Aug 19 07:09:02 quadrireme ollama[569414]: time=2025-08-19T07:09:02.039-04:00 level=WARN source=types.go:626 msg="invalid option provided" option=keep_alive
Aug 19 07:09:02 quadrireme ollama[569414]: time=2025-08-19T07:09:02.258-04:00 level=INFO source=server.go:135 msg="system memory" total="62.6 GiB" free="51.1 GiB" free_swap="0 B"
Aug 19 07:09:02 quadrireme ollama[569414]: time=2025-08-19T07:09:02.259-04:00 level=INFO source=server.go:175 msg=offload library=cuda layers.requested=-1 layers.model=29 layers.offload=27 layers.split="" memory.available="[6.5 GiB]" memory.gpu_overhead="0 B" memory.required.full="7.0 GiB" memory.required.partial="6.4 GiB" memory.required.kv="1.1 GiB" memory.required.allocations="[6.4 GiB]" memory.weights.total="3.8 GiB" memory.weights.repeating="3.4 GiB" memory.weights.nonrepeating="426.4 MiB" memory.graph.full="1.1 GiB" memory.graph.partial="1.4 GiB"
Aug 19 07:09:02 quadrireme ollama[569414]: llama_model_loader: loaded meta data with 34 key-value pairs and 339 tensors from /var/lib/ollama/models/blobs/sha256-e37c9e2996ab00cbe2ea633cc0ca37a872b2df67b7229659874df63775e88c29 (version GGUF V3 (latest))
Aug 19 07:09:02 quadrireme ollama[569414]: llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
Aug 19 07:09:02 quadrireme ollama[569414]: llama_model_loader: - kv   0:                       general.architecture str              = qwen2
Aug 19 07:09:02 quadrireme ollama[569414]: llama_model_loader: - kv   1:                               general.type str              = model
Aug 19 07:09:02 quadrireme ollama[569414]: llama_model_loader: - kv   2:                               general.name str              = Qwen2.5 Coder 7B Instruct
Aug 19 07:09:02 quadrireme ollama[569414]: llama_model_loader: - kv   3:                           general.finetune str              = Instruct
Aug 19 07:09:02 quadrireme ollama[569414]: llama_model_loader: - kv   4:                           general.basename str              = Qwen2.5-Coder
Aug 19 07:09:02 quadrireme ollama[569414]: llama_model_loader: - kv   5:                         general.size_label str              = 7B
Aug 19 07:09:02 quadrireme ollama[569414]: llama_model_loader: - kv   6:                            general.license str              = apache-2.0
Aug 19 07:09:02 quadrireme ollama[569414]: llama_model_loader: - kv   7:                       general.license.link str              = https://huggingface.co/Qwen/Qwen2.5-C...
Aug 19 07:09:02 quadrireme ollama[569414]: llama_model_loader: - kv   8:                   general.base_model.count u32              = 1
Aug 19 07:09:02 quadrireme ollama[569414]: llama_model_loader: - kv   9:                  general.base_model.0.name str              = Qwen2.5 Coder 7B
Aug 19 07:09:02 quadrireme ollama[569414]: llama_model_loader: - kv  10:          general.base_model.0.organization str              = Qwen
Aug 19 07:09:02 quadrireme ollama[569414]: llama_model_loader: - kv  11:              general.base_model.0.repo_url str              = https://huggingface.co/Qwen/Qwen2.5-C...
Aug 19 07:09:02 quadrireme ollama[569414]: llama_model_loader: - kv  12:                               general.tags arr[str,6]       = ["code", "codeqwen", "chat", "qwen", ...
Aug 19 07:09:02 quadrireme ollama[569414]: llama_model_loader: - kv  13:                          general.languages arr[str,1]       = ["en"]
Aug 19 07:09:02 quadrireme ollama[569414]: llama_model_loader: - kv  14:                          qwen2.block_count u32              = 28
Aug 19 07:09:02 quadrireme ollama[569414]: llama_model_loader: - kv  15:                       qwen2.context_length u32              = 32768
Aug 19 07:09:02 quadrireme ollama[569414]: llama_model_loader: - kv  16:                     qwen2.embedding_length u32              = 3584
Aug 19 07:09:02 quadrireme ollama[569414]: llama_model_loader: - kv  17:                  qwen2.feed_forward_length u32              = 18944
Aug 19 07:09:02 quadrireme ollama[569414]: llama_model_loader: - kv  18:                 qwen2.attention.head_count u32              = 28
Aug 19 07:09:02 quadrireme ollama[569414]: llama_model_loader: - kv  19:              qwen2.attention.head_count_kv u32              = 4
Aug 19 07:09:02 quadrireme ollama[569414]: llama_model_loader: - kv  20:                       qwen2.rope.freq_base f32              = 1000000.000000
Aug 19 07:09:02 quadrireme ollama[569414]: llama_model_loader: - kv  21:     qwen2.attention.layer_norm_rms_epsilon f32              = 0.000001
Aug 19 07:09:02 quadrireme ollama[569414]: llama_model_loader: - kv  22:                          general.file_type u32              = 2
Aug 19 07:09:02 quadrireme ollama[569414]: llama_model_loader: - kv  23:                       tokenizer.ggml.model str              = gpt2
Aug 19 07:09:02 quadrireme ollama[569414]: llama_model_loader: - kv  24:                         tokenizer.ggml.pre str              = qwen2
Aug 19 07:09:02 quadrireme ollama[569414]: llama_model_loader: - kv  25:                      tokenizer.ggml.tokens arr[str,152064]  = ["!", "\"", "#", "$", "%", "&", "'", ...
Aug 19 07:09:02 quadrireme ollama[569414]: llama_model_loader: - kv  26:                  tokenizer.ggml.token_type arr[i32,152064]  = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
Aug 19 07:09:02 quadrireme ollama[569414]: llama_model_loader: - kv  27:                      tokenizer.ggml.merges arr[str,151387]  = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
Aug 19 07:09:02 quadrireme ollama[569414]: llama_model_loader: - kv  28:                tokenizer.ggml.eos_token_id u32              = 151645
Aug 19 07:09:02 quadrireme ollama[569414]: llama_model_loader: - kv  29:            tokenizer.ggml.padding_token_id u32              = 151643
Aug 19 07:09:02 quadrireme ollama[569414]: llama_model_loader: - kv  30:                tokenizer.ggml.bos_token_id u32              = 151643
Aug 19 07:09:02 quadrireme ollama[569414]: llama_model_loader: - kv  31:               tokenizer.ggml.add_bos_token bool             = false
Aug 19 07:09:02 quadrireme ollama[569414]: llama_model_loader: - kv  32:                    tokenizer.chat_template str              = {%- if tools %}\n    {{- '<|im_start|>...
Aug 19 07:09:02 quadrireme ollama[569414]: llama_model_loader: - kv  33:               general.quantization_version u32              = 2
Aug 19 07:09:02 quadrireme ollama[569414]: llama_model_loader: - type  f32:  141 tensors
Aug 19 07:09:02 quadrireme ollama[569414]: llama_model_loader: - type q4_0:  197 tensors
Aug 19 07:09:02 quadrireme ollama[569414]: llama_model_loader: - type q6_K:    1 tensors
Aug 19 07:09:02 quadrireme ollama[569414]: print_info: file format = GGUF V3 (latest)
Aug 19 07:09:02 quadrireme ollama[569414]: print_info: file type   = Q4_0
Aug 19 07:09:02 quadrireme ollama[569414]: print_info: file size   = 4.12 GiB (4.65 BPW)
Aug 19 07:09:02 quadrireme ollama[569414]: load: special tokens cache size = 22
Aug 19 07:09:02 quadrireme ollama[569414]: load: token to piece cache size = 0.9310 MB
Aug 19 07:09:02 quadrireme ollama[569414]: print_info: arch             = qwen2
Aug 19 07:09:02 quadrireme ollama[569414]: print_info: vocab_only       = 1
Aug 19 07:09:02 quadrireme ollama[569414]: print_info: model type       = ?B
Aug 19 07:09:02 quadrireme ollama[569414]: print_info: model params     = 7.62 B
Aug 19 07:09:02 quadrireme ollama[569414]: print_info: general.name     = Qwen2.5 Coder 7B Instruct
Aug 19 07:09:02 quadrireme ollama[569414]: print_info: vocab type       = BPE
Aug 19 07:09:02 quadrireme ollama[569414]: print_info: n_vocab          = 152064
Aug 19 07:09:02 quadrireme ollama[569414]: print_info: n_merges         = 151387
Aug 19 07:09:02 quadrireme ollama[569414]: print_info: BOS token        = 151643 '<|endoftext|>'
Aug 19 07:09:02 quadrireme ollama[569414]: print_info: EOS token        = 151645 '<|im_end|>'
Aug 19 07:09:02 quadrireme ollama[569414]: print_info: EOT token        = 151645 '<|im_end|>'
Aug 19 07:09:02 quadrireme ollama[569414]: print_info: PAD token        = 151643 '<|endoftext|>'
Aug 19 07:09:02 quadrireme ollama[569414]: print_info: LF token         = 198 'Ċ'
Aug 19 07:09:02 quadrireme ollama[569414]: print_info: FIM PRE token    = 151659 '<|fim_prefix|>'
Aug 19 07:09:02 quadrireme ollama[569414]: print_info: FIM SUF token    = 151661 '<|fim_suffix|>'
Aug 19 07:09:02 quadrireme ollama[569414]: print_info: FIM MID token    = 151660 '<|fim_middle|>'
Aug 19 07:09:02 quadrireme ollama[569414]: print_info: FIM PAD token    = 151662 '<|fim_pad|>'
Aug 19 07:09:02 quadrireme ollama[569414]: print_info: FIM REP token    = 151663 '<|repo_name|>'
Aug 19 07:09:02 quadrireme ollama[569414]: print_info: FIM SEP token    = 151664 '<|file_sep|>'
Aug 19 07:09:02 quadrireme ollama[569414]: print_info: EOG token        = 151643 '<|endoftext|>'
Aug 19 07:09:02 quadrireme ollama[569414]: print_info: EOG token        = 151645 '<|im_end|>'
Aug 19 07:09:02 quadrireme ollama[569414]: print_info: EOG token        = 151662 '<|fim_pad|>'
Aug 19 07:09:02 quadrireme ollama[569414]: print_info: EOG token        = 151663 '<|repo_name|>'
Aug 19 07:09:02 quadrireme ollama[569414]: print_info: EOG token        = 151664 '<|file_sep|>'
Aug 19 07:09:02 quadrireme ollama[569414]: print_info: max token length = 256
Aug 19 07:09:02 quadrireme ollama[569414]: llama_model_load: vocab only - skipping tensors
Aug 19 07:09:02 quadrireme ollama[569414]: time=2025-08-19T07:09:02.473-04:00 level=INFO source=server.go:438 msg="starting llama server" cmd="/nix/store/b7r9lvm65c52h3pvjhgq514knqc4a969-ollama-0.11.4/bin/.ollama-wrapped runner --model /var/lib/ollama/models/blobs/sha256-e37c9e2996ab00cbe2ea633cc0ca37a872b2df67b7229659874df63775e88c29 --ctx-size 20480 --batch-size 512 --n-gpu-layers 27 --threads 6 --parallel 1 --port 33523"
Aug 19 07:09:02 quadrireme ollama[569414]: time=2025-08-19T07:09:02.474-04:00 level=INFO source=sched.go:481 msg="loaded runners" count=1
Aug 19 07:09:02 quadrireme ollama[569414]: time=2025-08-19T07:09:02.474-04:00 level=INFO source=server.go:598 msg="waiting for llama runner to start responding"
Aug 19 07:09:02 quadrireme ollama[569414]: time=2025-08-19T07:09:02.474-04:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server not responding"
Aug 19 07:09:02 quadrireme ollama[569414]: time=2025-08-19T07:09:02.484-04:00 level=INFO source=runner.go:815 msg="starting go runner"
Aug 19 07:09:02 quadrireme ollama[569414]: ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
Aug 19 07:09:02 quadrireme ollama[569414]: ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
Aug 19 07:09:02 quadrireme ollama[569414]: ggml_cuda_init: found 1 CUDA devices:
Aug 19 07:09:02 quadrireme ollama[569414]:   Device 0: NVIDIA GeForce GTX 1070 with Max-Q Design, compute capability 6.1, VMM: yes
Aug 19 07:09:02 quadrireme ollama[569414]: load_backend: loaded CUDA backend from /nix/store/b7r9lvm65c52h3pvjhgq514knqc4a969-ollama-0.11.4/lib/ollama/libggml-cuda.so
Aug 19 07:09:02 quadrireme ollama[569414]: load_backend: loaded CPU backend from /nix/store/b7r9lvm65c52h3pvjhgq514knqc4a969-ollama-0.11.4/lib/ollama/libggml-cpu-haswell.so
Aug 19 07:09:02 quadrireme ollama[569414]: time=2025-08-19T07:09:02.547-04:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 CUDA.0.ARCHS=750,800,860,890,900,1000,1200 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(gcc)
Aug 19 07:09:02 quadrireme ollama[569414]: time=2025-08-19T07:09:02.547-04:00 level=INFO source=runner.go:874 msg="Server listening on 127.0.0.1:33523"
Aug 19 07:09:02 quadrireme ollama[569414]: llama_model_load_from_file_impl: using device CUDA0 (NVIDIA GeForce GTX 1070 with Max-Q Design) - 6642 MiB free
Aug 19 07:09:02 quadrireme ollama[569414]: llama_model_loader: loaded meta data with 34 key-value pairs and 339 tensors from /var/lib/ollama/models/blobs/sha256-e37c9e2996ab00cbe2ea633cc0ca37a872b2df67b7229659874df63775e88c29 (version GGUF V3 (latest))
Aug 19 07:09:02 quadrireme ollama[569414]: llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
Aug 19 07:09:02 quadrireme ollama[569414]: llama_model_loader: - kv   0:                       general.architecture str              = qwen2
Aug 19 07:09:02 quadrireme ollama[569414]: llama_model_loader: - kv   1:                               general.type str              = model
Aug 19 07:09:02 quadrireme ollama[569414]: llama_model_loader: - kv   2:                               general.name str              = Qwen2.5 Coder 7B Instruct
Aug 19 07:09:02 quadrireme ollama[569414]: llama_model_loader: - kv   3:                           general.finetune str              = Instruct
Aug 19 07:09:02 quadrireme ollama[569414]: llama_model_loader: - kv   4:                           general.basename str              = Qwen2.5-Coder
Aug 19 07:09:02 quadrireme ollama[569414]: llama_model_loader: - kv   5:                         general.size_label str              = 7B
Aug 19 07:09:02 quadrireme ollama[569414]: llama_model_loader: - kv   6:                            general.license str              = apache-2.0
Aug 19 07:09:02 quadrireme ollama[569414]: llama_model_loader: - kv   7:                       general.license.link str              = https://huggingface.co/Qwen/Qwen2.5-C...
Aug 19 07:09:02 quadrireme ollama[569414]: llama_model_loader: - kv   8:                   general.base_model.count u32              = 1
Aug 19 07:09:02 quadrireme ollama[569414]: llama_model_loader: - kv   9:                  general.base_model.0.name str              = Qwen2.5 Coder 7B
Aug 19 07:09:02 quadrireme ollama[569414]: llama_model_loader: - kv  10:          general.base_model.0.organization str              = Qwen
Aug 19 07:09:02 quadrireme ollama[569414]: llama_model_loader: - kv  11:              general.base_model.0.repo_url str              = https://huggingface.co/Qwen/Qwen2.5-C...
Aug 19 07:09:02 quadrireme ollama[569414]: llama_model_loader: - kv  12:                               general.tags arr[str,6]       = ["code", "codeqwen", "chat", "qwen", ...
Aug 19 07:09:02 quadrireme ollama[569414]: llama_model_loader: - kv  13:                          general.languages arr[str,1]       = ["en"]
Aug 19 07:09:02 quadrireme ollama[569414]: llama_model_loader: - kv  14:                          qwen2.block_count u32              = 28
Aug 19 07:09:02 quadrireme ollama[569414]: llama_model_loader: - kv  15:                       qwen2.context_length u32              = 32768
Aug 19 07:09:02 quadrireme ollama[569414]: llama_model_loader: - kv  16:                     qwen2.embedding_length u32              = 3584
Aug 19 07:09:02 quadrireme ollama[569414]: llama_model_loader: - kv  17:                  qwen2.feed_forward_length u32              = 18944
Aug 19 07:09:02 quadrireme ollama[569414]: llama_model_loader: - kv  18:                 qwen2.attention.head_count u32              = 28
Aug 19 07:09:02 quadrireme ollama[569414]: llama_model_loader: - kv  19:              qwen2.attention.head_count_kv u32              = 4
Aug 19 07:09:02 quadrireme ollama[569414]: llama_model_loader: - kv  20:                       qwen2.rope.freq_base f32              = 1000000.000000
Aug 19 07:09:02 quadrireme ollama[569414]: llama_model_loader: - kv  21:     qwen2.attention.layer_norm_rms_epsilon f32              = 0.000001
Aug 19 07:09:02 quadrireme ollama[569414]: llama_model_loader: - kv  22:                          general.file_type u32              = 2
Aug 19 07:09:02 quadrireme ollama[569414]: llama_model_loader: - kv  23:                       tokenizer.ggml.model str              = gpt2
Aug 19 07:09:02 quadrireme ollama[569414]: llama_model_loader: - kv  24:                         tokenizer.ggml.pre str              = qwen2
Aug 19 07:09:02 quadrireme ollama[569414]: llama_model_loader: - kv  25:                      tokenizer.ggml.tokens arr[str,152064]  = ["!", "\"", "#", "$", "%", "&", "'", ...
Aug 19 07:09:02 quadrireme ollama[569414]: llama_model_loader: - kv  26:                  tokenizer.ggml.token_type arr[i32,152064]  = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
Aug 19 07:09:02 quadrireme ollama[569414]: llama_model_loader: - kv  27:                      tokenizer.ggml.merges arr[str,151387]  = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
Aug 19 07:09:02 quadrireme ollama[569414]: llama_model_loader: - kv  28:                tokenizer.ggml.eos_token_id u32              = 151645
Aug 19 07:09:02 quadrireme ollama[569414]: llama_model_loader: - kv  29:            tokenizer.ggml.padding_token_id u32              = 151643
Aug 19 07:09:02 quadrireme ollama[569414]: llama_model_loader: - kv  30:                tokenizer.ggml.bos_token_id u32              = 151643
Aug 19 07:09:02 quadrireme ollama[569414]: llama_model_loader: - kv  31:               tokenizer.ggml.add_bos_token bool             = false
Aug 19 07:09:02 quadrireme ollama[569414]: llama_model_loader: - kv  32:                    tokenizer.chat_template str              = {%- if tools %}\n    {{- '<|im_start|>...
Aug 19 07:09:02 quadrireme ollama[569414]: llama_model_loader: - kv  33:               general.quantization_version u32              = 2
Aug 19 07:09:02 quadrireme ollama[569414]: llama_model_loader: - type  f32:  141 tensors
Aug 19 07:09:02 quadrireme ollama[569414]: llama_model_loader: - type q4_0:  197 tensors
Aug 19 07:09:02 quadrireme ollama[569414]: llama_model_loader: - type q6_K:    1 tensors
Aug 19 07:09:02 quadrireme ollama[569414]: print_info: file format = GGUF V3 (latest)
Aug 19 07:09:02 quadrireme ollama[569414]: print_info: file type   = Q4_0
Aug 19 07:09:02 quadrireme ollama[569414]: print_info: file size   = 4.12 GiB (4.65 BPW)
Aug 19 07:09:02 quadrireme ollama[569414]: time=2025-08-19T07:09:02.725-04:00 level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server loading model"
Aug 19 07:09:02 quadrireme ollama[569414]: load: special tokens cache size = 22
Aug 19 07:09:02 quadrireme ollama[569414]: load: token to piece cache size = 0.9310 MB
Aug 19 07:09:02 quadrireme ollama[569414]: print_info: arch             = qwen2
Aug 19 07:09:02 quadrireme ollama[569414]: print_info: vocab_only       = 0
Aug 19 07:09:02 quadrireme ollama[569414]: print_info: n_ctx_train      = 32768
Aug 19 07:09:02 quadrireme ollama[569414]: print_info: n_embd           = 3584
Aug 19 07:09:02 quadrireme ollama[569414]: print_info: n_layer          = 28
Aug 19 07:09:02 quadrireme ollama[569414]: print_info: n_head           = 28
Aug 19 07:09:02 quadrireme ollama[569414]: print_info: n_head_kv        = 4
Aug 19 07:09:02 quadrireme ollama[569414]: print_info: n_rot            = 128
Aug 19 07:09:02 quadrireme ollama[569414]: print_info: n_swa            = 0
Aug 19 07:09:02 quadrireme ollama[569414]: print_info: n_swa_pattern    = 1
Aug 19 07:09:02 quadrireme ollama[569414]: print_info: n_embd_head_k    = 128
Aug 19 07:09:02 quadrireme ollama[569414]: print_info: n_embd_head_v    = 128
Aug 19 07:09:02 quadrireme ollama[569414]: print_info: n_gqa            = 7
Aug 19 07:09:02 quadrireme ollama[569414]: print_info: n_embd_k_gqa     = 512
Aug 19 07:09:02 quadrireme ollama[569414]: print_info: n_embd_v_gqa     = 512
Aug 19 07:09:02 quadrireme ollama[569414]: print_info: f_norm_eps       = 0.0e+00
Aug 19 07:09:02 quadrireme ollama[569414]: print_info: f_norm_rms_eps   = 1.0e-06
Aug 19 07:09:02 quadrireme ollama[569414]: print_info: f_clamp_kqv      = 0.0e+00
Aug 19 07:09:02 quadrireme ollama[569414]: print_info: f_max_alibi_bias = 0.0e+00
Aug 19 07:09:02 quadrireme ollama[569414]: print_info: f_logit_scale    = 0.0e+00
Aug 19 07:09:02 quadrireme ollama[569414]: print_info: f_attn_scale     = 0.0e+00
Aug 19 07:09:02 quadrireme ollama[569414]: print_info: n_ff             = 18944
Aug 19 07:09:02 quadrireme ollama[569414]: print_info: n_expert         = 0
Aug 19 07:09:02 quadrireme ollama[569414]: print_info: n_expert_used    = 0
Aug 19 07:09:02 quadrireme ollama[569414]: print_info: causal attn      = 1
Aug 19 07:09:02 quadrireme ollama[569414]: print_info: pooling type     = -1
Aug 19 07:09:02 quadrireme ollama[569414]: print_info: rope type        = 2
Aug 19 07:09:02 quadrireme ollama[569414]: print_info: rope scaling     = linear
Aug 19 07:09:02 quadrireme ollama[569414]: print_info: freq_base_train  = 1000000.0
Aug 19 07:09:02 quadrireme ollama[569414]: print_info: freq_scale_train = 1
Aug 19 07:09:02 quadrireme ollama[569414]: print_info: n_ctx_orig_yarn  = 32768
Aug 19 07:09:02 quadrireme ollama[569414]: print_info: rope_finetuned   = unknown
Aug 19 07:09:02 quadrireme ollama[569414]: print_info: ssm_d_conv       = 0
Aug 19 07:09:02 quadrireme ollama[569414]: print_info: ssm_d_inner      = 0
Aug 19 07:09:02 quadrireme ollama[569414]: print_info: ssm_d_state      = 0
Aug 19 07:09:02 quadrireme ollama[569414]: print_info: ssm_dt_rank      = 0
Aug 19 07:09:02 quadrireme ollama[569414]: print_info: ssm_dt_b_c_rms   = 0
Aug 19 07:09:02 quadrireme ollama[569414]: print_info: model type       = 7B
Aug 19 07:09:02 quadrireme ollama[569414]: print_info: model params     = 7.62 B
Aug 19 07:09:02 quadrireme ollama[569414]: print_info: general.name     = Qwen2.5 Coder 7B Instruct
Aug 19 07:09:02 quadrireme ollama[569414]: print_info: vocab type       = BPE
Aug 19 07:09:02 quadrireme ollama[569414]: print_info: n_vocab          = 152064
Aug 19 07:09:02 quadrireme ollama[569414]: print_info: n_merges         = 151387
Aug 19 07:09:02 quadrireme ollama[569414]: print_info: BOS token        = 151643 '<|endoftext|>'
Aug 19 07:09:02 quadrireme ollama[569414]: print_info: EOS token        = 151645 '<|im_end|>'
Aug 19 07:09:02 quadrireme ollama[569414]: print_info: EOT token        = 151645 '<|im_end|>'
Aug 19 07:09:02 quadrireme ollama[569414]: print_info: PAD token        = 151643 '<|endoftext|>'
Aug 19 07:09:02 quadrireme ollama[569414]: print_info: LF token         = 198 'Ċ'
Aug 19 07:09:02 quadrireme ollama[569414]: print_info: FIM PRE token    = 151659 '<|fim_prefix|>'
Aug 19 07:09:02 quadrireme ollama[569414]: print_info: FIM SUF token    = 151661 '<|fim_suffix|>'
Aug 19 07:09:02 quadrireme ollama[569414]: print_info: FIM MID token    = 151660 '<|fim_middle|>'
Aug 19 07:09:02 quadrireme ollama[569414]: print_info: FIM PAD token    = 151662 '<|fim_pad|>'
Aug 19 07:09:02 quadrireme ollama[569414]: print_info: FIM REP token    = 151663 '<|repo_name|>'
Aug 19 07:09:02 quadrireme ollama[569414]: print_info: FIM SEP token    = 151664 '<|file_sep|>'
Aug 19 07:09:02 quadrireme ollama[569414]: print_info: EOG token        = 151643 '<|endoftext|>'
Aug 19 07:09:02 quadrireme ollama[569414]: print_info: EOG token        = 151645 '<|im_end|>'
Aug 19 07:09:02 quadrireme ollama[569414]: print_info: EOG token        = 151662 '<|fim_pad|>'
Aug 19 07:09:02 quadrireme ollama[569414]: print_info: EOG token        = 151663 '<|repo_name|>'
Aug 19 07:09:02 quadrireme ollama[569414]: print_info: EOG token        = 151664 '<|file_sep|>'
Aug 19 07:09:02 quadrireme ollama[569414]: print_info: max token length = 256
Aug 19 07:09:02 quadrireme ollama[569414]: load_tensors: loading model tensors, this can take a while... (mmap = true)
Aug 19 07:09:03 quadrireme ollama[569414]: load_tensors: offloading 27 repeating layers to GPU
Aug 19 07:09:03 quadrireme ollama[569414]: load_tensors: offloaded 27/29 layers to GPU
Aug 19 07:09:03 quadrireme ollama[569414]: load_tensors:        CUDA0 model buffer size =  3376.63 MiB
Aug 19 07:09:03 quadrireme ollama[569414]: load_tensors:   CPU_Mapped model buffer size =  4220.43 MiB
Aug 19 07:09:03 quadrireme ollama[569414]: llama_context: constructing llama_context
Aug 19 07:09:03 quadrireme ollama[569414]: llama_context: n_seq_max     = 1
Aug 19 07:09:03 quadrireme ollama[569414]: llama_context: n_ctx         = 20480
Aug 19 07:09:03 quadrireme ollama[569414]: llama_context: n_ctx_per_seq = 20480
Aug 19 07:09:03 quadrireme ollama[569414]: llama_context: n_batch       = 512
Aug 19 07:09:03 quadrireme ollama[569414]: llama_context: n_ubatch      = 512
Aug 19 07:09:03 quadrireme ollama[569414]: llama_context: causal_attn   = 1
Aug 19 07:09:03 quadrireme ollama[569414]: llama_context: flash_attn    = 0
Aug 19 07:09:03 quadrireme ollama[569414]: llama_context: freq_base     = 1000000.0
Aug 19 07:09:03 quadrireme ollama[569414]: llama_context: freq_scale    = 1
Aug 19 07:09:03 quadrireme ollama[569414]: llama_context: n_ctx_per_seq (20480) < n_ctx_train (32768) -- the full capacity of the model will not be utilized
Aug 19 07:09:03 quadrireme ollama[569414]: llama_context:        CPU  output buffer size =     0.59 MiB
Aug 19 07:09:03 quadrireme ollama[569414]: llama_kv_cache_unified: kv_size = 20480, type_k = 'f16', type_v = 'f16', n_layer = 28, can_shift = 1, padding = 32
Aug 19 07:09:03 quadrireme ollama[569414]: llama_kv_cache_unified:      CUDA0 KV buffer size =  1080.00 MiB
Aug 19 07:09:03 quadrireme ollama[569414]: llama_kv_cache_unified:        CPU KV buffer size =    40.00 MiB
Aug 19 07:09:03 quadrireme ollama[569414]: llama_kv_cache_unified: KV self size  = 1120.00 MiB, K (f16):  560.00 MiB, V (f16):  560.00 MiB
Aug 19 07:09:03 quadrireme ollama[569414]: llama_context:      CUDA0 compute buffer size =  1234.89 MiB
Aug 19 07:09:03 quadrireme ollama[569414]: llama_context:  CUDA_Host compute buffer size =    47.01 MiB
Aug 19 07:09:03 quadrireme ollama[569414]: llama_context: graph nodes  = 1042
Aug 19 07:09:03 quadrireme ollama[569414]: llama_context: graph splits = 18 (with bs=512), 3 (with bs=1)
Aug 19 07:09:03 quadrireme ollama[569414]: time=2025-08-19T07:09:03.478-04:00 level=INFO source=server.go:637 msg="llama runner started in 1.00 seconds"
Aug 19 07:09:04 quadrireme ollama[569414]: ggml_cuda_compute_forward: RMS_NORM failed
Aug 19 07:09:04 quadrireme ollama[569414]: CUDA error: no kernel image is available for execution on the device
Aug 19 07:09:04 quadrireme ollama[569414]:   current device: 0, in function ggml_cuda_compute_forward at /build/source/ml/backend/ggml/ggml/src/ggml-cuda/ggml-cuda.cu:2377
Aug 19 07:09:04 quadrireme ollama[569414]:   err
Aug 19 07:09:04 quadrireme ollama[569414]: /build/source/ml/backend/ggml/ggml/src/ggml-cuda/ggml-cuda.cu:77: CUDA error
Aug 19 07:09:04 quadrireme ollama[569414]: SIGSEGV: segmentation violation
Aug 19 07:09:04 quadrireme ollama[569414]: PC=0x7f8c574a4287 m=11 sigcode=1 addr=0x206003fd8
Aug 19 07:09:04 quadrireme ollama[569414]: signal arrived during cgo execution
Aug 19 07:09:04 quadrireme ollama[569414]: goroutine 51 gp=0xc000103340 m=11 mp=0xc000581008 [syscall]:
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.cgocall(0x1169c40, 0xc000088bd8)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/cgocall.go:167 +0x4b fp=0xc000088bb0 sp=0xc000088b78 pc=0x49726b
Aug 19 07:09:04 quadrireme ollama[569414]: github.com/ollama/ollama/llama._Cfunc_llama_decode(0x7f8ce0630cd0, {0x200, 0x7f8ce057abc0, 0x0, 0x7f8ce063b570, 0x7f8ce057cfe0, 0x7f8ce0577bb0, 0x7f8ce058ca90})
Aug 19 07:09:04 quadrireme ollama[569414]:         _cgo_gotypes.go:605 +0x46 fp=0xc000088bd8 sp=0xc000088bb0 pc=0x847366
Aug 19 07:09:04 quadrireme ollama[569414]: github.com/ollama/ollama/llama.(*Context).Decode.func1(...)
Aug 19 07:09:04 quadrireme ollama[569414]:         github.com/ollama/ollama/llama/llama.go:133
Aug 19 07:09:04 quadrireme ollama[569414]: github.com/ollama/ollama/llama.(*Context).Decode(0xc00050d588?, 0x1?)
Aug 19 07:09:04 quadrireme ollama[569414]:         github.com/ollama/ollama/llama/llama.go:133 +0xed fp=0xc000088cc0 sp=0xc000088bd8 pc=0x84948d
Aug 19 07:09:04 quadrireme ollama[569414]: github.com/ollama/ollama/runner/llamarunner.(*Server).processBatch(0xc0005a0000, 0xc00059c3c0, 0xc00050d728)
Aug 19 07:09:04 quadrireme ollama[569414]:         github.com/ollama/ollama/runner/llamarunner/runner.go:436 +0x209 fp=0xc000088ee8 sp=0xc000088cc0 pc=0x904ce9
Aug 19 07:09:04 quadrireme ollama[569414]: github.com/ollama/ollama/runner/llamarunner.(*Server).run(0xc0005a0000, {0x176e020, 0xc00059c140})
Aug 19 07:09:04 quadrireme ollama[569414]:         github.com/ollama/ollama/runner/llamarunner/runner.go:341 +0x1bb fp=0xc000088fb8 sp=0xc000088ee8 pc=0x90495b
Aug 19 07:09:04 quadrireme ollama[569414]: github.com/ollama/ollama/runner/llamarunner.Execute.gowrap2()
Aug 19 07:09:04 quadrireme ollama[569414]:         github.com/ollama/ollama/runner/llamarunner/runner.go:855 +0x28 fp=0xc000088fe0 sp=0xc000088fb8 pc=0x909128
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.goexit({})
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc000088fe8 sp=0xc000088fe0 pc=0x4a2581
Aug 19 07:09:04 quadrireme ollama[569414]: created by github.com/ollama/ollama/runner/llamarunner.Execute in goroutine 1
Aug 19 07:09:04 quadrireme ollama[569414]:         github.com/ollama/ollama/runner/llamarunner/runner.go:855 +0xc37
Aug 19 07:09:04 quadrireme ollama[569414]: goroutine 1 gp=0xc000002380 m=nil [IO wait]:
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/proc.go:435 +0xce fp=0xc0005c7608 sp=0xc0005c75e8 pc=0x49a6ee
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.netpollblock(0xc0000c1658?, 0x434006?, 0x0?)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/netpoll.go:575 +0xf7 fp=0xc0005c7640 sp=0xc0005c7608 pc=0x45fbf7
Aug 19 07:09:04 quadrireme ollama[569414]: internal/poll.runtime_pollWait(0x7f8cea685de0, 0x72)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/netpoll.go:351 +0x85 fp=0xc0005c7660 sp=0xc0005c7640 pc=0x499905
Aug 19 07:09:04 quadrireme ollama[569414]: internal/poll.(*pollDesc).wait(0xc00059a180?, 0x900000036?, 0x0)
Aug 19 07:09:04 quadrireme ollama[569414]:         internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc0005c7688 sp=0xc0005c7660 pc=0x521c27
Aug 19 07:09:04 quadrireme ollama[569414]: internal/poll.(*pollDesc).waitRead(...)
Aug 19 07:09:04 quadrireme ollama[569414]:         internal/poll/fd_poll_runtime.go:89
Aug 19 07:09:04 quadrireme ollama[569414]: internal/poll.(*FD).Accept(0xc00059a180)
Aug 19 07:09:04 quadrireme ollama[569414]:         internal/poll/fd_unix.go:620 +0x295 fp=0xc0005c7730 sp=0xc0005c7688 pc=0x526ff5
Aug 19 07:09:04 quadrireme ollama[569414]: net.(*netFD).accept(0xc00059a180)
Aug 19 07:09:04 quadrireme ollama[569414]:         net/fd_unix.go:172 +0x29 fp=0xc0005c77e8 sp=0xc0005c7730 pc=0x599769
Aug 19 07:09:04 quadrireme ollama[569414]: net.(*TCPListener).accept(0xc00012f980)
Aug 19 07:09:04 quadrireme ollama[569414]:         net/tcpsock_posix.go:159 +0x1b fp=0xc0005c7838 sp=0xc0005c77e8 pc=0x5af0db
Aug 19 07:09:04 quadrireme ollama[569414]: net.(*TCPListener).Accept(0xc00012f980)
Aug 19 07:09:04 quadrireme ollama[569414]:         net/tcpsock.go:380 +0x30 fp=0xc0005c7868 sp=0xc0005c7838 pc=0x5adf90
Aug 19 07:09:04 quadrireme ollama[569414]: net/http.(*onceCloseListener).Accept(0xc0005a0120?)
Aug 19 07:09:04 quadrireme ollama[569414]:         <autogenerated>:1 +0x24 fp=0xc0005c7880 sp=0xc0005c7868 pc=0x7c5f84
Aug 19 07:09:04 quadrireme ollama[569414]: net/http.(*Server).Serve(0xc000132800, {0x176b9c8, 0xc00012f980})
Aug 19 07:09:04 quadrireme ollama[569414]:         net/http/server.go:3424 +0x30c fp=0xc0005c79b0 sp=0xc0005c7880 pc=0x79d7ac
Aug 19 07:09:04 quadrireme ollama[569414]: github.com/ollama/ollama/runner/llamarunner.Execute({0xc000132020, 0xe, 0xe})
Aug 19 07:09:04 quadrireme ollama[569414]:         github.com/ollama/ollama/runner/llamarunner/runner.go:875 +0x100a fp=0xc0005c7d08 sp=0xc0005c79b0 pc=0x908e6a
Aug 19 07:09:04 quadrireme ollama[569414]: github.com/ollama/ollama/runner.Execute({0xc000132010?, 0x0?, 0x0?})
Aug 19 07:09:04 quadrireme ollama[569414]:         github.com/ollama/ollama/runner/runner.go:22 +0xd4 fp=0xc0005c7d30 sp=0xc0005c7d08 pc=0x992714
Aug 19 07:09:04 quadrireme ollama[569414]: github.com/ollama/ollama/cmd.NewCLI.func2(0xc000035000?, {0x1591a86?, 0x4?, 0x1591a8a?})
Aug 19 07:09:04 quadrireme ollama[569414]:         github.com/ollama/ollama/cmd/cmd.go:1583 +0x45 fp=0xc0005c7d58 sp=0xc0005c7d30 pc=0x10f7625
Aug 19 07:09:04 quadrireme ollama[569414]: github.com/spf13/cobra.(*Command).execute(0xc0006c4f08, {0xc0001cf500, 0xe, 0xe})
Aug 19 07:09:04 quadrireme ollama[569414]:         github.com/spf13/cobra@v1.7.0/command.go:940 +0x894 fp=0xc0005c7e78 sp=0xc0005c7d58 pc=0x613074
Aug 19 07:09:04 quadrireme ollama[569414]: github.com/spf13/cobra.(*Command).ExecuteC(0xc0000f3508)
Aug 19 07:09:04 quadrireme ollama[569414]:         github.com/spf13/cobra@v1.7.0/command.go:1068 +0x3a5 fp=0xc0005c7f30 sp=0xc0005c7e78 pc=0x6138c5
Aug 19 07:09:04 quadrireme ollama[569414]: github.com/spf13/cobra.(*Command).Execute(...)
Aug 19 07:09:04 quadrireme ollama[569414]:         github.com/spf13/cobra@v1.7.0/command.go:992
Aug 19 07:09:04 quadrireme ollama[569414]: github.com/spf13/cobra.(*Command).ExecuteContext(...)
Aug 19 07:09:04 quadrireme ollama[569414]:         github.com/spf13/cobra@v1.7.0/command.go:985
Aug 19 07:09:04 quadrireme ollama[569414]: main.main()
Aug 19 07:09:04 quadrireme ollama[569414]:         github.com/ollama/ollama/main.go:12 +0x4d fp=0xc0005c7f50 sp=0xc0005c7f30 pc=0x10f810d
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.main()
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/proc.go:283 +0x28b fp=0xc0005c7fe0 sp=0xc0005c7f50 pc=0x46722b
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.goexit({})
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0005c7fe8 sp=0xc0005c7fe0 pc=0x4a2581
Aug 19 07:09:04 quadrireme ollama[569414]: goroutine 2 gp=0xc000002e00 m=nil [force gc (idle)]:
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/proc.go:435 +0xce fp=0xc000078fa8 sp=0xc000078f88 pc=0x49a6ee
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.goparkunlock(...)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/proc.go:441
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.forcegchelper()
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/proc.go:348 +0xb3 fp=0xc000078fe0 sp=0xc000078fa8 pc=0x467573
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.goexit({})
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc000078fe8 sp=0xc000078fe0 pc=0x4a2581
Aug 19 07:09:04 quadrireme ollama[569414]: created by runtime.init.7 in goroutine 1
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/proc.go:336 +0x1a
Aug 19 07:09:04 quadrireme ollama[569414]: goroutine 3 gp=0xc000003340 m=nil [GC sweep wait]:
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gopark(0x1?, 0x0?, 0x0?, 0x0?, 0x0?)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/proc.go:435 +0xce fp=0xc000079780 sp=0xc000079760 pc=0x49a6ee
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.goparkunlock(...)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/proc.go:441
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.bgsweep(0xc0000a4000)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgcsweep.go:316 +0xdf fp=0xc0000797c8 sp=0xc000079780 pc=0x451d1f
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gcenable.gowrap1()
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgc.go:204 +0x25 fp=0xc0000797e0 sp=0xc0000797c8 pc=0x446185
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.goexit({})
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0000797e8 sp=0xc0000797e0 pc=0x4a2581
Aug 19 07:09:04 quadrireme ollama[569414]: created by runtime.gcenable in goroutine 1
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgc.go:204 +0x66
Aug 19 07:09:04 quadrireme ollama[569414]: goroutine 4 gp=0xc000003500 m=nil [GC scavenge wait]:
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gopark(0x10000?, 0x1758e30?, 0x0?, 0x0?, 0x0?)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/proc.go:435 +0xce fp=0xc000079f78 sp=0xc000079f58 pc=0x49a6ee
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.goparkunlock(...)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/proc.go:441
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.(*scavengerState).park(0x20ae6a0)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgcscavenge.go:425 +0x49 fp=0xc000079fa8 sp=0xc000079f78 pc=0x44f769
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.bgscavenge(0xc0000a4000)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgcscavenge.go:658 +0x59 fp=0xc000079fc8 sp=0xc000079fa8 pc=0x44fcf9
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gcenable.gowrap2()
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgc.go:205 +0x25 fp=0xc000079fe0 sp=0xc000079fc8 pc=0x446125
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.goexit({})
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc000079fe8 sp=0xc000079fe0 pc=0x4a2581
Aug 19 07:09:04 quadrireme ollama[569414]: created by runtime.gcenable in goroutine 1
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgc.go:205 +0xa5
Aug 19 07:09:04 quadrireme ollama[569414]: goroutine 18 gp=0xc000102700 m=nil [finalizer wait]:
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gopark(0x1b8?, 0xc000002380?, 0x1?, 0x23?, 0xc000078688?)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/proc.go:435 +0xce fp=0xc000078630 sp=0xc000078610 pc=0x49a6ee
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.runfinq()
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mfinal.go:196 +0x107 fp=0xc0000787e0 sp=0xc000078630 pc=0x445147
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.goexit({})
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0000787e8 sp=0xc0000787e0 pc=0x4a2581
Aug 19 07:09:04 quadrireme ollama[569414]: created by runtime.createfing in goroutine 1
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mfinal.go:166 +0x3d
Aug 19 07:09:04 quadrireme ollama[569414]: goroutine 19 gp=0xc000103180 m=nil [chan receive]:
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gopark(0xc00022b860?, 0xc000380018?, 0x60?, 0x47?, 0x5803a8?)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/proc.go:435 +0xce fp=0xc000074718 sp=0xc0000746f8 pc=0x49a6ee
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.chanrecv(0xc000110310, 0x0, 0x1)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/chan.go:664 +0x445 fp=0xc000074790 sp=0xc000074718 pc=0x436ba5
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.chanrecv1(0x0?, 0x0?)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/chan.go:506 +0x12 fp=0xc0000747b8 sp=0xc000074790 pc=0x436732
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.unique_runtime_registerUniqueMapCleanup.func2(...)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgc.go:1797
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.unique_runtime_registerUniqueMapCleanup.gowrap1()
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgc.go:1800 +0x2f fp=0xc0000747e0 sp=0xc0000747b8 pc=0x4492cf
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.goexit({})
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0000747e8 sp=0xc0000747e0 pc=0x4a2581
Aug 19 07:09:04 quadrireme ollama[569414]: created by unique.runtime_registerUniqueMapCleanup in goroutine 1
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgc.go:1795 +0x79
Aug 19 07:09:04 quadrireme ollama[569414]: goroutine 20 gp=0xc000103500 m=nil [GC worker (idle)]:
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/proc.go:435 +0xce fp=0xc000074f38 sp=0xc000074f18 pc=0x49a6ee
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gcBgMarkWorker(0xc000111730)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgc.go:1423 +0xe9 fp=0xc000074fc8 sp=0xc000074f38 pc=0x4485e9
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gcBgMarkStartWorkers.gowrap1()
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgc.go:1339 +0x25 fp=0xc000074fe0 sp=0xc000074fc8 pc=0x4484c5
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.goexit({})
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc000074fe8 sp=0xc000074fe0 pc=0x4a2581
Aug 19 07:09:04 quadrireme ollama[569414]: created by runtime.gcBgMarkStartWorkers in goroutine 1
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgc.go:1339 +0x105
Aug 19 07:09:04 quadrireme ollama[569414]: goroutine 34 gp=0xc000504000 m=nil [GC worker (idle)]:
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/proc.go:435 +0xce fp=0xc00050a738 sp=0xc00050a718 pc=0x49a6ee
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gcBgMarkWorker(0xc000111730)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgc.go:1423 +0xe9 fp=0xc00050a7c8 sp=0xc00050a738 pc=0x4485e9
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gcBgMarkStartWorkers.gowrap1()
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgc.go:1339 +0x25 fp=0xc00050a7e0 sp=0xc00050a7c8 pc=0x4484c5
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.goexit({})
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc00050a7e8 sp=0xc00050a7e0 pc=0x4a2581
Aug 19 07:09:04 quadrireme ollama[569414]: created by runtime.gcBgMarkStartWorkers in goroutine 1
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgc.go:1339 +0x105
Aug 19 07:09:04 quadrireme ollama[569414]: goroutine 35 gp=0xc0005041c0 m=nil [GC worker (idle)]:
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/proc.go:435 +0xce fp=0xc00050af38 sp=0xc00050af18 pc=0x49a6ee
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gcBgMarkWorker(0xc000111730)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgc.go:1423 +0xe9 fp=0xc00050afc8 sp=0xc00050af38 pc=0x4485e9
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gcBgMarkStartWorkers.gowrap1()
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgc.go:1339 +0x25 fp=0xc00050afe0 sp=0xc00050afc8 pc=0x4484c5
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.goexit({})
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc00050afe8 sp=0xc00050afe0 pc=0x4a2581
Aug 19 07:09:04 quadrireme ollama[569414]: created by runtime.gcBgMarkStartWorkers in goroutine 1
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgc.go:1339 +0x105
Aug 19 07:09:04 quadrireme ollama[569414]: goroutine 36 gp=0xc000504380 m=nil [GC worker (idle)]:
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/proc.go:435 +0xce fp=0xc00050b738 sp=0xc00050b718 pc=0x49a6ee
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gcBgMarkWorker(0xc000111730)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgc.go:1423 +0xe9 fp=0xc00050b7c8 sp=0xc00050b738 pc=0x4485e9
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gcBgMarkStartWorkers.gowrap1()
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgc.go:1339 +0x25 fp=0xc00050b7e0 sp=0xc00050b7c8 pc=0x4484c5
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.goexit({})
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc00050b7e8 sp=0xc00050b7e0 pc=0x4a2581
Aug 19 07:09:04 quadrireme ollama[569414]: created by runtime.gcBgMarkStartWorkers in goroutine 1
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgc.go:1339 +0x105
Aug 19 07:09:04 quadrireme ollama[569414]: goroutine 37 gp=0xc000504540 m=nil [GC worker (idle)]:
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/proc.go:435 +0xce fp=0xc00050bf38 sp=0xc00050bf18 pc=0x49a6ee
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gcBgMarkWorker(0xc000111730)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgc.go:1423 +0xe9 fp=0xc00050bfc8 sp=0xc00050bf38 pc=0x4485e9
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gcBgMarkStartWorkers.gowrap1()
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgc.go:1339 +0x25 fp=0xc00050bfe0 sp=0xc00050bfc8 pc=0x4484c5
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.goexit({})
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc00050bfe8 sp=0xc00050bfe0 pc=0x4a2581
Aug 19 07:09:04 quadrireme ollama[569414]: created by runtime.gcBgMarkStartWorkers in goroutine 1
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgc.go:1339 +0x105
Aug 19 07:09:04 quadrireme ollama[569414]: goroutine 38 gp=0xc000504700 m=nil [GC worker (idle)]:
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/proc.go:435 +0xce fp=0xc00050c738 sp=0xc00050c718 pc=0x49a6ee
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gcBgMarkWorker(0xc000111730)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgc.go:1423 +0xe9 fp=0xc00050c7c8 sp=0xc00050c738 pc=0x4485e9
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gcBgMarkStartWorkers.gowrap1()
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgc.go:1339 +0x25 fp=0xc00050c7e0 sp=0xc00050c7c8 pc=0x4484c5
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.goexit({})
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc00050c7e8 sp=0xc00050c7e0 pc=0x4a2581
Aug 19 07:09:04 quadrireme ollama[569414]: created by runtime.gcBgMarkStartWorkers in goroutine 1
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgc.go:1339 +0x105
Aug 19 07:09:04 quadrireme ollama[569414]: goroutine 5 gp=0xc000003a40 m=nil [GC worker (idle)]:
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gopark(0x4350ce299f8e?, 0x0?, 0x0?, 0x0?, 0x0?)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/proc.go:435 +0xce fp=0xc00007a738 sp=0xc00007a718 pc=0x49a6ee
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gcBgMarkWorker(0xc000111730)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgc.go:1423 +0xe9 fp=0xc00007a7c8 sp=0xc00007a738 pc=0x4485e9
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gcBgMarkStartWorkers.gowrap1()
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgc.go:1339 +0x25 fp=0xc00007a7e0 sp=0xc00007a7c8 pc=0x4484c5
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.goexit({})
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc00007a7e8 sp=0xc00007a7e0 pc=0x4a2581
Aug 19 07:09:04 quadrireme ollama[569414]: created by runtime.gcBgMarkStartWorkers in goroutine 1
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgc.go:1339 +0x105
Aug 19 07:09:04 quadrireme ollama[569414]: goroutine 21 gp=0xc0001036c0 m=nil [GC worker (idle)]:
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gopark(0x4350ce29b987?, 0x0?, 0x0?, 0x0?, 0x0?)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/proc.go:435 +0xce fp=0xc000075738 sp=0xc000075718 pc=0x49a6ee
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gcBgMarkWorker(0xc000111730)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgc.go:1423 +0xe9 fp=0xc0000757c8 sp=0xc000075738 pc=0x4485e9
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gcBgMarkStartWorkers.gowrap1()
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgc.go:1339 +0x25 fp=0xc0000757e0 sp=0xc0000757c8 pc=0x4484c5
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.goexit({})
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0000757e8 sp=0xc0000757e0 pc=0x4a2581
Aug 19 07:09:04 quadrireme ollama[569414]: created by runtime.gcBgMarkStartWorkers in goroutine 1
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgc.go:1339 +0x105
Aug 19 07:09:04 quadrireme ollama[569414]: goroutine 6 gp=0xc000003c00 m=nil [GC worker (idle)]:
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gopark(0x4350ce29c5a8?, 0x3?, 0xd4?, 0x11?, 0x0?)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/proc.go:435 +0xce fp=0xc00007af38 sp=0xc00007af18 pc=0x49a6ee
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gcBgMarkWorker(0xc000111730)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgc.go:1423 +0xe9 fp=0xc00007afc8 sp=0xc00007af38 pc=0x4485e9
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gcBgMarkStartWorkers.gowrap1()
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgc.go:1339 +0x25 fp=0xc00007afe0 sp=0xc00007afc8 pc=0x4484c5
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.goexit({})
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc00007afe8 sp=0xc00007afe0 pc=0x4a2581
Aug 19 07:09:04 quadrireme ollama[569414]: created by runtime.gcBgMarkStartWorkers in goroutine 1
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgc.go:1339 +0x105
Aug 19 07:09:04 quadrireme ollama[569414]: goroutine 7 gp=0xc000003dc0 m=nil [GC worker (idle)]:
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gopark(0x215cec0?, 0x1?, 0x9e?, 0x7?, 0x0?)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/proc.go:435 +0xce fp=0xc00007b738 sp=0xc00007b718 pc=0x49a6ee
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gcBgMarkWorker(0xc000111730)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgc.go:1423 +0xe9 fp=0xc00007b7c8 sp=0xc00007b738 pc=0x4485e9
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gcBgMarkStartWorkers.gowrap1()
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgc.go:1339 +0x25 fp=0xc00007b7e0 sp=0xc00007b7c8 pc=0x4484c5
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.goexit({})
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc00007b7e8 sp=0xc00007b7e0 pc=0x4a2581
Aug 19 07:09:04 quadrireme ollama[569414]: created by runtime.gcBgMarkStartWorkers in goroutine 1
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgc.go:1339 +0x105
Aug 19 07:09:04 quadrireme ollama[569414]: goroutine 8 gp=0xc0000b0000 m=nil [GC worker (idle)]:
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gopark(0x4350ce297a72?, 0x0?, 0x0?, 0x0?, 0x0?)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/proc.go:435 +0xce fp=0xc00007bf38 sp=0xc00007bf18 pc=0x49a6ee
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gcBgMarkWorker(0xc000111730)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgc.go:1423 +0xe9 fp=0xc00007bfc8 sp=0xc00007bf38 pc=0x4485e9
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gcBgMarkStartWorkers.gowrap1()
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgc.go:1339 +0x25 fp=0xc00007bfe0 sp=0xc00007bfc8 pc=0x4484c5
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.goexit({})
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc00007bfe8 sp=0xc00007bfe0 pc=0x4a2581
Aug 19 07:09:04 quadrireme ollama[569414]: created by runtime.gcBgMarkStartWorkers in goroutine 1
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgc.go:1339 +0x105
Aug 19 07:09:04 quadrireme ollama[569414]: goroutine 9 gp=0xc0000b01c0 m=nil [GC worker (idle)]:
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gopark(0x4350ce29a883?, 0x1?, 0x36?, 0x61?, 0x0?)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/proc.go:435 +0xce fp=0xc000506738 sp=0xc000506718 pc=0x49a6ee
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gcBgMarkWorker(0xc000111730)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgc.go:1423 +0xe9 fp=0xc0005067c8 sp=0xc000506738 pc=0x4485e9
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gcBgMarkStartWorkers.gowrap1()
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgc.go:1339 +0x25 fp=0xc0005067e0 sp=0xc0005067c8 pc=0x4484c5
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.goexit({})
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0005067e8 sp=0xc0005067e0 pc=0x4a2581
Aug 19 07:09:04 quadrireme ollama[569414]: created by runtime.gcBgMarkStartWorkers in goroutine 1
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgc.go:1339 +0x105
Aug 19 07:09:04 quadrireme ollama[569414]: goroutine 52 gp=0xc000103880 m=nil [select]:
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gopark(0xc00004fa78?, 0x2?, 0x0?, 0xc?, 0xc00004f8c4?)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/proc.go:435 +0xce fp=0xc00004f6f8 sp=0xc00004f6d8 pc=0x49a6ee
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.selectgo(0xc00004fa78, 0xc00004f8c0, 0x3346?, 0x0, 0x1?, 0x1)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/select.go:351 +0x837 fp=0xc00004f830 sp=0xc00004f6f8 pc=0x479637
Aug 19 07:09:04 quadrireme ollama[569414]: github.com/ollama/ollama/runner/llamarunner.(*Server).completion(0xc0005a0000, {0x176bba8, 0xc0006141c0}, 0xc0000b6280)
Aug 19 07:09:04 quadrireme ollama[569414]:         github.com/ollama/ollama/runner/llamarunner/runner.go:624 +0xb34 fp=0xc00004fac0 sp=0xc00004f830 pc=0x9068d4
Aug 19 07:09:04 quadrireme ollama[569414]: github.com/ollama/ollama/runner/llamarunner.(*Server).completion-fm({0x176bba8?, 0xc0006141c0?}, 0xc000175b40?)
Aug 19 07:09:04 quadrireme ollama[569414]:         <autogenerated>:1 +0x36 fp=0xc00004faf0 sp=0xc00004fac0 pc=0x909696
Aug 19 07:09:04 quadrireme ollama[569414]: net/http.HandlerFunc.ServeHTTP(0xc00015a240?, {0x176bba8?, 0xc0006141c0?}, 0xc000175b60?)
Aug 19 07:09:04 quadrireme ollama[569414]:         net/http/server.go:2294 +0x29 fp=0xc00004fb18 sp=0xc00004faf0 pc=0x799de9
Aug 19 07:09:04 quadrireme ollama[569414]: net/http.(*ServeMux).ServeHTTP(0x43f6e5?, {0x176bba8, 0xc0006141c0}, 0xc0000b6280)
Aug 19 07:09:04 quadrireme ollama[569414]:         net/http/server.go:2822 +0x1c4 fp=0xc00004fb68 sp=0xc00004fb18 pc=0x79bce4
Aug 19 07:09:04 quadrireme ollama[569414]: net/http.serverHandler.ServeHTTP({0x17681d0?}, {0x176bba8?, 0xc0006141c0?}, 0x1?)
Aug 19 07:09:04 quadrireme ollama[569414]:         net/http/server.go:3301 +0x8e fp=0xc00004fb98 sp=0xc00004fb68 pc=0x7b980e
Aug 19 07:09:04 quadrireme ollama[569414]: net/http.(*conn).serve(0xc0005a0120, {0x176dfe8, 0xc000596450})
Aug 19 07:09:04 quadrireme ollama[569414]:         net/http/server.go:2102 +0x625 fp=0xc00004ffb8 sp=0xc00004fb98 pc=0x7982e5
Aug 19 07:09:04 quadrireme ollama[569414]: net/http.(*Server).Serve.gowrap3()
Aug 19 07:09:04 quadrireme ollama[569414]:         net/http/server.go:3454 +0x28 fp=0xc00004ffe0 sp=0xc00004ffb8 pc=0x79dba8
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.goexit({})
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc00004ffe8 sp=0xc00004ffe0 pc=0x4a2581
Aug 19 07:09:04 quadrireme ollama[569414]: created by net/http.(*Server).Serve in goroutine 1
Aug 19 07:09:04 quadrireme ollama[569414]:         net/http/server.go:3454 +0x485
Aug 19 07:09:04 quadrireme ollama[569414]: goroutine 40 gp=0xc0000b0380 m=nil [IO wait]:
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gopark(0x2042e20?, 0xc00050de38?, 0x38?, 0xde?, 0xb?)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/proc.go:435 +0xce fp=0xc00050ddd8 sp=0xc00050ddb8 pc=0x49a6ee
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.netpollblock(0x4be198?, 0x434006?, 0x0?)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/netpoll.go:575 +0xf7 fp=0xc00050de10 sp=0xc00050ddd8 pc=0x45fbf7
Aug 19 07:09:04 quadrireme ollama[569414]: internal/poll.runtime_pollWait(0x7f8cea685cc8, 0x72)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/netpoll.go:351 +0x85 fp=0xc00050de30 sp=0xc00050de10 pc=0x499905
Aug 19 07:09:04 quadrireme ollama[569414]: internal/poll.(*pollDesc).wait(0xc00059a280?, 0xc00001e041?, 0x0)
Aug 19 07:09:04 quadrireme ollama[569414]:         internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc00050de58 sp=0xc00050de30 pc=0x521c27
Aug 19 07:09:04 quadrireme ollama[569414]: internal/poll.(*pollDesc).waitRead(...)
Aug 19 07:09:04 quadrireme ollama[569414]:         internal/poll/fd_poll_runtime.go:89
Aug 19 07:09:04 quadrireme ollama[569414]: internal/poll.(*FD).Read(0xc00059a280, {0xc00001e041, 0x1, 0x1})
Aug 19 07:09:04 quadrireme ollama[569414]:         internal/poll/fd_unix.go:165 +0x27a fp=0xc00050def0 sp=0xc00050de58 pc=0x522f1a
Aug 19 07:09:04 quadrireme ollama[569414]: net.(*netFD).Read(0xc00059a280, {0xc00001e041?, 0xc000300098?, 0xc00050df70?})
Aug 19 07:09:04 quadrireme ollama[569414]:         net/fd_posix.go:55 +0x25 fp=0xc00050df38 sp=0xc00050def0 pc=0x5977c5
Aug 19 07:09:04 quadrireme ollama[569414]: net.(*conn).Read(0xc00007c0c8, {0xc00001e041?, 0x0?, 0x0?})
Aug 19 07:09:04 quadrireme ollama[569414]:         net/net.go:194 +0x45 fp=0xc00050df80 sp=0xc00050df38 pc=0x5a5b65
Aug 19 07:09:04 quadrireme ollama[569414]: net/http.(*connReader).backgroundRead(0xc00001e030)
Aug 19 07:09:04 quadrireme ollama[569414]:         net/http/server.go:690 +0x37 fp=0xc00050dfc8 sp=0xc00050df80 pc=0x7921b7
Aug 19 07:09:04 quadrireme ollama[569414]: net/http.(*connReader).startBackgroundRead.gowrap2()
Aug 19 07:09:04 quadrireme ollama[569414]:         net/http/server.go:686 +0x25 fp=0xc00050dfe0 sp=0xc00050dfc8 pc=0x7920e5
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.goexit({})
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc00050dfe8 sp=0xc00050dfe0 pc=0x4a2581
Aug 19 07:09:04 quadrireme ollama[569414]: created by net/http.(*connReader).startBackgroundRead in goroutine 52
Aug 19 07:09:04 quadrireme ollama[569414]:         net/http/server.go:686 +0xb6
Aug 19 07:09:04 quadrireme ollama[569414]: rax    0x206003fd8
Aug 19 07:09:04 quadrireme ollama[569414]: rbx    0x7f8ce014c1d0
Aug 19 07:09:04 quadrireme ollama[569414]: rcx    0xff6
Aug 19 07:09:04 quadrireme ollama[569414]: rdx    0x7f8ce0008780
Aug 19 07:09:04 quadrireme ollama[569414]: rdi    0x0
Aug 19 07:09:04 quadrireme ollama[569414]: rsi    0x0
Aug 19 07:09:04 quadrireme ollama[569414]: rbp    0x7f89a8ffc500
Aug 19 07:09:04 quadrireme ollama[569414]: rsp    0x7f89a8ffc4e0
Aug 19 07:09:04 quadrireme ollama[569414]: r8     0x0
Aug 19 07:09:04 quadrireme ollama[569414]: r9     0x0
Aug 19 07:09:04 quadrireme ollama[569414]: r10    0x0
Aug 19 07:09:04 quadrireme ollama[569414]: r11    0x0
Aug 19 07:09:04 quadrireme ollama[569414]: r12    0x7f89a001ac70
Aug 19 07:09:04 quadrireme ollama[569414]: r13    0x7f8ce0008790
Aug 19 07:09:04 quadrireme ollama[569414]: r14    0x0
Aug 19 07:09:04 quadrireme ollama[569414]: r15    0x231dbd70
Aug 19 07:09:04 quadrireme ollama[569414]: rip    0x7f8c574a4287
Aug 19 07:09:04 quadrireme ollama[569414]: rflags 0x10297
Aug 19 07:09:04 quadrireme ollama[569414]: cs     0x33
Aug 19 07:09:04 quadrireme ollama[569414]: fs     0x0
Aug 19 07:09:04 quadrireme ollama[569414]: gs     0x0
Aug 19 07:09:04 quadrireme ollama[569414]: SIGABRT: abort
Aug 19 07:09:04 quadrireme ollama[569414]: PC=0x7f8d3289984c m=11 sigcode=18446744073709551610
Aug 19 07:09:04 quadrireme ollama[569414]: signal arrived during cgo execution
Aug 19 07:09:04 quadrireme ollama[569414]: goroutine 51 gp=0xc000103340 m=11 mp=0xc000581008 [syscall]:
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.cgocall(0x1169c40, 0xc000088bd8)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/cgocall.go:167 +0x4b fp=0xc000088bb0 sp=0xc000088b78 pc=0x49726b
Aug 19 07:09:04 quadrireme ollama[569414]: github.com/ollama/ollama/llama._Cfunc_llama_decode(0x7f8ce0630cd0, {0x200, 0x7f8ce057abc0, 0x0, 0x7f8ce063b570, 0x7f8ce057cfe0, 0x7f8ce0577bb0, 0x7f8ce058ca90})
Aug 19 07:09:04 quadrireme ollama[569414]:         _cgo_gotypes.go:605 +0x46 fp=0xc000088bd8 sp=0xc000088bb0 pc=0x847366
Aug 19 07:09:04 quadrireme ollama[569414]: github.com/ollama/ollama/llama.(*Context).Decode.func1(...)
Aug 19 07:09:04 quadrireme ollama[569414]:         github.com/ollama/ollama/llama/llama.go:133
Aug 19 07:09:04 quadrireme ollama[569414]: github.com/ollama/ollama/llama.(*Context).Decode(0xc00050d588?, 0x1?)
Aug 19 07:09:04 quadrireme ollama[569414]:         github.com/ollama/ollama/llama/llama.go:133 +0xed fp=0xc000088cc0 sp=0xc000088bd8 pc=0x84948d
Aug 19 07:09:04 quadrireme ollama[569414]: github.com/ollama/ollama/runner/llamarunner.(*Server).processBatch(0xc0005a0000, 0xc00059c3c0, 0xc00050d728)
Aug 19 07:09:04 quadrireme ollama[569414]:         github.com/ollama/ollama/runner/llamarunner/runner.go:436 +0x209 fp=0xc000088ee8 sp=0xc000088cc0 pc=0x904ce9
Aug 19 07:09:04 quadrireme ollama[569414]: github.com/ollama/ollama/runner/llamarunner.(*Server).run(0xc0005a0000, {0x176e020, 0xc00059c140})
Aug 19 07:09:04 quadrireme ollama[569414]:         github.com/ollama/ollama/runner/llamarunner/runner.go:341 +0x1bb fp=0xc000088fb8 sp=0xc000088ee8 pc=0x90495b
Aug 19 07:09:04 quadrireme ollama[569414]: github.com/ollama/ollama/runner/llamarunner.Execute.gowrap2()
Aug 19 07:09:04 quadrireme ollama[569414]:         github.com/ollama/ollama/runner/llamarunner/runner.go:855 +0x28 fp=0xc000088fe0 sp=0xc000088fb8 pc=0x909128
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.goexit({})
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc000088fe8 sp=0xc000088fe0 pc=0x4a2581
Aug 19 07:09:04 quadrireme ollama[569414]: created by github.com/ollama/ollama/runner/llamarunner.Execute in goroutine 1
Aug 19 07:09:04 quadrireme ollama[569414]:         github.com/ollama/ollama/runner/llamarunner/runner.go:855 +0xc37
Aug 19 07:09:04 quadrireme ollama[569414]: goroutine 1 gp=0xc000002380 m=nil [IO wait]:
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/proc.go:435 +0xce fp=0xc0005c7608 sp=0xc0005c75e8 pc=0x49a6ee
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.netpollblock(0xc0000c1658?, 0x434006?, 0x0?)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/netpoll.go:575 +0xf7 fp=0xc0005c7640 sp=0xc0005c7608 pc=0x45fbf7
Aug 19 07:09:04 quadrireme ollama[569414]: internal/poll.runtime_pollWait(0x7f8cea685de0, 0x72)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/netpoll.go:351 +0x85 fp=0xc0005c7660 sp=0xc0005c7640 pc=0x499905
Aug 19 07:09:04 quadrireme ollama[569414]: internal/poll.(*pollDesc).wait(0xc00059a180?, 0x900000036?, 0x0)
Aug 19 07:09:04 quadrireme ollama[569414]:         internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc0005c7688 sp=0xc0005c7660 pc=0x521c27
Aug 19 07:09:04 quadrireme ollama[569414]: internal/poll.(*pollDesc).waitRead(...)
Aug 19 07:09:04 quadrireme ollama[569414]:         internal/poll/fd_poll_runtime.go:89
Aug 19 07:09:04 quadrireme ollama[569414]: internal/poll.(*FD).Accept(0xc00059a180)
Aug 19 07:09:04 quadrireme ollama[569414]:         internal/poll/fd_unix.go:620 +0x295 fp=0xc0005c7730 sp=0xc0005c7688 pc=0x526ff5
Aug 19 07:09:04 quadrireme ollama[569414]: net.(*netFD).accept(0xc00059a180)
Aug 19 07:09:04 quadrireme ollama[569414]:         net/fd_unix.go:172 +0x29 fp=0xc0005c77e8 sp=0xc0005c7730 pc=0x599769
Aug 19 07:09:04 quadrireme ollama[569414]: net.(*TCPListener).accept(0xc00012f980)
Aug 19 07:09:04 quadrireme ollama[569414]:         net/tcpsock_posix.go:159 +0x1b fp=0xc0005c7838 sp=0xc0005c77e8 pc=0x5af0db
Aug 19 07:09:04 quadrireme ollama[569414]: net.(*TCPListener).Accept(0xc00012f980)
Aug 19 07:09:04 quadrireme ollama[569414]:         net/tcpsock.go:380 +0x30 fp=0xc0005c7868 sp=0xc0005c7838 pc=0x5adf90
Aug 19 07:09:04 quadrireme ollama[569414]: net/http.(*onceCloseListener).Accept(0xc0005a0120?)
Aug 19 07:09:04 quadrireme ollama[569414]:         <autogenerated>:1 +0x24 fp=0xc0005c7880 sp=0xc0005c7868 pc=0x7c5f84
Aug 19 07:09:04 quadrireme ollama[569414]: net/http.(*Server).Serve(0xc000132800, {0x176b9c8, 0xc00012f980})
Aug 19 07:09:04 quadrireme ollama[569414]:         net/http/server.go:3424 +0x30c fp=0xc0005c79b0 sp=0xc0005c7880 pc=0x79d7ac
Aug 19 07:09:04 quadrireme ollama[569414]: github.com/ollama/ollama/runner/llamarunner.Execute({0xc000132020, 0xe, 0xe})
Aug 19 07:09:04 quadrireme ollama[569414]:         github.com/ollama/ollama/runner/llamarunner/runner.go:875 +0x100a fp=0xc0005c7d08 sp=0xc0005c79b0 pc=0x908e6a
Aug 19 07:09:04 quadrireme ollama[569414]: github.com/ollama/ollama/runner.Execute({0xc000132010?, 0x0?, 0x0?})
Aug 19 07:09:04 quadrireme ollama[569414]:         github.com/ollama/ollama/runner/runner.go:22 +0xd4 fp=0xc0005c7d30 sp=0xc0005c7d08 pc=0x992714
Aug 19 07:09:04 quadrireme ollama[569414]: github.com/ollama/ollama/cmd.NewCLI.func2(0xc000035000?, {0x1591a86?, 0x4?, 0x1591a8a?})
Aug 19 07:09:04 quadrireme ollama[569414]:         github.com/ollama/ollama/cmd/cmd.go:1583 +0x45 fp=0xc0005c7d58 sp=0xc0005c7d30 pc=0x10f7625
Aug 19 07:09:04 quadrireme ollama[569414]: github.com/spf13/cobra.(*Command).execute(0xc0006c4f08, {0xc0001cf500, 0xe, 0xe})
Aug 19 07:09:04 quadrireme ollama[569414]:         github.com/spf13/cobra@v1.7.0/command.go:940 +0x894 fp=0xc0005c7e78 sp=0xc0005c7d58 pc=0x613074
Aug 19 07:09:04 quadrireme ollama[569414]: github.com/spf13/cobra.(*Command).ExecuteC(0xc0000f3508)
Aug 19 07:09:04 quadrireme ollama[569414]:         github.com/spf13/cobra@v1.7.0/command.go:1068 +0x3a5 fp=0xc0005c7f30 sp=0xc0005c7e78 pc=0x6138c5
Aug 19 07:09:04 quadrireme ollama[569414]: github.com/spf13/cobra.(*Command).Execute(...)
Aug 19 07:09:04 quadrireme ollama[569414]:         github.com/spf13/cobra@v1.7.0/command.go:992
Aug 19 07:09:04 quadrireme ollama[569414]: github.com/spf13/cobra.(*Command).ExecuteContext(...)
Aug 19 07:09:04 quadrireme ollama[569414]:         github.com/spf13/cobra@v1.7.0/command.go:985
Aug 19 07:09:04 quadrireme ollama[569414]: main.main()
Aug 19 07:09:04 quadrireme ollama[569414]:         github.com/ollama/ollama/main.go:12 +0x4d fp=0xc0005c7f50 sp=0xc0005c7f30 pc=0x10f810d
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.main()
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/proc.go:283 +0x28b fp=0xc0005c7fe0 sp=0xc0005c7f50 pc=0x46722b
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.goexit({})
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0005c7fe8 sp=0xc0005c7fe0 pc=0x4a2581
Aug 19 07:09:04 quadrireme ollama[569414]: goroutine 2 gp=0xc000002e00 m=nil [force gc (idle)]:
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/proc.go:435 +0xce fp=0xc000078fa8 sp=0xc000078f88 pc=0x49a6ee
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.goparkunlock(...)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/proc.go:441
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.forcegchelper()
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/proc.go:348 +0xb3 fp=0xc000078fe0 sp=0xc000078fa8 pc=0x467573
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.goexit({})
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc000078fe8 sp=0xc000078fe0 pc=0x4a2581
Aug 19 07:09:04 quadrireme ollama[569414]: created by runtime.init.7 in goroutine 1
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/proc.go:336 +0x1a
Aug 19 07:09:04 quadrireme ollama[569414]: goroutine 3 gp=0xc000003340 m=nil [GC sweep wait]:
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gopark(0x1?, 0x0?, 0x0?, 0x0?, 0x0?)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/proc.go:435 +0xce fp=0xc000079780 sp=0xc000079760 pc=0x49a6ee
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.goparkunlock(...)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/proc.go:441
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.bgsweep(0xc0000a4000)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgcsweep.go:316 +0xdf fp=0xc0000797c8 sp=0xc000079780 pc=0x451d1f
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gcenable.gowrap1()
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgc.go:204 +0x25 fp=0xc0000797e0 sp=0xc0000797c8 pc=0x446185
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.goexit({})
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0000797e8 sp=0xc0000797e0 pc=0x4a2581
Aug 19 07:09:04 quadrireme ollama[569414]: created by runtime.gcenable in goroutine 1
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgc.go:204 +0x66
Aug 19 07:09:04 quadrireme ollama[569414]: goroutine 4 gp=0xc000003500 m=nil [GC scavenge wait]:
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gopark(0x10000?, 0x1758e30?, 0x0?, 0x0?, 0x0?)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/proc.go:435 +0xce fp=0xc000079f78 sp=0xc000079f58 pc=0x49a6ee
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.goparkunlock(...)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/proc.go:441
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.(*scavengerState).park(0x20ae6a0)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgcscavenge.go:425 +0x49 fp=0xc000079fa8 sp=0xc000079f78 pc=0x44f769
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.bgscavenge(0xc0000a4000)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgcscavenge.go:658 +0x59 fp=0xc000079fc8 sp=0xc000079fa8 pc=0x44fcf9
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gcenable.gowrap2()
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgc.go:205 +0x25 fp=0xc000079fe0 sp=0xc000079fc8 pc=0x446125
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.goexit({})
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc000079fe8 sp=0xc000079fe0 pc=0x4a2581
Aug 19 07:09:04 quadrireme ollama[569414]: created by runtime.gcenable in goroutine 1
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgc.go:205 +0xa5
Aug 19 07:09:04 quadrireme ollama[569414]: goroutine 18 gp=0xc000102700 m=nil [finalizer wait]:
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gopark(0x1b8?, 0xc000002380?, 0x1?, 0x23?, 0xc000078688?)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/proc.go:435 +0xce fp=0xc000078630 sp=0xc000078610 pc=0x49a6ee
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.runfinq()
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mfinal.go:196 +0x107 fp=0xc0000787e0 sp=0xc000078630 pc=0x445147
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.goexit({})
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0000787e8 sp=0xc0000787e0 pc=0x4a2581
Aug 19 07:09:04 quadrireme ollama[569414]: created by runtime.createfing in goroutine 1
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mfinal.go:166 +0x3d
Aug 19 07:09:04 quadrireme ollama[569414]: goroutine 19 gp=0xc000103180 m=nil [chan receive]:
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gopark(0xc00022b860?, 0xc000380018?, 0x60?, 0x47?, 0x5803a8?)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/proc.go:435 +0xce fp=0xc000074718 sp=0xc0000746f8 pc=0x49a6ee
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.chanrecv(0xc000110310, 0x0, 0x1)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/chan.go:664 +0x445 fp=0xc000074790 sp=0xc000074718 pc=0x436ba5
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.chanrecv1(0x0?, 0x0?)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/chan.go:506 +0x12 fp=0xc0000747b8 sp=0xc000074790 pc=0x436732
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.unique_runtime_registerUniqueMapCleanup.func2(...)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgc.go:1797
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.unique_runtime_registerUniqueMapCleanup.gowrap1()
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgc.go:1800 +0x2f fp=0xc0000747e0 sp=0xc0000747b8 pc=0x4492cf
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.goexit({})
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0000747e8 sp=0xc0000747e0 pc=0x4a2581
Aug 19 07:09:04 quadrireme ollama[569414]: created by unique.runtime_registerUniqueMapCleanup in goroutine 1
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgc.go:1795 +0x79
Aug 19 07:09:04 quadrireme ollama[569414]: goroutine 20 gp=0xc000103500 m=nil [GC worker (idle)]:
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/proc.go:435 +0xce fp=0xc000074f38 sp=0xc000074f18 pc=0x49a6ee
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gcBgMarkWorker(0xc000111730)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgc.go:1423 +0xe9 fp=0xc000074fc8 sp=0xc000074f38 pc=0x4485e9
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gcBgMarkStartWorkers.gowrap1()
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgc.go:1339 +0x25 fp=0xc000074fe0 sp=0xc000074fc8 pc=0x4484c5
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.goexit({})
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc000074fe8 sp=0xc000074fe0 pc=0x4a2581
Aug 19 07:09:04 quadrireme ollama[569414]: created by runtime.gcBgMarkStartWorkers in goroutine 1
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgc.go:1339 +0x105
Aug 19 07:09:04 quadrireme ollama[569414]: goroutine 34 gp=0xc000504000 m=nil [GC worker (idle)]:
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/proc.go:435 +0xce fp=0xc00050a738 sp=0xc00050a718 pc=0x49a6ee
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gcBgMarkWorker(0xc000111730)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgc.go:1423 +0xe9 fp=0xc00050a7c8 sp=0xc00050a738 pc=0x4485e9
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gcBgMarkStartWorkers.gowrap1()
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgc.go:1339 +0x25 fp=0xc00050a7e0 sp=0xc00050a7c8 pc=0x4484c5
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.goexit({})
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc00050a7e8 sp=0xc00050a7e0 pc=0x4a2581
Aug 19 07:09:04 quadrireme ollama[569414]: created by runtime.gcBgMarkStartWorkers in goroutine 1
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgc.go:1339 +0x105
Aug 19 07:09:04 quadrireme ollama[569414]: goroutine 35 gp=0xc0005041c0 m=nil [GC worker (idle)]:
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/proc.go:435 +0xce fp=0xc00050af38 sp=0xc00050af18 pc=0x49a6ee
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gcBgMarkWorker(0xc000111730)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgc.go:1423 +0xe9 fp=0xc00050afc8 sp=0xc00050af38 pc=0x4485e9
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gcBgMarkStartWorkers.gowrap1()
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgc.go:1339 +0x25 fp=0xc00050afe0 sp=0xc00050afc8 pc=0x4484c5
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.goexit({})
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc00050afe8 sp=0xc00050afe0 pc=0x4a2581
Aug 19 07:09:04 quadrireme ollama[569414]: created by runtime.gcBgMarkStartWorkers in goroutine 1
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgc.go:1339 +0x105
Aug 19 07:09:04 quadrireme ollama[569414]: goroutine 36 gp=0xc000504380 m=nil [GC worker (idle)]:
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/proc.go:435 +0xce fp=0xc00050b738 sp=0xc00050b718 pc=0x49a6ee
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gcBgMarkWorker(0xc000111730)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgc.go:1423 +0xe9 fp=0xc00050b7c8 sp=0xc00050b738 pc=0x4485e9
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gcBgMarkStartWorkers.gowrap1()
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgc.go:1339 +0x25 fp=0xc00050b7e0 sp=0xc00050b7c8 pc=0x4484c5
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.goexit({})
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc00050b7e8 sp=0xc00050b7e0 pc=0x4a2581
Aug 19 07:09:04 quadrireme ollama[569414]: created by runtime.gcBgMarkStartWorkers in goroutine 1
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgc.go:1339 +0x105
Aug 19 07:09:04 quadrireme ollama[569414]: goroutine 37 gp=0xc000504540 m=nil [GC worker (idle)]:
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/proc.go:435 +0xce fp=0xc00050bf38 sp=0xc00050bf18 pc=0x49a6ee
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gcBgMarkWorker(0xc000111730)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgc.go:1423 +0xe9 fp=0xc00050bfc8 sp=0xc00050bf38 pc=0x4485e9
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gcBgMarkStartWorkers.gowrap1()
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgc.go:1339 +0x25 fp=0xc00050bfe0 sp=0xc00050bfc8 pc=0x4484c5
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.goexit({})
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc00050bfe8 sp=0xc00050bfe0 pc=0x4a2581
Aug 19 07:09:04 quadrireme ollama[569414]: created by runtime.gcBgMarkStartWorkers in goroutine 1
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgc.go:1339 +0x105
Aug 19 07:09:04 quadrireme ollama[569414]: goroutine 38 gp=0xc000504700 m=nil [GC worker (idle)]:
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/proc.go:435 +0xce fp=0xc00050c738 sp=0xc00050c718 pc=0x49a6ee
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gcBgMarkWorker(0xc000111730)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgc.go:1423 +0xe9 fp=0xc00050c7c8 sp=0xc00050c738 pc=0x4485e9
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gcBgMarkStartWorkers.gowrap1()
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgc.go:1339 +0x25 fp=0xc00050c7e0 sp=0xc00050c7c8 pc=0x4484c5
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.goexit({})
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc00050c7e8 sp=0xc00050c7e0 pc=0x4a2581
Aug 19 07:09:04 quadrireme ollama[569414]: created by runtime.gcBgMarkStartWorkers in goroutine 1
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgc.go:1339 +0x105
Aug 19 07:09:04 quadrireme ollama[569414]: goroutine 5 gp=0xc000003a40 m=nil [GC worker (idle)]:
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gopark(0x4350ce299f8e?, 0x0?, 0x0?, 0x0?, 0x0?)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/proc.go:435 +0xce fp=0xc00007a738 sp=0xc00007a718 pc=0x49a6ee
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gcBgMarkWorker(0xc000111730)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgc.go:1423 +0xe9 fp=0xc00007a7c8 sp=0xc00007a738 pc=0x4485e9
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gcBgMarkStartWorkers.gowrap1()
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgc.go:1339 +0x25 fp=0xc00007a7e0 sp=0xc00007a7c8 pc=0x4484c5
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.goexit({})
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc00007a7e8 sp=0xc00007a7e0 pc=0x4a2581
Aug 19 07:09:04 quadrireme ollama[569414]: created by runtime.gcBgMarkStartWorkers in goroutine 1
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgc.go:1339 +0x105
Aug 19 07:09:04 quadrireme ollama[569414]: goroutine 21 gp=0xc0001036c0 m=nil [GC worker (idle)]:
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gopark(0x4350ce29b987?, 0x0?, 0x0?, 0x0?, 0x0?)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/proc.go:435 +0xce fp=0xc000075738 sp=0xc000075718 pc=0x49a6ee
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gcBgMarkWorker(0xc000111730)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgc.go:1423 +0xe9 fp=0xc0000757c8 sp=0xc000075738 pc=0x4485e9
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gcBgMarkStartWorkers.gowrap1()
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgc.go:1339 +0x25 fp=0xc0000757e0 sp=0xc0000757c8 pc=0x4484c5
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.goexit({})
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0000757e8 sp=0xc0000757e0 pc=0x4a2581
Aug 19 07:09:04 quadrireme ollama[569414]: created by runtime.gcBgMarkStartWorkers in goroutine 1
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgc.go:1339 +0x105
Aug 19 07:09:04 quadrireme ollama[569414]: goroutine 6 gp=0xc000003c00 m=nil [GC worker (idle)]:
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gopark(0x4350ce29c5a8?, 0x3?, 0xd4?, 0x11?, 0x0?)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/proc.go:435 +0xce fp=0xc00007af38 sp=0xc00007af18 pc=0x49a6ee
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gcBgMarkWorker(0xc000111730)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgc.go:1423 +0xe9 fp=0xc00007afc8 sp=0xc00007af38 pc=0x4485e9
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gcBgMarkStartWorkers.gowrap1()
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgc.go:1339 +0x25 fp=0xc00007afe0 sp=0xc00007afc8 pc=0x4484c5
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.goexit({})
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc00007afe8 sp=0xc00007afe0 pc=0x4a2581
Aug 19 07:09:04 quadrireme ollama[569414]: created by runtime.gcBgMarkStartWorkers in goroutine 1
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgc.go:1339 +0x105
Aug 19 07:09:04 quadrireme ollama[569414]: goroutine 7 gp=0xc000003dc0 m=nil [GC worker (idle)]:
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gopark(0x215cec0?, 0x1?, 0x9e?, 0x7?, 0x0?)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/proc.go:435 +0xce fp=0xc00007b738 sp=0xc00007b718 pc=0x49a6ee
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gcBgMarkWorker(0xc000111730)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgc.go:1423 +0xe9 fp=0xc00007b7c8 sp=0xc00007b738 pc=0x4485e9
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gcBgMarkStartWorkers.gowrap1()
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgc.go:1339 +0x25 fp=0xc00007b7e0 sp=0xc00007b7c8 pc=0x4484c5
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.goexit({})
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc00007b7e8 sp=0xc00007b7e0 pc=0x4a2581
Aug 19 07:09:04 quadrireme ollama[569414]: created by runtime.gcBgMarkStartWorkers in goroutine 1
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgc.go:1339 +0x105
Aug 19 07:09:04 quadrireme ollama[569414]: goroutine 8 gp=0xc0000b0000 m=nil [GC worker (idle)]:
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gopark(0x4350ce297a72?, 0x0?, 0x0?, 0x0?, 0x0?)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/proc.go:435 +0xce fp=0xc00007bf38 sp=0xc00007bf18 pc=0x49a6ee
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gcBgMarkWorker(0xc000111730)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgc.go:1423 +0xe9 fp=0xc00007bfc8 sp=0xc00007bf38 pc=0x4485e9
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gcBgMarkStartWorkers.gowrap1()
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgc.go:1339 +0x25 fp=0xc00007bfe0 sp=0xc00007bfc8 pc=0x4484c5
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.goexit({})
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc00007bfe8 sp=0xc00007bfe0 pc=0x4a2581
Aug 19 07:09:04 quadrireme ollama[569414]: created by runtime.gcBgMarkStartWorkers in goroutine 1
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgc.go:1339 +0x105
Aug 19 07:09:04 quadrireme ollama[569414]: goroutine 9 gp=0xc0000b01c0 m=nil [GC worker (idle)]:
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gopark(0x4350ce29a883?, 0x1?, 0x36?, 0x61?, 0x0?)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/proc.go:435 +0xce fp=0xc000506738 sp=0xc000506718 pc=0x49a6ee
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gcBgMarkWorker(0xc000111730)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgc.go:1423 +0xe9 fp=0xc0005067c8 sp=0xc000506738 pc=0x4485e9
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gcBgMarkStartWorkers.gowrap1()
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgc.go:1339 +0x25 fp=0xc0005067e0 sp=0xc0005067c8 pc=0x4484c5
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.goexit({})
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc0005067e8 sp=0xc0005067e0 pc=0x4a2581
Aug 19 07:09:04 quadrireme ollama[569414]: created by runtime.gcBgMarkStartWorkers in goroutine 1
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/mgc.go:1339 +0x105
Aug 19 07:09:04 quadrireme ollama[569414]: goroutine 52 gp=0xc000103880 m=nil [select]:
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gopark(0xc00004fa78?, 0x2?, 0x0?, 0xc?, 0xc00004f8c4?)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/proc.go:435 +0xce fp=0xc00004f6f8 sp=0xc00004f6d8 pc=0x49a6ee
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.selectgo(0xc00004fa78, 0xc00004f8c0, 0x3346?, 0x0, 0x1?, 0x1)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/select.go:351 +0x837 fp=0xc00004f830 sp=0xc00004f6f8 pc=0x479637
Aug 19 07:09:04 quadrireme ollama[569414]: github.com/ollama/ollama/runner/llamarunner.(*Server).completion(0xc0005a0000, {0x176bba8, 0xc0006141c0}, 0xc0000b6280)
Aug 19 07:09:04 quadrireme ollama[569414]:         github.com/ollama/ollama/runner/llamarunner/runner.go:624 +0xb34 fp=0xc00004fac0 sp=0xc00004f830 pc=0x9068d4
Aug 19 07:09:04 quadrireme ollama[569414]: github.com/ollama/ollama/runner/llamarunner.(*Server).completion-fm({0x176bba8?, 0xc0006141c0?}, 0xc000175b40?)
Aug 19 07:09:04 quadrireme ollama[569414]:         <autogenerated>:1 +0x36 fp=0xc00004faf0 sp=0xc00004fac0 pc=0x909696
Aug 19 07:09:04 quadrireme ollama[569414]: net/http.HandlerFunc.ServeHTTP(0xc00015a240?, {0x176bba8?, 0xc0006141c0?}, 0xc000175b60?)
Aug 19 07:09:04 quadrireme ollama[569414]:         net/http/server.go:2294 +0x29 fp=0xc00004fb18 sp=0xc00004faf0 pc=0x799de9
Aug 19 07:09:04 quadrireme ollama[569414]: net/http.(*ServeMux).ServeHTTP(0x43f6e5?, {0x176bba8, 0xc0006141c0}, 0xc0000b6280)
Aug 19 07:09:04 quadrireme ollama[569414]:         net/http/server.go:2822 +0x1c4 fp=0xc00004fb68 sp=0xc00004fb18 pc=0x79bce4
Aug 19 07:09:04 quadrireme ollama[569414]: net/http.serverHandler.ServeHTTP({0x17681d0?}, {0x176bba8?, 0xc0006141c0?}, 0x1?)
Aug 19 07:09:04 quadrireme ollama[569414]:         net/http/server.go:3301 +0x8e fp=0xc00004fb98 sp=0xc00004fb68 pc=0x7b980e
Aug 19 07:09:04 quadrireme ollama[569414]: net/http.(*conn).serve(0xc0005a0120, {0x176dfe8, 0xc000596450})
Aug 19 07:09:04 quadrireme ollama[569414]:         net/http/server.go:2102 +0x625 fp=0xc00004ffb8 sp=0xc00004fb98 pc=0x7982e5
Aug 19 07:09:04 quadrireme ollama[569414]: net/http.(*Server).Serve.gowrap3()
Aug 19 07:09:04 quadrireme ollama[569414]:         net/http/server.go:3454 +0x28 fp=0xc00004ffe0 sp=0xc00004ffb8 pc=0x79dba8
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.goexit({})
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc00004ffe8 sp=0xc00004ffe0 pc=0x4a2581
Aug 19 07:09:04 quadrireme ollama[569414]: created by net/http.(*Server).Serve in goroutine 1
Aug 19 07:09:04 quadrireme ollama[569414]:         net/http/server.go:3454 +0x485
Aug 19 07:09:04 quadrireme ollama[569414]: goroutine 40 gp=0xc0000b0380 m=nil [IO wait]:
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.gopark(0x2042e20?, 0xc00050de38?, 0x38?, 0xde?, 0xb?)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/proc.go:435 +0xce fp=0xc00050ddd8 sp=0xc00050ddb8 pc=0x49a6ee
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.netpollblock(0x4be198?, 0x434006?, 0x0?)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/netpoll.go:575 +0xf7 fp=0xc00050de10 sp=0xc00050ddd8 pc=0x45fbf7
Aug 19 07:09:04 quadrireme ollama[569414]: internal/poll.runtime_pollWait(0x7f8cea685cc8, 0x72)
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/netpoll.go:351 +0x85 fp=0xc00050de30 sp=0xc00050de10 pc=0x499905
Aug 19 07:09:04 quadrireme ollama[569414]: internal/poll.(*pollDesc).wait(0xc00059a280?, 0xc00001e041?, 0x0)
Aug 19 07:09:04 quadrireme ollama[569414]:         internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc00050de58 sp=0xc00050de30 pc=0x521c27
Aug 19 07:09:04 quadrireme ollama[569414]: internal/poll.(*pollDesc).waitRead(...)
Aug 19 07:09:04 quadrireme ollama[569414]:         internal/poll/fd_poll_runtime.go:89
Aug 19 07:09:04 quadrireme ollama[569414]: internal/poll.(*FD).Read(0xc00059a280, {0xc00001e041, 0x1, 0x1})
Aug 19 07:09:04 quadrireme ollama[569414]:         internal/poll/fd_unix.go:165 +0x27a fp=0xc00050def0 sp=0xc00050de58 pc=0x522f1a
Aug 19 07:09:04 quadrireme ollama[569414]: net.(*netFD).Read(0xc00059a280, {0xc00001e041?, 0xc000300098?, 0xc00050df70?})
Aug 19 07:09:04 quadrireme ollama[569414]:         net/fd_posix.go:55 +0x25 fp=0xc00050df38 sp=0xc00050def0 pc=0x5977c5
Aug 19 07:09:04 quadrireme ollama[569414]: net.(*conn).Read(0xc00007c0c8, {0xc00001e041?, 0x0?, 0x0?})
Aug 19 07:09:04 quadrireme ollama[569414]:         net/net.go:194 +0x45 fp=0xc00050df80 sp=0xc00050df38 pc=0x5a5b65
Aug 19 07:09:04 quadrireme ollama[569414]: net/http.(*connReader).backgroundRead(0xc00001e030)
Aug 19 07:09:04 quadrireme ollama[569414]:         net/http/server.go:690 +0x37 fp=0xc00050dfc8 sp=0xc00050df80 pc=0x7921b7
Aug 19 07:09:04 quadrireme ollama[569414]: net/http.(*connReader).startBackgroundRead.gowrap2()
Aug 19 07:09:04 quadrireme ollama[569414]:         net/http/server.go:686 +0x25 fp=0xc00050dfe0 sp=0xc00050dfc8 pc=0x7920e5
Aug 19 07:09:04 quadrireme ollama[569414]: runtime.goexit({})
Aug 19 07:09:04 quadrireme ollama[569414]:         runtime/asm_amd64.s:1700 +0x1 fp=0xc00050dfe8 sp=0xc00050dfe0 pc=0x4a2581
Aug 19 07:09:04 quadrireme ollama[569414]: created by net/http.(*connReader).startBackgroundRead in goroutine 52
Aug 19 07:09:04 quadrireme ollama[569414]:         net/http/server.go:686 +0xb6
Aug 19 07:09:04 quadrireme ollama[569414]: rax    0x0
Aug 19 07:09:04 quadrireme ollama[569414]: rbx    0xf4e58
Aug 19 07:09:04 quadrireme ollama[569414]: rcx    0x7f8d3289984c
Aug 19 07:09:04 quadrireme ollama[569414]: rdx    0x6
Aug 19 07:09:04 quadrireme ollama[569414]: rdi    0xf4e24
Aug 19 07:09:04 quadrireme ollama[569414]: rsi    0xf4e58
Aug 19 07:09:04 quadrireme ollama[569414]: rbp    0x7f89a8ffd6c0
Aug 19 07:09:04 quadrireme ollama[569414]: rsp    0x7f89a8ffc650
Aug 19 07:09:04 quadrireme ollama[569414]: r8     0x0
Aug 19 07:09:04 quadrireme ollama[569414]: r9     0x0
Aug 19 07:09:04 quadrireme ollama[569414]: r10    0x8
Aug 19 07:09:04 quadrireme ollama[569414]: r11    0x246
Aug 19 07:09:04 quadrireme ollama[569414]: r12    0x7f8c9539b9f8
Aug 19 07:09:04 quadrireme ollama[569414]: r13    0x6
Aug 19 07:09:04 quadrireme ollama[569414]: r14    0x7f8c94c93378
Aug 19 07:09:04 quadrireme ollama[569414]: r15    0x7f8ce057bd60
Aug 19 07:09:04 quadrireme ollama[569414]: rip    0x7f8d3289984c
Aug 19 07:09:04 quadrireme ollama[569414]: rflags 0x246
Aug 19 07:09:04 quadrireme ollama[569414]: cs     0x33
Aug 19 07:09:04 quadrireme ollama[569414]: fs     0x0
Aug 19 07:09:04 quadrireme ollama[569414]: gs     0x0
Aug 19 07:09:04 quadrireme ollama[569414]: time=2025-08-19T07:09:04.985-04:00 level=ERROR source=server.go:807 msg="post predict" error="Post \"http://127.0.0.1:33523/completion\": EOF"
Aug 19 07:09:04 quadrireme ollama[569414]: [GIN] 2025/08/19 - 07:09:04 | 200 |  2.983162556s |       127.0.0.1 | POST     "/api/chat"
Aug 19 07:09:05 quadrireme ollama[569414]: time=2025-08-19T07:09:05.012-04:00 level=ERROR source=server.go:464 msg="llama runner terminated" error="exit status 2"