv 0: general.architecture str = qwen3 Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: llama_model_loader: - kv 1: general.basename str = Qwen3 Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: llama_model_loader: - kv 2: general.file_type u32 = 15 Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: llama_model_loader: - kv 3: general.finetune str = Thinking Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: llama_model_loader: - kv 4: general.license str = apache-2.0 Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: llama_model_loader: - kv 5: general.license.link str = https://huggingface.co/Qwen/Qwen3-4B-... Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: llama_model_loader: - kv 6: general.name str = Qwen3 4B Thinking 2507 Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: llama_model_loader: - kv 7: general.parameter_count u64 = 4022468096 Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: llama_model_loader: - kv 8: general.quantization_version u32 = 2 Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: llama_model_loader: - kv 9: general.size_label str = 4B Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: llama_model_loader: - kv 10: general.tags arr[str,1] = ["text-generation"] Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: llama_model_loader: - kv 11: general.type str = model Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: llama_model_loader: - kv 12: general.version str = 2507 Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: llama_model_loader: - kv 13: qwen3.attention.head_count u32 = 32 Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: llama_model_loader: - kv 14: qwen3.attention.head_count_kv u32 = 8 Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: llama_model_loader: - kv 15: qwen3.attention.key_length u32 = 128 Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: llama_model_loader: - kv 16: qwen3.attention.layer_norm_rms_epsilon f32 = 0.000001 Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: llama_model_loader: - kv 17: qwen3.attention.value_length u32 = 128 Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: llama_model_loader: - kv 18: qwen3.block_count u32 = 36 Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: llama_model_loader: - kv 19: qwen3.context_length u32 = 262144 Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: llama_model_loader: - kv 20: qwen3.embedding_length u32 = 2560 Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: llama_model_loader: - kv 21: qwen3.feed_forward_length u32 = 9728 Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: llama_model_loader: - kv 22: qwen3.rope.freq_base f32 = 5000000.000000 Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: llama_model_loader: - kv 23: tokenizer.chat_template str = {%- if tools %}\n {{- '<|im_start|>... Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: llama_model_loader: - kv 24: tokenizer.ggml.add_bos_token bool = false Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: llama_model_loader: - kv 25: tokenizer.ggml.bos_token_id u32 = 151643 Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: llama_model_loader: - kv 26: tokenizer.ggml.eos_token_id u32 = 151645 Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: llama_model_loader: - kv 27: tokenizer.ggml.merges arr[str,151387] = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",... Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: llama_model_loader: - kv 28: tokenizer.ggml.model str = gpt2 Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: llama_model_loader: - kv 29: tokenizer.ggml.padding_token_id u32 = 151643 Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: llama_model_loader: - kv 30: tokenizer.ggml.pre str = qwen2 Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: llama_model_loader: - kv 31: tokenizer.ggml.token_type arr[i32,151936] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: llama_model_loader: - kv 32: tokenizer.ggml.tokens arr[str,151936] = ["!", "\"", "#", "$", "%", "&", "'", ... Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: llama_model_loader: - type f32: 145 tensors Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: llama_model_loader: - type q4_K: 216 tensors Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: llama_model_loader: - type q6_K: 37 tensors Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: print_info: file format = GGUF V3 (latest) Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: print_info: file type = Q4_K - Medium Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: print_info: file size = 2.32 GiB (4.95 BPW) Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: load: printing all EOG tokens: Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: load: - 151643 ('<|endoftext|>') Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: load: - 151645 ('<|im_end|>') Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: load: - 151662 ('<|fim_pad|>') Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: load: - 151663 ('<|repo_name|>') Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: load: - 151664 ('<|file_sep|>') Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: load: special tokens cache size = 26 Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: load: token to piece cache size = 0.9311 MB Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: print_info: arch = qwen3 Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: print_info: vocab_only = 1 Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: print_info: model type = ?B Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: print_info: model params = 4.02 B Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: print_info: general.name = Qwen3 4B Thinking 2507 Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: print_info: vocab type = BPE Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: print_info: n_vocab = 151936 Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: print_info: n_merges = 151387 Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: print_info: BOS token = 151643 '<|endoftext|>' Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: print_info: EOS token = 151645 '<|im_end|>' Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: print_info: EOT token = 151645 '<|im_end|>' Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: print_info: PAD token = 151643 '<|endoftext|>' Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: print_info: LF token = 198 'Ċ' Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: print_info: FIM PRE token = 151659 '<|fim_prefix|>' Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: print_info: FIM SUF token = 151661 '<|fim_suffix|>' Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: print_info: FIM MID token = 151660 '<|fim_middle|>' Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: print_info: FIM PAD token = 151662 '<|fim_pad|>' Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: print_info: FIM REP token = 151663 '<|repo_name|>' Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: print_info: FIM SEP token = 151664 '<|file_sep|>' Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: print_info: EOG token = 151643 '<|endoftext|>' Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: print_info: EOG token = 151645 '<|im_end|>' Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: print_info: EOG token = 151662 '<|fim_pad|>' Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: print_info: EOG token = 151663 '<|repo_name|>' Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: print_info: EOG token = 151664 '<|file_sep|>' Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: print_info: max token length = 256 Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: llama_model_load: vocab only - skipping tensors Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: time=2025-09-05T17:00:18.886+08:00 level=INFO source=server.go:398 msg="starting runner" cmd="/usr/local/bin/ollama runner --model /home/zhangj99/.ollama/models/blobs/sha256-3e4cb14174460404e7a233e531675303b2fbf7749c02f91864fe311ab6344e4f --port 38697" Sep 05 17:00:18 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: time=2025-09-05T17:00:18.909+08:00 level=INFO source=runner.go:864 msg="starting go runner" Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: time=2025-09-05T17:00:19.097+08:00 level=INFO source=server.go:503 msg="system memory" total="31.0 GiB" free="29.0 GiB" free_swap="0 B" Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: time=2025-09-05T17:00:19.098+08:00 level=INFO source=memory.go:36 msg="new model will fit in available VRAM across minimum required GPUs, loading" model=/home/zhangj99/.ollama/models/blobs/sha256-3e4cb14174460404e7a233e531675303b2fbf7749c02f91864fe311ab6344e4f library=cuda parallel=1 required="3.8 GiB" gpus=1 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: time=2025-09-05T17:00:19.098+08:00 level=INFO source=server.go:543 msg=offload library=cuda layers.requested=-1 layers.model=37 layers.offload=37 layers.split=[37] memory.available="[15.5 GiB]" memory.gpu_overhead="0 B" memory.required.full="3.8 GiB" memory.required.partial="3.8 GiB" memory.required.kv="576.0 MiB" memory.required.allocations="[3.8 GiB]" memory.weights.total="2.3 GiB" memory.weights.repeating="2.0 GiB" memory.weights.nonrepeating="304.3 MiB" memory.graph.full="384.0 MiB" memory.graph.partial="384.0 MiB" Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: ggml_cuda_init: found 1 CUDA devices: Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: Device 0: Tesla V100-SXM2-16GB, compute capability 7.0, VMM: yes, ID: GPU-897caf43-6646-3de4-3d9d-1e22730db58f Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: load_backend: loaded CUDA backend from /usr/local/lib/ollama/libggml-cuda.so Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: SIGILL: illegal instruction Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: PC=0x74b79c0b34d6 m=0 sigcode=2 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: signal arrived during cgo execution Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: instruction bytes: 0xc5 0xf9 0x6e 0xfa 0xc5 0xc2 0x5c 0x35 0xe 0x99 0xa 0x0 0xc5 0xf9 0x7e 0xf2 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: goroutine 1 gp=0xc000002380 m=0 mp=0x5f09ab54dd60 [syscall]: Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.cgocall(0x5f09aa4ee7c0, 0xc000515710) Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime/cgocall.go:167 +0x4b fp=0xc0005156e8 sp=0xc0005156b0 pc=0x5f09a97fc3eb Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: github.com/ollama/ollama/ml/backend/ggml/ggml/src._Cfunc_ggml_backend_load_all_from_path(0x5f09dfbbd3f0) Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: _cgo_gotypes.go:195 +0x3e fp=0xc000515710 sp=0xc0005156e8 pc=0x5f09a9ba967e Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: github.com/ollama/ollama/ml/backend/ggml/ggml/src.init.func1.1({0xc00003a074, 0x15}) Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: github.com/ollama/ollama/ml/backend/ggml/ggml/src/ggml.go:97 +0xf5 fp=0xc0005157a8 sp=0xc000515710 pc=0x5f09a9ba9115 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: github.com/ollama/ollama/ml/backend/ggml/ggml/src.init.func1() Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: github.com/ollama/ollama/ml/backend/ggml/ggml/src/ggml.go:98 +0x526 fp=0xc000515a38 sp=0xc0005157a8 pc=0x5f09a9ba8f66 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: github.com/ollama/ollama/ml/backend/ggml/ggml/src.init.OnceFunc.func2() Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: sync/oncefunc.go:27 +0x62 fp=0xc000515a80 sp=0xc000515a38 pc=0x5f09a9ba8962 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: sync.(*Once).doSlow(0x0?, 0x0?) Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: sync/once.go:78 +0xab fp=0xc000515ad8 sp=0xc000515a80 pc=0x5f09a98114ab Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: sync.(*Once).Do(0x0?, 0x0?) Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: sync/once.go:69 +0x19 fp=0xc000515af8 sp=0xc000515ad8 pc=0x5f09a98113d9 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: github.com/ollama/ollama/ml/backend/ggml/ggml/src.init.OnceFunc.func3() Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: sync/oncefunc.go:32 +0x2d fp=0xc000515b28 sp=0xc000515af8 pc=0x5f09a9ba88cd Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: github.com/ollama/ollama/llama.BackendInit() Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: github.com/ollama/ollama/llama/llama.go:61 +0x16 fp=0xc000515b38 sp=0xc000515b28 pc=0x5f09a9badc36 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: github.com/ollama/ollama/runner/llamarunner.Execute({0xc000034260, 0x4, 0x4}) Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: github.com/ollama/ollama/runner/llamarunner/runner.go:866 +0x395 fp=0xc000515d08 sp=0xc000515b38 pc=0x5f09a9c79415 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: github.com/ollama/ollama/runner.Execute({0xc000034250?, 0x0?, 0x0?}) Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: github.com/ollama/ollama/runner/runner.go:22 +0xd4 fp=0xc000515d30 sp=0xc000515d08 pc=0x5f09a9d08074 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: github.com/ollama/ollama/cmd.NewCLI.func2(0xc0001f3400?, {0x5f09aa7c1084?, 0x4?, 0x5f09aa7c1088?}) Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: github.com/ollama/ollama/cmd/cmd.go:1583 +0x45 fp=0xc000515d58 sp=0xc000515d30 pc=0x5f09aa46bce5 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: github.com/spf13/cobra.(*Command).execute(0xc0004caf08, {0xc000412500, 0x4, 0x4}) Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: github.com/spf13/cobra@v1.7.0/command.go:940 +0x85c fp=0xc000515e78 sp=0xc000515d58 pc=0x5f09a997789c Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: github.com/spf13/cobra.(*Command).ExecuteC(0xc00013b208) Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: github.com/spf13/cobra@v1.7.0/command.go:1068 +0x3a5 fp=0xc000515f30 sp=0xc000515e78 pc=0x5f09a99780e5 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: github.com/spf13/cobra.(*Command).Execute(...) Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: github.com/spf13/cobra@v1.7.0/command.go:992 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: github.com/spf13/cobra.(*Command).ExecuteContext(...) Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: github.com/spf13/cobra@v1.7.0/command.go:985 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: main.main() Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: github.com/ollama/ollama/main.go:12 +0x4d fp=0xc000515f50 sp=0xc000515f30 pc=0x5f09aa46c7cd Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.main() Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime/proc.go:283 +0x29d fp=0xc000515fe0 sp=0xc000515f50 pc=0x5f09a97cb9dd Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.goexit({}) Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime/asm_amd64.s:1700 +0x1 fp=0xc000515fe8 sp=0xc000515fe0 pc=0x5f09a9806fa1 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: goroutine 2 gp=0xc000002e00 m=nil [force gc (idle)]: Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime/proc.go:435 +0xce fp=0xc000070fa8 sp=0xc000070f88 pc=0x5f09a97ff86e Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.goparkunlock(...) Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime/proc.go:441 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.forcegchelper() Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime/proc.go:348 +0xb8 fp=0xc000070fe0 sp=0xc000070fa8 pc=0x5f09a97cbd18 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.goexit({}) Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime/asm_amd64.s:1700 +0x1 fp=0xc000070fe8 sp=0xc000070fe0 pc=0x5f09a9806fa1 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: created by runtime.init.7 in goroutine 1 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime/proc.go:336 +0x1a Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: goroutine 3 gp=0xc000003340 m=nil [GC sweep wait]: Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.gopark(0x1?, 0x0?, 0x0?, 0x0?, 0x0?) Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime/proc.go:435 +0xce fp=0xc000071780 sp=0xc000071760 pc=0x5f09a97ff86e Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.goparkunlock(...) Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime/proc.go:441 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.bgsweep(0xc00009c000) Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime/mgcsweep.go:316 +0xdf fp=0xc0000717c8 sp=0xc000071780 pc=0x5f09a97b64bf Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.gcenable.gowrap1() Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime/mgc.go:204 +0x25 fp=0xc0000717e0 sp=0xc0000717c8 pc=0x5f09a97aa8a5 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.goexit({}) Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0000717e8 sp=0xc0000717e0 pc=0x5f09a9806fa1 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: created by runtime.gcenable in goroutine 1 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime/mgc.go:204 +0x66 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: goroutine 4 gp=0xc000003500 m=nil [GC scavenge wait]: Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.gopark(0x10000?, 0x5f09aa985380?, 0x0?, 0x0?, 0x0?) Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime/proc.go:435 +0xce fp=0xc000071f78 sp=0xc000071f58 pc=0x5f09a97ff86e Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.goparkunlock(...) Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime/proc.go:441 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.(*scavengerState).park(0x5f09ab54af40) Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime/mgcscavenge.go:425 +0x49 fp=0xc000071fa8 sp=0xc000071f78 pc=0x5f09a97b3f09 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.bgscavenge(0xc00009c000) Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime/mgcscavenge.go:658 +0x59 fp=0xc000071fc8 sp=0xc000071fa8 pc=0x5f09a97b4499 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.gcenable.gowrap2() Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime/mgc.go:205 +0x25 fp=0xc000071fe0 sp=0xc000071fc8 pc=0x5f09a97aa845 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.goexit({}) Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime/asm_amd64.s:1700 +0x1 fp=0xc000071fe8 sp=0xc000071fe0 pc=0x5f09a9806fa1 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: created by runtime.gcenable in goroutine 1 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime/mgc.go:205 +0xa5 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: goroutine 5 gp=0xc000003dc0 m=nil [finalizer wait]: Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.gopark(0x1b8?, 0xc000002380?, 0x1?, 0x23?, 0xc000070688?) Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime/proc.go:435 +0xce fp=0xc000070630 sp=0xc000070610 pc=0x5f09a97ff86e Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.runfinq() Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime/mfinal.go:196 +0x107 fp=0xc0000707e0 sp=0xc000070630 pc=0x5f09a97a9867 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.goexit({}) Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0000707e8 sp=0xc0000707e0 pc=0x5f09a9806fa1 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: created by runtime.createfing in goroutine 1 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime/mfinal.go:166 +0x3d Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: goroutine 6 gp=0xc0001d08c0 m=nil [chan receive]: Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.gopark(0xc000225900?, 0xc000590018?, 0x60?, 0x27?, 0x5f09a98e4e88?) Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime/proc.go:435 +0xce fp=0xc000072718 sp=0xc0000726f8 pc=0x5f09a97ff86e Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.chanrecv(0xc0000a6310, 0x0, 0x1) Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime/chan.go:664 +0x445 fp=0xc000072790 sp=0xc000072718 pc=0x5f09a979b245 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.chanrecv1(0x0?, 0x0?) Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime/chan.go:506 +0x12 fp=0xc0000727b8 sp=0xc000072790 pc=0x5f09a979add2 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.unique_runtime_registerUniqueMapCleanup.func2(...) Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime/mgc.go:1796 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.unique_runtime_registerUniqueMapCleanup.gowrap1() Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime/mgc.go:1799 +0x2f fp=0xc0000727e0 sp=0xc0000727b8 pc=0x5f09a97ada4f Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.goexit({}) Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0000727e8 sp=0xc0000727e0 pc=0x5f09a9806fa1 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: created by unique.runtime_registerUniqueMapCleanup in goroutine 1 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime/mgc.go:1794 +0x85 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: goroutine 7 gp=0xc0001d0c40 m=nil [GC worker (idle)]: Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime/proc.go:435 +0xce fp=0xc000072f38 sp=0xc000072f18 pc=0x5f09a97ff86e Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.gcBgMarkWorker(0xc0000a7730) Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime/mgc.go:1423 +0xe9 fp=0xc000072fc8 sp=0xc000072f38 pc=0x5f09a97acd69 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.gcBgMarkStartWorkers.gowrap1() Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime/mgc.go:1339 +0x25 fp=0xc000072fe0 sp=0xc000072fc8 pc=0x5f09a97acc45 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.goexit({}) Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime/asm_amd64.s:1700 +0x1 fp=0xc000072fe8 sp=0xc000072fe0 pc=0x5f09a9806fa1 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: created by runtime.gcBgMarkStartWorkers in goroutine 1 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime/mgc.go:1339 +0x105 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: goroutine 18 gp=0xc000102380 m=nil [GC worker (idle)]: Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime/proc.go:435 +0xce fp=0xc00006c738 sp=0xc00006c718 pc=0x5f09a97ff86e Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.gcBgMarkWorker(0xc0000a7730) Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime/mgc.go:1423 +0xe9 fp=0xc00006c7c8 sp=0xc00006c738 pc=0x5f09a97acd69 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.gcBgMarkStartWorkers.gowrap1() Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime/mgc.go:1339 +0x25 fp=0xc00006c7e0 sp=0xc00006c7c8 pc=0x5f09a97acc45 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.goexit({}) Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime/asm_amd64.s:1700 +0x1 fp=0xc00006c7e8 sp=0xc00006c7e0 pc=0x5f09a9806fa1 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: created by runtime.gcBgMarkStartWorkers in goroutine 1 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime/mgc.go:1339 +0x105 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: goroutine 34 gp=0xc000504000 m=nil [GC worker (idle)]: Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.gopark(0x4c40a32673?, 0x0?, 0x0?, 0x0?, 0x0?) Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime/proc.go:435 +0xce fp=0xc00050a738 sp=0xc00050a718 pc=0x5f09a97ff86e Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.gcBgMarkWorker(0xc0000a7730) Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime/mgc.go:1423 +0xe9 fp=0xc00050a7c8 sp=0xc00050a738 pc=0x5f09a97acd69 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.gcBgMarkStartWorkers.gowrap1() Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime/mgc.go:1339 +0x25 fp=0xc00050a7e0 sp=0xc00050a7c8 pc=0x5f09a97acc45 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.goexit({}) Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime/asm_amd64.s:1700 +0x1 fp=0xc00050a7e8 sp=0xc00050a7e0 pc=0x5f09a9806fa1 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: created by runtime.gcBgMarkStartWorkers in goroutine 1 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime/mgc.go:1339 +0x105 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: goroutine 8 gp=0xc0001d0e00 m=nil [GC worker (idle)]: Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.gopark(0x4c40a0e2c6?, 0x0?, 0x0?, 0x0?, 0x0?) Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime/proc.go:435 +0xce fp=0xc000073738 sp=0xc000073718 pc=0x5f09a97ff86e Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.gcBgMarkWorker(0xc0000a7730) Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime/mgc.go:1423 +0xe9 fp=0xc0000737c8 sp=0xc000073738 pc=0x5f09a97acd69 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.gcBgMarkStartWorkers.gowrap1() Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime/mgc.go:1339 +0x25 fp=0xc0000737e0 sp=0xc0000737c8 pc=0x5f09a97acc45 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.goexit({}) Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime/asm_amd64.s:1700 +0x1 fp=0xc0000737e8 sp=0xc0000737e0 pc=0x5f09a9806fa1 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: created by runtime.gcBgMarkStartWorkers in goroutine 1 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime/mgc.go:1339 +0x105 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: goroutine 19 gp=0xc000102540 m=nil [GC worker (idle)]: Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.gopark(0x4c409e61f1?, 0x0?, 0x0?, 0x0?, 0x0?) Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime/proc.go:435 +0xce fp=0xc00006cf38 sp=0xc00006cf18 pc=0x5f09a97ff86e Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.gcBgMarkWorker(0xc0000a7730) Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime/mgc.go:1423 +0xe9 fp=0xc00006cfc8 sp=0xc00006cf38 pc=0x5f09a97acd69 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.gcBgMarkStartWorkers.gowrap1() Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime/mgc.go:1339 +0x25 fp=0xc00006cfe0 sp=0xc00006cfc8 pc=0x5f09a97acc45 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.goexit({}) Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime/asm_amd64.s:1700 +0x1 fp=0xc00006cfe8 sp=0xc00006cfe0 pc=0x5f09a9806fa1 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: created by runtime.gcBgMarkStartWorkers in goroutine 1 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime/mgc.go:1339 +0x105 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: goroutine 9 gp=0xc0001d0fc0 m=nil [GC worker (idle)]: Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.gopark(0x4c40a13639?, 0x3?, 0xc?, 0x71?, 0x0?) Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime/proc.go:435 +0xce fp=0xc000073f38 sp=0xc000073f18 pc=0x5f09a97ff86e Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.gcBgMarkWorker(0xc0000a7730) Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime/mgc.go:1423 +0xe9 fp=0xc000073fc8 sp=0xc000073f38 pc=0x5f09a97acd69 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.gcBgMarkStartWorkers.gowrap1() Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime/mgc.go:1339 +0x25 fp=0xc000073fe0 sp=0xc000073fc8 pc=0x5f09a97acc45 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.goexit({}) Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime/asm_amd64.s:1700 +0x1 fp=0xc000073fe8 sp=0xc000073fe0 pc=0x5f09a9806fa1 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: created by runtime.gcBgMarkStartWorkers in goroutine 1 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime/mgc.go:1339 +0x105 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: goroutine 20 gp=0xc000102700 m=nil [GC worker (idle)]: Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.gopark(0x4c40a0f489?, 0x3?, 0x8c?, 0x3?, 0x0?) Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime/proc.go:435 +0xce fp=0xc00006d738 sp=0xc00006d718 pc=0x5f09a97ff86e Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.gcBgMarkWorker(0xc0000a7730) Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime/mgc.go:1423 +0xe9 fp=0xc00006d7c8 sp=0xc00006d738 pc=0x5f09a97acd69 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.gcBgMarkStartWorkers.gowrap1() Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime/mgc.go:1339 +0x25 fp=0xc00006d7e0 sp=0xc00006d7c8 pc=0x5f09a97acc45 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.goexit({}) Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime/asm_amd64.s:1700 +0x1 fp=0xc00006d7e8 sp=0xc00006d7e0 pc=0x5f09a9806fa1 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: created by runtime.gcBgMarkStartWorkers in goroutine 1 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime/mgc.go:1339 +0x105 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: goroutine 21 gp=0xc0001028c0 m=nil [GC worker (idle)]: Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.gopark(0x5f09ab5fac00?, 0x1?, 0x7a?, 0x9c?, 0x0?) Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime/proc.go:435 +0xce fp=0xc00006df38 sp=0xc00006df18 pc=0x5f09a97ff86e Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.gcBgMarkWorker(0xc0000a7730) Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime/mgc.go:1423 +0xe9 fp=0xc00006dfc8 sp=0xc00006df38 pc=0x5f09a97acd69 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.gcBgMarkStartWorkers.gowrap1() Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime/mgc.go:1339 +0x25 fp=0xc00006dfe0 sp=0xc00006dfc8 pc=0x5f09a97acc45 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime.goexit({}) Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime/asm_amd64.s:1700 +0x1 fp=0xc00006dfe8 sp=0xc00006dfe0 pc=0x5f09a9806fa1 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: created by runtime.gcBgMarkStartWorkers in goroutine 1 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: runtime/mgc.go:1339 +0x105 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: rax 0x0 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: rbx 0x74b79c1bfe20 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: rcx 0x0 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: rdx 0x3f000000 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: rdi 0x0 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: rsi 0x138ce200 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: rbp 0x74b79c1dfe20 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: rsp 0x7ffd72abd940 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: r8 0x0 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: r9 0x0 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: r10 0x0 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: r11 0x0 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: r12 0x74b79c17bc40 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: r13 0x0 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: r14 0x5f09ab5729e0 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: r15 0x74b79c15b7c0 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: rip 0x74b79c0b34d6 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: rflags 0x10206 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: cs 0x33 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: fs 0x0 Sep 05 17:00:19 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: gs 0x0 Sep 05 17:06:43 iZuf6bi9mf5aqzrm5qyr47Z ollama[1593]: time=2025-09-05T17:06:43.313+08:00 level=INFO source=sched.go:441 msg="Load failed" model=/home/zhangj99/.ollama/models/blobs/sha256-3e4cb14174460404e7a233e531675303b2fbf7749c02f91864fe311ab6344e4f error="context canceled" Sep 05 17:06:43 iZuf6bi9mf5aqzrm5qyr47Z systemd[1]: Stopping ollama.service - Ollama Service... Sep 05 17:06:43 iZuf6bi9mf5aqzrm5qyr47Z systemd[1]: ollama.service: Deactivated successfully. Sep 05 17:06:43 iZuf6bi9mf5aqzrm5qyr47Z systemd[1]: Stopped ollama.service - Ollama Service. Sep 05 17:06:43 iZuf6bi9mf5aqzrm5qyr47Z systemd[1]: ollama.service: Consumed 4.756s CPU time, 381.1M memory peak, 0B memory swap peak. v0.6.7: Sep 05 21:18:08 iZuf6bi9mf5aqzrm5qyr47Z systemd[1]: Started ollama.service - Ollama Service. Sep 05 21:18:08 iZuf6bi9mf5aqzrm5qyr47Z ollama[23038]: 2025/09/05 21:18:08 routes.go:1233: INFO server config env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:4096 OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/usr/share/ollama/.ollama/models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:0 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://* vscode-file://*] OLLAMA_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]" Sep 05 21:18:08 iZuf6bi9mf5aqzrm5qyr47Z ollama[23038]: time=2025-09-05T21:18:08.510+08:00 level=INFO source=images.go:458 msg="total blobs: 0" Sep 05 21:18:08 iZuf6bi9mf5aqzrm5qyr47Z ollama[23038]: time=2025-09-05T21:18:08.510+08:00 level=INFO source=images.go:465 msg="total unused blobs removed: 0" Sep 05 21:18:08 iZuf6bi9mf5aqzrm5qyr47Z ollama[23038]: time=2025-09-05T21:18:08.510+08:00 level=INFO source=routes.go:1300 msg="Listening on 127.0.0.1:11434 (version 0.6.7)" Sep 05 21:18:08 iZuf6bi9mf5aqzrm5qyr47Z ollama[23038]: time=2025-09-05T21:18:08.510+08:00 level=INFO source=gpu.go:217 msg="looking for compatible GPUs" Sep 05 21:18:08 iZuf6bi9mf5aqzrm5qyr47Z ollama[23038]: time=2025-09-05T21:18:08.759+08:00 level=INFO source=types.go:130 msg="inference compute" id=GPU-897caf43-6646-3de4-3d9d-1e22730db58f library=cuda variant=v12 compute=7.0 driver=12.8 name="Tesla V100-SXM2-16GB" total="15.8 GiB" available="15.5 GiB" Sep 05 21:19:40 iZuf6bi9mf5aqzrm5qyr47Z systemd[1]: Stopping ollama.service - Ollama Service... Sep 05 21:19:40 iZuf6bi9mf5aqzrm5qyr47Z systemd[1]: ollama.service: Deactivated successfully. Sep 05 21:19:40 iZuf6bi9mf5aqzrm5qyr47Z systemd[1]: Stopped ollama.service - Ollama Service. ``` ### OS Linux ### GPU Nvidia ### CPU Intel ### Ollama version _No response_
GiteaMirror added the bug label 2026-04-22 16:59:44 -05:00
GiteaMirror commented 2026-04-22 16:59:50 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Sep 5, 2025):

The GPU is not the problem. Ollama is trying to execute an instruction that your CPU doesn't support:

   0:	c5 f9 6e fa          	vmovd  %edx,%xmm7
   4:	c5 c2 5c 35 0e 99 0a 	vsubss 0xa990e(%rip),%xmm7,%xmm6        # 0xa991a
   b:	00 
   c:	c5 f9 7e f2          	vmovd  %xmm6,%edx

What's the output of sudo lscpu?

<!-- gh-comment-id:3258944515 --> @rick-github commented on GitHub (Sep 5, 2025): The GPU is not the problem. Ollama is trying to execute an instruction that your CPU doesn't support: ``` 0: c5 f9 6e fa vmovd %edx,%xmm7 4: c5 c2 5c 35 0e 99 0a vsubss 0xa990e(%rip),%xmm7,%xmm6 # 0xa991a b: 00 c: c5 f9 7e f2 vmovd %xmm6,%edx ``` What's the output of `sudo lscpu`?
GiteaMirror commented 2026-04-22 16:59:50 -05:00
Author
Owner
Copy Link

@rohitkhatri75436 commented on GitHub (Sep 5, 2025):

The GPU is not the problem. Ollama is trying to execute an instruction that your CPU doesn't support:

   0:	c5 f9 6e fa          	vmovd  %edx,%xmm7
   4:	c5 c2 5c 35 0e 99 0a 	vsubss 0xa990e(%rip),%xmm7,%xmm6        # 0xa991a
   b:	00 
   c:	c5 f9 7e f2          	vmovd  %xmm6,%edx

What's the output of sudo lscpu?

Is this only happening on the latest 0.11.10 version? If yes then i have to downgrade it.

<!-- gh-comment-id:3259015068 --> @rohitkhatri75436 commented on GitHub (Sep 5, 2025): > The GPU is not the problem. Ollama is trying to execute an instruction that your CPU doesn't support: > ``` > 0: c5 f9 6e fa vmovd %edx,%xmm7 > 4: c5 c2 5c 35 0e 99 0a vsubss 0xa990e(%rip),%xmm7,%xmm6 # 0xa991a > b: 00 > c: c5 f9 7e f2 vmovd %xmm6,%edx > ``` > What's the output of `sudo lscpu`? Is this only happening on the latest 0.11.10 version? If yes then i have to downgrade it.
GiteaMirror commented 2026-04-22 16:59:51 -05:00
Author
Owner
Copy Link

@jingzhang94 commented on GitHub (Sep 5, 2025):

The GPU is not the problem. Ollama is trying to execute an instruction that your CPU doesn't support:

   0:	c5 f9 6e fa          	vmovd  %edx,%xmm7
   4:	c5 c2 5c 35 0e 99 0a 	vsubss 0xa990e(%rip),%xmm7,%xmm6        # 0xa991a
   b:	00 
   c:	c5 f9 7e f2          	vmovd  %xmm6,%edx

What's the output of sudo lscpu?

@rick-github below are the output. Thanks for your support in advance.

Architecture: x86_64
CPU op-mode(s): 32-bit, 64-bit
Address sizes: 46 bits physical, 48 bits virtual
Byte Order: Little Endian
CPU(s): 8
On-line CPU(s) list: 0-7
Vendor ID: GenuineIntel
BIOS Vendor ID: Alibaba Cloud
Model name: Intel(R) Xeon(R) Platinum 8163 CPU @ 2.50GHz
BIOS Model name: pc-i440fx-2.1 CPU @ 0.0GHz
BIOS CPU family: 1
CPU family: 6
Model: 85
Thread(s) per core: 2
Core(s) per socket: 4
Socket(s): 1
Stepping: 4
BogoMIPS: 4999.98
Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge m
ca cmov pat pse36 clflush mmx fxsr sse sse2 ss ht sysc
all nx pdpe1gb rdtscp lm constant_tsc rep_good nopl no
nstop_tsc cpuid tsc_known_freq pni pclmulqdq monitor s
sse3 cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_d
eadline_timer aes f16c rdrand hypervisor lahf_lm abm 3
dnowprefetch pti ibrs ibpb stibp fsgsbase tsc_adjust b
mi1 hle smep bmi2 erms invpcid rtm rdseed adx smap ara
t
Virtualization features:
Hypervisor vendor: KVM
Virtualization type: full
Caches (sum of all):
L1d: 128 KiB (4 instances)
L1i: 128 KiB (4 instances)
L2: 4 MiB (4 instances)
L3: 33 MiB (1 instance)
NUMA:
NUMA node(s): 1
NUMA node0 CPU(s): 0-7
Vulnerabilities:
Gather data sampling: Unknown: Dependent on hypervisor status
Itlb multihit: KVM: Mitigation: VMX unsupported
L1tf: Mitigation; PTE Inversion
Mds: Vulnerable: Clear CPU buffers attempted, no microcode;
SMT Host state unknown
Meltdown: Mitigation; PTI
Mmio stale data: Vulnerable: Clear CPU buffers attempted, no microcode;
SMT Host state unknown
Reg file data sampling: Not affected
Retbleed: Mitigation; IBRS
Spec rstack overflow: Not affected
Spec store bypass: Vulnerable
Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointe
r sanitization
Spectre v2: Mitigation; IBRS; IBPB conditional; STIBP conditional;
RSB filling; PBRSB-eIBRS Not affected; BHI SW loop, K
VM SW loop
Srbds: Not affected
Tsx async abort: Vulnerable: Clear CPU buffers attempted, no microcode;
SMT Host state unknown

<!-- gh-comment-id:3259167480 --> @jingzhang94 commented on GitHub (Sep 5, 2025): > The GPU is not the problem. Ollama is trying to execute an instruction that your CPU doesn't support: > > ``` > 0: c5 f9 6e fa vmovd %edx,%xmm7 > 4: c5 c2 5c 35 0e 99 0a vsubss 0xa990e(%rip),%xmm7,%xmm6 # 0xa991a > b: 00 > c: c5 f9 7e f2 vmovd %xmm6,%edx > ``` > > What's the output of `sudo lscpu`? @rick-github below are the output. Thanks for your support in advance. Architecture: x86_64 CPU op-mode(s): 32-bit, 64-bit Address sizes: 46 bits physical, 48 bits virtual Byte Order: Little Endian CPU(s): 8 On-line CPU(s) list: 0-7 Vendor ID: GenuineIntel BIOS Vendor ID: Alibaba Cloud Model name: Intel(R) Xeon(R) Platinum 8163 CPU @ 2.50GHz BIOS Model name: pc-i440fx-2.1 CPU @ 0.0GHz BIOS CPU family: 1 CPU family: 6 Model: 85 Thread(s) per core: 2 Core(s) per socket: 4 Socket(s): 1 Stepping: 4 BogoMIPS: 4999.98 Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge m ca cmov pat pse36 clflush mmx fxsr sse sse2 ss ht sysc all nx pdpe1gb rdtscp lm constant_tsc rep_good nopl no nstop_tsc cpuid tsc_known_freq pni pclmulqdq monitor s sse3 cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_d eadline_timer aes f16c rdrand hypervisor lahf_lm abm 3 dnowprefetch pti ibrs ibpb stibp fsgsbase tsc_adjust b mi1 hle smep bmi2 erms invpcid rtm rdseed adx smap ara t Virtualization features: Hypervisor vendor: KVM Virtualization type: full Caches (sum of all): L1d: 128 KiB (4 instances) L1i: 128 KiB (4 instances) L2: 4 MiB (4 instances) L3: 33 MiB (1 instance) NUMA: NUMA node(s): 1 NUMA node0 CPU(s): 0-7 Vulnerabilities: Gather data sampling: Unknown: Dependent on hypervisor status Itlb multihit: KVM: Mitigation: VMX unsupported L1tf: Mitigation; PTE Inversion Mds: Vulnerable: Clear CPU buffers attempted, no microcode; SMT Host state unknown Meltdown: Mitigation; PTI Mmio stale data: Vulnerable: Clear CPU buffers attempted, no microcode; SMT Host state unknown Reg file data sampling: Not affected Retbleed: Mitigation; IBRS Spec rstack overflow: Not affected Spec store bypass: Vulnerable Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointe r sanitization Spectre v2: Mitigation; IBRS; IBPB conditional; STIBP conditional; RSB filling; PBRSB-eIBRS Not affected; BHI SW loop, K VM SW loop Srbds: Not affected Tsx async abort: Vulnerable: Clear CPU buffers attempted, no microcode; SMT Host state unknown
GiteaMirror commented 2026-04-22 16:59:52 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Sep 5, 2025):

Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge m
ca cmov pat pse36 clflush mmx fxsr sse sse2 ss ht sysc
all nx pdpe1gb rdtscp lm constant_tsc rep_good nopl no
nstop_tsc cpuid tsc_known_freq pni pclmulqdq monitor s
sse3 cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_d
eadline_timer aes f16c rdrand hypervisor lahf_lm abm 3
dnowprefetch pti ibrs ibpb stibp fsgsbase tsc_adjust b
mi1 hle smep bmi2 erms invpcid rtm rdseed adx smap arat

SSE but no AVX. According to https://en.wikichip.org/wiki/intel/xeon_platinum/8163 the chip supports AVX, so you need to enable AVX/AVX2/AVX512 pass-through in the hypervisor.

<!-- gh-comment-id:3259191588 --> @rick-github commented on GitHub (Sep 5, 2025): ``` Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge m ca cmov pat pse36 clflush mmx fxsr sse sse2 ss ht sysc all nx pdpe1gb rdtscp lm constant_tsc rep_good nopl no nstop_tsc cpuid tsc_known_freq pni pclmulqdq monitor s sse3 cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_d eadline_timer aes f16c rdrand hypervisor lahf_lm abm 3 dnowprefetch pti ibrs ibpb stibp fsgsbase tsc_adjust b mi1 hle smep bmi2 erms invpcid rtm rdseed adx smap arat ``` SSE but no AVX. According to https://en.wikichip.org/wiki/intel/xeon_platinum/8163 the chip supports AVX, so you need to enable AVX/AVX2/AVX512 pass-through in the hypervisor.
GiteaMirror commented 2026-04-22 16:59:53 -05:00
Author
Owner
Copy Link

@Mikhail42 commented on GitHub (Sep 5, 2025):

Have you tried to reboot your PC? The issue may occur after "hibernation" due to Nvidia problem on Linux.
https://github.com/ollama/ollama/issues/8426

<!-- gh-comment-id:3259207878 --> @Mikhail42 commented on GitHub (Sep 5, 2025): Have you tried to reboot your PC? The issue may occur after "hibernation" due to Nvidia problem on Linux. https://github.com/ollama/ollama/issues/8426
GiteaMirror commented 2026-04-22 16:59:54 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Sep 5, 2025):

It has nothing to do with the GPU, #8426 is not relevant.

<!-- gh-comment-id:3259212336 --> @rick-github commented on GitHub (Sep 5, 2025): It has nothing to do with the GPU, #8426 is not relevant.
GiteaMirror commented 2026-04-22 16:59:55 -05:00
Author
Owner
Copy Link

@jingzhang94 commented on GitHub (Sep 8, 2025):

@rick-github I tried editing [CMakeLists.txt] and build a backend free of AVX instructions following https://github.com/ollama/ollama/issues/10977. It's now working very well.

But how can I run the local build version through command 'ollama serve'?

<!-- gh-comment-id:3264449943 --> @jingzhang94 commented on GitHub (Sep 8, 2025): @rick-github I tried editing [CMakeLists.txt] and build a backend free of AVX instructions following https://github.com/ollama/ollama/issues/10977. It's now working very well. But how can I run the local build version through command 'ollama serve'?
GiteaMirror commented 2026-04-22 16:59:55 -05:00
Author
Owner
Copy Link

@jingzhang94 commented on GitHub (Sep 8, 2025):

Resolve by 'go build'. Thanks.

<!-- gh-comment-id:3264523735 --> @jingzhang94 commented on GitHub (Sep 8, 2025): Resolve by 'go build'. Thanks.
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#33870
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?