[GH-ISSUE #7568] CUDA error: unspecified launch failure in function ggml_backend_cuda_synchronize at ggml-cuda.cu:2508 #66877

New Issue

GiteaMirror · 2026-05-04T08:35:19-05:00

GiteaMirror commented

2026-05-04 08:35:19 -05:00

Originally created by @romansvet on GitHub (Nov 8, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/7568

Originally assigned to: @dhiltgen on GitHub.

What is the issue?

I am using open webUI version v0.3.30 and when I try to analyze an image using the llama3.2-vision:latest model I get nothing.
In the ollama service log I see the following:

Nov 08 07:06:28  ollama[11902]: time=2024-11-08T07:06:28.729Z level=WARN source=sched.go:137 msg="multimodal models don't support parallel requests yet"
Nov 08 07:06:28  ollama[11902]: time=2024-11-08T07:06:28.905Z level=INFO source=sched.go:730 msg="new model will fit in available VRAM, loading" model=/usr/share/ollama/.ollama/models/blobs/sha256-11f274007f093fefeec994a5dbbb33d0733a4feb87f7ab66dcd7c1069fef0068 library=cuda parallel=1 required="13.0 GiB"
Nov 08 07:06:29  ollama[11902]: time=2024-11-08T07:06:29.030Z level=INFO source=server.go:105 msg="system memory" total="125.7 GiB" free="123.6 GiB" free_swap="32.0 GiB"
Nov 08 07:06:29  ollama[11902]: time=2024-11-08T07:06:29.032Z level=INFO source=memory.go:343 msg="offload to cuda" projector.weights="1.8 GiB" projector.graph="2.8 GiB" layers.requested=-1 layers.model=41 layers.offload=41 layers.split=13,28 memory.available="[7.6 GiB 7.6 GiB]" memory.gpu_overhead="0 B" memory.required.full="13.0 GiB" memory.required.partial="13.0 GiB" memory.required.kv="656.2 MiB" memory.required.allocations="[7.6 GiB 5.4 GiB]" memory.weights.total="5.5 GiB" memory.weights.repeating="5.1 GiB" memory.weights.nonrepeating="411.0 MiB" memory.graph.full="669.5 MiB" memory.graph.partial="669.5 MiB"
Nov 08 07:06:29  ollama[11902]: time=2024-11-08T07:06:29.032Z level=INFO source=server.go:388 msg="starting llama server" cmd="/tmp/ollama1948393618/runners/cuda_v12/ollama_llama_server --model /usr/share/ollama/.ollama/models/blobs/sha256-11f274007f093fefeec994a5dbbb33d0733a4feb87f7ab66dcd7c1069fef0068 --ctx-size 2048 --batch-size 512 --embedding --n-gpu-layers 41 --mmproj /usr/share/ollama/.ollama/models/blobs/sha256-ece5e659647a20a5c28ab9eea1c12a1ad430bc0f2a27021d00ad103b3bf5206f --threads 4 --parallel 1 --tensor-split 13,28 --port 40263"
Nov 08 07:06:29  ollama[11902]: time=2024-11-08T07:06:29.032Z level=INFO source=sched.go:449 msg="loaded runners" count=1
Nov 08 07:06:29  ollama[11902]: time=2024-11-08T07:06:29.032Z level=INFO source=server.go:567 msg="waiting for llama runner to start responding"
Nov 08 07:06:29  ollama[11902]: time=2024-11-08T07:06:29.032Z level=INFO source=server.go:601 msg="waiting for server to become available" status="llm server error"
Nov 08 07:06:29  ollama[11902]: time=2024-11-08T07:06:29.056Z level=INFO source=runner.go:869 msg="starting go runner"
Nov 08 07:06:29  ollama[11902]: time=2024-11-08T07:06:29.056Z level=INFO source=runner.go:870 msg=system info="AVX = 1 | AVX_VNNI = 0 | AVX2 = 0 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | AVX512_BF16 = 0 | FMA = 0 | NEON = 0 | SVE = 0 | ARM_FMA = 0 | F16C = 0 | FP16_VA = 0 | RISCV_VECT = 0 | WASM_SIMD = 0 | BLAS = 1 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | MATMUL_INT8 = 0 | LLAMAFILE = 1 | cgo(gcc)" threads=4
Nov 08 07:06:29  ollama[11902]: time=2024-11-08T07:06:29.056Z level=INFO source=.:0 msg="Server listening on 127.0.0.1:40263"
Nov 08 07:06:29  ollama[11902]: llama_model_loader: loaded meta data with 27 key-value pairs and 396 tensors from /usr/share/ollama/.ollama/models/blobs/sha256-11f274007f093fefeec994a5dbbb33d0733a4feb87f7ab66dcd7c1069fef0068 (version GGUF V3 (latest))
Nov 08 07:06:29  ollama[11902]: llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
Nov 08 07:06:29  ollama[11902]: llama_model_loader: - kv   0:                       general.architecture str              = mllama
Nov 08 07:06:29  ollama[11902]: llama_model_loader: - kv   1:                               general.type str              = model
Nov 08 07:06:29  ollama[11902]: llama_model_loader: - kv   2:                               general.name str              = Model
Nov 08 07:06:29  ollama[11902]: llama_model_loader: - kv   3:                         general.size_label str              = 10B
Nov 08 07:06:29  ollama[11902]: llama_model_loader: - kv   4:                         mllama.block_count u32              = 40
Nov 08 07:06:29  ollama[11902]: llama_model_loader: - kv   5:                      mllama.context_length u32              = 131072
Nov 08 07:06:29  ollama[11902]: llama_model_loader: - kv   6:                    mllama.embedding_length u32              = 4096
Nov 08 07:06:29  ollama[11902]: llama_model_loader: - kv   7:                 mllama.feed_forward_length u32              = 14336
Nov 08 07:06:29  ollama[11902]: llama_model_loader: - kv   8:                mllama.attention.head_count u32              = 32
Nov 08 07:06:29  ollama[11902]: llama_model_loader: - kv   9:             mllama.attention.head_count_kv u32              = 8
Nov 08 07:06:29  ollama[11902]: llama_model_loader: - kv  10:                      mllama.rope.freq_base f32              = 500000.000000
Nov 08 07:06:29  ollama[11902]: llama_model_loader: - kv  11:    mllama.attention.layer_norm_rms_epsilon f32              = 0.000010
Nov 08 07:06:29  ollama[11902]: llama_model_loader: - kv  12:                          general.file_type u32              = 15
Nov 08 07:06:29  ollama[11902]: llama_model_loader: - kv  13:                          mllama.vocab_size u32              = 128256
Nov 08 07:06:29  ollama[11902]: llama_model_loader: - kv  14:                mllama.rope.dimension_count u32              = 128
Nov 08 07:06:29  ollama[11902]: llama_model_loader: - kv  15:    mllama.attention.cross_attention_layers arr[i32,8]       = [3, 8, 13, 18, 23, 28, 33, 38]
Nov 08 07:06:29  ollama[11902]: llama_model_loader: - kv  16:               tokenizer.ggml.add_bos_token bool             = true
Nov 08 07:06:29  ollama[11902]: llama_model_loader: - kv  17:                       tokenizer.ggml.model str              = gpt2
Nov 08 07:06:29  ollama[11902]: llama_model_loader: - kv  18:                         tokenizer.ggml.pre str              = llama-bpe
Nov 08 07:06:29  ollama[11902]: llama_model_loader: - kv  19:                      tokenizer.ggml.tokens arr[str,128257]  = ["!", "\"", "#", "$", "%", "&", "'", ...
Nov 08 07:06:29  ollama[11902]: llama_model_loader: - kv  20:                  tokenizer.ggml.token_type arr[i32,128257]  = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
Nov 08 07:06:29  ollama[11902]: llama_model_loader: - kv  21:                      tokenizer.ggml.merges arr[str,280147]  = ["Ġ Ġ", "Ġ ĠĠĠ", "ĠĠ ĠĠ", "...
Nov 08 07:06:29  ollama[11902]: llama_model_loader: - kv  22:                tokenizer.ggml.bos_token_id u32              = 128000
Nov 08 07:06:29  ollama[11902]: llama_model_loader: - kv  23:                tokenizer.ggml.eos_token_id u32              = 128009
Nov 08 07:06:29  ollama[11902]: llama_model_loader: - kv  24:            tokenizer.ggml.padding_token_id u32              = 128004
Nov 08 07:06:29  ollama[11902]: llama_model_loader: - kv  25:                    tokenizer.chat_template str              = {{- bos_token }}\n{%- if custom_tools ...
Nov 08 07:06:29  ollama[11902]: llama_model_loader: - kv  26:               general.quantization_version u32              = 2
Nov 08 07:06:29  ollama[11902]: llama_model_loader: - type  f32:  114 tensors
Nov 08 07:06:29  ollama[11902]: llama_model_loader: - type q4_K:  245 tensors
Nov 08 07:06:29  ollama[11902]: llama_model_loader: - type q6_K:   37 tensors
Nov 08 07:06:29  ollama[11902]: time=2024-11-08T07:06:29.283Z level=INFO source=server.go:601 msg="waiting for server to become available" status="llm server loading model"
Nov 08 07:06:29  ollama[11902]: llm_load_vocab: special tokens cache size = 257
Nov 08 07:06:29  ollama[11902]: llm_load_vocab: token to piece cache size = 0.7999 MB
Nov 08 07:06:29  ollama[11902]: llm_load_print_meta: format           = GGUF V3 (latest)
Nov 08 07:06:29  ollama[11902]: llm_load_print_meta: arch             = mllama
Nov 08 07:06:29  ollama[11902]: llm_load_print_meta: vocab type       = BPE
Nov 08 07:06:29  ollama[11902]: llm_load_print_meta: n_vocab          = 128256
Nov 08 07:06:29  ollama[11902]: llm_load_print_meta: n_merges         = 280147
Nov 08 07:06:29  ollama[11902]: llm_load_print_meta: vocab_only       = 0
Nov 08 07:06:29  ollama[11902]: llm_load_print_meta: n_ctx_train      = 131072
Nov 08 07:06:29  ollama[11902]: llm_load_print_meta: n_embd           = 4096
Nov 08 07:06:29  ollama[11902]: llm_load_print_meta: n_layer          = 40
Nov 08 07:06:29  ollama[11902]: llm_load_print_meta: n_head           = 32
Nov 08 07:06:29  ollama[11902]: llm_load_print_meta: n_head_kv        = 8
Nov 08 07:06:29  ollama[11902]: llm_load_print_meta: n_rot            = 128
Nov 08 07:06:29  ollama[11902]: llm_load_print_meta: n_swa            = 0
Nov 08 07:06:29  ollama[11902]: llm_load_print_meta: n_embd_head_k    = 128
Nov 08 07:06:29  ollama[11902]: llm_load_print_meta: n_embd_head_v    = 128
Nov 08 07:06:29  ollama[11902]: llm_load_print_meta: n_gqa            = 4
Nov 08 07:06:29  ollama[11902]: llm_load_print_meta: n_embd_k_gqa     = 1024
Nov 08 07:06:29  ollama[11902]: llm_load_print_meta: n_embd_v_gqa     = 1024
Nov 08 07:06:29  ollama[11902]: llm_load_print_meta: f_norm_eps       = 0.0e+00
Nov 08 07:06:29  ollama[11902]: llm_load_print_meta: f_norm_rms_eps   = 1.0e-05
Nov 08 07:06:29  ollama[11902]: llm_load_print_meta: f_clamp_kqv      = 0.0e+00
Nov 08 07:06:29  ollama[11902]: llm_load_print_meta: f_max_alibi_bias = 0.0e+00
Nov 08 07:06:29  ollama[11902]: llm_load_print_meta: f_logit_scale    = 0.0e+00
Nov 08 07:06:29  ollama[11902]: llm_load_print_meta: n_ff             = 14336
Nov 08 07:06:29  ollama[11902]: llm_load_print_meta: n_expert         = 0
Nov 08 07:06:29  ollama[11902]: llm_load_print_meta: n_expert_used    = 0
Nov 08 07:06:29  ollama[11902]: llm_load_print_meta: causal attn      = 1
Nov 08 07:06:29  ollama[11902]: llm_load_print_meta: pooling type     = 0
Nov 08 07:06:29  ollama[11902]: llm_load_print_meta: rope type        = 0
Nov 08 07:06:29  ollama[11902]: llm_load_print_meta: rope scaling     = linear
Nov 08 07:06:29  ollama[11902]: llm_load_print_meta: freq_base_train  = 500000.0
Nov 08 07:06:29  ollama[11902]: llm_load_print_meta: freq_scale_train = 1
Nov 08 07:06:29  ollama[11902]: llm_load_print_meta: n_ctx_orig_yarn  = 131072
Nov 08 07:06:29  ollama[11902]: llm_load_print_meta: rope_finetuned   = unknown
Nov 08 07:06:29  ollama[11902]: llm_load_print_meta: ssm_d_conv       = 0
Nov 08 07:06:29  ollama[11902]: llm_load_print_meta: ssm_d_inner      = 0
Nov 08 07:06:29  ollama[11902]: llm_load_print_meta: ssm_d_state      = 0
Nov 08 07:06:29  ollama[11902]: llm_load_print_meta: ssm_dt_rank      = 0
Nov 08 07:06:29  ollama[11902]: llm_load_print_meta: ssm_dt_b_c_rms   = 0
Nov 08 07:06:29  ollama[11902]: llm_load_print_meta: model type       = 11B
Nov 08 07:06:29  ollama[11902]: llm_load_print_meta: model ftype      = Q4_K - Medium
Nov 08 07:06:29  ollama[11902]: llm_load_print_meta: model params     = 9.78 B
Nov 08 07:06:29  ollama[11902]: llm_load_print_meta: model size       = 5.55 GiB (4.87 BPW)
Nov 08 07:06:29  ollama[11902]: llm_load_print_meta: general.name     = Model
Nov 08 07:06:29  ollama[11902]: llm_load_print_meta: BOS token        = 128000 '<|begin_of_text|>'
Nov 08 07:06:29  ollama[11902]: llm_load_print_meta: EOS token        = 128009 '<|eot_id|>'
Nov 08 07:06:29  ollama[11902]: llm_load_print_meta: PAD token        = 128004 '<|finetune_right_pad_id|>'
Nov 08 07:06:29  ollama[11902]: llm_load_print_meta: LF token         = 128 'Ä'
Nov 08 07:06:29  ollama[11902]: llm_load_print_meta: EOT token        = 128009 '<|eot_id|>'
Nov 08 07:06:29  ollama[11902]: llm_load_print_meta: EOM token        = 128008 '<|eom_id|>'
Nov 08 07:06:29  ollama[11902]: llm_load_print_meta: EOG token        = 128008 '<|eom_id|>'
Nov 08 07:06:29  ollama[11902]: llm_load_print_meta: EOG token        = 128009 '<|eot_id|>'
Nov 08 07:06:29  ollama[11902]: llm_load_print_meta: max token length = 256
Nov 08 07:06:29  ollama[11902]: llama_model_load: vocab mismatch 128256 !- 128257 ...
Nov 08 07:06:29  ollama[11902]: ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
Nov 08 07:06:29  ollama[11902]: ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
Nov 08 07:06:29  ollama[11902]: ggml_cuda_init: found 2 CUDA devices:
Nov 08 07:06:29  ollama[11902]:   Device 0: NVIDIA GeForce RTX 3070, compute capability 8.6, VMM: yes
Nov 08 07:06:29  ollama[11902]:   Device 1: NVIDIA GeForce RTX 3070, compute capability 8.6, VMM: yes
Nov 08 07:06:29  ollama[11902]: llm_load_tensors: ggml ctx size =    0.54 MiB
Nov 08 07:06:29  ollama[11902]: llm_load_tensors: offloading 40 repeating layers to GPU
Nov 08 07:06:29  ollama[11902]: llm_load_tensors: offloading non-repeating layers to GPU
Nov 08 07:06:29  ollama[11902]: llm_load_tensors: offloaded 41/41 layers to GPU
Nov 08 07:06:29  ollama[11902]: llm_load_tensors:        CPU buffer size =   281.83 MiB
Nov 08 07:06:29  ollama[11902]: llm_load_tensors:      CUDA0 buffer size =  1628.66 MiB
Nov 08 07:06:29  ollama[11902]: llm_load_tensors:      CUDA1 buffer size =  3768.85 MiB
Nov 08 07:06:35  ollama[11902]: llama_new_context_with_model: n_ctx      = 2048
Nov 08 07:06:35  ollama[11902]: llama_new_context_with_model: n_batch    = 512
Nov 08 07:06:35  ollama[11902]: llama_new_context_with_model: n_ubatch   = 512
Nov 08 07:06:35  ollama[11902]: llama_new_context_with_model: flash_attn = 0
Nov 08 07:06:35  ollama[11902]: llama_new_context_with_model: freq_base  = 500000.0
Nov 08 07:06:35  ollama[11902]: llama_new_context_with_model: freq_scale = 1
Nov 08 07:06:35  ollama[11902]: llama_kv_cache_init:      CUDA0 KV buffer size =   188.06 MiB
Nov 08 07:06:35  ollama[11902]: llama_kv_cache_init:      CUDA1 KV buffer size =   468.19 MiB
Nov 08 07:06:35  ollama[11902]: llama_new_context_with_model: KV self size  =  656.25 MiB, K (f16):  328.12 MiB, V (f16):  328.12 MiB
Nov 08 07:06:35  ollama[11902]: llama_new_context_with_model:  CUDA_Host  output buffer size =     0.50 MiB
Nov 08 07:06:35  ollama[11902]: llama_new_context_with_model: pipeline parallelism enabled (n_copies=4)
Nov 08 07:06:35  ollama[11902]: llama_new_context_with_model:      CUDA0 compute buffer size =   208.01 MiB
Nov 08 07:06:35  ollama[11902]: llama_new_context_with_model:      CUDA1 compute buffer size =   306.52 MiB
Nov 08 07:06:35  ollama[11902]: llama_new_context_with_model:  CUDA_Host compute buffer size =    24.02 MiB
Nov 08 07:06:35  ollama[11902]: llama_new_context_with_model: graph nodes  = 1030
Nov 08 07:06:35  ollama[11902]: llama_new_context_with_model: graph splits = 3
Nov 08 07:06:35  ollama[11902]: mllama_model_load: model name:   Llama-3.2-11B-Vision-Instruct
Nov 08 07:06:35  ollama[11902]: mllama_model_load: description:  vision encoder for Mllama
Nov 08 07:06:35  ollama[11902]: mllama_model_load: GGUF version: 3
Nov 08 07:06:35  ollama[11902]: mllama_model_load: alignment:    32
Nov 08 07:06:35  ollama[11902]: mllama_model_load: n_tensors:    512
Nov 08 07:06:35  ollama[11902]: mllama_model_load: n_kv:         17
Nov 08 07:06:35  ollama[11902]: mllama_model_load: ftype:        f16
Nov 08 07:06:35  ollama[11902]: mllama_model_load:
Nov 08 07:06:35  ollama[11902]: mllama_model_load: vision using CUDA backend
Nov 08 07:06:36  ollama[11902]: mllama_model_load: compute allocated memory: 2853.34 MB
Nov 08 07:06:36  ollama[11902]: time=2024-11-08T07:06:36.555Z level=INFO source=server.go:606 msg="llama runner started in 7.52 seconds"
Nov 08 07:06:40  ollama[11902]: CUDA error: unspecified launch failure
Nov 08 07:06:40  ollama[11902]:   current device: 1, in function ggml_backend_cuda_synchronize at ggml-cuda.cu:2508
Nov 08 07:06:40  ollama[11902]:   cudaStreamSynchronize(cuda_ctx->stream())
Nov 08 07:06:40  ollama[11902]: ggml-cuda.cu:132: CUDA error
Nov 08 07:06:40  ollama[11902]: SIGSEGV: segmentation violation
Nov 08 07:06:40  ollama[11902]: PC=0x7f36e43b4c47 m=9 sigcode=1 addr=0x209e03fd4
Nov 08 07:06:40  ollama[11902]: signal arrived during cgo execution
Nov 08 07:06:40  ollama[11902]: goroutine 7 gp=0xc000164000 m=9 mp=0xc0001a2808 [syscall]:
Nov 08 07:06:40  ollama[11902]: runtime.cgocall(0x559312fb4eb0, 0xc000065b60)
Nov 08 07:06:40  ollama[11902]:         runtime/cgocall.go:157 +0x4b fp=0xc000065b38 sp=0xc000065b00 pc=0x559312d373cb
Nov 08 07:06:40  ollama[11902]: github.com/ollama/ollama/llama._Cfunc_llama_decode(0x7f365005b650, {0xe, 0x7f36503ad760, 0x0, 0x0, 0x7f36503adf70, 0x7f365019ef40, 0x7f365019f750, 0x7f3642c4d360, 0x0, ...})
Nov 08 07:06:40  ollama[11902]:         _cgo_gotypes.go:543 +0x52 fp=0xc000065b60 sp=0xc000065b38 pc=0x559312e34952
Nov 08 07:06:40  ollama[11902]: github.com/ollama/ollama/llama.(*Context).Decode.func1(0x559312fb0ceb?, 0x7f365005b650?)
Nov 08 07:06:40  ollama[11902]:         github.com/ollama/ollama/llama/llama.go:167 +0xd8 fp=0xc000065c80 sp=0xc000065b60 pc=0x559312e36e78
Nov 08 07:06:40  ollama[11902]: github.com/ollama/ollama/llama.(*Context).Decode(0xc0000163c0?, 0x1?)
Nov 08 07:06:40  ollama[11902]:         github.com/ollama/ollama/llama/llama.go:167 +0x17 fp=0xc000065cc8 sp=0xc000065c80 pc=0x559312e36cd7
Nov 08 07:06:40  ollama[11902]: main.(*Server).processBatch(0xc000128120, 0xc0000c0000, 0xc0000c0070)
Nov 08 07:06:40  ollama[11902]:         github.com/ollama/ollama/llama/runner/runner.go:424 +0x29e fp=0xc000065ed0 sp=0xc000065cc8 pc=0x559312fafd1e
Nov 08 07:06:40  ollama[11902]: main.(*Server).run(0xc000128120, {0x5593132eea40, 0xc00007c0a0})
Nov 08 07:06:40  ollama[11902]:         github.com/ollama/ollama/llama/runner/runner.go:338 +0x1a5 fp=0xc000065fb8 sp=0xc000065ed0 pc=0x559312faf705
Nov 08 07:06:40  ollama[11902]: main.main.gowrap2()
Nov 08 07:06:40  ollama[11902]:         github.com/ollama/ollama/llama/runner/runner.go:907 +0x28 fp=0xc000065fe0 sp=0xc000065fb8 pc=0x559312fb3ee8
Nov 08 07:06:40  ollama[11902]: runtime.goexit({})
Nov 08 07:06:40  ollama[11902]:         runtime/asm_amd64.s:1695 +0x1 fp=0xc000065fe8 sp=0xc000065fe0 pc=0x559312d9fde1
Nov 08 07:06:40  ollama[11902]: created by main.main in goroutine 1
Nov 08 07:06:40  ollama[11902]:         github.com/ollama/ollama/llama/runner/runner.go:907 +0xcab
Nov 08 07:06:40  ollama[11902]: goroutine 1 gp=0xc0000061c0 m=nil [IO wait]:
Nov 08 07:06:40  ollama[11902]: runtime.gopark(0xc000030008?, 0x0?, 0xc0?, 0x61?, 0xc0000298c0?)
Nov 08 07:06:40  ollama[11902]:         runtime/proc.go:402 +0xce fp=0xc00014d888 sp=0xc00014d868 pc=0x559312d6e00e
Nov 08 07:06:40  ollama[11902]: runtime.netpollblock(0xc000029920?, 0x12d36b26?, 0x93?)
Nov 08 07:06:40  ollama[11902]:         runtime/netpoll.go:573 +0xf7 fp=0xc00014d8c0 sp=0xc00014d888 pc=0x559312d66257
Nov 08 07:06:40  ollama[11902]: internal/poll.runtime_pollWait(0x7f36dcfc9860, 0x72)
Nov 08 07:06:40  ollama[11902]:         runtime/netpoll.go:345 +0x85 fp=0xc00014d8e0 sp=0xc00014d8c0 pc=0x559312d9aaa5
Nov 08 07:06:40  ollama[11902]: internal/poll.(*pollDesc).wait(0x3?, 0x3fe?, 0x0)
Nov 08 07:06:40  ollama[11902]:         internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc00014d908 sp=0xc00014d8e0 pc=0x559312dea9c7
Nov 08 07:06:40  ollama[11902]: internal/poll.(*pollDesc).waitRead(...)
Nov 08 07:06:40  ollama[11902]:         internal/poll/fd_poll_runtime.go:89
Nov 08 07:06:40  ollama[11902]: internal/poll.(*FD).Accept(0xc000152100)
Nov 08 07:06:40  ollama[11902]:         internal/poll/fd_unix.go:611 +0x2ac fp=0xc00014d9b0 sp=0xc00014d908 pc=0x559312debe8c
Nov 08 07:06:40  ollama[11902]: net.(*netFD).accept(0xc000152100)
Nov 08 07:06:40  ollama[11902]:         net/fd_unix.go:172 +0x29 fp=0xc00014da68 sp=0xc00014d9b0 pc=0x559312e5a8a9
Nov 08 07:06:40  ollama[11902]: net.(*TCPListener).accept(0xc000070200)
Nov 08 07:06:40  ollama[11902]:         net/tcpsock_posix.go:159 +0x1e fp=0xc00014da90 sp=0xc00014da68 pc=0x559312e6b5de
Nov 08 07:06:40  ollama[11902]: net.(*TCPListener).Accept(0xc000070200)
Nov 08 07:06:40  ollama[11902]:         net/tcpsock.go:327 +0x30 fp=0xc00014dac0 sp=0xc00014da90 pc=0x559312e6a930
Nov 08 07:06:40  ollama[11902]: net/http.(*onceCloseListener).Accept(0xc0001281b0?)
Nov 08 07:06:40  ollama[11902]:         <autogenerated>:1 +0x24 fp=0xc00014dad8 sp=0xc00014dac0 pc=0x559312f91a44
Nov 08 07:06:40  ollama[11902]: net/http.(*Server).Serve(0xc0001620f0, {0x5593132ee400, 0xc000070200})
Nov 08 07:06:40  ollama[11902]:         net/http/server.go:3260 +0x33e fp=0xc00014dc08 sp=0xc00014dad8 pc=0x559312f8885e
Nov 08 07:06:40  ollama[11902]: main.main()
Nov 08 07:06:40  ollama[11902]:         github.com/ollama/ollama/llama/runner/runner.go:927 +0x104c fp=0xc00014df50 sp=0xc00014dc08 pc=0x559312fb3c6c
Nov 08 07:06:40  ollama[11902]: runtime.main()
Nov 08 07:06:40  ollama[11902]:         runtime/proc.go:271 +0x29d fp=0xc00014dfe0 sp=0xc00014df50 pc=0x559312d6dbdd
Nov 08 07:06:40  ollama[11902]: runtime.goexit({})
Nov 08 07:06:40  ollama[11902]:         runtime/asm_amd64.s:1695 +0x1 fp=0xc00014dfe8 sp=0xc00014dfe0 pc=0x559312d9fde1
Nov 08 07:06:40  ollama[11902]: goroutine 2 gp=0xc000006c40 m=nil [force gc (idle)]:
Nov 08 07:06:40  ollama[11902]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
Nov 08 07:06:40  ollama[11902]:         runtime/proc.go:402 +0xce fp=0xc000050fa8 sp=0xc000050f88 pc=0x559312d6e00e
Nov 08 07:06:40  ollama[11902]: runtime.goparkunlock(...)
Nov 08 07:06:40  ollama[11902]:         runtime/proc.go:408
Nov 08 07:06:40  ollama[11902]: runtime.forcegchelper()
Nov 08 07:06:40  ollama[11902]:         runtime/proc.go:326 +0xb8 fp=0xc000050fe0 sp=0xc000050fa8 pc=0x559312d6de98
Nov 08 07:06:40  ollama[11902]: runtime.goexit({})
Nov 08 07:06:40  ollama[11902]:         runtime/asm_amd64.s:1695 +0x1 fp=0xc000050fe8 sp=0xc000050fe0 pc=0x559312d9fde1
Nov 08 07:06:40  ollama[11902]: created by runtime.init.6 in goroutine 1
Nov 08 07:06:40  ollama[11902]:         runtime/proc.go:314 +0x1a
Nov 08 07:06:40  ollama[11902]: goroutine 3 gp=0xc000007180 m=nil [GC sweep wait]:
Nov 08 07:06:40  ollama[11902]: runtime.gopark(0x1?, 0x0?, 0x0?, 0x0?, 0x0?)
Nov 08 07:06:40  ollama[11902]:         runtime/proc.go:402 +0xce fp=0xc000051780 sp=0xc000051760 pc=0x559312d6e00e
Nov 08 07:06:40  ollama[11902]: runtime.goparkunlock(...)
Nov 08 07:06:40  ollama[11902]:         runtime/proc.go:408
Nov 08 07:06:40  ollama[11902]: runtime.bgsweep(0xc000022070)
Nov 08 07:06:40  ollama[11902]:         runtime/mgcsweep.go:318 +0xdf fp=0xc0000517c8 sp=0xc000051780 pc=0x559312d58b9f
Nov 08 07:06:40  ollama[11902]: runtime.gcenable.gowrap1()
Nov 08 07:06:40  ollama[11902]:         runtime/mgc.go:203 +0x25 fp=0xc0000517e0 sp=0xc0000517c8 pc=0x559312d4d685
Nov 08 07:06:40  ollama[11902]: runtime.goexit({})
Nov 08 07:06:40  ollama[11902]:         runtime/asm_amd64.s:1695 +0x1 fp=0xc0000517e8 sp=0xc0000517e0 pc=0x559312d9fde1
Nov 08 07:06:40  ollama[11902]: created by runtime.gcenable in goroutine 1
Nov 08 07:06:40  ollama[11902]:         runtime/mgc.go:203 +0x66
Nov 08 07:06:40  ollama[11902]: goroutine 4 gp=0xc000007340 m=nil [GC scavenge wait]:
Nov 08 07:06:40  ollama[11902]: runtime.gopark(0x10000?, 0x5593131eff98?, 0x0?, 0x0?, 0x0?)
Nov 08 07:06:40  ollama[11902]:         runtime/proc.go:402 +0xce fp=0xc000051f78 sp=0xc000051f58 pc=0x559312d6e00e
Nov 08 07:06:40  ollama[11902]: runtime.goparkunlock(...)
Nov 08 07:06:40  ollama[11902]:         runtime/proc.go:408
Nov 08 07:06:40  ollama[11902]: runtime.(*scavengerState).park(0x5593134bc4c0)
Nov 08 07:06:40  ollama[11902]:         runtime/mgcscavenge.go:425 +0x49 fp=0xc000051fa8 sp=0xc000051f78 pc=0x559312d56549
Nov 08 07:06:40  ollama[11902]: runtime.bgscavenge(0xc000022070)
Nov 08 07:06:40  ollama[11902]:         runtime/mgcscavenge.go:658 +0x59 fp=0xc000051fc8 sp=0xc000051fa8 pc=0x559312d56af9
Nov 08 07:06:40  ollama[11902]: runtime.gcenable.gowrap2()
Nov 08 07:06:40  ollama[11902]:         runtime/mgc.go:204 +0x25 fp=0xc000051fe0 sp=0xc000051fc8 pc=0x559312d4d625
Nov 08 07:06:40  ollama[11902]: runtime.goexit({})
Nov 08 07:06:40  ollama[11902]:         runtime/asm_amd64.s:1695 +0x1 fp=0xc000051fe8 sp=0xc000051fe0 pc=0x559312d9fde1
Nov 08 07:06:40  ollama[11902]: created by runtime.gcenable in goroutine 1
Nov 08 07:06:40  ollama[11902]:         runtime/mgc.go:204 +0xa5
Nov 08 07:06:40  ollama[11902]: goroutine 5 gp=0xc000007c00 m=nil [finalizer wait]:
Nov 08 07:06:40  ollama[11902]: runtime.gopark(0x0?, 0x5593132ea600?, 0x0?, 0xc0?, 0x1000000010?)
Nov 08 07:06:40  ollama[11902]:         runtime/proc.go:402 +0xce fp=0xc000050620 sp=0xc000050600 pc=0x559312d6e00e
Nov 08 07:06:40  ollama[11902]: runtime.runfinq()
Nov 08 07:06:40  ollama[11902]:         runtime/mfinal.go:194 +0x107 fp=0xc0000507e0 sp=0xc000050620 pc=0x559312d4c6c7
Nov 08 07:06:40  ollama[11902]: runtime.goexit({})
Nov 08 07:06:40  ollama[11902]:         runtime/asm_amd64.s:1695 +0x1 fp=0xc0000507e8 sp=0xc0000507e0 pc=0x559312d9fde1
Nov 08 07:06:40  ollama[11902]: created by runtime.createfing in goroutine 1
Nov 08 07:06:40  ollama[11902]:         runtime/mfinal.go:164 +0x3d
Nov 08 07:06:40  ollama[11902]: goroutine 49 gp=0xc000007dc0 m=nil [GC worker (idle)]:
Nov 08 07:06:40  ollama[11902]: runtime.gopark(0x2736bc2b5abd3?, 0xc00002e9d0?, 0x0?, 0x0?, 0x5593135a5060?)
Nov 08 07:06:40  ollama[11902]:         runtime/proc.go:402 +0xce fp=0xc000052f50 sp=0xc000052f30 pc=0x559312d6e00e
Nov 08 07:06:40  ollama[11902]: runtime.gcBgMarkWorker()
Nov 08 07:06:40  ollama[11902]:         runtime/mgc.go:1310 +0xe5 fp=0xc000052fe0 sp=0xc000052f50 pc=0x559312d4f585
Nov 08 07:06:40  ollama[11902]: runtime.goexit({})
Nov 08 07:06:40  ollama[11902]:         runtime/asm_amd64.s:1695 +0x1 fp=0xc000052fe8 sp=0xc000052fe0 pc=0x559312d9fde1
Nov 08 07:06:40  ollama[11902]: created by runtime.gcBgMarkStartWorkers in goroutine 8
Nov 08 07:06:40  ollama[11902]:         runtime/mgc.go:1234 +0x1c
Nov 08 07:06:40  ollama[11902]: goroutine 8 gp=0xc0001641c0 m=nil [select]:
Nov 08 07:06:40  ollama[11902]: runtime.gopark(0xc000029a80?, 0x2?, 0x60?, 0x0?, 0xc000029824?)
Nov 08 07:06:40  ollama[11902]:         runtime/proc.go:402 +0xce fp=0xc000029698 sp=0xc000029678 pc=0x559312d6e00e
Nov 08 07:06:40  ollama[11902]: runtime.selectgo(0xc000029a80, 0xc000029820, 0x14?, 0x0, 0x1?, 0x1)
Nov 08 07:06:40  ollama[11902]:         runtime/select.go:327 +0x725 fp=0xc0000297b8 sp=0xc000029698 pc=0x559312d7f3e5
Nov 08 07:06:40  ollama[11902]: main.(*Server).completion(0xc000128120, {0x5593132ee5b0, 0xc0001507e0}, 0xc00012a900)
Nov 08 07:06:40  ollama[11902]:         github.com/ollama/ollama/llama/runner/runner.go:652 +0x8fe fp=0xc000029ab8 sp=0xc0000297b8 pc=0x559312fb167e
Nov 08 07:06:40  ollama[11902]: main.(*Server).completion-fm({0x5593132ee5b0?, 0xc0001507e0?}, 0x559312f8cb8d?)
Nov 08 07:06:40  ollama[11902]:         <autogenerated>:1 +0x36 fp=0xc000029ae8 sp=0xc000029ab8 pc=0x559312fb46d6
Nov 08 07:06:40  ollama[11902]: net/http.HandlerFunc.ServeHTTP(0xc00010cc30?, {0x5593132ee5b0?, 0xc0001507e0?}, 0x10?)
Nov 08 07:06:40  ollama[11902]:         net/http/server.go:2171 +0x29 fp=0xc000029b10 sp=0xc000029ae8 pc=0x559312f85629
Nov 08 07:06:40  ollama[11902]: net/http.(*ServeMux).ServeHTTP(0x559312d40f85?, {0x5593132ee5b0, 0xc0001507e0}, 0xc00012a900)
Nov 08 07:06:40  ollama[11902]:         net/http/server.go:2688 +0x1ad fp=0xc000029b60 sp=0xc000029b10 pc=0x559312f874ad
Nov 08 07:06:40  ollama[11902]: net/http.serverHandler.ServeHTTP({0x5593132ed900?}, {0x5593132ee5b0?, 0xc0001507e0?}, 0x6?)
Nov 08 07:06:40  ollama[11902]:         net/http/server.go:3142 +0x8e fp=0xc000029b90 sp=0xc000029b60 pc=0x559312f884ce
Nov 08 07:06:40  ollama[11902]: net/http.(*conn).serve(0xc0001281b0, {0x5593132eea08, 0xc00010ae10})
Nov 08 07:06:40  ollama[11902]:         net/http/server.go:2044 +0x5e8 fp=0xc000029fb8 sp=0xc000029b90 pc=0x559312f84268
Nov 08 07:06:40  ollama[11902]: net/http.(*Server).Serve.gowrap3()
Nov 08 07:06:40  ollama[11902]:         net/http/server.go:3290 +0x28 fp=0xc000029fe0 sp=0xc000029fb8 pc=0x559312f88c48
Nov 08 07:06:40  ollama[11902]: runtime.goexit({})
Nov 08 07:06:40  ollama[11902]:         runtime/asm_amd64.s:1695 +0x1 fp=0xc000029fe8 sp=0xc000029fe0 pc=0x559312d9fde1
Nov 08 07:06:40  ollama[11902]: created by net/http.(*Server).Serve in goroutine 1
Nov 08 07:06:40  ollama[11902]:         net/http/server.go:3290 +0x4b4
Nov 08 07:06:40  ollama[11902]: goroutine 33 gp=0xc000164380 m=nil [GC worker (idle)]:
Nov 08 07:06:40  ollama[11902]: runtime.gopark(0x2736bc93ca49d?, 0x1?, 0x76?, 0x48?, 0x5593135a5060?)
Nov 08 07:06:40  ollama[11902]:         runtime/proc.go:402 +0xce fp=0xc000052750 sp=0xc000052730 pc=0x559312d6e00e
Nov 08 07:06:40  ollama[11902]: runtime.gcBgMarkWorker()
Nov 08 07:06:40  ollama[11902]:         runtime/mgc.go:1310 +0xe5 fp=0xc0000527e0 sp=0xc000052750 pc=0x559312d4f585
Nov 08 07:06:40  ollama[11902]: runtime.goexit({})
Nov 08 07:06:40  ollama[11902]:         runtime/asm_amd64.s:1695 +0x1 fp=0xc0000527e8 sp=0xc0000527e0 pc=0x559312d9fde1
Nov 08 07:06:40  ollama[11902]: created by runtime.gcBgMarkStartWorkers in goroutine 8
Nov 08 07:06:40  ollama[11902]:         runtime/mgc.go:1234 +0x1c
Nov 08 07:06:40  ollama[11902]: goroutine 66 gp=0xc00019a000 m=nil [IO wait]:
Nov 08 07:06:40  ollama[11902]: runtime.gopark(0x10?, 0x10?, 0xf0?, 0xc5?, 0xb?)
Nov 08 07:06:40  ollama[11902]:         runtime/proc.go:402 +0xce fp=0xc00004c5a8 sp=0xc00004c588 pc=0x559312d6e00e
Nov 08 07:06:40  ollama[11902]: runtime.netpollblock(0x559312dd4558?, 0x12d36b26?, 0x93?)
Nov 08 07:06:40  ollama[11902]:         runtime/netpoll.go:573 +0xf7 fp=0xc00004c5e0 sp=0xc00004c5a8 pc=0x559312d66257
Nov 08 07:06:40  ollama[11902]: internal/poll.runtime_pollWait(0x7f36dcfc9768, 0x72)
Nov 08 07:06:40  ollama[11902]:         runtime/netpoll.go:345 +0x85 fp=0xc00004c600 sp=0xc00004c5e0 pc=0x559312d9aaa5
Nov 08 07:06:40  ollama[11902]: internal/poll.(*pollDesc).wait(0xc000152180?, 0xc00010af41?, 0x0)
Nov 08 07:06:40  ollama[11902]:         internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc00004c628 sp=0xc00004c600 pc=0x559312dea9c7
Nov 08 07:06:40  ollama[11902]: internal/poll.(*pollDesc).waitRead(...)
Nov 08 07:06:40  ollama[11902]:         internal/poll/fd_poll_runtime.go:89
Nov 08 07:06:40  ollama[11902]: internal/poll.(*FD).Read(0xc000152180, {0xc00010af41, 0x1, 0x1})
Nov 08 07:06:40  ollama[11902]:         internal/poll/fd_unix.go:164 +0x27a fp=0xc00004c6c0 sp=0xc00004c628 pc=0x559312deb51a
Nov 08 07:06:40  ollama[11902]: net.(*netFD).Read(0xc000152180, {0xc00010af41?, 0xc00004c748?, 0x559312d9c6d0?})
Nov 08 07:06:40  ollama[11902]:         net/fd_posix.go:55 +0x25 fp=0xc00004c708 sp=0xc00004c6c0 pc=0x559312e597a5
Nov 08 07:06:40  ollama[11902]: net.(*conn).Read(0xc0000540a8, {0xc00010af41?, 0x0?, 0x5593135a5060?})
Nov 08 07:06:40  ollama[11902]:         net/net.go:185 +0x45 fp=0xc00004c750 sp=0xc00004c708 pc=0x559312e63a65
Nov 08 07:06:40  ollama[11902]: net.(*TCPConn).Read(0x55931347d840?, {0xc00010af41?, 0x0?, 0x0?})
Nov 08 07:06:40  ollama[11902]:         <autogenerated>:1 +0x25 fp=0xc00004c780 sp=0xc00004c750 pc=0x559312e6f445
Nov 08 07:06:40  ollama[11902]: net/http.(*connReader).backgroundRead(0xc00010af30)
Nov 08 07:06:40  ollama[11902]:         net/http/server.go:681 +0x37 fp=0xc00004c7c8 sp=0xc00004c780 pc=0x559312f7e1d7
Nov 08 07:06:40  ollama[11902]: net/http.(*connReader).startBackgroundRead.gowrap2()
Nov 08 07:06:40  ollama[11902]:         net/http/server.go:677 +0x25 fp=0xc00004c7e0 sp=0xc00004c7c8 pc=0x559312f7e105
Nov 08 07:06:40  ollama[11902]: runtime.goexit({})
Nov 08 07:06:40  ollama[11902]:         runtime/asm_amd64.s:1695 +0x1 fp=0xc00004c7e8 sp=0xc00004c7e0 pc=0x559312d9fde1
Nov 08 07:06:40  ollama[11902]: created by net/http.(*connReader).startBackgroundRead in goroutine 8
Nov 08 07:06:40  ollama[11902]:         net/http/server.go:677 +0xba
Nov 08 07:06:40  ollama[11902]: goroutine 32 gp=0xc00008a380 m=nil [GC worker (idle)]:
Nov 08 07:06:40  ollama[11902]: runtime.gopark(0x2736bc93d3ed0?, 0xc00002e9d0?, 0x0?, 0x0?, 0x5593135a5060?)
Nov 08 07:06:40  ollama[11902]:         runtime/proc.go:402 +0xce fp=0xc0000b2750 sp=0xc0000b2730 pc=0x559312d6e00e
Nov 08 07:06:40  ollama[11902]: runtime.gcBgMarkWorker()
Nov 08 07:06:40  ollama[11902]:         runtime/mgc.go:1310 +0xe5 fp=0xc0000b27e0 sp=0xc0000b2750 pc=0x559312d4f585
Nov 08 07:06:40  ollama[11902]: runtime.goexit({})
Nov 08 07:06:40  ollama[11902]:         runtime/asm_amd64.s:1695 +0x1 fp=0xc0000b27e8 sp=0xc0000b27e0 pc=0x559312d9fde1
Nov 08 07:06:40  ollama[11902]: created by runtime.gcBgMarkStartWorkers in goroutine 8
Nov 08 07:06:40  ollama[11902]:         runtime/mgc.go:1234 +0x1c
Nov 08 07:06:40  ollama[11902]: goroutine 48 gp=0xc00008a540 m=nil [GC worker (idle)]:
Nov 08 07:06:40  ollama[11902]: runtime.gopark(0x2736bc93d3fdc?, 0x3?, 0x98?, 0x4d?, 0x5593135a5060?)
Nov 08 07:06:40  ollama[11902]:         runtime/proc.go:402 +0xce fp=0xc0000b2f50 sp=0xc0000b2f30 pc=0x559312d6e00e
Nov 08 07:06:40  ollama[11902]: runtime.gcBgMarkWorker()
Nov 08 07:06:40  ollama[11902]:         runtime/mgc.go:1310 +0xe5 fp=0xc0000b2fe0 sp=0xc0000b2f50 pc=0x559312d4f585
Nov 08 07:06:40  ollama[11902]: runtime.goexit({})
Nov 08 07:06:40  ollama[11902]:         runtime/asm_amd64.s:1695 +0x1 fp=0xc0000b2fe8 sp=0xc0000b2fe0 pc=0x559312d9fde1
Nov 08 07:06:40  ollama[11902]: created by runtime.gcBgMarkStartWorkers in goroutine 8
Nov 08 07:06:40  ollama[11902]:         runtime/mgc.go:1234 +0x1c
Nov 08 07:06:40  ollama[11902]: goroutine 50 gp=0xc00008a700 m=nil [GC worker (idle)]:
Nov 08 07:06:40  ollama[11902]: runtime.gopark(0x2736bc93d3def?, 0xc00002e9d0?, 0x0?, 0x0?, 0x5593135a5060?)
Nov 08 07:06:40  ollama[11902]:         runtime/proc.go:402 +0xce fp=0xc0000b3750 sp=0xc0000b3730 pc=0x559312d6e00e
Nov 08 07:06:40  ollama[11902]: runtime.gcBgMarkWorker()
Nov 08 07:06:40  ollama[11902]:         runtime/mgc.go:1310 +0xe5 fp=0xc0000b37e0 sp=0xc0000b3750 pc=0x559312d4f585
Nov 08 07:06:40  ollama[11902]: runtime.goexit({})
Nov 08 07:06:40  ollama[11902]:         runtime/asm_amd64.s:1695 +0x1 fp=0xc0000b37e8 sp=0xc0000b37e0 pc=0x559312d9fde1
Nov 08 07:06:40  ollama[11902]: created by runtime.gcBgMarkStartWorkers in goroutine 8
Nov 08 07:06:40  ollama[11902]:         runtime/mgc.go:1234 +0x1c
Nov 08 07:06:40  ollama[11902]: goroutine 12 gp=0xc000164540 m=nil [GC worker (idle)]:
Nov 08 07:06:40  ollama[11902]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
Nov 08 07:06:40  ollama[11902]:         runtime/proc.go:402 +0xce fp=0xc000053750 sp=0xc000053730 pc=0x559312d6e00e
Nov 08 07:06:40  ollama[11902]: runtime.gcBgMarkWorker()
Nov 08 07:06:40  ollama[11902]:         runtime/mgc.go:1310 +0xe5 fp=0xc0000537e0 sp=0xc000053750 pc=0x559312d4f585
Nov 08 07:06:40  ollama[11902]: runtime.goexit({})
Nov 08 07:06:40  ollama[11902]:         runtime/asm_amd64.s:1695 +0x1 fp=0xc0000537e8 sp=0xc0000537e0 pc=0x559312d9fde1
Nov 08 07:06:40  ollama[11902]: created by runtime.gcBgMarkStartWorkers in goroutine 8
Nov 08 07:06:40  ollama[11902]:         runtime/mgc.go:1234 +0x1c
Nov 08 07:06:40  ollama[11902]: goroutine 13 gp=0xc000164700 m=nil [GC worker (idle)]:
Nov 08 07:06:40  ollama[11902]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
Nov 08 07:06:40  ollama[11902]:         runtime/proc.go:402 +0xce fp=0xc000053f50 sp=0xc000053f30 pc=0x559312d6e00e
Nov 08 07:06:40  ollama[11902]: runtime.gcBgMarkWorker()
Nov 08 07:06:40  ollama[11902]:         runtime/mgc.go:1310 +0xe5 fp=0xc000053fe0 sp=0xc000053f50 pc=0x559312d4f585
Nov 08 07:06:40  ollama[11902]: runtime.goexit({})
Nov 08 07:06:40  ollama[11902]:         runtime/asm_amd64.s:1695 +0x1 fp=0xc000053fe8 sp=0xc000053fe0 pc=0x559312d9fde1
Nov 08 07:06:40  ollama[11902]: created by runtime.gcBgMarkStartWorkers in goroutine 8
Nov 08 07:06:40  ollama[11902]:         runtime/mgc.go:1234 +0x1c
Nov 08 07:06:40  ollama[11902]: goroutine 14 gp=0xc0001648c0 m=nil [GC worker (idle)]:
Nov 08 07:06:40  ollama[11902]: runtime.gopark(0x2736bc93ca34d?, 0x0?, 0x0?, 0x0?, 0x0?)
Nov 08 07:06:40  ollama[11902]:         runtime/proc.go:402 +0xce fp=0xc0000ae750 sp=0xc0000ae730 pc=0x559312d6e00e
Nov 08 07:06:40  ollama[11902]: runtime.gcBgMarkWorker()
Nov 08 07:06:40  ollama[11902]:         runtime/mgc.go:1310 +0xe5 fp=0xc0000ae7e0 sp=0xc0000ae750 pc=0x559312d4f585
Nov 08 07:06:40  ollama[11902]: runtime.goexit({})
Nov 08 07:06:40  ollama[11902]:         runtime/asm_amd64.s:1695 +0x1 fp=0xc0000ae7e8 sp=0xc0000ae7e0 pc=0x559312d9fde1
Nov 08 07:06:40  ollama[11902]: created by runtime.gcBgMarkStartWorkers in goroutine 8
Nov 08 07:06:40  ollama[11902]:         runtime/mgc.go:1234 +0x1c
Nov 08 07:06:40  ollama[11902]: rax    0x209e03fd4
Nov 08 07:06:40  ollama[11902]: rbx    0x7f364255c000
Nov 08 07:06:40  ollama[11902]: rcx    0xff5
Nov 08 07:06:40  ollama[11902]: rdx    0x7f3642118290
Nov 08 07:06:40  ollama[11902]: rdi    0x7f36421182a0
Nov 08 07:06:40  ollama[11902]: rsi    0x0
Nov 08 07:06:40  ollama[11902]: rbp    0x7f361ffd5240
Nov 08 07:06:40  ollama[11902]: rsp    0x7f361ffd5220
Nov 08 07:06:40  ollama[11902]: r8     0x1
Nov 08 07:06:40  ollama[11902]: r9     0x7f36423d2790
Nov 08 07:06:40  ollama[11902]: r10    0x0
Nov 08 07:06:40  ollama[11902]: r11    0x246
Nov 08 07:06:40  ollama[11902]: r12    0x7f34d7569420
Nov 08 07:06:40  ollama[11902]: r13    0x7f36421182a0
Nov 08 07:06:40  ollama[11902]: r14    0x0
Nov 08 07:06:40  ollama[11902]: r15    0x7f372f6497f0
Nov 08 07:06:40  ollama[11902]: rip    0x7f36e43b4c47
Nov 08 07:06:40  ollama[11902]: rflags 0x10297
Nov 08 07:06:40  ollama[11902]: cs     0x33
Nov 08 07:06:40  ollama[11902]: fs     0x0
Nov 08 07:06:40  ollama[11902]: gs     0x0
Nov 08 07:06:40  ollama[11902]: SIGABRT: abort
Nov 08 07:06:40  ollama[11902]: PC=0x7f36bec419fc m=9 sigcode=18446744073709551610
Nov 08 07:06:40  ollama[11902]: signal arrived during cgo execution
Nov 08 07:06:40  ollama[11902]: goroutine 7 gp=0xc000164000 m=9 mp=0xc0001a2808 [syscall]:
Nov 08 07:06:40  ollama[11902]: runtime.cgocall(0x559312fb4eb0, 0xc000065b60)
Nov 08 07:06:40  ollama[11902]:         runtime/cgocall.go:157 +0x4b fp=0xc000065b38 sp=0xc000065b00 pc=0x559312d373cb
Nov 08 07:06:40  ollama[11902]: github.com/ollama/ollama/llama._Cfunc_llama_decode(0x7f365005b650, {0xe, 0x7f36503ad760, 0x0, 0x0, 0x7f36503adf70, 0x7f365019ef40, 0x7f365019f750, 0x7f3642c4d360, 0x0, ...})
Nov 08 07:06:40  ollama[11902]:         _cgo_gotypes.go:543 +0x52 fp=0xc000065b60 sp=0xc000065b38 pc=0x559312e34952
Nov 08 07:06:40  ollama[11902]: github.com/ollama/ollama/llama.(*Context).Decode.func1(0x559312fb0ceb?, 0x7f365005b650?)
Nov 08 07:06:40  ollama[11902]:         github.com/ollama/ollama/llama/llama.go:167 +0xd8 fp=0xc000065c80 sp=0xc000065b60 pc=0x559312e36e78
Nov 08 07:06:40  ollama[11902]: github.com/ollama/ollama/llama.(*Context).Decode(0xc0000163c0?, 0x1?)
Nov 08 07:06:40  ollama[11902]:         github.com/ollama/ollama/llama/llama.go:167 +0x17 fp=0xc000065cc8 sp=0xc000065c80 pc=0x559312e36cd7
Nov 08 07:06:40  ollama[11902]: main.(*Server).processBatch(0xc000128120, 0xc0000c0000, 0xc0000c0070)
Nov 08 07:06:40  ollama[11902]:         github.com/ollama/ollama/llama/runner/runner.go:424 +0x29e fp=0xc000065ed0 sp=0xc000065cc8 pc=0x559312fafd1e
Nov 08 07:06:40  ollama[11902]: main.(*Server).run(0xc000128120, {0x5593132eea40, 0xc00007c0a0})
Nov 08 07:06:40  ollama[11902]:         github.com/ollama/ollama/llama/runner/runner.go:338 +0x1a5 fp=0xc000065fb8 sp=0xc000065ed0 pc=0x559312faf705
Nov 08 07:06:40  ollama[11902]: main.main.gowrap2()
Nov 08 07:06:40  ollama[11902]:         github.com/ollama/ollama/llama/runner/runner.go:907 +0x28 fp=0xc000065fe0 sp=0xc000065fb8 pc=0x559312fb3ee8
Nov 08 07:06:40  ollama[11902]: runtime.goexit({})
Nov 08 07:06:40  ollama[11902]:         runtime/asm_amd64.s:1695 +0x1 fp=0xc000065fe8 sp=0xc000065fe0 pc=0x559312d9fde1
Nov 08 07:06:40  ollama[11902]: created by main.main in goroutine 1
Nov 08 07:06:40  ollama[11902]:         github.com/ollama/ollama/llama/runner/runner.go:907 +0xcab
Nov 08 07:06:40  ollama[11902]: goroutine 1 gp=0xc0000061c0 m=nil [IO wait]:
Nov 08 07:06:40  ollama[11902]: runtime.gopark(0xc000030008?, 0x0?, 0xc0?, 0x61?, 0xc0000298c0?)
Nov 08 07:06:40  ollama[11902]:         runtime/proc.go:402 +0xce fp=0xc00014d888 sp=0xc00014d868 pc=0x559312d6e00e
Nov 08 07:06:40  ollama[11902]: runtime.netpollblock(0xc000029920?, 0x12d36b26?, 0x93?)
Nov 08 07:06:40  ollama[11902]:         runtime/netpoll.go:573 +0xf7 fp=0xc00014d8c0 sp=0xc00014d888 pc=0x559312d66257
Nov 08 07:06:40  ollama[11902]: internal/poll.runtime_pollWait(0x7f36dcfc9860, 0x72)
Nov 08 07:06:40  ollama[11902]:         runtime/netpoll.go:345 +0x85 fp=0xc00014d8e0 sp=0xc00014d8c0 pc=0x559312d9aaa5
Nov 08 07:06:40  ollama[11902]: internal/poll.(*pollDesc).wait(0x3?, 0x3fe?, 0x0)
Nov 08 07:06:40  ollama[11902]:         internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc00014d908 sp=0xc00014d8e0 pc=0x559312dea9c7
Nov 08 07:06:40  ollama[11902]: internal/poll.(*pollDesc).waitRead(...)
Nov 08 07:06:40  ollama[11902]:         internal/poll/fd_poll_runtime.go:89
Nov 08 07:06:40  ollama[11902]: internal/poll.(*FD).Accept(0xc000152100)
Nov 08 07:06:40  ollama[11902]:         internal/poll/fd_unix.go:611 +0x2ac fp=0xc00014d9b0 sp=0xc00014d908 pc=0x559312debe8c
Nov 08 07:06:40  ollama[11902]: net.(*netFD).accept(0xc000152100)
Nov 08 07:06:40  ollama[11902]:         net/fd_unix.go:172 +0x29 fp=0xc00014da68 sp=0xc00014d9b0 pc=0x559312e5a8a9
Nov 08 07:06:40  ollama[11902]: net.(*TCPListener).accept(0xc000070200)
Nov 08 07:06:40  ollama[11902]:         net/tcpsock_posix.go:159 +0x1e fp=0xc00014da90 sp=0xc00014da68 pc=0x559312e6b5de
Nov 08 07:06:40  ollama[11902]: net.(*TCPListener).Accept(0xc000070200)
Nov 08 07:06:40  ollama[11902]:         net/tcpsock.go:327 +0x30 fp=0xc00014dac0 sp=0xc00014da90 pc=0x559312e6a930
Nov 08 07:06:40  ollama[11902]: net/http.(*onceCloseListener).Accept(0xc0001281b0?)
Nov 08 07:06:40  ollama[11902]:         <autogenerated>:1 +0x24 fp=0xc00014dad8 sp=0xc00014dac0 pc=0x559312f91a44
Nov 08 07:06:40  ollama[11902]: net/http.(*Server).Serve(0xc0001620f0, {0x5593132ee400, 0xc000070200})
Nov 08 07:06:40  ollama[11902]:         net/http/server.go:3260 +0x33e fp=0xc00014dc08 sp=0xc00014dad8 pc=0x559312f8885e
Nov 08 07:06:40  ollama[11902]: main.main()
Nov 08 07:06:40  ollama[11902]:         github.com/ollama/ollama/llama/runner/runner.go:927 +0x104c fp=0xc00014df50 sp=0xc00014dc08 pc=0x559312fb3c6c
Nov 08 07:06:40  ollama[11902]: runtime.main()
Nov 08 07:06:40  ollama[11902]:         runtime/proc.go:271 +0x29d fp=0xc00014dfe0 sp=0xc00014df50 pc=0x559312d6dbdd
Nov 08 07:06:40  ollama[11902]: runtime.goexit({})
Nov 08 07:06:40  ollama[11902]:         runtime/asm_amd64.s:1695 +0x1 fp=0xc00014dfe8 sp=0xc00014dfe0 pc=0x559312d9fde1
Nov 08 07:06:40  ollama[11902]: goroutine 2 gp=0xc000006c40 m=nil [force gc (idle)]:
Nov 08 07:06:40  ollama[11902]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
Nov 08 07:06:40  ollama[11902]:         runtime/proc.go:402 +0xce fp=0xc000050fa8 sp=0xc000050f88 pc=0x559312d6e00e
Nov 08 07:06:40  ollama[11902]: runtime.goparkunlock(...)
Nov 08 07:06:40  ollama[11902]:         runtime/proc.go:408
Nov 08 07:06:40  ollama[11902]: runtime.forcegchelper()
Nov 08 07:06:40  ollama[11902]:         runtime/proc.go:326 +0xb8 fp=0xc000050fe0 sp=0xc000050fa8 pc=0x559312d6de98
Nov 08 07:06:40  ollama[11902]: runtime.goexit({})
Nov 08 07:06:40  ollama[11902]:         runtime/asm_amd64.s:1695 +0x1 fp=0xc000050fe8 sp=0xc000050fe0 pc=0x559312d9fde1
Nov 08 07:06:40  ollama[11902]: created by runtime.init.6 in goroutine 1
Nov 08 07:06:40  ollama[11902]:         runtime/proc.go:314 +0x1a
Nov 08 07:06:40  ollama[11902]: goroutine 3 gp=0xc000007180 m=nil [GC sweep wait]:
Nov 08 07:06:40  ollama[11902]: runtime.gopark(0x1?, 0x0?, 0x0?, 0x0?, 0x0?)
Nov 08 07:06:40  ollama[11902]:         runtime/proc.go:402 +0xce fp=0xc000051780 sp=0xc000051760 pc=0x559312d6e00e
Nov 08 07:06:40  ollama[11902]: runtime.goparkunlock(...)
Nov 08 07:06:40  ollama[11902]:         runtime/proc.go:408
Nov 08 07:06:40  ollama[11902]: runtime.bgsweep(0xc000022070)
Nov 08 07:06:40  ollama[11902]:         runtime/mgcsweep.go:318 +0xdf fp=0xc0000517c8 sp=0xc000051780 pc=0x559312d58b9f
Nov 08 07:06:40  ollama[11902]: runtime.gcenable.gowrap1()
Nov 08 07:06:40  ollama[11902]:         runtime/mgc.go:203 +0x25 fp=0xc0000517e0 sp=0xc0000517c8 pc=0x559312d4d685
Nov 08 07:06:40  ollama[11902]: runtime.goexit({})
Nov 08 07:06:40  ollama[11902]:         runtime/asm_amd64.s:1695 +0x1 fp=0xc0000517e8 sp=0xc0000517e0 pc=0x559312d9fde1
Nov 08 07:06:40  ollama[11902]: created by runtime.gcenable in goroutine 1
Nov 08 07:06:40  ollama[11902]:         runtime/mgc.go:203 +0x66
Nov 08 07:06:40  ollama[11902]: goroutine 4 gp=0xc000007340 m=nil [GC scavenge wait]:
Nov 08 07:06:40  ollama[11902]: runtime.gopark(0x10000?, 0x5593131eff98?, 0x0?, 0x0?, 0x0?)
Nov 08 07:06:40  ollama[11902]:         runtime/proc.go:402 +0xce fp=0xc000051f78 sp=0xc000051f58 pc=0x559312d6e00e
Nov 08 07:06:40  ollama[11902]: runtime.goparkunlock(...)
Nov 08 07:06:40  ollama[11902]:         runtime/proc.go:408
Nov 08 07:06:40  ollama[11902]: runtime.(*scavengerState).park(0x5593134bc4c0)
Nov 08 07:06:40  ollama[11902]:         runtime/mgcscavenge.go:425 +0x49 fp=0xc000051fa8 sp=0xc000051f78 pc=0x559312d56549
Nov 08 07:06:40  ollama[11902]: runtime.bgscavenge(0xc000022070)
Nov 08 07:06:40  ollama[11902]:         runtime/mgcscavenge.go:658 +0x59 fp=0xc000051fc8 sp=0xc000051fa8 pc=0x559312d56af9
Nov 08 07:06:40  ollama[11902]: runtime.gcenable.gowrap2()
Nov 08 07:06:40  ollama[11902]:         runtime/mgc.go:204 +0x25 fp=0xc000051fe0 sp=0xc000051fc8 pc=0x559312d4d625
Nov 08 07:06:40  ollama[11902]: runtime.goexit({})
Nov 08 07:06:40  ollama[11902]:         runtime/asm_amd64.s:1695 +0x1 fp=0xc000051fe8 sp=0xc000051fe0 pc=0x559312d9fde1
Nov 08 07:06:40  ollama[11902]: created by runtime.gcenable in goroutine 1
Nov 08 07:06:40  ollama[11902]:         runtime/mgc.go:204 +0xa5
Nov 08 07:06:40  ollama[11902]: goroutine 5 gp=0xc000007c00 m=nil [finalizer wait]:
Nov 08 07:06:40  ollama[11902]: runtime.gopark(0x0?, 0x5593132ea600?, 0x0?, 0xc0?, 0x1000000010?)
Nov 08 07:06:40  ollama[11902]:         runtime/proc.go:402 +0xce fp=0xc000050620 sp=0xc000050600 pc=0x559312d6e00e
Nov 08 07:06:40  ollama[11902]: runtime.runfinq()
Nov 08 07:06:40  ollama[11902]:         runtime/mfinal.go:194 +0x107 fp=0xc0000507e0 sp=0xc000050620 pc=0x559312d4c6c7
Nov 08 07:06:40  ollama[11902]: runtime.goexit({})
Nov 08 07:06:40  ollama[11902]:         runtime/asm_amd64.s:1695 +0x1 fp=0xc0000507e8 sp=0xc0000507e0 pc=0x559312d9fde1
Nov 08 07:06:40  ollama[11902]: created by runtime.createfing in goroutine 1
Nov 08 07:06:40  ollama[11902]:         runtime/mfinal.go:164 +0x3d
Nov 08 07:06:40  ollama[11902]: goroutine 49 gp=0xc000007dc0 m=nil [GC worker (idle)]:
Nov 08 07:06:40  ollama[11902]: runtime.gopark(0x2736bc2b5abd3?, 0xc00002e9d0?, 0x0?, 0x0?, 0x5593135a5060?)
Nov 08 07:06:40  ollama[11902]:         runtime/proc.go:402 +0xce fp=0xc000052f50 sp=0xc000052f30 pc=0x559312d6e00e
Nov 08 07:06:40  ollama[11902]: runtime.gcBgMarkWorker()
Nov 08 07:06:40  ollama[11902]:         runtime/mgc.go:1310 +0xe5 fp=0xc000052fe0 sp=0xc000052f50 pc=0x559312d4f585
Nov 08 07:06:40  ollama[11902]: runtime.goexit({})
Nov 08 07:06:40  ollama[11902]:         runtime/asm_amd64.s:1695 +0x1 fp=0xc000052fe8 sp=0xc000052fe0 pc=0x559312d9fde1
Nov 08 07:06:40  ollama[11902]: created by runtime.gcBgMarkStartWorkers in goroutine 8
Nov 08 07:06:40  ollama[11902]:         runtime/mgc.go:1234 +0x1c
Nov 08 07:06:40  ollama[11902]: goroutine 8 gp=0xc0001641c0 m=nil [select]:
Nov 08 07:06:40  ollama[11902]: runtime.gopark(0xc000029a80?, 0x2?, 0x60?, 0x0?, 0xc000029824?)
Nov 08 07:06:40  ollama[11902]:         runtime/proc.go:402 +0xce fp=0xc000029698 sp=0xc000029678 pc=0x559312d6e00e
Nov 08 07:06:40  ollama[11902]: runtime.selectgo(0xc000029a80, 0xc000029820, 0x14?, 0x0, 0x1?, 0x1)
Nov 08 07:06:40  ollama[11902]:         runtime/select.go:327 +0x725 fp=0xc0000297b8 sp=0xc000029698 pc=0x559312d7f3e5
Nov 08 07:06:40  ollama[11902]: main.(*Server).completion(0xc000128120, {0x5593132ee5b0, 0xc0001507e0}, 0xc00012a900)
Nov 08 07:06:40  ollama[11902]:         github.com/ollama/ollama/llama/runner/runner.go:652 +0x8fe fp=0xc000029ab8 sp=0xc0000297b8 pc=0x559312fb167e
Nov 08 07:06:40  ollama[11902]: main.(*Server).completion-fm({0x5593132ee5b0?, 0xc0001507e0?}, 0x559312f8cb8d?)
Nov 08 07:06:40  ollama[11902]:         <autogenerated>:1 +0x36 fp=0xc000029ae8 sp=0xc000029ab8 pc=0x559312fb46d6
Nov 08 07:06:40  ollama[11902]: net/http.HandlerFunc.ServeHTTP(0xc00010cc30?, {0x5593132ee5b0?, 0xc0001507e0?}, 0x10?)
Nov 08 07:06:40  ollama[11902]:         net/http/server.go:2171 +0x29 fp=0xc000029b10 sp=0xc000029ae8 pc=0x559312f85629
Nov 08 07:06:40  ollama[11902]: net/http.(*ServeMux).ServeHTTP(0x559312d40f85?, {0x5593132ee5b0, 0xc0001507e0}, 0xc00012a900)
Nov 08 07:06:40  ollama[11902]:         net/http/server.go:2688 +0x1ad fp=0xc000029b60 sp=0xc000029b10 pc=0x559312f874ad
Nov 08 07:06:40  ollama[11902]: net/http.serverHandler.ServeHTTP({0x5593132ed900?}, {0x5593132ee5b0?, 0xc0001507e0?}, 0x6?)
Nov 08 07:06:40  ollama[11902]:         net/http/server.go:3142 +0x8e fp=0xc000029b90 sp=0xc000029b60 pc=0x559312f884ce
Nov 08 07:06:40  ollama[11902]: net/http.(*conn).serve(0xc0001281b0, {0x5593132eea08, 0xc00010ae10})
Nov 08 07:06:40  ollama[11902]:         net/http/server.go:2044 +0x5e8 fp=0xc000029fb8 sp=0xc000029b90 pc=0x559312f84268
Nov 08 07:06:40  ollama[11902]: net/http.(*Server).Serve.gowrap3()
Nov 08 07:06:40  ollama[11902]:         net/http/server.go:3290 +0x28 fp=0xc000029fe0 sp=0xc000029fb8 pc=0x559312f88c48
Nov 08 07:06:40  ollama[11902]: runtime.goexit({})
Nov 08 07:06:40  ollama[11902]:         runtime/asm_amd64.s:1695 +0x1 fp=0xc000029fe8 sp=0xc000029fe0 pc=0x559312d9fde1
Nov 08 07:06:40  ollama[11902]: created by net/http.(*Server).Serve in goroutine 1
Nov 08 07:06:40  ollama[11902]:         net/http/server.go:3290 +0x4b4
Nov 08 07:06:40  ollama[11902]: goroutine 33 gp=0xc000164380 m=nil [GC worker (idle)]:
Nov 08 07:06:40  ollama[11902]: runtime.gopark(0x2736bc93ca49d?, 0x1?, 0x76?, 0x48?, 0x5593135a5060?)
Nov 08 07:06:40  ollama[11902]:         runtime/proc.go:402 +0xce fp=0xc000052750 sp=0xc000052730 pc=0x559312d6e00e
Nov 08 07:06:40  ollama[11902]: runtime.gcBgMarkWorker()
Nov 08 07:06:40  ollama[11902]:         runtime/mgc.go:1310 +0xe5 fp=0xc0000527e0 sp=0xc000052750 pc=0x559312d4f585
Nov 08 07:06:40  ollama[11902]: runtime.goexit({})
Nov 08 07:06:40  ollama[11902]:         runtime/asm_amd64.s:1695 +0x1 fp=0xc0000527e8 sp=0xc0000527e0 pc=0x559312d9fde1
Nov 08 07:06:40  ollama[11902]: created by runtime.gcBgMarkStartWorkers in goroutine 8
Nov 08 07:06:40  ollama[11902]:         runtime/mgc.go:1234 +0x1c
Nov 08 07:06:40  ollama[11902]: goroutine 66 gp=0xc00019a000 m=nil [IO wait]:
Nov 08 07:06:40  ollama[11902]: runtime.gopark(0x10?, 0x10?, 0xf0?, 0xc5?, 0xb?)
Nov 08 07:06:40  ollama[11902]:         runtime/proc.go:402 +0xce fp=0xc00004c5a8 sp=0xc00004c588 pc=0x559312d6e00e
Nov 08 07:06:40  ollama[11902]: runtime.netpollblock(0x559312dd4558?, 0x12d36b26?, 0x93?)
Nov 08 07:06:40  ollama[11902]:         runtime/netpoll.go:573 +0xf7 fp=0xc00004c5e0 sp=0xc00004c5a8 pc=0x559312d66257
Nov 08 07:06:40  ollama[11902]: internal/poll.runtime_pollWait(0x7f36dcfc9768, 0x72)
Nov 08 07:06:40  ollama[11902]:         runtime/netpoll.go:345 +0x85 fp=0xc00004c600 sp=0xc00004c5e0 pc=0x559312d9aaa5
Nov 08 07:06:40  ollama[11902]: internal/poll.(*pollDesc).wait(0xc000152180?, 0xc00010af41?, 0x0)
Nov 08 07:06:40  ollama[11902]:         internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc00004c628 sp=0xc00004c600 pc=0x559312dea9c7
Nov 08 07:06:40  ollama[11902]: internal/poll.(*pollDesc).waitRead(...)
Nov 08 07:06:40  ollama[11902]:         internal/poll/fd_poll_runtime.go:89
Nov 08 07:06:40  ollama[11902]: internal/poll.(*FD).Read(0xc000152180, {0xc00010af41, 0x1, 0x1})
Nov 08 07:06:40  ollama[11902]:         internal/poll/fd_unix.go:164 +0x27a fp=0xc00004c6c0 sp=0xc00004c628 pc=0x559312deb51a
Nov 08 07:06:40  ollama[11902]: net.(*netFD).Read(0xc000152180, {0xc00010af41?, 0xc00004c748?, 0x559312d9c6d0?})
Nov 08 07:06:40  ollama[11902]:         net/fd_posix.go:55 +0x25 fp=0xc00004c708 sp=0xc00004c6c0 pc=0x559312e597a5
Nov 08 07:06:40  ollama[11902]: net.(*conn).Read(0xc0000540a8, {0xc00010af41?, 0x0?, 0x5593135a5060?})
Nov 08 07:06:40  ollama[11902]:         net/net.go:185 +0x45 fp=0xc00004c750 sp=0xc00004c708 pc=0x559312e63a65
Nov 08 07:06:40  ollama[11902]: net.(*TCPConn).Read(0x55931347d840?, {0xc00010af41?, 0x0?, 0x0?})
Nov 08 07:06:40  ollama[11902]:         <autogenerated>:1 +0x25 fp=0xc00004c780 sp=0xc00004c750 pc=0x559312e6f445
Nov 08 07:06:40  ollama[11902]: net/http.(*connReader).backgroundRead(0xc00010af30)
Nov 08 07:06:40  ollama[11902]:         net/http/server.go:681 +0x37 fp=0xc00004c7c8 sp=0xc00004c780 pc=0x559312f7e1d7
Nov 08 07:06:40  ollama[11902]: net/http.(*connReader).startBackgroundRead.gowrap2()
Nov 08 07:06:40  ollama[11902]:         net/http/server.go:677 +0x25 fp=0xc00004c7e0 sp=0xc00004c7c8 pc=0x559312f7e105
Nov 08 07:06:40  ollama[11902]: runtime.goexit({})
Nov 08 07:06:40  ollama[11902]:         runtime/asm_amd64.s:1695 +0x1 fp=0xc00004c7e8 sp=0xc00004c7e0 pc=0x559312d9fde1
Nov 08 07:06:40  ollama[11902]: created by net/http.(*connReader).startBackgroundRead in goroutine 8
Nov 08 07:06:40  ollama[11902]:         net/http/server.go:677 +0xba
Nov 08 07:06:40  ollama[11902]: goroutine 32 gp=0xc00008a380 m=nil [GC worker (idle)]:
Nov 08 07:06:40  ollama[11902]: runtime.gopark(0x2736bc93d3ed0?, 0xc00002e9d0?, 0x0?, 0x0?, 0x5593135a5060?)
Nov 08 07:06:40  ollama[11902]:         runtime/proc.go:402 +0xce fp=0xc0000b2750 sp=0xc0000b2730 pc=0x559312d6e00e
Nov 08 07:06:40  ollama[11902]: runtime.gcBgMarkWorker()
Nov 08 07:06:40  ollama[11902]:         runtime/mgc.go:1310 +0xe5 fp=0xc0000b27e0 sp=0xc0000b2750 pc=0x559312d4f585
Nov 08 07:06:40  ollama[11902]: runtime.goexit({})
Nov 08 07:06:40  ollama[11902]:         runtime/asm_amd64.s:1695 +0x1 fp=0xc0000b27e8 sp=0xc0000b27e0 pc=0x559312d9fde1
Nov 08 07:06:40  ollama[11902]: created by runtime.gcBgMarkStartWorkers in goroutine 8
Nov 08 07:06:40  ollama[11902]:         runtime/mgc.go:1234 +0x1c
Nov 08 07:06:40  ollama[11902]: goroutine 48 gp=0xc00008a540 m=nil [GC worker (idle)]:
Nov 08 07:06:40  ollama[11902]: runtime.gopark(0x2736bc93d3fdc?, 0x3?, 0x98?, 0x4d?, 0x5593135a5060?)
Nov 08 07:06:40  ollama[11902]:         runtime/proc.go:402 +0xce fp=0xc0000b2f50 sp=0xc0000b2f30 pc=0x559312d6e00e
Nov 08 07:06:40  ollama[11902]: runtime.gcBgMarkWorker()
Nov 08 07:06:40  ollama[11902]:         runtime/mgc.go:1310 +0xe5 fp=0xc0000b2fe0 sp=0xc0000b2f50 pc=0x559312d4f585
Nov 08 07:06:40  ollama[11902]: runtime.goexit({})
Nov 08 07:06:40  ollama[11902]:         runtime/asm_amd64.s:1695 +0x1 fp=0xc0000b2fe8 sp=0xc0000b2fe0 pc=0x559312d9fde1
Nov 08 07:06:40  ollama[11902]: created by runtime.gcBgMarkStartWorkers in goroutine 8
Nov 08 07:06:40  ollama[11902]:         runtime/mgc.go:1234 +0x1c
Nov 08 07:06:40  ollama[11902]: goroutine 50 gp=0xc00008a700 m=nil [GC worker (idle)]:
Nov 08 07:06:40  ollama[11902]: runtime.gopark(0x2736bc93d3def?, 0xc00002e9d0?, 0x0?, 0x0?, 0x5593135a5060?)
Nov 08 07:06:40  ollama[11902]:         runtime/proc.go:402 +0xce fp=0xc0000b3750 sp=0xc0000b3730 pc=0x559312d6e00e
Nov 08 07:06:40  ollama[11902]: runtime.gcBgMarkWorker()
Nov 08 07:06:40  ollama[11902]:         runtime/mgc.go:1310 +0xe5 fp=0xc0000b37e0 sp=0xc0000b3750 pc=0x559312d4f585
Nov 08 07:06:40  ollama[11902]: runtime.goexit({})
Nov 08 07:06:40  ollama[11902]:         runtime/asm_amd64.s:1695 +0x1 fp=0xc0000b37e8 sp=0xc0000b37e0 pc=0x559312d9fde1
Nov 08 07:06:40  ollama[11902]: created by runtime.gcBgMarkStartWorkers in goroutine 8
Nov 08 07:06:40  ollama[11902]:         runtime/mgc.go:1234 +0x1c
Nov 08 07:06:40  ollama[11902]: goroutine 12 gp=0xc000164540 m=nil [GC worker (idle)]:
Nov 08 07:06:40  ollama[11902]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
Nov 08 07:06:40  ollama[11902]:         runtime/proc.go:402 +0xce fp=0xc000053750 sp=0xc000053730 pc=0x559312d6e00e
Nov 08 07:06:40  ollama[11902]: runtime.gcBgMarkWorker()
Nov 08 07:06:40  ollama[11902]:         runtime/mgc.go:1310 +0xe5 fp=0xc0000537e0 sp=0xc000053750 pc=0x559312d4f585
Nov 08 07:06:40  ollama[11902]: runtime.goexit({})
Nov 08 07:06:40  ollama[11902]:         runtime/asm_amd64.s:1695 +0x1 fp=0xc0000537e8 sp=0xc0000537e0 pc=0x559312d9fde1
Nov 08 07:06:40  ollama[11902]: created by runtime.gcBgMarkStartWorkers in goroutine 8
Nov 08 07:06:40  ollama[11902]:         runtime/mgc.go:1234 +0x1c
Nov 08 07:06:40  ollama[11902]: goroutine 13 gp=0xc000164700 m=nil [GC worker (idle)]:
Nov 08 07:06:40  ollama[11902]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
Nov 08 07:06:40  ollama[11902]:         runtime/proc.go:402 +0xce fp=0xc000053f50 sp=0xc000053f30 pc=0x559312d6e00e
Nov 08 07:06:40  ollama[11902]: runtime.gcBgMarkWorker()
Nov 08 07:06:40  ollama[11902]:         runtime/mgc.go:1310 +0xe5 fp=0xc000053fe0 sp=0xc000053f50 pc=0x559312d4f585
Nov 08 07:06:40  ollama[11902]: runtime.goexit({})
Nov 08 07:06:40  ollama[11902]:         runtime/asm_amd64.s:1695 +0x1 fp=0xc000053fe8 sp=0xc000053fe0 pc=0x559312d9fde1
Nov 08 07:06:40  ollama[11902]: created by runtime.gcBgMarkStartWorkers in goroutine 8
Nov 08 07:06:40  ollama[11902]:         runtime/mgc.go:1234 +0x1c
Nov 08 07:06:40  ollama[11902]: goroutine 14 gp=0xc0001648c0 m=nil [GC worker (idle)]:
Nov 08 07:06:40  ollama[11902]: runtime.gopark(0x2736bc93ca34d?, 0x0?, 0x0?, 0x0?, 0x0?)
Nov 08 07:06:40  ollama[11902]:         runtime/proc.go:402 +0xce fp=0xc0000ae750 sp=0xc0000ae730 pc=0x559312d6e00e
Nov 08 07:06:40  ollama[11902]: runtime.gcBgMarkWorker()
Nov 08 07:06:40  ollama[11902]:         runtime/mgc.go:1310 +0xe5 fp=0xc0000ae7e0 sp=0xc0000ae750 pc=0x559312d4f585
Nov 08 07:06:40  ollama[11902]: runtime.goexit({})
Nov 08 07:06:40  ollama[11902]:         runtime/asm_amd64.s:1695 +0x1 fp=0xc0000ae7e8 sp=0xc0000ae7e0 pc=0x559312d9fde1
Nov 08 07:06:40  ollama[11902]: created by runtime.gcBgMarkStartWorkers in goroutine 8
Nov 08 07:06:40  ollama[11902]:         runtime/mgc.go:1234 +0x1c
Nov 08 07:06:40  ollama[11902]: rax    0x0
Nov 08 07:06:40  ollama[11902]: rbx    0x7f361fffe000
Nov 08 07:06:40  ollama[11902]: rcx    0x7f36bec419fc
Nov 08 07:06:40  ollama[11902]: rdx    0x6
Nov 08 07:06:40  ollama[11902]: rdi    0x839d
Nov 08 07:06:40  ollama[11902]: rsi    0x83aa
Nov 08 07:06:40  ollama[11902]: rbp    0x83aa
Nov 08 07:06:40  ollama[11902]: rsp    0x7f361ffd52b0
Nov 08 07:06:40  ollama[11902]: r8     0x7f361ffd5380
Nov 08 07:06:40  ollama[11902]: r9     0x7f361ffd5350
Nov 08 07:06:40  ollama[11902]: r10    0x8
Nov 08 07:06:40  ollama[11902]: r11    0x246
Nov 08 07:06:40  ollama[11902]: r12    0x6
Nov 08 07:06:40  ollama[11902]: r13    0x16
Nov 08 07:06:40  ollama[11902]: r14    0x7f36e609f54b
Nov 08 07:06:40  ollama[11902]: r15    0x7f365005b650
Nov 08 07:06:40  ollama[11902]: rip    0x7f36bec419fc
Nov 08 07:06:40  ollama[11902]: rflags 0x246
Nov 08 07:06:40  ollama[11902]: cs     0x33
Nov 08 07:06:40  ollama[11902]: fs     0x0
Nov 08 07:06:40  ollama[11902]: gs     0x0

System Information:

OS: Ubuntu 22.04.5 LTS
CPU: Intel(R) Core(TM) i3-10300 CPU @ 3.70GHz
GPU: 2x NVIDIA GeForce RTX 3070
Driver Version: 550.120
CUDA Version: 12.4

OS

Linux

GPU

Nvidia

CPU

Intel

Ollama version

0.4.0

Originally created by @romansvet on GitHub (Nov 8, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/7568 Originally assigned to: @dhiltgen on GitHub. ### What is the issue? I am using open webUI version v0.3.30 and when I try to analyze an image using the llama3.2-vision:latest model I get nothing. In the ollama service log I see the following: ``` Nov 08 07:06:28 ollama[11902]: time=2024-11-08T07:06:28.729Z level=WARN source=sched.go:137 msg="multimodal models don't support parallel requests yet" Nov 08 07:06:28 ollama[11902]: time=2024-11-08T07:06:28.905Z level=INFO source=sched.go:730 msg="new model will fit in available VRAM, loading" model=/usr/share/ollama/.ollama/models/blobs/sha256-11f274007f093fefeec994a5dbbb33d0733a4feb87f7ab66dcd7c1069fef0068 library=cuda parallel=1 required="13.0 GiB" Nov 08 07:06:29 ollama[11902]: time=2024-11-08T07:06:29.030Z level=INFO source=server.go:105 msg="system memory" total="125.7 GiB" free="123.6 GiB" free_swap="32.0 GiB" Nov 08 07:06:29 ollama[11902]: time=2024-11-08T07:06:29.032Z level=INFO source=memory.go:343 msg="offload to cuda" projector.weights="1.8 GiB" projector.graph="2.8 GiB" layers.requested=-1 layers.model=41 layers.offload=41 layers.split=13,28 memory.available="[7.6 GiB 7.6 GiB]" memory.gpu_overhead="0 B" memory.required.full="13.0 GiB" memory.required.partial="13.0 GiB" memory.required.kv="656.2 MiB" memory.required.allocations="[7.6 GiB 5.4 GiB]" memory.weights.total="5.5 GiB" memory.weights.repeating="5.1 GiB" memory.weights.nonrepeating="411.0 MiB" memory.graph.full="669.5 MiB" memory.graph.partial="669.5 MiB" Nov 08 07:06:29 ollama[11902]: time=2024-11-08T07:06:29.032Z level=INFO source=server.go:388 msg="starting llama server" cmd="/tmp/ollama1948393618/runners/cuda_v12/ollama_llama_server --model /usr/share/ollama/.ollama/models/blobs/sha256-11f274007f093fefeec994a5dbbb33d0733a4feb87f7ab66dcd7c1069fef0068 --ctx-size 2048 --batch-size 512 --embedding --n-gpu-layers 41 --mmproj /usr/share/ollama/.ollama/models/blobs/sha256-ece5e659647a20a5c28ab9eea1c12a1ad430bc0f2a27021d00ad103b3bf5206f --threads 4 --parallel 1 --tensor-split 13,28 --port 40263" Nov 08 07:06:29 ollama[11902]: time=2024-11-08T07:06:29.032Z level=INFO source=sched.go:449 msg="loaded runners" count=1 Nov 08 07:06:29 ollama[11902]: time=2024-11-08T07:06:29.032Z level=INFO source=server.go:567 msg="waiting for llama runner to start responding" Nov 08 07:06:29 ollama[11902]: time=2024-11-08T07:06:29.032Z level=INFO source=server.go:601 msg="waiting for server to become available" status="llm server error" Nov 08 07:06:29 ollama[11902]: time=2024-11-08T07:06:29.056Z level=INFO source=runner.go:869 msg="starting go runner" Nov 08 07:06:29 ollama[11902]: time=2024-11-08T07:06:29.056Z level=INFO source=runner.go:870 msg=system info="AVX = 1 | AVX_VNNI = 0 | AVX2 = 0 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | AVX512_BF16 = 0 | FMA = 0 | NEON = 0 | SVE = 0 | ARM_FMA = 0 | F16C = 0 | FP16_VA = 0 | RISCV_VECT = 0 | WASM_SIMD = 0 | BLAS = 1 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | MATMUL_INT8 = 0 | LLAMAFILE = 1 | cgo(gcc)" threads=4 Nov 08 07:06:29 ollama[11902]: time=2024-11-08T07:06:29.056Z level=INFO source=.:0 msg="Server listening on 127.0.0.1:40263" Nov 08 07:06:29 ollama[11902]: llama_model_loader: loaded meta data with 27 key-value pairs and 396 tensors from /usr/share/ollama/.ollama/models/blobs/sha256-11f274007f093fefeec994a5dbbb33d0733a4feb87f7ab66dcd7c1069fef0068 (version GGUF V3 (latest)) Nov 08 07:06:29 ollama[11902]: llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output. Nov 08 07:06:29 ollama[11902]: llama_model_loader: - kv 0: general.architecture str = mllama Nov 08 07:06:29 ollama[11902]: llama_model_loader: - kv 1: general.type str = model Nov 08 07:06:29 ollama[11902]: llama_model_loader: - kv 2: general.name str = Model Nov 08 07:06:29 ollama[11902]: llama_model_loader: - kv 3: general.size_label str = 10B Nov 08 07:06:29 ollama[11902]: llama_model_loader: - kv 4: mllama.block_count u32 = 40 Nov 08 07:06:29 ollama[11902]: llama_model_loader: - kv 5: mllama.context_length u32 = 131072 Nov 08 07:06:29 ollama[11902]: llama_model_loader: - kv 6: mllama.embedding_length u32 = 4096 Nov 08 07:06:29 ollama[11902]: llama_model_loader: - kv 7: mllama.feed_forward_length u32 = 14336 Nov 08 07:06:29 ollama[11902]: llama_model_loader: - kv 8: mllama.attention.head_count u32 = 32 Nov 08 07:06:29 ollama[11902]: llama_model_loader: - kv 9: mllama.attention.head_count_kv u32 = 8 Nov 08 07:06:29 ollama[11902]: llama_model_loader: - kv 10: mllama.rope.freq_base f32 = 500000.000000 Nov 08 07:06:29 ollama[11902]: llama_model_loader: - kv 11: mllama.attention.layer_norm_rms_epsilon f32 = 0.000010 Nov 08 07:06:29 ollama[11902]: llama_model_loader: - kv 12: general.file_type u32 = 15 Nov 08 07:06:29 ollama[11902]: llama_model_loader: - kv 13: mllama.vocab_size u32 = 128256 Nov 08 07:06:29 ollama[11902]: llama_model_loader: - kv 14: mllama.rope.dimension_count u32 = 128 Nov 08 07:06:29 ollama[11902]: llama_model_loader: - kv 15: mllama.attention.cross_attention_layers arr[i32,8] = [3, 8, 13, 18, 23, 28, 33, 38] Nov 08 07:06:29 ollama[11902]: llama_model_loader: - kv 16: tokenizer.ggml.add_bos_token bool = true Nov 08 07:06:29 ollama[11902]: llama_model_loader: - kv 17: tokenizer.ggml.model str = gpt2 Nov 08 07:06:29 ollama[11902]: llama_model_loader: - kv 18: tokenizer.ggml.pre str = llama-bpe Nov 08 07:06:29 ollama[11902]: llama_model_loader: - kv 19: tokenizer.ggml.tokens arr[str,128257] = ["!", "\"", "#", "$", "%", "&", "'", ... Nov 08 07:06:29 ollama[11902]: llama_model_loader: - kv 20: tokenizer.ggml.token_type arr[i32,128257] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... Nov 08 07:06:29 ollama[11902]: llama_model_loader: - kv 21: tokenizer.ggml.merges arr[str,280147] = ["Ġ Ġ", "Ġ ĠĠĠ", "ĠĠ ĠĠ", "... Nov 08 07:06:29 ollama[11902]: llama_model_loader: - kv 22: tokenizer.ggml.bos_token_id u32 = 128000 Nov 08 07:06:29 ollama[11902]: llama_model_loader: - kv 23: tokenizer.ggml.eos_token_id u32 = 128009 Nov 08 07:06:29 ollama[11902]: llama_model_loader: - kv 24: tokenizer.ggml.padding_token_id u32 = 128004 Nov 08 07:06:29 ollama[11902]: llama_model_loader: - kv 25: tokenizer.chat_template str = {{- bos_token }}\n{%- if custom_tools ... Nov 08 07:06:29 ollama[11902]: llama_model_loader: - kv 26: general.quantization_version u32 = 2 Nov 08 07:06:29 ollama[11902]: llama_model_loader: - type f32: 114 tensors Nov 08 07:06:29 ollama[11902]: llama_model_loader: - type q4_K: 245 tensors Nov 08 07:06:29 ollama[11902]: llama_model_loader: - type q6_K: 37 tensors Nov 08 07:06:29 ollama[11902]: time=2024-11-08T07:06:29.283Z level=INFO source=server.go:601 msg="waiting for server to become available" status="llm server loading model" Nov 08 07:06:29 ollama[11902]: llm_load_vocab: special tokens cache size = 257 Nov 08 07:06:29 ollama[11902]: llm_load_vocab: token to piece cache size = 0.7999 MB Nov 08 07:06:29 ollama[11902]: llm_load_print_meta: format = GGUF V3 (latest) Nov 08 07:06:29 ollama[11902]: llm_load_print_meta: arch = mllama Nov 08 07:06:29 ollama[11902]: llm_load_print_meta: vocab type = BPE Nov 08 07:06:29 ollama[11902]: llm_load_print_meta: n_vocab = 128256 Nov 08 07:06:29 ollama[11902]: llm_load_print_meta: n_merges = 280147 Nov 08 07:06:29 ollama[11902]: llm_load_print_meta: vocab_only = 0 Nov 08 07:06:29 ollama[11902]: llm_load_print_meta: n_ctx_train = 131072 Nov 08 07:06:29 ollama[11902]: llm_load_print_meta: n_embd = 4096 Nov 08 07:06:29 ollama[11902]: llm_load_print_meta: n_layer = 40 Nov 08 07:06:29 ollama[11902]: llm_load_print_meta: n_head = 32 Nov 08 07:06:29 ollama[11902]: llm_load_print_meta: n_head_kv = 8 Nov 08 07:06:29 ollama[11902]: llm_load_print_meta: n_rot = 128 Nov 08 07:06:29 ollama[11902]: llm_load_print_meta: n_swa = 0 Nov 08 07:06:29 ollama[11902]: llm_load_print_meta: n_embd_head_k = 128 Nov 08 07:06:29 ollama[11902]: llm_load_print_meta: n_embd_head_v = 128 Nov 08 07:06:29 ollama[11902]: llm_load_print_meta: n_gqa = 4 Nov 08 07:06:29 ollama[11902]: llm_load_print_meta: n_embd_k_gqa = 1024 Nov 08 07:06:29 ollama[11902]: llm_load_print_meta: n_embd_v_gqa = 1024 Nov 08 07:06:29 ollama[11902]: llm_load_print_meta: f_norm_eps = 0.0e+00 Nov 08 07:06:29 ollama[11902]: llm_load_print_meta: f_norm_rms_eps = 1.0e-05 Nov 08 07:06:29 ollama[11902]: llm_load_print_meta: f_clamp_kqv = 0.0e+00 Nov 08 07:06:29 ollama[11902]: llm_load_print_meta: f_max_alibi_bias = 0.0e+00 Nov 08 07:06:29 ollama[11902]: llm_load_print_meta: f_logit_scale = 0.0e+00 Nov 08 07:06:29 ollama[11902]: llm_load_print_meta: n_ff = 14336 Nov 08 07:06:29 ollama[11902]: llm_load_print_meta: n_expert = 0 Nov 08 07:06:29 ollama[11902]: llm_load_print_meta: n_expert_used = 0 Nov 08 07:06:29 ollama[11902]: llm_load_print_meta: causal attn = 1 Nov 08 07:06:29 ollama[11902]: llm_load_print_meta: pooling type = 0 Nov 08 07:06:29 ollama[11902]: llm_load_print_meta: rope type = 0 Nov 08 07:06:29 ollama[11902]: llm_load_print_meta: rope scaling = linear Nov 08 07:06:29 ollama[11902]: llm_load_print_meta: freq_base_train = 500000.0 Nov 08 07:06:29 ollama[11902]: llm_load_print_meta: freq_scale_train = 1 Nov 08 07:06:29 ollama[11902]: llm_load_print_meta: n_ctx_orig_yarn = 131072 Nov 08 07:06:29 ollama[11902]: llm_load_print_meta: rope_finetuned = unknown Nov 08 07:06:29 ollama[11902]: llm_load_print_meta: ssm_d_conv = 0 Nov 08 07:06:29 ollama[11902]: llm_load_print_meta: ssm_d_inner = 0 Nov 08 07:06:29 ollama[11902]: llm_load_print_meta: ssm_d_state = 0 Nov 08 07:06:29 ollama[11902]: llm_load_print_meta: ssm_dt_rank = 0 Nov 08 07:06:29 ollama[11902]: llm_load_print_meta: ssm_dt_b_c_rms = 0 Nov 08 07:06:29 ollama[11902]: llm_load_print_meta: model type = 11B Nov 08 07:06:29 ollama[11902]: llm_load_print_meta: model ftype = Q4_K - Medium Nov 08 07:06:29 ollama[11902]: llm_load_print_meta: model params = 9.78 B Nov 08 07:06:29 ollama[11902]: llm_load_print_meta: model size = 5.55 GiB (4.87 BPW) Nov 08 07:06:29 ollama[11902]: llm_load_print_meta: general.name = Model Nov 08 07:06:29 ollama[11902]: llm_load_print_meta: BOS token = 128000 '<|begin_of_text|>' Nov 08 07:06:29 ollama[11902]: llm_load_print_meta: EOS token = 128009 '<|eot_id|>' Nov 08 07:06:29 ollama[11902]: llm_load_print_meta: PAD token = 128004 '<|finetune_right_pad_id|>' Nov 08 07:06:29 ollama[11902]: llm_load_print_meta: LF token = 128 'Ä' Nov 08 07:06:29 ollama[11902]: llm_load_print_meta: EOT token = 128009 '<|eot_id|>' Nov 08 07:06:29 ollama[11902]: llm_load_print_meta: EOM token = 128008 '<|eom_id|>' Nov 08 07:06:29 ollama[11902]: llm_load_print_meta: EOG token = 128008 '<|eom_id|>' Nov 08 07:06:29 ollama[11902]: llm_load_print_meta: EOG token = 128009 '<|eot_id|>' Nov 08 07:06:29 ollama[11902]: llm_load_print_meta: max token length = 256 Nov 08 07:06:29 ollama[11902]: llama_model_load: vocab mismatch 128256 !- 128257 ... Nov 08 07:06:29 ollama[11902]: ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no Nov 08 07:06:29 ollama[11902]: ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no Nov 08 07:06:29 ollama[11902]: ggml_cuda_init: found 2 CUDA devices: Nov 08 07:06:29 ollama[11902]: Device 0: NVIDIA GeForce RTX 3070, compute capability 8.6, VMM: yes Nov 08 07:06:29 ollama[11902]: Device 1: NVIDIA GeForce RTX 3070, compute capability 8.6, VMM: yes Nov 08 07:06:29 ollama[11902]: llm_load_tensors: ggml ctx size = 0.54 MiB Nov 08 07:06:29 ollama[11902]: llm_load_tensors: offloading 40 repeating layers to GPU Nov 08 07:06:29 ollama[11902]: llm_load_tensors: offloading non-repeating layers to GPU Nov 08 07:06:29 ollama[11902]: llm_load_tensors: offloaded 41/41 layers to GPU Nov 08 07:06:29 ollama[11902]: llm_load_tensors: CPU buffer size = 281.83 MiB Nov 08 07:06:29 ollama[11902]: llm_load_tensors: CUDA0 buffer size = 1628.66 MiB Nov 08 07:06:29 ollama[11902]: llm_load_tensors: CUDA1 buffer size = 3768.85 MiB Nov 08 07:06:35 ollama[11902]: llama_new_context_with_model: n_ctx = 2048 Nov 08 07:06:35 ollama[11902]: llama_new_context_with_model: n_batch = 512 Nov 08 07:06:35 ollama[11902]: llama_new_context_with_model: n_ubatch = 512 Nov 08 07:06:35 ollama[11902]: llama_new_context_with_model: flash_attn = 0 Nov 08 07:06:35 ollama[11902]: llama_new_context_with_model: freq_base = 500000.0 Nov 08 07:06:35 ollama[11902]: llama_new_context_with_model: freq_scale = 1 Nov 08 07:06:35 ollama[11902]: llama_kv_cache_init: CUDA0 KV buffer size = 188.06 MiB Nov 08 07:06:35 ollama[11902]: llama_kv_cache_init: CUDA1 KV buffer size = 468.19 MiB Nov 08 07:06:35 ollama[11902]: llama_new_context_with_model: KV self size = 656.25 MiB, K (f16): 328.12 MiB, V (f16): 328.12 MiB Nov 08 07:06:35 ollama[11902]: llama_new_context_with_model: CUDA_Host output buffer size = 0.50 MiB Nov 08 07:06:35 ollama[11902]: llama_new_context_with_model: pipeline parallelism enabled (n_copies=4) Nov 08 07:06:35 ollama[11902]: llama_new_context_with_model: CUDA0 compute buffer size = 208.01 MiB Nov 08 07:06:35 ollama[11902]: llama_new_context_with_model: CUDA1 compute buffer size = 306.52 MiB Nov 08 07:06:35 ollama[11902]: llama_new_context_with_model: CUDA_Host compute buffer size = 24.02 MiB Nov 08 07:06:35 ollama[11902]: llama_new_context_with_model: graph nodes = 1030 Nov 08 07:06:35 ollama[11902]: llama_new_context_with_model: graph splits = 3 Nov 08 07:06:35 ollama[11902]: mllama_model_load: model name: Llama-3.2-11B-Vision-Instruct Nov 08 07:06:35 ollama[11902]: mllama_model_load: description: vision encoder for Mllama Nov 08 07:06:35 ollama[11902]: mllama_model_load: GGUF version: 3 Nov 08 07:06:35 ollama[11902]: mllama_model_load: alignment: 32 Nov 08 07:06:35 ollama[11902]: mllama_model_load: n_tensors: 512 Nov 08 07:06:35 ollama[11902]: mllama_model_load: n_kv: 17 Nov 08 07:06:35 ollama[11902]: mllama_model_load: ftype: f16 Nov 08 07:06:35 ollama[11902]: mllama_model_load: Nov 08 07:06:35 ollama[11902]: mllama_model_load: vision using CUDA backend Nov 08 07:06:36 ollama[11902]: mllama_model_load: compute allocated memory: 2853.34 MB Nov 08 07:06:36 ollama[11902]: time=2024-11-08T07:06:36.555Z level=INFO source=server.go:606 msg="llama runner started in 7.52 seconds" Nov 08 07:06:40 ollama[11902]: CUDA error: unspecified launch failure Nov 08 07:06:40 ollama[11902]: current device: 1, in function ggml_backend_cuda_synchronize at ggml-cuda.cu:2508 Nov 08 07:06:40 ollama[11902]: cudaStreamSynchronize(cuda_ctx->stream()) Nov 08 07:06:40 ollama[11902]: ggml-cuda.cu:132: CUDA error Nov 08 07:06:40 ollama[11902]: SIGSEGV: segmentation violation Nov 08 07:06:40 ollama[11902]: PC=0x7f36e43b4c47 m=9 sigcode=1 addr=0x209e03fd4 Nov 08 07:06:40 ollama[11902]: signal arrived during cgo execution Nov 08 07:06:40 ollama[11902]: goroutine 7 gp=0xc000164000 m=9 mp=0xc0001a2808 [syscall]: Nov 08 07:06:40 ollama[11902]: runtime.cgocall(0x559312fb4eb0, 0xc000065b60) Nov 08 07:06:40 ollama[11902]: runtime/cgocall.go:157 +0x4b fp=0xc000065b38 sp=0xc000065b00 pc=0x559312d373cb Nov 08 07:06:40 ollama[11902]: github.com/ollama/ollama/llama._Cfunc_llama_decode(0x7f365005b650, {0xe, 0x7f36503ad760, 0x0, 0x0, 0x7f36503adf70, 0x7f365019ef40, 0x7f365019f750, 0x7f3642c4d360, 0x0, ...}) Nov 08 07:06:40 ollama[11902]: _cgo_gotypes.go:543 +0x52 fp=0xc000065b60 sp=0xc000065b38 pc=0x559312e34952 Nov 08 07:06:40 ollama[11902]: github.com/ollama/ollama/llama.(*Context).Decode.func1(0x559312fb0ceb?, 0x7f365005b650?) Nov 08 07:06:40 ollama[11902]: github.com/ollama/ollama/llama/llama.go:167 +0xd8 fp=0xc000065c80 sp=0xc000065b60 pc=0x559312e36e78 Nov 08 07:06:40 ollama[11902]: github.com/ollama/ollama/llama.(*Context).Decode(0xc0000163c0?, 0x1?) Nov 08 07:06:40 ollama[11902]: github.com/ollama/ollama/llama/llama.go:167 +0x17 fp=0xc000065cc8 sp=0xc000065c80 pc=0x559312e36cd7 Nov 08 07:06:40 ollama[11902]: main.(*Server).processBatch(0xc000128120, 0xc0000c0000, 0xc0000c0070) Nov 08 07:06:40 ollama[11902]: github.com/ollama/ollama/llama/runner/runner.go:424 +0x29e fp=0xc000065ed0 sp=0xc000065cc8 pc=0x559312fafd1e Nov 08 07:06:40 ollama[11902]: main.(*Server).run(0xc000128120, {0x5593132eea40, 0xc00007c0a0}) Nov 08 07:06:40 ollama[11902]: github.com/ollama/ollama/llama/runner/runner.go:338 +0x1a5 fp=0xc000065fb8 sp=0xc000065ed0 pc=0x559312faf705 Nov 08 07:06:40 ollama[11902]: main.main.gowrap2() Nov 08 07:06:40 ollama[11902]: github.com/ollama/ollama/llama/runner/runner.go:907 +0x28 fp=0xc000065fe0 sp=0xc000065fb8 pc=0x559312fb3ee8 Nov 08 07:06:40 ollama[11902]: runtime.goexit({}) Nov 08 07:06:40 ollama[11902]: runtime/asm_amd64.s:1695 +0x1 fp=0xc000065fe8 sp=0xc000065fe0 pc=0x559312d9fde1 Nov 08 07:06:40 ollama[11902]: created by main.main in goroutine 1 Nov 08 07:06:40 ollama[11902]: github.com/ollama/ollama/llama/runner/runner.go:907 +0xcab Nov 08 07:06:40 ollama[11902]: goroutine 1 gp=0xc0000061c0 m=nil [IO wait]: Nov 08 07:06:40 ollama[11902]: runtime.gopark(0xc000030008?, 0x0?, 0xc0?, 0x61?, 0xc0000298c0?) Nov 08 07:06:40 ollama[11902]: runtime/proc.go:402 +0xce fp=0xc00014d888 sp=0xc00014d868 pc=0x559312d6e00e Nov 08 07:06:40 ollama[11902]: runtime.netpollblock(0xc000029920?, 0x12d36b26?, 0x93?) Nov 08 07:06:40 ollama[11902]: runtime/netpoll.go:573 +0xf7 fp=0xc00014d8c0 sp=0xc00014d888 pc=0x559312d66257 Nov 08 07:06:40 ollama[11902]: internal/poll.runtime_pollWait(0x7f36dcfc9860, 0x72) Nov 08 07:06:40 ollama[11902]: runtime/netpoll.go:345 +0x85 fp=0xc00014d8e0 sp=0xc00014d8c0 pc=0x559312d9aaa5 Nov 08 07:06:40 ollama[11902]: internal/poll.(*pollDesc).wait(0x3?, 0x3fe?, 0x0) Nov 08 07:06:40 ollama[11902]: internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc00014d908 sp=0xc00014d8e0 pc=0x559312dea9c7 Nov 08 07:06:40 ollama[11902]: internal/poll.(*pollDesc).waitRead(...) Nov 08 07:06:40 ollama[11902]: internal/poll/fd_poll_runtime.go:89 Nov 08 07:06:40 ollama[11902]: internal/poll.(*FD).Accept(0xc000152100) Nov 08 07:06:40 ollama[11902]: internal/poll/fd_unix.go:611 +0x2ac fp=0xc00014d9b0 sp=0xc00014d908 pc=0x559312debe8c Nov 08 07:06:40 ollama[11902]: net.(*netFD).accept(0xc000152100) Nov 08 07:06:40 ollama[11902]: net/fd_unix.go:172 +0x29 fp=0xc00014da68 sp=0xc00014d9b0 pc=0x559312e5a8a9 Nov 08 07:06:40 ollama[11902]: net.(*TCPListener).accept(0xc000070200) Nov 08 07:06:40 ollama[11902]: net/tcpsock_posix.go:159 +0x1e fp=0xc00014da90 sp=0xc00014da68 pc=0x559312e6b5de Nov 08 07:06:40 ollama[11902]: net.(*TCPListener).Accept(0xc000070200) Nov 08 07:06:40 ollama[11902]: net/tcpsock.go:327 +0x30 fp=0xc00014dac0 sp=0xc00014da90 pc=0x559312e6a930 Nov 08 07:06:40 ollama[11902]: net/http.(*onceCloseListener).Accept(0xc0001281b0?) Nov 08 07:06:40 ollama[11902]: <autogenerated>:1 +0x24 fp=0xc00014dad8 sp=0xc00014dac0 pc=0x559312f91a44 Nov 08 07:06:40 ollama[11902]: net/http.(*Server).Serve(0xc0001620f0, {0x5593132ee400, 0xc000070200}) Nov 08 07:06:40 ollama[11902]: net/http/server.go:3260 +0x33e fp=0xc00014dc08 sp=0xc00014dad8 pc=0x559312f8885e Nov 08 07:06:40 ollama[11902]: main.main() Nov 08 07:06:40 ollama[11902]: github.com/ollama/ollama/llama/runner/runner.go:927 +0x104c fp=0xc00014df50 sp=0xc00014dc08 pc=0x559312fb3c6c Nov 08 07:06:40 ollama[11902]: runtime.main() Nov 08 07:06:40 ollama[11902]: runtime/proc.go:271 +0x29d fp=0xc00014dfe0 sp=0xc00014df50 pc=0x559312d6dbdd Nov 08 07:06:40 ollama[11902]: runtime.goexit({}) Nov 08 07:06:40 ollama[11902]: runtime/asm_amd64.s:1695 +0x1 fp=0xc00014dfe8 sp=0xc00014dfe0 pc=0x559312d9fde1 Nov 08 07:06:40 ollama[11902]: goroutine 2 gp=0xc000006c40 m=nil [force gc (idle)]: Nov 08 07:06:40 ollama[11902]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) Nov 08 07:06:40 ollama[11902]: runtime/proc.go:402 +0xce fp=0xc000050fa8 sp=0xc000050f88 pc=0x559312d6e00e Nov 08 07:06:40 ollama[11902]: runtime.goparkunlock(...) Nov 08 07:06:40 ollama[11902]: runtime/proc.go:408 Nov 08 07:06:40 ollama[11902]: runtime.forcegchelper() Nov 08 07:06:40 ollama[11902]: runtime/proc.go:326 +0xb8 fp=0xc000050fe0 sp=0xc000050fa8 pc=0x559312d6de98 Nov 08 07:06:40 ollama[11902]: runtime.goexit({}) Nov 08 07:06:40 ollama[11902]: runtime/asm_amd64.s:1695 +0x1 fp=0xc000050fe8 sp=0xc000050fe0 pc=0x559312d9fde1 Nov 08 07:06:40 ollama[11902]: created by runtime.init.6 in goroutine 1 Nov 08 07:06:40 ollama[11902]: runtime/proc.go:314 +0x1a Nov 08 07:06:40 ollama[11902]: goroutine 3 gp=0xc000007180 m=nil [GC sweep wait]: Nov 08 07:06:40 ollama[11902]: runtime.gopark(0x1?, 0x0?, 0x0?, 0x0?, 0x0?) Nov 08 07:06:40 ollama[11902]: runtime/proc.go:402 +0xce fp=0xc000051780 sp=0xc000051760 pc=0x559312d6e00e Nov 08 07:06:40 ollama[11902]: runtime.goparkunlock(...) Nov 08 07:06:40 ollama[11902]: runtime/proc.go:408 Nov 08 07:06:40 ollama[11902]: runtime.bgsweep(0xc000022070) Nov 08 07:06:40 ollama[11902]: runtime/mgcsweep.go:318 +0xdf fp=0xc0000517c8 sp=0xc000051780 pc=0x559312d58b9f Nov 08 07:06:40 ollama[11902]: runtime.gcenable.gowrap1() Nov 08 07:06:40 ollama[11902]: runtime/mgc.go:203 +0x25 fp=0xc0000517e0 sp=0xc0000517c8 pc=0x559312d4d685 Nov 08 07:06:40 ollama[11902]: runtime.goexit({}) Nov 08 07:06:40 ollama[11902]: runtime/asm_amd64.s:1695 +0x1 fp=0xc0000517e8 sp=0xc0000517e0 pc=0x559312d9fde1 Nov 08 07:06:40 ollama[11902]: created by runtime.gcenable in goroutine 1 Nov 08 07:06:40 ollama[11902]: runtime/mgc.go:203 +0x66 Nov 08 07:06:40 ollama[11902]: goroutine 4 gp=0xc000007340 m=nil [GC scavenge wait]: Nov 08 07:06:40 ollama[11902]: runtime.gopark(0x10000?, 0x5593131eff98?, 0x0?, 0x0?, 0x0?) Nov 08 07:06:40 ollama[11902]: runtime/proc.go:402 +0xce fp=0xc000051f78 sp=0xc000051f58 pc=0x559312d6e00e Nov 08 07:06:40 ollama[11902]: runtime.goparkunlock(...) Nov 08 07:06:40 ollama[11902]: runtime/proc.go:408 Nov 08 07:06:40 ollama[11902]: runtime.(*scavengerState).park(0x5593134bc4c0) Nov 08 07:06:40 ollama[11902]: runtime/mgcscavenge.go:425 +0x49 fp=0xc000051fa8 sp=0xc000051f78 pc=0x559312d56549 Nov 08 07:06:40 ollama[11902]: runtime.bgscavenge(0xc000022070) Nov 08 07:06:40 ollama[11902]: runtime/mgcscavenge.go:658 +0x59 fp=0xc000051fc8 sp=0xc000051fa8 pc=0x559312d56af9 Nov 08 07:06:40 ollama[11902]: runtime.gcenable.gowrap2() Nov 08 07:06:40 ollama[11902]: runtime/mgc.go:204 +0x25 fp=0xc000051fe0 sp=0xc000051fc8 pc=0x559312d4d625 Nov 08 07:06:40 ollama[11902]: runtime.goexit({}) Nov 08 07:06:40 ollama[11902]: runtime/asm_amd64.s:1695 +0x1 fp=0xc000051fe8 sp=0xc000051fe0 pc=0x559312d9fde1 Nov 08 07:06:40 ollama[11902]: created by runtime.gcenable in goroutine 1 Nov 08 07:06:40 ollama[11902]: runtime/mgc.go:204 +0xa5 Nov 08 07:06:40 ollama[11902]: goroutine 5 gp=0xc000007c00 m=nil [finalizer wait]: Nov 08 07:06:40 ollama[11902]: runtime.gopark(0x0?, 0x5593132ea600?, 0x0?, 0xc0?, 0x1000000010?) Nov 08 07:06:40 ollama[11902]: runtime/proc.go:402 +0xce fp=0xc000050620 sp=0xc000050600 pc=0x559312d6e00e Nov 08 07:06:40 ollama[11902]: runtime.runfinq() Nov 08 07:06:40 ollama[11902]: runtime/mfinal.go:194 +0x107 fp=0xc0000507e0 sp=0xc000050620 pc=0x559312d4c6c7 Nov 08 07:06:40 ollama[11902]: runtime.goexit({}) Nov 08 07:06:40 ollama[11902]: runtime/asm_amd64.s:1695 +0x1 fp=0xc0000507e8 sp=0xc0000507e0 pc=0x559312d9fde1 Nov 08 07:06:40 ollama[11902]: created by runtime.createfing in goroutine 1 Nov 08 07:06:40 ollama[11902]: runtime/mfinal.go:164 +0x3d Nov 08 07:06:40 ollama[11902]: goroutine 49 gp=0xc000007dc0 m=nil [GC worker (idle)]: Nov 08 07:06:40 ollama[11902]: runtime.gopark(0x2736bc2b5abd3?, 0xc00002e9d0?, 0x0?, 0x0?, 0x5593135a5060?) Nov 08 07:06:40 ollama[11902]: runtime/proc.go:402 +0xce fp=0xc000052f50 sp=0xc000052f30 pc=0x559312d6e00e Nov 08 07:06:40 ollama[11902]: runtime.gcBgMarkWorker() Nov 08 07:06:40 ollama[11902]: runtime/mgc.go:1310 +0xe5 fp=0xc000052fe0 sp=0xc000052f50 pc=0x559312d4f585 Nov 08 07:06:40 ollama[11902]: runtime.goexit({}) Nov 08 07:06:40 ollama[11902]: runtime/asm_amd64.s:1695 +0x1 fp=0xc000052fe8 sp=0xc000052fe0 pc=0x559312d9fde1 Nov 08 07:06:40 ollama[11902]: created by runtime.gcBgMarkStartWorkers in goroutine 8 Nov 08 07:06:40 ollama[11902]: runtime/mgc.go:1234 +0x1c Nov 08 07:06:40 ollama[11902]: goroutine 8 gp=0xc0001641c0 m=nil [select]: Nov 08 07:06:40 ollama[11902]: runtime.gopark(0xc000029a80?, 0x2?, 0x60?, 0x0?, 0xc000029824?) Nov 08 07:06:40 ollama[11902]: runtime/proc.go:402 +0xce fp=0xc000029698 sp=0xc000029678 pc=0x559312d6e00e Nov 08 07:06:40 ollama[11902]: runtime.selectgo(0xc000029a80, 0xc000029820, 0x14?, 0x0, 0x1?, 0x1) Nov 08 07:06:40 ollama[11902]: runtime/select.go:327 +0x725 fp=0xc0000297b8 sp=0xc000029698 pc=0x559312d7f3e5 Nov 08 07:06:40 ollama[11902]: main.(*Server).completion(0xc000128120, {0x5593132ee5b0, 0xc0001507e0}, 0xc00012a900) Nov 08 07:06:40 ollama[11902]: github.com/ollama/ollama/llama/runner/runner.go:652 +0x8fe fp=0xc000029ab8 sp=0xc0000297b8 pc=0x559312fb167e Nov 08 07:06:40 ollama[11902]: main.(*Server).completion-fm({0x5593132ee5b0?, 0xc0001507e0?}, 0x559312f8cb8d?) Nov 08 07:06:40 ollama[11902]: <autogenerated>:1 +0x36 fp=0xc000029ae8 sp=0xc000029ab8 pc=0x559312fb46d6 Nov 08 07:06:40 ollama[11902]: net/http.HandlerFunc.ServeHTTP(0xc00010cc30?, {0x5593132ee5b0?, 0xc0001507e0?}, 0x10?) Nov 08 07:06:40 ollama[11902]: net/http/server.go:2171 +0x29 fp=0xc000029b10 sp=0xc000029ae8 pc=0x559312f85629 Nov 08 07:06:40 ollama[11902]: net/http.(*ServeMux).ServeHTTP(0x559312d40f85?, {0x5593132ee5b0, 0xc0001507e0}, 0xc00012a900) Nov 08 07:06:40 ollama[11902]: net/http/server.go:2688 +0x1ad fp=0xc000029b60 sp=0xc000029b10 pc=0x559312f874ad Nov 08 07:06:40 ollama[11902]: net/http.serverHandler.ServeHTTP({0x5593132ed900?}, {0x5593132ee5b0?, 0xc0001507e0?}, 0x6?) Nov 08 07:06:40 ollama[11902]: net/http/server.go:3142 +0x8e fp=0xc000029b90 sp=0xc000029b60 pc=0x559312f884ce Nov 08 07:06:40 ollama[11902]: net/http.(*conn).serve(0xc0001281b0, {0x5593132eea08, 0xc00010ae10}) Nov 08 07:06:40 ollama[11902]: net/http/server.go:2044 +0x5e8 fp=0xc000029fb8 sp=0xc000029b90 pc=0x559312f84268 Nov 08 07:06:40 ollama[11902]: net/http.(*Server).Serve.gowrap3() Nov 08 07:06:40 ollama[11902]: net/http/server.go:3290 +0x28 fp=0xc000029fe0 sp=0xc000029fb8 pc=0x559312f88c48 Nov 08 07:06:40 ollama[11902]: runtime.goexit({}) Nov 08 07:06:40 ollama[11902]: runtime/asm_amd64.s:1695 +0x1 fp=0xc000029fe8 sp=0xc000029fe0 pc=0x559312d9fde1 Nov 08 07:06:40 ollama[11902]: created by net/http.(*Server).Serve in goroutine 1 Nov 08 07:06:40 ollama[11902]: net/http/server.go:3290 +0x4b4 Nov 08 07:06:40 ollama[11902]: goroutine 33 gp=0xc000164380 m=nil [GC worker (idle)]: Nov 08 07:06:40 ollama[11902]: runtime.gopark(0x2736bc93ca49d?, 0x1?, 0x76?, 0x48?, 0x5593135a5060?) Nov 08 07:06:40 ollama[11902]: runtime/proc.go:402 +0xce fp=0xc000052750 sp=0xc000052730 pc=0x559312d6e00e Nov 08 07:06:40 ollama[11902]: runtime.gcBgMarkWorker() Nov 08 07:06:40 ollama[11902]: runtime/mgc.go:1310 +0xe5 fp=0xc0000527e0 sp=0xc000052750 pc=0x559312d4f585 Nov 08 07:06:40 ollama[11902]: runtime.goexit({}) Nov 08 07:06:40 ollama[11902]: runtime/asm_amd64.s:1695 +0x1 fp=0xc0000527e8 sp=0xc0000527e0 pc=0x559312d9fde1 Nov 08 07:06:40 ollama[11902]: created by runtime.gcBgMarkStartWorkers in goroutine 8 Nov 08 07:06:40 ollama[11902]: runtime/mgc.go:1234 +0x1c Nov 08 07:06:40 ollama[11902]: goroutine 66 gp=0xc00019a000 m=nil [IO wait]: Nov 08 07:06:40 ollama[11902]: runtime.gopark(0x10?, 0x10?, 0xf0?, 0xc5?, 0xb?) Nov 08 07:06:40 ollama[11902]: runtime/proc.go:402 +0xce fp=0xc00004c5a8 sp=0xc00004c588 pc=0x559312d6e00e Nov 08 07:06:40 ollama[11902]: runtime.netpollblock(0x559312dd4558?, 0x12d36b26?, 0x93?) Nov 08 07:06:40 ollama[11902]: runtime/netpoll.go:573 +0xf7 fp=0xc00004c5e0 sp=0xc00004c5a8 pc=0x559312d66257 Nov 08 07:06:40 ollama[11902]: internal/poll.runtime_pollWait(0x7f36dcfc9768, 0x72) Nov 08 07:06:40 ollama[11902]: runtime/netpoll.go:345 +0x85 fp=0xc00004c600 sp=0xc00004c5e0 pc=0x559312d9aaa5 Nov 08 07:06:40 ollama[11902]: internal/poll.(*pollDesc).wait(0xc000152180?, 0xc00010af41?, 0x0) Nov 08 07:06:40 ollama[11902]: internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc00004c628 sp=0xc00004c600 pc=0x559312dea9c7 Nov 08 07:06:40 ollama[11902]: internal/poll.(*pollDesc).waitRead(...) Nov 08 07:06:40 ollama[11902]: internal/poll/fd_poll_runtime.go:89 Nov 08 07:06:40 ollama[11902]: internal/poll.(*FD).Read(0xc000152180, {0xc00010af41, 0x1, 0x1}) Nov 08 07:06:40 ollama[11902]: internal/poll/fd_unix.go:164 +0x27a fp=0xc00004c6c0 sp=0xc00004c628 pc=0x559312deb51a Nov 08 07:06:40 ollama[11902]: net.(*netFD).Read(0xc000152180, {0xc00010af41?, 0xc00004c748?, 0x559312d9c6d0?}) Nov 08 07:06:40 ollama[11902]: net/fd_posix.go:55 +0x25 fp=0xc00004c708 sp=0xc00004c6c0 pc=0x559312e597a5 Nov 08 07:06:40 ollama[11902]: net.(*conn).Read(0xc0000540a8, {0xc00010af41?, 0x0?, 0x5593135a5060?}) Nov 08 07:06:40 ollama[11902]: net/net.go:185 +0x45 fp=0xc00004c750 sp=0xc00004c708 pc=0x559312e63a65 Nov 08 07:06:40 ollama[11902]: net.(*TCPConn).Read(0x55931347d840?, {0xc00010af41?, 0x0?, 0x0?}) Nov 08 07:06:40 ollama[11902]: <autogenerated>:1 +0x25 fp=0xc00004c780 sp=0xc00004c750 pc=0x559312e6f445 Nov 08 07:06:40 ollama[11902]: net/http.(*connReader).backgroundRead(0xc00010af30) Nov 08 07:06:40 ollama[11902]: net/http/server.go:681 +0x37 fp=0xc00004c7c8 sp=0xc00004c780 pc=0x559312f7e1d7 Nov 08 07:06:40 ollama[11902]: net/http.(*connReader).startBackgroundRead.gowrap2() Nov 08 07:06:40 ollama[11902]: net/http/server.go:677 +0x25 fp=0xc00004c7e0 sp=0xc00004c7c8 pc=0x559312f7e105 Nov 08 07:06:40 ollama[11902]: runtime.goexit({}) Nov 08 07:06:40 ollama[11902]: runtime/asm_amd64.s:1695 +0x1 fp=0xc00004c7e8 sp=0xc00004c7e0 pc=0x559312d9fde1 Nov 08 07:06:40 ollama[11902]: created by net/http.(*connReader).startBackgroundRead in goroutine 8 Nov 08 07:06:40 ollama[11902]: net/http/server.go:677 +0xba Nov 08 07:06:40 ollama[11902]: goroutine 32 gp=0xc00008a380 m=nil [GC worker (idle)]: Nov 08 07:06:40 ollama[11902]: runtime.gopark(0x2736bc93d3ed0?, 0xc00002e9d0?, 0x0?, 0x0?, 0x5593135a5060?) Nov 08 07:06:40 ollama[11902]: runtime/proc.go:402 +0xce fp=0xc0000b2750 sp=0xc0000b2730 pc=0x559312d6e00e Nov 08 07:06:40 ollama[11902]: runtime.gcBgMarkWorker() Nov 08 07:06:40 ollama[11902]: runtime/mgc.go:1310 +0xe5 fp=0xc0000b27e0 sp=0xc0000b2750 pc=0x559312d4f585 Nov 08 07:06:40 ollama[11902]: runtime.goexit({}) Nov 08 07:06:40 ollama[11902]: runtime/asm_amd64.s:1695 +0x1 fp=0xc0000b27e8 sp=0xc0000b27e0 pc=0x559312d9fde1 Nov 08 07:06:40 ollama[11902]: created by runtime.gcBgMarkStartWorkers in goroutine 8 Nov 08 07:06:40 ollama[11902]: runtime/mgc.go:1234 +0x1c Nov 08 07:06:40 ollama[11902]: goroutine 48 gp=0xc00008a540 m=nil [GC worker (idle)]: Nov 08 07:06:40 ollama[11902]: runtime.gopark(0x2736bc93d3fdc?, 0x3?, 0x98?, 0x4d?, 0x5593135a5060?) Nov 08 07:06:40 ollama[11902]: runtime/proc.go:402 +0xce fp=0xc0000b2f50 sp=0xc0000b2f30 pc=0x559312d6e00e Nov 08 07:06:40 ollama[11902]: runtime.gcBgMarkWorker() Nov 08 07:06:40 ollama[11902]: runtime/mgc.go:1310 +0xe5 fp=0xc0000b2fe0 sp=0xc0000b2f50 pc=0x559312d4f585 Nov 08 07:06:40 ollama[11902]: runtime.goexit({}) Nov 08 07:06:40 ollama[11902]: runtime/asm_amd64.s:1695 +0x1 fp=0xc0000b2fe8 sp=0xc0000b2fe0 pc=0x559312d9fde1 Nov 08 07:06:40 ollama[11902]: created by runtime.gcBgMarkStartWorkers in goroutine 8 Nov 08 07:06:40 ollama[11902]: runtime/mgc.go:1234 +0x1c Nov 08 07:06:40 ollama[11902]: goroutine 50 gp=0xc00008a700 m=nil [GC worker (idle)]: Nov 08 07:06:40 ollama[11902]: runtime.gopark(0x2736bc93d3def?, 0xc00002e9d0?, 0x0?, 0x0?, 0x5593135a5060?) Nov 08 07:06:40 ollama[11902]: runtime/proc.go:402 +0xce fp=0xc0000b3750 sp=0xc0000b3730 pc=0x559312d6e00e Nov 08 07:06:40 ollama[11902]: runtime.gcBgMarkWorker() Nov 08 07:06:40 ollama[11902]: runtime/mgc.go:1310 +0xe5 fp=0xc0000b37e0 sp=0xc0000b3750 pc=0x559312d4f585 Nov 08 07:06:40 ollama[11902]: runtime.goexit({}) Nov 08 07:06:40 ollama[11902]: runtime/asm_amd64.s:1695 +0x1 fp=0xc0000b37e8 sp=0xc0000b37e0 pc=0x559312d9fde1 Nov 08 07:06:40 ollama[11902]: created by runtime.gcBgMarkStartWorkers in goroutine 8 Nov 08 07:06:40 ollama[11902]: runtime/mgc.go:1234 +0x1c Nov 08 07:06:40 ollama[11902]: goroutine 12 gp=0xc000164540 m=nil [GC worker (idle)]: Nov 08 07:06:40 ollama[11902]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) Nov 08 07:06:40 ollama[11902]: runtime/proc.go:402 +0xce fp=0xc000053750 sp=0xc000053730 pc=0x559312d6e00e Nov 08 07:06:40 ollama[11902]: runtime.gcBgMarkWorker() Nov 08 07:06:40 ollama[11902]: runtime/mgc.go:1310 +0xe5 fp=0xc0000537e0 sp=0xc000053750 pc=0x559312d4f585 Nov 08 07:06:40 ollama[11902]: runtime.goexit({}) Nov 08 07:06:40 ollama[11902]: runtime/asm_amd64.s:1695 +0x1 fp=0xc0000537e8 sp=0xc0000537e0 pc=0x559312d9fde1 Nov 08 07:06:40 ollama[11902]: created by runtime.gcBgMarkStartWorkers in goroutine 8 Nov 08 07:06:40 ollama[11902]: runtime/mgc.go:1234 +0x1c Nov 08 07:06:40 ollama[11902]: goroutine 13 gp=0xc000164700 m=nil [GC worker (idle)]: Nov 08 07:06:40 ollama[11902]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) Nov 08 07:06:40 ollama[11902]: runtime/proc.go:402 +0xce fp=0xc000053f50 sp=0xc000053f30 pc=0x559312d6e00e Nov 08 07:06:40 ollama[11902]: runtime.gcBgMarkWorker() Nov 08 07:06:40 ollama[11902]: runtime/mgc.go:1310 +0xe5 fp=0xc000053fe0 sp=0xc000053f50 pc=0x559312d4f585 Nov 08 07:06:40 ollama[11902]: runtime.goexit({}) Nov 08 07:06:40 ollama[11902]: runtime/asm_amd64.s:1695 +0x1 fp=0xc000053fe8 sp=0xc000053fe0 pc=0x559312d9fde1 Nov 08 07:06:40 ollama[11902]: created by runtime.gcBgMarkStartWorkers in goroutine 8 Nov 08 07:06:40 ollama[11902]: runtime/mgc.go:1234 +0x1c Nov 08 07:06:40 ollama[11902]: goroutine 14 gp=0xc0001648c0 m=nil [GC worker (idle)]: Nov 08 07:06:40 ollama[11902]: runtime.gopark(0x2736bc93ca34d?, 0x0?, 0x0?, 0x0?, 0x0?) Nov 08 07:06:40 ollama[11902]: runtime/proc.go:402 +0xce fp=0xc0000ae750 sp=0xc0000ae730 pc=0x559312d6e00e Nov 08 07:06:40 ollama[11902]: runtime.gcBgMarkWorker() Nov 08 07:06:40 ollama[11902]: runtime/mgc.go:1310 +0xe5 fp=0xc0000ae7e0 sp=0xc0000ae750 pc=0x559312d4f585 Nov 08 07:06:40 ollama[11902]: runtime.goexit({}) Nov 08 07:06:40 ollama[11902]: runtime/asm_amd64.s:1695 +0x1 fp=0xc0000ae7e8 sp=0xc0000ae7e0 pc=0x559312d9fde1 Nov 08 07:06:40 ollama[11902]: created by runtime.gcBgMarkStartWorkers in goroutine 8 Nov 08 07:06:40 ollama[11902]: runtime/mgc.go:1234 +0x1c Nov 08 07:06:40 ollama[11902]: rax 0x209e03fd4 Nov 08 07:06:40 ollama[11902]: rbx 0x7f364255c000 Nov 08 07:06:40 ollama[11902]: rcx 0xff5 Nov 08 07:06:40 ollama[11902]: rdx 0x7f3642118290 Nov 08 07:06:40 ollama[11902]: rdi 0x7f36421182a0 Nov 08 07:06:40 ollama[11902]: rsi 0x0 Nov 08 07:06:40 ollama[11902]: rbp 0x7f361ffd5240 Nov 08 07:06:40 ollama[11902]: rsp 0x7f361ffd5220 Nov 08 07:06:40 ollama[11902]: r8 0x1 Nov 08 07:06:40 ollama[11902]: r9 0x7f36423d2790 Nov 08 07:06:40 ollama[11902]: r10 0x0 Nov 08 07:06:40 ollama[11902]: r11 0x246 Nov 08 07:06:40 ollama[11902]: r12 0x7f34d7569420 Nov 08 07:06:40 ollama[11902]: r13 0x7f36421182a0 Nov 08 07:06:40 ollama[11902]: r14 0x0 Nov 08 07:06:40 ollama[11902]: r15 0x7f372f6497f0 Nov 08 07:06:40 ollama[11902]: rip 0x7f36e43b4c47 Nov 08 07:06:40 ollama[11902]: rflags 0x10297 Nov 08 07:06:40 ollama[11902]: cs 0x33 Nov 08 07:06:40 ollama[11902]: fs 0x0 Nov 08 07:06:40 ollama[11902]: gs 0x0 Nov 08 07:06:40 ollama[11902]: SIGABRT: abort Nov 08 07:06:40 ollama[11902]: PC=0x7f36bec419fc m=9 sigcode=18446744073709551610 Nov 08 07:06:40 ollama[11902]: signal arrived during cgo execution Nov 08 07:06:40 ollama[11902]: goroutine 7 gp=0xc000164000 m=9 mp=0xc0001a2808 [syscall]: Nov 08 07:06:40 ollama[11902]: runtime.cgocall(0x559312fb4eb0, 0xc000065b60) Nov 08 07:06:40 ollama[11902]: runtime/cgocall.go:157 +0x4b fp=0xc000065b38 sp=0xc000065b00 pc=0x559312d373cb Nov 08 07:06:40 ollama[11902]: github.com/ollama/ollama/llama._Cfunc_llama_decode(0x7f365005b650, {0xe, 0x7f36503ad760, 0x0, 0x0, 0x7f36503adf70, 0x7f365019ef40, 0x7f365019f750, 0x7f3642c4d360, 0x0, ...}) Nov 08 07:06:40 ollama[11902]: _cgo_gotypes.go:543 +0x52 fp=0xc000065b60 sp=0xc000065b38 pc=0x559312e34952 Nov 08 07:06:40 ollama[11902]: github.com/ollama/ollama/llama.(*Context).Decode.func1(0x559312fb0ceb?, 0x7f365005b650?) Nov 08 07:06:40 ollama[11902]: github.com/ollama/ollama/llama/llama.go:167 +0xd8 fp=0xc000065c80 sp=0xc000065b60 pc=0x559312e36e78 Nov 08 07:06:40 ollama[11902]: github.com/ollama/ollama/llama.(*Context).Decode(0xc0000163c0?, 0x1?) Nov 08 07:06:40 ollama[11902]: github.com/ollama/ollama/llama/llama.go:167 +0x17 fp=0xc000065cc8 sp=0xc000065c80 pc=0x559312e36cd7 Nov 08 07:06:40 ollama[11902]: main.(*Server).processBatch(0xc000128120, 0xc0000c0000, 0xc0000c0070) Nov 08 07:06:40 ollama[11902]: github.com/ollama/ollama/llama/runner/runner.go:424 +0x29e fp=0xc000065ed0 sp=0xc000065cc8 pc=0x559312fafd1e Nov 08 07:06:40 ollama[11902]: main.(*Server).run(0xc000128120, {0x5593132eea40, 0xc00007c0a0}) Nov 08 07:06:40 ollama[11902]: github.com/ollama/ollama/llama/runner/runner.go:338 +0x1a5 fp=0xc000065fb8 sp=0xc000065ed0 pc=0x559312faf705 Nov 08 07:06:40 ollama[11902]: main.main.gowrap2() Nov 08 07:06:40 ollama[11902]: github.com/ollama/ollama/llama/runner/runner.go:907 +0x28 fp=0xc000065fe0 sp=0xc000065fb8 pc=0x559312fb3ee8 Nov 08 07:06:40 ollama[11902]: runtime.goexit({}) Nov 08 07:06:40 ollama[11902]: runtime/asm_amd64.s:1695 +0x1 fp=0xc000065fe8 sp=0xc000065fe0 pc=0x559312d9fde1 Nov 08 07:06:40 ollama[11902]: created by main.main in goroutine 1 Nov 08 07:06:40 ollama[11902]: github.com/ollama/ollama/llama/runner/runner.go:907 +0xcab Nov 08 07:06:40 ollama[11902]: goroutine 1 gp=0xc0000061c0 m=nil [IO wait]: Nov 08 07:06:40 ollama[11902]: runtime.gopark(0xc000030008?, 0x0?, 0xc0?, 0x61?, 0xc0000298c0?) Nov 08 07:06:40 ollama[11902]: runtime/proc.go:402 +0xce fp=0xc00014d888 sp=0xc00014d868 pc=0x559312d6e00e Nov 08 07:06:40 ollama[11902]: runtime.netpollblock(0xc000029920?, 0x12d36b26?, 0x93?) Nov 08 07:06:40 ollama[11902]: runtime/netpoll.go:573 +0xf7 fp=0xc00014d8c0 sp=0xc00014d888 pc=0x559312d66257 Nov 08 07:06:40 ollama[11902]: internal/poll.runtime_pollWait(0x7f36dcfc9860, 0x72) Nov 08 07:06:40 ollama[11902]: runtime/netpoll.go:345 +0x85 fp=0xc00014d8e0 sp=0xc00014d8c0 pc=0x559312d9aaa5 Nov 08 07:06:40 ollama[11902]: internal/poll.(*pollDesc).wait(0x3?, 0x3fe?, 0x0) Nov 08 07:06:40 ollama[11902]: internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc00014d908 sp=0xc00014d8e0 pc=0x559312dea9c7 Nov 08 07:06:40 ollama[11902]: internal/poll.(*pollDesc).waitRead(...) Nov 08 07:06:40 ollama[11902]: internal/poll/fd_poll_runtime.go:89 Nov 08 07:06:40 ollama[11902]: internal/poll.(*FD).Accept(0xc000152100) Nov 08 07:06:40 ollama[11902]: internal/poll/fd_unix.go:611 +0x2ac fp=0xc00014d9b0 sp=0xc00014d908 pc=0x559312debe8c Nov 08 07:06:40 ollama[11902]: net.(*netFD).accept(0xc000152100) Nov 08 07:06:40 ollama[11902]: net/fd_unix.go:172 +0x29 fp=0xc00014da68 sp=0xc00014d9b0 pc=0x559312e5a8a9 Nov 08 07:06:40 ollama[11902]: net.(*TCPListener).accept(0xc000070200) Nov 08 07:06:40 ollama[11902]: net/tcpsock_posix.go:159 +0x1e fp=0xc00014da90 sp=0xc00014da68 pc=0x559312e6b5de Nov 08 07:06:40 ollama[11902]: net.(*TCPListener).Accept(0xc000070200) Nov 08 07:06:40 ollama[11902]: net/tcpsock.go:327 +0x30 fp=0xc00014dac0 sp=0xc00014da90 pc=0x559312e6a930 Nov 08 07:06:40 ollama[11902]: net/http.(*onceCloseListener).Accept(0xc0001281b0?) Nov 08 07:06:40 ollama[11902]: <autogenerated>:1 +0x24 fp=0xc00014dad8 sp=0xc00014dac0 pc=0x559312f91a44 Nov 08 07:06:40 ollama[11902]: net/http.(*Server).Serve(0xc0001620f0, {0x5593132ee400, 0xc000070200}) Nov 08 07:06:40 ollama[11902]: net/http/server.go:3260 +0x33e fp=0xc00014dc08 sp=0xc00014dad8 pc=0x559312f8885e Nov 08 07:06:40 ollama[11902]: main.main() Nov 08 07:06:40 ollama[11902]: github.com/ollama/ollama/llama/runner/runner.go:927 +0x104c fp=0xc00014df50 sp=0xc00014dc08 pc=0x559312fb3c6c Nov 08 07:06:40 ollama[11902]: runtime.main() Nov 08 07:06:40 ollama[11902]: runtime/proc.go:271 +0x29d fp=0xc00014dfe0 sp=0xc00014df50 pc=0x559312d6dbdd Nov 08 07:06:40 ollama[11902]: runtime.goexit({}) Nov 08 07:06:40 ollama[11902]: runtime/asm_amd64.s:1695 +0x1 fp=0xc00014dfe8 sp=0xc00014dfe0 pc=0x559312d9fde1 Nov 08 07:06:40 ollama[11902]: goroutine 2 gp=0xc000006c40 m=nil [force gc (idle)]: Nov 08 07:06:40 ollama[11902]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) Nov 08 07:06:40 ollama[11902]: runtime/proc.go:402 +0xce fp=0xc000050fa8 sp=0xc000050f88 pc=0x559312d6e00e Nov 08 07:06:40 ollama[11902]: runtime.goparkunlock(...) Nov 08 07:06:40 ollama[11902]: runtime/proc.go:408 Nov 08 07:06:40 ollama[11902]: runtime.forcegchelper() Nov 08 07:06:40 ollama[11902]: runtime/proc.go:326 +0xb8 fp=0xc000050fe0 sp=0xc000050fa8 pc=0x559312d6de98 Nov 08 07:06:40 ollama[11902]: runtime.goexit({}) Nov 08 07:06:40 ollama[11902]: runtime/asm_amd64.s:1695 +0x1 fp=0xc000050fe8 sp=0xc000050fe0 pc=0x559312d9fde1 Nov 08 07:06:40 ollama[11902]: created by runtime.init.6 in goroutine 1 Nov 08 07:06:40 ollama[11902]: runtime/proc.go:314 +0x1a Nov 08 07:06:40 ollama[11902]: goroutine 3 gp=0xc000007180 m=nil [GC sweep wait]: Nov 08 07:06:40 ollama[11902]: runtime.gopark(0x1?, 0x0?, 0x0?, 0x0?, 0x0?) Nov 08 07:06:40 ollama[11902]: runtime/proc.go:402 +0xce fp=0xc000051780 sp=0xc000051760 pc=0x559312d6e00e Nov 08 07:06:40 ollama[11902]: runtime.goparkunlock(...) Nov 08 07:06:40 ollama[11902]: runtime/proc.go:408 Nov 08 07:06:40 ollama[11902]: runtime.bgsweep(0xc000022070) Nov 08 07:06:40 ollama[11902]: runtime/mgcsweep.go:318 +0xdf fp=0xc0000517c8 sp=0xc000051780 pc=0x559312d58b9f Nov 08 07:06:40 ollama[11902]: runtime.gcenable.gowrap1() Nov 08 07:06:40 ollama[11902]: runtime/mgc.go:203 +0x25 fp=0xc0000517e0 sp=0xc0000517c8 pc=0x559312d4d685 Nov 08 07:06:40 ollama[11902]: runtime.goexit({}) Nov 08 07:06:40 ollama[11902]: runtime/asm_amd64.s:1695 +0x1 fp=0xc0000517e8 sp=0xc0000517e0 pc=0x559312d9fde1 Nov 08 07:06:40 ollama[11902]: created by runtime.gcenable in goroutine 1 Nov 08 07:06:40 ollama[11902]: runtime/mgc.go:203 +0x66 Nov 08 07:06:40 ollama[11902]: goroutine 4 gp=0xc000007340 m=nil [GC scavenge wait]: Nov 08 07:06:40 ollama[11902]: runtime.gopark(0x10000?, 0x5593131eff98?, 0x0?, 0x0?, 0x0?) Nov 08 07:06:40 ollama[11902]: runtime/proc.go:402 +0xce fp=0xc000051f78 sp=0xc000051f58 pc=0x559312d6e00e Nov 08 07:06:40 ollama[11902]: runtime.goparkunlock(...) Nov 08 07:06:40 ollama[11902]: runtime/proc.go:408 Nov 08 07:06:40 ollama[11902]: runtime.(*scavengerState).park(0x5593134bc4c0) Nov 08 07:06:40 ollama[11902]: runtime/mgcscavenge.go:425 +0x49 fp=0xc000051fa8 sp=0xc000051f78 pc=0x559312d56549 Nov 08 07:06:40 ollama[11902]: runtime.bgscavenge(0xc000022070) Nov 08 07:06:40 ollama[11902]: runtime/mgcscavenge.go:658 +0x59 fp=0xc000051fc8 sp=0xc000051fa8 pc=0x559312d56af9 Nov 08 07:06:40 ollama[11902]: runtime.gcenable.gowrap2() Nov 08 07:06:40 ollama[11902]: runtime/mgc.go:204 +0x25 fp=0xc000051fe0 sp=0xc000051fc8 pc=0x559312d4d625 Nov 08 07:06:40 ollama[11902]: runtime.goexit({}) Nov 08 07:06:40 ollama[11902]: runtime/asm_amd64.s:1695 +0x1 fp=0xc000051fe8 sp=0xc000051fe0 pc=0x559312d9fde1 Nov 08 07:06:40 ollama[11902]: created by runtime.gcenable in goroutine 1 Nov 08 07:06:40 ollama[11902]: runtime/mgc.go:204 +0xa5 Nov 08 07:06:40 ollama[11902]: goroutine 5 gp=0xc000007c00 m=nil [finalizer wait]: Nov 08 07:06:40 ollama[11902]: runtime.gopark(0x0?, 0x5593132ea600?, 0x0?, 0xc0?, 0x1000000010?) Nov 08 07:06:40 ollama[11902]: runtime/proc.go:402 +0xce fp=0xc000050620 sp=0xc000050600 pc=0x559312d6e00e Nov 08 07:06:40 ollama[11902]: runtime.runfinq() Nov 08 07:06:40 ollama[11902]: runtime/mfinal.go:194 +0x107 fp=0xc0000507e0 sp=0xc000050620 pc=0x559312d4c6c7 Nov 08 07:06:40 ollama[11902]: runtime.goexit({}) Nov 08 07:06:40 ollama[11902]: runtime/asm_amd64.s:1695 +0x1 fp=0xc0000507e8 sp=0xc0000507e0 pc=0x559312d9fde1 Nov 08 07:06:40 ollama[11902]: created by runtime.createfing in goroutine 1 Nov 08 07:06:40 ollama[11902]: runtime/mfinal.go:164 +0x3d Nov 08 07:06:40 ollama[11902]: goroutine 49 gp=0xc000007dc0 m=nil [GC worker (idle)]: Nov 08 07:06:40 ollama[11902]: runtime.gopark(0x2736bc2b5abd3?, 0xc00002e9d0?, 0x0?, 0x0?, 0x5593135a5060?) Nov 08 07:06:40 ollama[11902]: runtime/proc.go:402 +0xce fp=0xc000052f50 sp=0xc000052f30 pc=0x559312d6e00e Nov 08 07:06:40 ollama[11902]: runtime.gcBgMarkWorker() Nov 08 07:06:40 ollama[11902]: runtime/mgc.go:1310 +0xe5 fp=0xc000052fe0 sp=0xc000052f50 pc=0x559312d4f585 Nov 08 07:06:40 ollama[11902]: runtime.goexit({}) Nov 08 07:06:40 ollama[11902]: runtime/asm_amd64.s:1695 +0x1 fp=0xc000052fe8 sp=0xc000052fe0 pc=0x559312d9fde1 Nov 08 07:06:40 ollama[11902]: created by runtime.gcBgMarkStartWorkers in goroutine 8 Nov 08 07:06:40 ollama[11902]: runtime/mgc.go:1234 +0x1c Nov 08 07:06:40 ollama[11902]: goroutine 8 gp=0xc0001641c0 m=nil [select]: Nov 08 07:06:40 ollama[11902]: runtime.gopark(0xc000029a80?, 0x2?, 0x60?, 0x0?, 0xc000029824?) Nov 08 07:06:40 ollama[11902]: runtime/proc.go:402 +0xce fp=0xc000029698 sp=0xc000029678 pc=0x559312d6e00e Nov 08 07:06:40 ollama[11902]: runtime.selectgo(0xc000029a80, 0xc000029820, 0x14?, 0x0, 0x1?, 0x1) Nov 08 07:06:40 ollama[11902]: runtime/select.go:327 +0x725 fp=0xc0000297b8 sp=0xc000029698 pc=0x559312d7f3e5 Nov 08 07:06:40 ollama[11902]: main.(*Server).completion(0xc000128120, {0x5593132ee5b0, 0xc0001507e0}, 0xc00012a900) Nov 08 07:06:40 ollama[11902]: github.com/ollama/ollama/llama/runner/runner.go:652 +0x8fe fp=0xc000029ab8 sp=0xc0000297b8 pc=0x559312fb167e Nov 08 07:06:40 ollama[11902]: main.(*Server).completion-fm({0x5593132ee5b0?, 0xc0001507e0?}, 0x559312f8cb8d?) Nov 08 07:06:40 ollama[11902]: <autogenerated>:1 +0x36 fp=0xc000029ae8 sp=0xc000029ab8 pc=0x559312fb46d6 Nov 08 07:06:40 ollama[11902]: net/http.HandlerFunc.ServeHTTP(0xc00010cc30?, {0x5593132ee5b0?, 0xc0001507e0?}, 0x10?) Nov 08 07:06:40 ollama[11902]: net/http/server.go:2171 +0x29 fp=0xc000029b10 sp=0xc000029ae8 pc=0x559312f85629 Nov 08 07:06:40 ollama[11902]: net/http.(*ServeMux).ServeHTTP(0x559312d40f85?, {0x5593132ee5b0, 0xc0001507e0}, 0xc00012a900) Nov 08 07:06:40 ollama[11902]: net/http/server.go:2688 +0x1ad fp=0xc000029b60 sp=0xc000029b10 pc=0x559312f874ad Nov 08 07:06:40 ollama[11902]: net/http.serverHandler.ServeHTTP({0x5593132ed900?}, {0x5593132ee5b0?, 0xc0001507e0?}, 0x6?) Nov 08 07:06:40 ollama[11902]: net/http/server.go:3142 +0x8e fp=0xc000029b90 sp=0xc000029b60 pc=0x559312f884ce Nov 08 07:06:40 ollama[11902]: net/http.(*conn).serve(0xc0001281b0, {0x5593132eea08, 0xc00010ae10}) Nov 08 07:06:40 ollama[11902]: net/http/server.go:2044 +0x5e8 fp=0xc000029fb8 sp=0xc000029b90 pc=0x559312f84268 Nov 08 07:06:40 ollama[11902]: net/http.(*Server).Serve.gowrap3() Nov 08 07:06:40 ollama[11902]: net/http/server.go:3290 +0x28 fp=0xc000029fe0 sp=0xc000029fb8 pc=0x559312f88c48 Nov 08 07:06:40 ollama[11902]: runtime.goexit({}) Nov 08 07:06:40 ollama[11902]: runtime/asm_amd64.s:1695 +0x1 fp=0xc000029fe8 sp=0xc000029fe0 pc=0x559312d9fde1 Nov 08 07:06:40 ollama[11902]: created by net/http.(*Server).Serve in goroutine 1 Nov 08 07:06:40 ollama[11902]: net/http/server.go:3290 +0x4b4 Nov 08 07:06:40 ollama[11902]: goroutine 33 gp=0xc000164380 m=nil [GC worker (idle)]: Nov 08 07:06:40 ollama[11902]: runtime.gopark(0x2736bc93ca49d?, 0x1?, 0x76?, 0x48?, 0x5593135a5060?) Nov 08 07:06:40 ollama[11902]: runtime/proc.go:402 +0xce fp=0xc000052750 sp=0xc000052730 pc=0x559312d6e00e Nov 08 07:06:40 ollama[11902]: runtime.gcBgMarkWorker() Nov 08 07:06:40 ollama[11902]: runtime/mgc.go:1310 +0xe5 fp=0xc0000527e0 sp=0xc000052750 pc=0x559312d4f585 Nov 08 07:06:40 ollama[11902]: runtime.goexit({}) Nov 08 07:06:40 ollama[11902]: runtime/asm_amd64.s:1695 +0x1 fp=0xc0000527e8 sp=0xc0000527e0 pc=0x559312d9fde1 Nov 08 07:06:40 ollama[11902]: created by runtime.gcBgMarkStartWorkers in goroutine 8 Nov 08 07:06:40 ollama[11902]: runtime/mgc.go:1234 +0x1c Nov 08 07:06:40 ollama[11902]: goroutine 66 gp=0xc00019a000 m=nil [IO wait]: Nov 08 07:06:40 ollama[11902]: runtime.gopark(0x10?, 0x10?, 0xf0?, 0xc5?, 0xb?) Nov 08 07:06:40 ollama[11902]: runtime/proc.go:402 +0xce fp=0xc00004c5a8 sp=0xc00004c588 pc=0x559312d6e00e Nov 08 07:06:40 ollama[11902]: runtime.netpollblock(0x559312dd4558?, 0x12d36b26?, 0x93?) Nov 08 07:06:40 ollama[11902]: runtime/netpoll.go:573 +0xf7 fp=0xc00004c5e0 sp=0xc00004c5a8 pc=0x559312d66257 Nov 08 07:06:40 ollama[11902]: internal/poll.runtime_pollWait(0x7f36dcfc9768, 0x72) Nov 08 07:06:40 ollama[11902]: runtime/netpoll.go:345 +0x85 fp=0xc00004c600 sp=0xc00004c5e0 pc=0x559312d9aaa5 Nov 08 07:06:40 ollama[11902]: internal/poll.(*pollDesc).wait(0xc000152180?, 0xc00010af41?, 0x0) Nov 08 07:06:40 ollama[11902]: internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc00004c628 sp=0xc00004c600 pc=0x559312dea9c7 Nov 08 07:06:40 ollama[11902]: internal/poll.(*pollDesc).waitRead(...) Nov 08 07:06:40 ollama[11902]: internal/poll/fd_poll_runtime.go:89 Nov 08 07:06:40 ollama[11902]: internal/poll.(*FD).Read(0xc000152180, {0xc00010af41, 0x1, 0x1}) Nov 08 07:06:40 ollama[11902]: internal/poll/fd_unix.go:164 +0x27a fp=0xc00004c6c0 sp=0xc00004c628 pc=0x559312deb51a Nov 08 07:06:40 ollama[11902]: net.(*netFD).Read(0xc000152180, {0xc00010af41?, 0xc00004c748?, 0x559312d9c6d0?}) Nov 08 07:06:40 ollama[11902]: net/fd_posix.go:55 +0x25 fp=0xc00004c708 sp=0xc00004c6c0 pc=0x559312e597a5 Nov 08 07:06:40 ollama[11902]: net.(*conn).Read(0xc0000540a8, {0xc00010af41?, 0x0?, 0x5593135a5060?}) Nov 08 07:06:40 ollama[11902]: net/net.go:185 +0x45 fp=0xc00004c750 sp=0xc00004c708 pc=0x559312e63a65 Nov 08 07:06:40 ollama[11902]: net.(*TCPConn).Read(0x55931347d840?, {0xc00010af41?, 0x0?, 0x0?}) Nov 08 07:06:40 ollama[11902]: <autogenerated>:1 +0x25 fp=0xc00004c780 sp=0xc00004c750 pc=0x559312e6f445 Nov 08 07:06:40 ollama[11902]: net/http.(*connReader).backgroundRead(0xc00010af30) Nov 08 07:06:40 ollama[11902]: net/http/server.go:681 +0x37 fp=0xc00004c7c8 sp=0xc00004c780 pc=0x559312f7e1d7 Nov 08 07:06:40 ollama[11902]: net/http.(*connReader).startBackgroundRead.gowrap2() Nov 08 07:06:40 ollama[11902]: net/http/server.go:677 +0x25 fp=0xc00004c7e0 sp=0xc00004c7c8 pc=0x559312f7e105 Nov 08 07:06:40 ollama[11902]: runtime.goexit({}) Nov 08 07:06:40 ollama[11902]: runtime/asm_amd64.s:1695 +0x1 fp=0xc00004c7e8 sp=0xc00004c7e0 pc=0x559312d9fde1 Nov 08 07:06:40 ollama[11902]: created by net/http.(*connReader).startBackgroundRead in goroutine 8 Nov 08 07:06:40 ollama[11902]: net/http/server.go:677 +0xba Nov 08 07:06:40 ollama[11902]: goroutine 32 gp=0xc00008a380 m=nil [GC worker (idle)]: Nov 08 07:06:40 ollama[11902]: runtime.gopark(0x2736bc93d3ed0?, 0xc00002e9d0?, 0x0?, 0x0?, 0x5593135a5060?) Nov 08 07:06:40 ollama[11902]: runtime/proc.go:402 +0xce fp=0xc0000b2750 sp=0xc0000b2730 pc=0x559312d6e00e Nov 08 07:06:40 ollama[11902]: runtime.gcBgMarkWorker() Nov 08 07:06:40 ollama[11902]: runtime/mgc.go:1310 +0xe5 fp=0xc0000b27e0 sp=0xc0000b2750 pc=0x559312d4f585 Nov 08 07:06:40 ollama[11902]: runtime.goexit({}) Nov 08 07:06:40 ollama[11902]: runtime/asm_amd64.s:1695 +0x1 fp=0xc0000b27e8 sp=0xc0000b27e0 pc=0x559312d9fde1 Nov 08 07:06:40 ollama[11902]: created by runtime.gcBgMarkStartWorkers in goroutine 8 Nov 08 07:06:40 ollama[11902]: runtime/mgc.go:1234 +0x1c Nov 08 07:06:40 ollama[11902]: goroutine 48 gp=0xc00008a540 m=nil [GC worker (idle)]: Nov 08 07:06:40 ollama[11902]: runtime.gopark(0x2736bc93d3fdc?, 0x3?, 0x98?, 0x4d?, 0x5593135a5060?) Nov 08 07:06:40 ollama[11902]: runtime/proc.go:402 +0xce fp=0xc0000b2f50 sp=0xc0000b2f30 pc=0x559312d6e00e Nov 08 07:06:40 ollama[11902]: runtime.gcBgMarkWorker() Nov 08 07:06:40 ollama[11902]: runtime/mgc.go:1310 +0xe5 fp=0xc0000b2fe0 sp=0xc0000b2f50 pc=0x559312d4f585 Nov 08 07:06:40 ollama[11902]: runtime.goexit({}) Nov 08 07:06:40 ollama[11902]: runtime/asm_amd64.s:1695 +0x1 fp=0xc0000b2fe8 sp=0xc0000b2fe0 pc=0x559312d9fde1 Nov 08 07:06:40 ollama[11902]: created by runtime.gcBgMarkStartWorkers in goroutine 8 Nov 08 07:06:40 ollama[11902]: runtime/mgc.go:1234 +0x1c Nov 08 07:06:40 ollama[11902]: goroutine 50 gp=0xc00008a700 m=nil [GC worker (idle)]: Nov 08 07:06:40 ollama[11902]: runtime.gopark(0x2736bc93d3def?, 0xc00002e9d0?, 0x0?, 0x0?, 0x5593135a5060?) Nov 08 07:06:40 ollama[11902]: runtime/proc.go:402 +0xce fp=0xc0000b3750 sp=0xc0000b3730 pc=0x559312d6e00e Nov 08 07:06:40 ollama[11902]: runtime.gcBgMarkWorker() Nov 08 07:06:40 ollama[11902]: runtime/mgc.go:1310 +0xe5 fp=0xc0000b37e0 sp=0xc0000b3750 pc=0x559312d4f585 Nov 08 07:06:40 ollama[11902]: runtime.goexit({}) Nov 08 07:06:40 ollama[11902]: runtime/asm_amd64.s:1695 +0x1 fp=0xc0000b37e8 sp=0xc0000b37e0 pc=0x559312d9fde1 Nov 08 07:06:40 ollama[11902]: created by runtime.gcBgMarkStartWorkers in goroutine 8 Nov 08 07:06:40 ollama[11902]: runtime/mgc.go:1234 +0x1c Nov 08 07:06:40 ollama[11902]: goroutine 12 gp=0xc000164540 m=nil [GC worker (idle)]: Nov 08 07:06:40 ollama[11902]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) Nov 08 07:06:40 ollama[11902]: runtime/proc.go:402 +0xce fp=0xc000053750 sp=0xc000053730 pc=0x559312d6e00e Nov 08 07:06:40 ollama[11902]: runtime.gcBgMarkWorker() Nov 08 07:06:40 ollama[11902]: runtime/mgc.go:1310 +0xe5 fp=0xc0000537e0 sp=0xc000053750 pc=0x559312d4f585 Nov 08 07:06:40 ollama[11902]: runtime.goexit({}) Nov 08 07:06:40 ollama[11902]: runtime/asm_amd64.s:1695 +0x1 fp=0xc0000537e8 sp=0xc0000537e0 pc=0x559312d9fde1 Nov 08 07:06:40 ollama[11902]: created by runtime.gcBgMarkStartWorkers in goroutine 8 Nov 08 07:06:40 ollama[11902]: runtime/mgc.go:1234 +0x1c Nov 08 07:06:40 ollama[11902]: goroutine 13 gp=0xc000164700 m=nil [GC worker (idle)]: Nov 08 07:06:40 ollama[11902]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) Nov 08 07:06:40 ollama[11902]: runtime/proc.go:402 +0xce fp=0xc000053f50 sp=0xc000053f30 pc=0x559312d6e00e Nov 08 07:06:40 ollama[11902]: runtime.gcBgMarkWorker() Nov 08 07:06:40 ollama[11902]: runtime/mgc.go:1310 +0xe5 fp=0xc000053fe0 sp=0xc000053f50 pc=0x559312d4f585 Nov 08 07:06:40 ollama[11902]: runtime.goexit({}) Nov 08 07:06:40 ollama[11902]: runtime/asm_amd64.s:1695 +0x1 fp=0xc000053fe8 sp=0xc000053fe0 pc=0x559312d9fde1 Nov 08 07:06:40 ollama[11902]: created by runtime.gcBgMarkStartWorkers in goroutine 8 Nov 08 07:06:40 ollama[11902]: runtime/mgc.go:1234 +0x1c Nov 08 07:06:40 ollama[11902]: goroutine 14 gp=0xc0001648c0 m=nil [GC worker (idle)]: Nov 08 07:06:40 ollama[11902]: runtime.gopark(0x2736bc93ca34d?, 0x0?, 0x0?, 0x0?, 0x0?) Nov 08 07:06:40 ollama[11902]: runtime/proc.go:402 +0xce fp=0xc0000ae750 sp=0xc0000ae730 pc=0x559312d6e00e Nov 08 07:06:40 ollama[11902]: runtime.gcBgMarkWorker() Nov 08 07:06:40 ollama[11902]: runtime/mgc.go:1310 +0xe5 fp=0xc0000ae7e0 sp=0xc0000ae750 pc=0x559312d4f585 Nov 08 07:06:40 ollama[11902]: runtime.goexit({}) Nov 08 07:06:40 ollama[11902]: runtime/asm_amd64.s:1695 +0x1 fp=0xc0000ae7e8 sp=0xc0000ae7e0 pc=0x559312d9fde1 Nov 08 07:06:40 ollama[11902]: created by runtime.gcBgMarkStartWorkers in goroutine 8 Nov 08 07:06:40 ollama[11902]: runtime/mgc.go:1234 +0x1c Nov 08 07:06:40 ollama[11902]: rax 0x0 Nov 08 07:06:40 ollama[11902]: rbx 0x7f361fffe000 Nov 08 07:06:40 ollama[11902]: rcx 0x7f36bec419fc Nov 08 07:06:40 ollama[11902]: rdx 0x6 Nov 08 07:06:40 ollama[11902]: rdi 0x839d Nov 08 07:06:40 ollama[11902]: rsi 0x83aa Nov 08 07:06:40 ollama[11902]: rbp 0x83aa Nov 08 07:06:40 ollama[11902]: rsp 0x7f361ffd52b0 Nov 08 07:06:40 ollama[11902]: r8 0x7f361ffd5380 Nov 08 07:06:40 ollama[11902]: r9 0x7f361ffd5350 Nov 08 07:06:40 ollama[11902]: r10 0x8 Nov 08 07:06:40 ollama[11902]: r11 0x246 Nov 08 07:06:40 ollama[11902]: r12 0x6 Nov 08 07:06:40 ollama[11902]: r13 0x16 Nov 08 07:06:40 ollama[11902]: r14 0x7f36e609f54b Nov 08 07:06:40 ollama[11902]: r15 0x7f365005b650 Nov 08 07:06:40 ollama[11902]: rip 0x7f36bec419fc Nov 08 07:06:40 ollama[11902]: rflags 0x246 Nov 08 07:06:40 ollama[11902]: cs 0x33 Nov 08 07:06:40 ollama[11902]: fs 0x0 Nov 08 07:06:40 ollama[11902]: gs 0x0 ``` **System Information**: **OS**: Ubuntu 22.04.5 LTS **CPU**: Intel(R) Core(TM) i3-10300 CPU @ 3.70GHz **GPU**: 2x NVIDIA GeForce RTX 3070 **Driver Version**: 550.120 **CUDA Version**: 12.4 ### OS Linux ### GPU Nvidia ### CPU Intel ### Ollama version 0.4.0

GiteaMirror added the bug nvidia labels 2026-05-04 08:35:19 -05:00

GiteaMirror closed this issue

2026-05-04 08:35:24 -05:00

GiteaMirror commented

2026-05-04 08:35:29 -05:00

@dhiltgen commented on GitHub (Nov 8, 2024):

We had a cuda link bug in 0.4.0 that will be fixed in 0.4.1 which should resolve this.

@dhiltgen commented on GitHub (Nov 8, 2024): We had a cuda link bug in 0.4.0 that will be fixed in 0.4.1 which should resolve this.

GiteaMirror commented

2026-05-04 08:35:31 -05:00

@dhiltgen commented on GitHub (Nov 8, 2024):

Quick update. This was not due to the link failure. There's a bug relating to the cross-attention implementation on cuda with multiple GPUs.

@dhiltgen commented on GitHub (Nov 8, 2024): Quick update. This was not due to the link failure. There's a bug relating to the cross-attention implementation on cuda with multiple GPUs.

GiteaMirror commented

2026-05-04 08:35:34 -05:00

@dhiltgen commented on GitHub (Nov 8, 2024):

We'll track this under #7558

@dhiltgen commented on GitHub (Nov 8, 2024): We'll track this under #7558

Sign in to join this conversation.

Branches Tags

main

hoyyeva/anthropic-local-image-path

dhiltgen/ci

dhiltgen/llama-runner

parth-remove-claude-desktop-launch

hoyyeva/anthropic-reference-images-path

parth-anthropic-reference-images-path

brucemacd/download-before-remove

hoyyeva/editor-config-repair

parth-mlx-decode-checkpoints

parth-launch-codex-app

hoyyeva/fix-codex-model-metadata-warning

hoyyeva/qwen

parth/hide-claude-desktop-till-release

hoyyeva/opencode-image-modality

parth-add-claude-code-autoinstall

release_v0.22.0

pdevine/manifest-list

codex/fix-codex-model-metadata-warning

pdevine/addressable-manifest

brucemacd/launch-fetch-reccomended

jmorganca/llama-compat

launch-copilot-cli

hoyyeva/opencode-thinking

release_v0.20.7

parth-auto-save-backup

parth-test

jmorganca/gemma4-audio-replacements

fix-manifest-digest-on-pull

hoyyeva/vscode-improve

brucemacd/install-server-wait

parth/update-claude-docs

brucemac/start-ap-install

pdevine/mlx-update

pdevine/qwen35_vision

drifkin/api-show-fallback

mintlify/image-generation-1773352582

hoyyeva/server-context-length-local-config

jmorganca/faster-reptition-penalties

jmorganca/convert-nemotron

parth-pi-thinking

pdevine/sampling-penalties

jmorganca/fix-create-quantization-memory

dongchen/resumable_transfer_fix

pdevine/sampling-cache-error

jessegross/mlx-usage

hoyyeva/openclaw-config

hoyyeva/app-html

pdevine/qwen3next

brucemacd/sign-sh-install

brucemacd/tui-update

brucemacd/usage-api

jmorganca/launch-empty

fix-app-dist-embed

mxyng/mlx-compile

mxyng/mlx-quant

mxyng/mlx-glm4.7

mxyng/mlx

brucemacd/simplify-model-picker

jmorganca/qwen3-concurrent

fix-glm-4.7-flash-mla-config

drifkin/qwen3-coder-opening-tag

brucemacd/usage-cli

fix-cuda12-fattn-shmem

ollama-imagegen-docs

parth/fix-multiline-inputs

brucemacd/config-docs

mxyng/model-files

mxyng/simple-execute

fix-imagegen-ollama-models

mxyng/async-upload

jmorganca/lazy-no-dtype-changes

imagegen-auto-detect-create

parth/decrease-concurrent-download-hf

fix-mlx-quantize-init

jmorganca/x-cleanup

usage

imagegen-readme

jmorganca/glm-image

mlx-gpu-cd

jmorganca/imagegen-modelfile

parth/agent-skills

parth/agent-allowlist

parth/signed-in-offline

parth/agents

parth/fix-context-chopping

improve-cloud-flow

parth/add-models-websearch

parth/prompt-renderer-mcp

jmorganca/native-settings

jmorganca/download-stream-hash

jmorganca/client2-rebased

brucemacd/oai-chat-req-multipart

jessegross/multi_chunk_reserve

grace/additional-omit-empty

grace/mistral-3-large

mxyng/tokenizer2

mxyng/tokenizer

jessegross/flash

hoyyeva/windows-nacked-app

mxyng/cleanup-attention

grace/deepseek-parser

hoyyeva/remember-unsent-prompt

parth/add-lfs-pointer-error-conversion

parth/olmo2-test2

hoyyeva/ollama-launchagent-plist

nicole/olmo-model

parth/olmo-test

mxyng/remove-embedded

parth/render-template

jmorganca/intellect-3

parth/remove-prealloc-linter

jmorganca/cmd-eval

nicole/nomic-embed-text-fix

mxyng/lint-2

hoyyeva/add-gemini-3-pro-preview

hoyyeva/load-model-list

mxyng/expand-path

mxyng/environ-2

hoyyeva/deeplink-json-encoding

parth/improve-tool-calling-tests

hoyyeva/conversation

hoyyeva/assistant-edit-response

hoyyeva/thinking

origin/brucemacd/invalid-char-i-err

parth/improve-tool-calling

jmorganca/required-omitempty

grace/qwen3-vl-tests

mxyng/iter-client

parth/docs-readme

nicole/embed-test

pdevine/integration-benchstat

parth/remove-generate-cmd

parth/add-toolcall-id

mxyng/server-tests

jmorganca/glm-4.6

jmorganca/gin-h-compat

drifkin/stable-tool-args

pdevine/qwen3-more-thinking

parth/add-websearch-client

nicole/websearch_local

jmorganca/qwen3-coder-updates

grace/deepseek-v3-migration-tests

mxyng/fix-create

jmorganca/cloud-errors

pdevine/parser-tidy

revert-12233-parth/simplify-entrypoints-runner

parth/enable-so-gpt-oss

brucemacd/qwen3vl

jmorganca/readme-simplify

parth/gpt-oss-structured-outputs

revert-12039-jmorganca/tools-braces

mxyng/embeddings

mxyng/gguf

mxyng/benchmark

mxyng/types-null

parth/move-parsing

mxyng/gemma2

jmorganca/docs

mxyng/16-bit

mxyng/create-stdin

pdevine/authorizedkeys

mxyng/quant

parth/opt-in-error-context-window

brucemacd/cache-models

brucemacd/runner-completion

jmorganca/llama-update-6

brucemacd/benchmark-list

brucemacd/partial-read-caps

parth/deepseek-r1-tools

mxyng/omit-array

parth/tool-prefix-temp

brucemacd/runner-test

jmorganca/qwen25vl

brucemacd/model-forward-test-ext

parth/python-function-parsing

jmorganca/cuda-compression-none

drifkin/num-parallel

drifkin/chat-truncation-fix

jmorganca/sync

parth/python-tools-calling

drifkin/array-head-count

brucemacd/create-no-loop

parth/server-enable-content-stream-with-tools

qwen25omni

mxyng/v3

brucemacd/ropeconfig

jmorganca/silence-tokenizer

parth/sample-so-test

parth/sampling-structured-outputs

brucemacd/doc-go-engine

parth/constrained-sampling-json

jmorganca/mistral-wip

brucemacd/mistral-small-convert

parth/sample-unmarshal-json-for-params

brucemacd/jomorganca/mistral

pdevine/bfloat16

jmorganca/mistral

brucemacd/mistral

pdevine/logging

parth/sample-correctness-fix

parth/sample-fix-sorting

jmorgan/sample-fix-sorting-extras

jmorganca/temp-0-images

brucemacd/parallel-embed-models

brucemacd/shim-grammar

jmorganca/fix-gguf-error

bmizerany/nameswork

jmorganca/faster-releases

bmizerany/validatenames

brucemacd/err-no-vocab

brucemacd/rope-config

brucemacd/err-hint

brucemacd/qwen2_5

brucemacd/logprobs

brucemacd/new_runner_graph_bench

progress-flicker

brucemacd/forward-test

brucemacd/go_qwen2

pdevine/gemma2

jmorganca/add-missing-symlink-eval

mxyng/next-debug

parth/set-context-size-openai

brucemacd/next-bpe-bench

brucemacd/next-bpe-test

brucemacd/new_runner_e2e

brucemacd/new_runner_qwen2

pdevine/convert-cohere2

brucemacd/convert-cli

parth/log-probs

mxyng/next-mlx

mxyng/cmd-history

parth/templating

parth/tokenize-detokenize

brucemacd/check-key-register

bmizerany/grammar

jmorganca/vendor-081b29bd

mxyng/func-checks

jmorganca/fix-null-format

parth/fix-default-to-warn-json

jmorganca/qwen2vl

jmorganca/no-concat

parth/cmd-cleanup-SO

brucemacd/check-key-register-structured-err

parth/openai-stream-usage

parth/fix-referencing-so

stream-tools-stop

jmorganca/degin-1

brucemacd/install-path-clean

brucemacd/push-name-validation

brucemacd/browser-key-register

jmorganca/openai-fix-first-message

jmorganca/fix-proxy

jessegross/sample

parth/disallow-streaming-tools

dhiltgen/remove_submodule

jmorganca/ga

jmorganca/mllama

pdevine/newlines

pdevine/geems-2b

jmorganca/llama-bump

mxyng/modelname-7

mxyng/gin-slog

mxyng/modelname-6

jyan/convert-prog

jyan/quant5

paligemma-support

pdevine/import-docs

jmorganca/openai-context

jyan/paligemma

jyan/p2

jyan/palitest

bmizerany/embedspeedup

jmorganca/llama-vit

brucemacd/allow-ollama

royh/ep-methods

royh/whisper

mxyng/api-models

mxyng/fix-memory

jyan/q4_4/8

jyan/ollama-v

royh/stream-tools

roy-embed-parallel

bmizerany/hrm

revert-5963-revert-5924-mxyng/llama3.1-rope

royh/embed-viz

jyan/local2

jyan/auth

jyan/local

jyan/parse-temp

jmorganca/template-mistral

jyan/reord-g

royh-openai-suffixdocs

royh-imgembed

royh-embed-parallel

jyan/quant4

royh-precision

jyan/progress

pdevine/fix-template

jyan/quant3

pdevine/ggla

mxyng/update-registry-domain

jmorganca/ggml-static

mxyng/create-context

jyan/v0.146

mxyng/layers-from-files

build_dist

bmizerany/noseek

royh-ls

royh-name

timeout

mxyng/server-timestamp

bmizerany/nosillyggufslurps

royh-params

jmorganca/llama-cpp-7c26775

royh-openai-delete

royh-show-rigid

jmorganca/enable-fa

jmorganca/no-error-template

jyan/format

royh-testdelete

bmizerany/fastverify

language_support

pdevine/ps-glitches

brucemacd/tokenize

bruce/iq-quants

bmizerany/filepathwithcoloninhost

mxyng/split-bin

bmizerany/client-registry

jmorganca/if-none-match

native

jmorganca/native

jmorganca/batch-embeddings

jmorganca/initcmake

jmorganca/mm

pdevine/showggmlinfo

modenameenforcealphanum

bmizerany/modenameenforcealphanum

jmorganca/done-reason

jmorganca/llama-cpp-8960fe8

ollama.com

bmizerany/filepathnobuild

bmizerany/types/model/defaultfix

rmdisplaylong

nogogen

bmizerany/x

modelfile-readme

bmizerany/replacecolon

jmorganca/limit

jmorganca/execstack

jmorganca/replace-assets

mxyng/tune-concurrency

jmorganca/testing

whitespace-detection

jmorganca/options

upgrade-all

scratch

cuda-search

mattw/airenamer

mattw/allmodelsonhuggingface

mattw/quantcontext

mattw/whatneedstorun

brucemacd/llama-mem-calc

mattw/faq-context

mattw/communitylinks

mattw/noprune

mattw/python-functioncalling

rename

mxyng/install

pulse

remove-first

editor

mattw/selfqueryingretrieval

cgo

mattw/howtoquant

api

matt/streamingapi

format-config

mxyng/extra-args

shell

update-nous-hermes

cp-model

upload-progress

fix-unknown-model

fix-model-names

delete-fix

insecure-registry

ls

deletemodels

progressbar

readme-updates

license-layers

skip-list

list-models

modelpath

matt/examplemodelfiles

distribution

go-opts

1 Participants

Notifications

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: github-starred/ollama#66877