[GH-ISSUE #8140] GGML_ASSERT(i01 >= 0 && i01 < ne01) failed and SIGSEGV had occoured #67251

Closed
opened 2026-05-04 09:43:52 -05:00 by GiteaMirror · 3 comments
Owner

Originally created by @9suns on GitHub (Dec 17, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/8140

What is the issue?

Dec 18 02:31:29 ksy ollama[2877902]: time=2024-12-18T02:31:29.468+08:00 level=INFO source=.:0 msg="Server listening on 127.0.0.1:45295"
Dec 18 02:31:29 ksy ollama[2877902]: llama_model_loader: loaded meta data with 23 key-value pairs and 197 tensors from /data/ollama/blobs/sha256-3757be8630cc587da3948fe2f1fbb646770a18fa04adc57f1c8977dd0e6281fa (version GGUF V3 (latest))
Dec 18 02:31:29 ksy ollama[2877902]: llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
Dec 18 02:31:29 ksy ollama[2877902]: llama_model_loader: - kv   0:                       general.architecture str              = bert
Dec 18 02:31:29 ksy ollama[2877902]: llama_model_loader: - kv   1:                               general.name str              = Dmeta-embedding-zh
Dec 18 02:31:29 ksy ollama[2877902]: llama_model_loader: - kv   2:                           bert.block_count u32              = 12
Dec 18 02:31:29 ksy ollama[2877902]: llama_model_loader: - kv   3:                        bert.context_length u32              = 1024
Dec 18 02:31:29 ksy ollama[2877902]: llama_model_loader: - kv   4:                      bert.embedding_length u32              = 768
Dec 18 02:31:29 ksy ollama[2877902]: llama_model_loader: - kv   5:                   bert.feed_forward_length u32              = 3072
Dec 18 02:31:29 ksy ollama[2877902]: llama_model_loader: - kv   6:                  bert.attention.head_count u32              = 12
Dec 18 02:31:29 ksy ollama[2877902]: llama_model_loader: - kv   7:          bert.attention.layer_norm_epsilon f32              = 0.000000
Dec 18 02:31:29 ksy ollama[2877902]: llama_model_loader: - kv   8:                          general.file_type u32              = 1
Dec 18 02:31:29 ksy ollama[2877902]: llama_model_loader: - kv   9:                      bert.attention.causal bool             = false
Dec 18 02:31:29 ksy ollama[2877902]: llama_model_loader: - kv  10:                          bert.pooling_type u32              = 2
Dec 18 02:31:29 ksy ollama[2877902]: llama_model_loader: - kv  11:            tokenizer.ggml.token_type_count u32              = 2
Dec 18 02:31:29 ksy ollama[2877902]: llama_model_loader: - kv  12:                       tokenizer.ggml.model str              = bert
Dec 18 02:31:29 ksy ollama[2877902]: llama_model_loader: - kv  13:                         tokenizer.ggml.pre str              = Dmeta-embedding-zh
Dec 18 02:31:29 ksy ollama[2877902]: llama_model_loader: - kv  14:                      tokenizer.ggml.tokens arr[str,21128]   = ["[PAD]", "[unused1]", "[unused2]", "...
Dec 18 02:31:29 ksy ollama[2877902]: llama_model_loader: - kv  15:                  tokenizer.ggml.token_type arr[i32,21128]   = [3, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
Dec 18 02:31:29 ksy ollama[2877902]: llama_model_loader: - kv  16:            tokenizer.ggml.unknown_token_id u32              = 100
Dec 18 02:31:29 ksy ollama[2877902]: llama_model_loader: - kv  17:          tokenizer.ggml.seperator_token_id u32              = 102
Dec 18 02:31:29 ksy ollama[2877902]: llama_model_loader: - kv  18:            tokenizer.ggml.padding_token_id u32              = 0
Dec 18 02:31:29 ksy ollama[2877902]: llama_model_loader: - kv  19:                tokenizer.ggml.cls_token_id u32              = 101
Dec 18 02:31:29 ksy ollama[2877902]: llama_model_loader: - kv  20:               tokenizer.ggml.mask_token_id u32              = 103
Dec 18 02:31:29 ksy ollama[2877902]: llama_model_loader: - kv  21:                tokenizer.ggml.bos_token_id u32              = 0
Dec 18 02:31:29 ksy ollama[2877902]: llama_model_loader: - kv  22:                tokenizer.ggml.eos_token_id u32              = 2
Dec 18 02:31:29 ksy ollama[2877902]: llama_model_loader: - type  f32:  123 tensors
Dec 18 02:31:29 ksy ollama[2877902]: llama_model_loader: - type  f16:   74 tensors
Dec 18 02:31:29 ksy ollama[2877902]: llm_load_vocab: special_eos_id is not in special_eog_ids - the tokenizer config may be incorrect
Dec 18 02:31:29 ksy ollama[2877902]: llm_load_vocab: special tokens cache size = 5
Dec 18 02:31:29 ksy ollama[2877902]: llm_load_vocab: token to piece cache size = 0.0769 MB
Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: format           = GGUF V3 (latest)
Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: arch             = bert
Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: vocab type       = WPM
Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: n_vocab          = 21128
Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: n_merges         = 0
Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: vocab_only       = 0
Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: n_ctx_train      = 1024
Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: n_embd           = 768
Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: n_layer          = 12
Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: n_head           = 12
Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: n_head_kv        = 12
Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: n_rot            = 64
Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: n_swa            = 0
Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: n_embd_head_k    = 64
Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: n_embd_head_v    = 64
Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: n_gqa            = 1
Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: n_embd_k_gqa     = 768
Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: n_embd_v_gqa     = 768
Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: f_norm_eps       = 1.0e-12
Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: f_norm_rms_eps   = 0.0e+00
Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: f_clamp_kqv      = 0.0e+00
Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: f_max_alibi_bias = 0.0e+00
Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: f_logit_scale    = 0.0e+00
Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: n_ff             = 3072
Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: n_expert         = 0
Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: n_expert_used    = 0
Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: causal attn      = 0
Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: pooling type     = 2
Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: rope type        = 2
Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: rope scaling     = linear
Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: freq_base_train  = 10000.0
Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: freq_scale_train = 1
Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: n_ctx_orig_yarn  = 1024
Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: rope_finetuned   = unknown
Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: ssm_d_conv       = 0
Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: ssm_d_inner      = 0
Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: ssm_d_state      = 0
Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: ssm_dt_rank      = 0
Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: ssm_dt_b_c_rms   = 0
Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: model type       = 109M
Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: model ftype      = F16
Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: model params     = 102.07 M
Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: model size       = 194.92 MiB (16.02 BPW)
Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: general.name     = Dmeta-embedding-zh
Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: BOS token        = 0 '[PAD]'
Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: EOS token        = 2 '[unused2]'
Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: UNK token        = 100 '[UNK]'
Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: SEP token        = 102 '[SEP]'
Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: PAD token        = 0 '[PAD]'
Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: CLS token        = 101 '[CLS]'
Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: MASK token       = 103 '[MASK]'
Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: LF token         = 0 '[PAD]'
Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: EOG token        = 2 '[unused2]'
Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: max token length = 48
Dec 18 02:31:29 ksy ollama[2877902]: ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
Dec 18 02:31:29 ksy ollama[2877902]: ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
Dec 18 02:31:29 ksy ollama[2877902]: ggml_cuda_init: found 1 CUDA devices:
Dec 18 02:31:29 ksy ollama[2877902]:   Device 0: NVIDIA GeForce RTX 3090, compute capability 8.6, VMM: yes
Dec 18 02:31:29 ksy ollama[2877902]: time=2024-12-18T02:31:29.550+08:00 level=WARN source=sched.go:646 msg="gpu VRAM usage didn't recover within timeout" seconds=5.309635673 model=/data/ollama/blobs/sha256-3757be8630cc587da3948fe2f1fbb646770a18fa04adc57f1c8977dd0e6281fa
Dec 18 02:31:29 ksy ollama[2877902]: time=2024-12-18T02:31:29.550+08:00 level=DEBUG source=gpu.go:398 msg="updating system memory data" before.total="31.2 GiB" before.free="22.2 GiB" before.free_swap="7.1 GiB" now.total="31.2 GiB" now.free="22.0 GiB" now.free_swap="7.1 GiB"
Dec 18 02:31:29 ksy ollama[2877902]: initializing /usr/lib/x86_64-linux-gnu/libcuda.so.535.161.07
Dec 18 02:31:29 ksy ollama[2877902]: dlsym: cuInit - 0x7f2482655430
Dec 18 02:31:29 ksy ollama[2877902]: dlsym: cuDriverGetVersion - 0x7f2482655450
Dec 18 02:31:29 ksy ollama[2877902]: dlsym: cuDeviceGetCount - 0x7f2482655490
Dec 18 02:31:29 ksy ollama[2877902]: dlsym: cuDeviceGet - 0x7f2482655470
Dec 18 02:31:29 ksy ollama[2877902]: dlsym: cuDeviceGetAttribute - 0x7f2482655570
Dec 18 02:31:29 ksy ollama[2877902]: dlsym: cuDeviceGetUuid - 0x7f24826554d0
Dec 18 02:31:29 ksy ollama[2877902]: dlsym: cuDeviceGetName - 0x7f24826554b0
Dec 18 02:31:29 ksy ollama[2877902]: dlsym: cuCtxCreate_v3 - 0x7f248265d130
Dec 18 02:31:29 ksy ollama[2877902]: dlsym: cuMemGetInfo_v2 - 0x7f2482668600
Dec 18 02:31:29 ksy ollama[2877902]: dlsym: cuCtxDestroy - 0x7f24826b7600
Dec 18 02:31:29 ksy ollama[2877902]: calling cuInit
Dec 18 02:31:29 ksy ollama[2877902]: calling cuDriverGetVersion
Dec 18 02:31:29 ksy ollama[2877902]: raw version 0x2ef4
Dec 18 02:31:29 ksy ollama[2877902]: CUDA driver version: 12.2
Dec 18 02:31:29 ksy ollama[2877902]: calling cuDeviceGetCount
Dec 18 02:31:29 ksy ollama[2877902]: device count 1
Dec 18 02:31:29 ksy ollama[2877902]: llm_load_tensors: ggml ctx size =    0.16 MiB
Dec 18 02:31:29 ksy ollama[2877902]: llm_load_tensors: offloading 12 repeating layers to GPU
Dec 18 02:31:29 ksy ollama[2877902]: llm_load_tensors: offloading non-repeating layers to GPU
Dec 18 02:31:29 ksy ollama[2877902]: llm_load_tensors: offloaded 13/13 layers to GPU
Dec 18 02:31:29 ksy ollama[2877902]: llm_load_tensors:        CPU buffer size =    32.46 MiB
Dec 18 02:31:29 ksy ollama[2877902]: llm_load_tensors:      CUDA0 buffer size =   162.46 MiB
Dec 18 02:31:29 ksy ollama[2877902]: llama_new_context_with_model: n_ctx      = 2048
Dec 18 02:31:29 ksy ollama[2877902]: llama_new_context_with_model: n_batch    = 512
Dec 18 02:31:29 ksy ollama[2877902]: llama_new_context_with_model: n_ubatch   = 512
Dec 18 02:31:29 ksy ollama[2877902]: llama_new_context_with_model: flash_attn = 0
Dec 18 02:31:29 ksy ollama[2877902]: llama_new_context_with_model: freq_base  = 10000.0
Dec 18 02:31:29 ksy ollama[2877902]: llama_new_context_with_model: freq_scale = 1
Dec 18 02:31:29 ksy ollama[2877902]: llama_kv_cache_init:      CUDA0 KV buffer size =    72.00 MiB
Dec 18 02:31:29 ksy ollama[2877902]: llama_new_context_with_model: KV self size  =   72.00 MiB, K (f16):   36.00 MiB, V (f16):   36.00 MiB
Dec 18 02:31:29 ksy ollama[2877902]: llama_new_context_with_model:        CPU  output buffer size =     0.00 MiB
Dec 18 02:31:29 ksy ollama[2877902]: llama_new_context_with_model:      CUDA0 compute buffer size =    19.00 MiB
Dec 18 02:31:29 ksy ollama[2877902]: llama_new_context_with_model:  CUDA_Host compute buffer size =     4.01 MiB
Dec 18 02:31:29 ksy ollama[2877902]: llama_new_context_with_model: graph nodes  = 429
Dec 18 02:31:29 ksy ollama[2877902]: llama_new_context_with_model: graph splits = 2
Dec 18 02:31:29 ksy ollama[2877902]: time=2024-12-18T02:31:29.598+08:00 level=DEBUG source=gpu.go:448 msg="updating cuda memory data" gpu=GPU-f4ac237a-4252-ac0e-b006-d7ae4f03cbf9 name="NVIDIA GeForce RTX 3090" overhead="0 B" before.total="23.7 GiB" before.free="23.4 GiB" now.total="23.7 GiB" now.free="23.0 GiB" now.used="681.8 MiB"
Dec 18 02:31:29 ksy ollama[2877902]: releasing cuda driver library
Dec 18 02:31:29 ksy ollama[2877902]: time=2024-12-18T02:31:29.598+08:00 level=DEBUG source=sched.go:659 msg="gpu VRAM free memory converged after 5.36 seconds" model=/data/ollama/blobs/sha256-3757be8630cc587da3948fe2f1fbb646770a18fa04adc57f1c8977dd0e6281fa
Dec 18 02:31:29 ksy ollama[2877902]: time=2024-12-18T02:31:29.700+08:00 level=INFO source=server.go:615 msg="llama runner started in 0.25 seconds"
Dec 18 02:31:29 ksy ollama[2877902]: time=2024-12-18T02:31:29.700+08:00 level=DEBUG source=sched.go:462 msg="finished setting up runner" model=/data/ollama/blobs/sha256-3757be8630cc587da3948fe2f1fbb646770a18fa04adc57f1c8977dd0e6281fa
Dec 18 02:31:29 ksy ollama[2877902]: time=2024-12-18T02:31:29.701+08:00 level=DEBUG source=runner.go:752 msg="embedding request" content="I\r\n目录\r\n第 1 章 概述.......................................................................................................................................................... 1\r\n1.1 适用范围.................................................................................................................................................. 1\r\n1.2 遵照标准.................................................................................................................................................. 1\r\n1.3 数据库说明.............................................................................................................................................. 1\r\n1.4 数据同步频率......................................................................................................................................... 2\r\n1.5 数据校验规则说明................................................................................................................................. 3\r\n1.6 数据表常见数据类型说明..................................................................................................................... 3\r\n第 2 章 数据采集内容 ......................................................................................................................................... 5\r\n2.1 实时采集数据表说明............................................................................................................................. 5\r\n2.1.1 患者基本信息表 emr_patient_info ............................................................................................. 5\r\n2.1.2 诊疗活动信息表 emr_activity_info ............................................................................................. 9\r\n2.1.3 传染病报告卡 emr_inf_report ................................................................................................... 14\r\n2.2 常规监测数据表说明........................................................................................................................... 36\r\n2.2.1 门(急)诊病历 emr_outpatient_record ................................................................................. 36\r\n2.2.2 门(急)诊留 观记录 emr_outpatient_obs ............................................................................. 42\r\n2.2.3 入院记录 emr_admission_info .................................................................................................."
Dec 18 02:31:29 ksy ollama[2877902]: time=2024-12-18T02:31:29.707+08:00 level=WARN source=runner.go:129 msg="truncating input prompt" limit=2048 prompt=2131 keep=1 new=2048
Dec 18 02:31:29 ksy ollama[2877902]: time=2024-12-18T02:31:29.707+08:00 level=DEBUG source=cache.go:104 msg="loading cache slot" id=0 cache=0 prompt=2048 used=0 remaining=2048
Dec 18 02:31:29 ksy ollama[2877902]: ggml.c:13343: GGML_ASSERT(i01 >= 0 && i01 < ne01) failed
Dec 18 02:31:29 ksy ollama[2877902]: SIGSEGV: segmentation violation
Dec 18 02:31:29 ksy ollama[2877902]: PC=0x7f7cc1f06f77 m=0 sigcode=1 addr=0x204a03fd8
Dec 18 02:31:29 ksy ollama[2877902]: signal arrived during cgo execution
Dec 18 02:31:29 ksy ollama[2877902]: goroutine 7 gp=0xc000184000 m=0 mp=0x556d1a36cf20 [syscall]:
Dec 18 02:31:29 ksy ollama[2877902]: runtime.cgocall(0x556d19e50a90, 0xc000080b48)
Dec 18 02:31:29 ksy ollama[2877902]:         runtime/cgocall.go:157 +0x4b fp=0xc000080b20 sp=0xc000080ae8 pc=0x556d19bd18ab
Dec 18 02:31:29 ksy ollama[2877902]: github.com/ollama/ollama/llama._Cfunc_llama_decode(0x7f7c48006490, {0x200, 0x7f7c4804a260, 0x0, 0x0, 0x7f7c4804aa70, 0x7f7c4804b280, 0x7f7c4804ba90, 0x7f7c487873d0, 0x0, ...})
Dec 18 02:31:29 ksy ollama[2877902]:         _cgo_gotypes.go:548 +0x52 fp=0xc000080b48 sp=0xc000080b20 pc=0x556d19ccee32
Dec 18 02:31:29 ksy ollama[2877902]: github.com/ollama/ollama/llama.(*Context).Decode.func1(0x556d19e4c4eb?, 0x7f7c48006490?)
Dec 18 02:31:29 ksy ollama[2877902]:         github.com/ollama/ollama/llama/llama.go:189 +0xd8 fp=0xc000080c68 sp=0xc000080b48 pc=0x556d19cd1518
Dec 18 02:31:29 ksy ollama[2877902]: github.com/ollama/ollama/llama.(*Context).Decode(0xc000080d58?, 0x0?)
Dec 18 02:31:29 ksy ollama[2877902]:         github.com/ollama/ollama/llama/llama.go:189 +0x13 fp=0xc000080cb0 sp=0xc000080c68 pc=0x556d19cd13b3
Dec 18 02:31:29 ksy ollama[2877902]: main.(*Server).processBatch(0xc0000ce120, 0xc00011a000, 0xc000080f10)
Dec 18 02:31:29 ksy ollama[2877902]:         github.com/ollama/ollama/llama/runner/runner.go:434 +0x24d fp=0xc000080ed0 sp=0xc000080cb0 pc=0x556d19e4b1ad
Dec 18 02:31:29 ksy ollama[2877902]: main.(*Server).run(0xc0000ce120, {0x556d1a19d9a0, 0xc0000a40a0})
Dec 18 02:31:29 ksy ollama[2877902]:         github.com/ollama/ollama/llama/runner/runner.go:342 +0x1e5 fp=0xc000080fb8 sp=0xc000080ed0 pc=0x556d19e4ac25
Dec 18 02:31:29 ksy ollama[2877902]: main.main.gowrap2()
Dec 18 02:31:29 ksy ollama[2877902]:         github.com/ollama/ollama/llama/runner/runner.go:980 +0x28 fp=0xc000080fe0 sp=0xc000080fb8 pc=0x556d19e4fa88
Dec 18 02:31:29 ksy ollama[2877902]: runtime.goexit({})
Dec 18 02:31:29 ksy ollama[2877902]:         runtime/asm_amd64.s:1695 +0x1 fp=0xc000080fe8 sp=0xc000080fe0 pc=0x556d19c3a2c1
Dec 18 02:31:29 ksy ollama[2877902]: created by main.main in goroutine 1
Dec 18 02:31:29 ksy ollama[2877902]:         github.com/ollama/ollama/llama/runner/runner.go:980 +0xd3e
Dec 18 02:31:29 ksy ollama[2877902]: goroutine 1 gp=0xc0000061c0 m=nil [IO wait]:
Dec 18 02:31:29 ksy ollama[2877902]: runtime.gopark(0x1?, 0xc0000298e0?, 0xd4?, 0x82?, 0xc0000298c0?)
Dec 18 02:31:29 ksy ollama[2877902]:         runtime/proc.go:402 +0xce fp=0xc000029860 sp=0xc000029840 pc=0x556d19c084ee
Dec 18 02:31:29 ksy ollama[2877902]: runtime.netpollblock(0x10?, 0x19bd1006?, 0x6d?)
Dec 18 02:31:29 ksy ollama[2877902]:         runtime/netpoll.go:573 +0xf7 fp=0xc000029898 sp=0xc000029860 pc=0x556d19c00737
Dec 18 02:31:29 ksy ollama[2877902]: internal/poll.runtime_pollWait(0x7f7cba9c8020, 0x72)
Dec 18 02:31:29 ksy ollama[2877902]:         runtime/netpoll.go:345 +0x85 fp=0xc0000298b8 sp=0xc000029898 pc=0x556d19c34f85
Dec 18 02:31:29 ksy ollama[2877902]: internal/poll.(*pollDesc).wait(0x3?, 0x7f7cc14c1368?, 0x0)
Dec 18 02:31:29 ksy ollama[2877902]:         internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc0000298e0 sp=0xc0000298b8 pc=0x556d19c84ea7
Dec 18 02:31:29 ksy ollama[2877902]: internal/poll.(*pollDesc).waitRead(...)
Dec 18 02:31:29 ksy ollama[2877902]:         internal/poll/fd_poll_runtime.go:89
Dec 18 02:31:29 ksy ollama[2877902]: internal/poll.(*FD).Accept(0xc0000fe080)
Dec 18 02:31:29 ksy ollama[2877902]:         internal/poll/fd_unix.go:611 +0x2ac fp=0xc000029988 sp=0xc0000298e0 pc=0x556d19c8636c
Dec 18 02:31:29 ksy ollama[2877902]: net.(*netFD).accept(0xc0000fe080)
Dec 18 02:31:29 ksy ollama[2877902]:         net/fd_unix.go:172 +0x29 fp=0xc000029a40 sp=0xc000029988 pc=0x556d19cf4fa9
Dec 18 02:31:29 ksy ollama[2877902]: net.(*TCPListener).accept(0xc00007c1c0)
Dec 18 02:31:29 ksy ollama[2877902]:         net/tcpsock_posix.go:159 +0x1e fp=0xc000029a68 sp=0xc000029a40 pc=0x556d19d05cde
Dec 18 02:31:29 ksy ollama[2877902]: net.(*TCPListener).Accept(0xc00007c1c0)
Dec 18 02:31:29 ksy ollama[2877902]:         net/tcpsock.go:327 +0x30 fp=0xc000029a98 sp=0xc000029a68 pc=0x556d19d05030
Dec 18 02:31:29 ksy ollama[2877902]: net/http.(*onceCloseListener).Accept(0xc000122000?)
Dec 18 02:31:29 ksy ollama[2877902]:         <autogenerated>:1 +0x24 fp=0xc000029ab0 sp=0xc000029a98 pc=0x556d19e2c244
Dec 18 02:31:29 ksy ollama[2877902]: net/http.(*Server).Serve(0xc0000181e0, {0x556d1a19d360, 0xc00007c1c0})
Dec 18 02:31:29 ksy ollama[2877902]:         net/http/server.go:3260 +0x33e fp=0xc000029be0 sp=0xc000029ab0 pc=0x556d19e2305e
Dec 18 02:31:29 ksy ollama[2877902]: main.main()
Dec 18 02:31:29 ksy ollama[2877902]:         github.com/ollama/ollama/llama/runner/runner.go:1000 +0x10cd fp=0xc000029f50 sp=0xc000029be0 pc=0x556d19e4f80d
Dec 18 02:31:29 ksy ollama[2877902]: runtime.main()
Dec 18 02:31:29 ksy ollama[2877902]:         runtime/proc.go:271 +0x29d fp=0xc000029fe0 sp=0xc000029f50 pc=0x556d19c080bd
Dec 18 02:31:29 ksy ollama[2877902]: runtime.goexit({})
Dec 18 02:31:29 ksy ollama[2877902]:         runtime/asm_amd64.s:1695 +0x1 fp=0xc000029fe8 sp=0xc000029fe0 pc=0x556d19c3a2c1
Dec 18 02:31:29 ksy ollama[2877902]: goroutine 2 gp=0xc000006c40 m=nil [force gc (idle)]:
Dec 18 02:31:29 ksy ollama[2877902]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
Dec 18 02:31:29 ksy ollama[2877902]:         runtime/proc.go:402 +0xce fp=0xc00006cfa8 sp=0xc00006cf88 pc=0x556d19c084ee
Dec 18 02:31:29 ksy ollama[2877902]: runtime.goparkunlock(...)
Dec 18 02:31:29 ksy ollama[2877902]:         runtime/proc.go:408
Dec 18 02:31:29 ksy ollama[2877902]: runtime.forcegchelper()
Dec 18 02:31:29 ksy ollama[2877902]:         runtime/proc.go:326 +0xb8 fp=0xc00006cfe0 sp=0xc00006cfa8 pc=0x556d19c08378
Dec 18 02:31:29 ksy ollama[2877902]: runtime.goexit({})
Dec 18 02:31:29 ksy ollama[2877902]:         runtime/asm_amd64.s:1695 +0x1 fp=0xc00006cfe8 sp=0xc00006cfe0 pc=0x556d19c3a2c1
Dec 18 02:31:29 ksy ollama[2877902]: created by runtime.init.6 in goroutine 1
Dec 18 02:31:29 ksy ollama[2877902]:         runtime/proc.go:314 +0x1a
Dec 18 02:31:29 ksy ollama[2877902]: goroutine 3 gp=0xc000007180 m=nil [GC sweep wait]:
Dec 18 02:31:29 ksy ollama[2877902]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
Dec 18 02:31:29 ksy ollama[2877902]:         runtime/proc.go:402 +0xce fp=0xc00006d780 sp=0xc00006d760 pc=0x556d19c084ee
Dec 18 02:31:29 ksy ollama[2877902]: runtime.goparkunlock(...)
Dec 18 02:31:29 ksy ollama[2877902]:         runtime/proc.go:408
Dec 18 02:31:29 ksy ollama[2877902]: runtime.bgsweep(0xc00007e000)
Dec 18 02:31:29 ksy ollama[2877902]:         runtime/mgcsweep.go:278 +0x94 fp=0xc00006d7c8 sp=0xc00006d780 pc=0x556d19bf3034
Dec 18 02:31:29 ksy ollama[2877902]: runtime.gcenable.gowrap1()
Dec 18 02:31:29 ksy ollama[2877902]:         runtime/mgc.go:203 +0x25 fp=0xc00006d7e0 sp=0xc00006d7c8 pc=0x556d19be7b65
Dec 18 02:31:29 ksy ollama[2877902]: runtime.goexit({})
Dec 18 02:31:29 ksy ollama[2877902]:         runtime/asm_amd64.s:1695 +0x1 fp=0xc00006d7e8 sp=0xc00006d7e0 pc=0x556d19c3a2c1
Dec 18 02:31:29 ksy ollama[2877902]: created by runtime.gcenable in goroutine 1
Dec 18 02:31:29 ksy ollama[2877902]:         runtime/mgc.go:203 +0x66
Dec 18 02:31:29 ksy ollama[2877902]: goroutine 4 gp=0xc000007340 m=nil [GC scavenge wait]:
Dec 18 02:31:29 ksy ollama[2877902]: runtime.gopark(0xc00007e000?, 0x556d1a09a4f0?, 0x1?, 0x0?, 0xc000007340?)
Dec 18 02:31:29 ksy ollama[2877902]:         runtime/proc.go:402 +0xce fp=0xc00006df78 sp=0xc00006df58 pc=0x556d19c084ee
Dec 18 02:31:29 ksy ollama[2877902]: runtime.goparkunlock(...)
Dec 18 02:31:29 ksy ollama[2877902]:         runtime/proc.go:408
Dec 18 02:31:29 ksy ollama[2877902]: runtime.(*scavengerState).park(0x556d1a36c560)
Dec 18 02:31:29 ksy ollama[2877902]:         runtime/mgcscavenge.go:425 +0x49 fp=0xc00006dfa8 sp=0xc00006df78 pc=0x556d19bf0a29
Dec 18 02:31:29 ksy ollama[2877902]: runtime.bgscavenge(0xc00007e000)
Dec 18 02:31:29 ksy ollama[2877902]:         runtime/mgcscavenge.go:653 +0x3c fp=0xc00006dfc8 sp=0xc00006dfa8 pc=0x556d19bf0fbc
Dec 18 02:31:29 ksy ollama[2877902]: runtime.gcenable.gowrap2()
Dec 18 02:31:29 ksy ollama[2877902]:         runtime/mgc.go:204 +0x25 fp=0xc00006dfe0 sp=0xc00006dfc8 pc=0x556d19be7b05
Dec 18 02:31:29 ksy ollama[2877902]: runtime.goexit({})
Dec 18 02:31:29 ksy ollama[2877902]:         runtime/asm_amd64.s:1695 +0x1 fp=0xc00006dfe8 sp=0xc00006dfe0 pc=0x556d19c3a2c1
Dec 18 02:31:29 ksy ollama[2877902]: created by runtime.gcenable in goroutine 1
Dec 18 02:31:29 ksy ollama[2877902]:         runtime/mgc.go:204 +0xa5
Dec 18 02:31:29 ksy ollama[2877902]: goroutine 5 gp=0xc000007c00 m=nil [finalizer wait]:
Dec 18 02:31:29 ksy ollama[2877902]: runtime.gopark(0xc00006c648?, 0x556d19bdb465?, 0xa8?, 0x1?, 0xc0000061c0?)
Dec 18 02:31:29 ksy ollama[2877902]:         runtime/proc.go:402 +0xce fp=0xc00006c620 sp=0xc00006c600 pc=0x556d19c084ee
Dec 18 02:31:29 ksy ollama[2877902]: runtime.runfinq()
Dec 18 02:31:29 ksy ollama[2877902]:         runtime/mfinal.go:194 +0x107 fp=0xc00006c7e0 sp=0xc00006c620 pc=0x556d19be6ba7
Dec 18 02:31:29 ksy ollama[2877902]: runtime.goexit({})
Dec 18 02:31:29 ksy ollama[2877902]:         runtime/asm_amd64.s:1695 +0x1 fp=0xc00006c7e8 sp=0xc00006c7e0 pc=0x556d19c3a2c1
Dec 18 02:31:29 ksy ollama[2877902]: created by runtime.createfing in goroutine 1
Dec 18 02:31:29 ksy ollama[2877902]:         runtime/mfinal.go:164 +0x3d
Dec 18 02:31:29 ksy ollama[2877902]: goroutine 18 gp=0xc000007dc0 m=nil [chan receive]:
Dec 18 02:31:29 ksy ollama[2877902]: runtime.gopark(0x556d19c382d4?, 0xc0000f3890?, 0x65?, 0xa6?, 0xc0000f3878?)
Dec 18 02:31:29 ksy ollama[2877902]:         runtime/proc.go:402 +0xce fp=0xc0000f3858 sp=0xc0000f3838 pc=0x556d19c084ee
Dec 18 02:31:29 ksy ollama[2877902]: runtime.chanrecv(0xc0002000c0, 0xc0000f3a08, 0x1)
Dec 18 02:31:29 ksy ollama[2877902]:         runtime/chan.go:583 +0x3bf fp=0xc0000f38d0 sp=0xc0000f3858 pc=0x556d19bd3ebf
Dec 18 02:31:29 ksy ollama[2877902]: runtime.chanrecv1(0xc000112030?, 0xc00029e000?)
Dec 18 02:31:29 ksy ollama[2877902]:         runtime/chan.go:442 +0x12 fp=0xc0000f38f8 sp=0xc0000f38d0 pc=0x556d19bd3af2
Dec 18 02:31:29 ksy ollama[2877902]: main.(*Server).embeddings(0xc0000ce120, {0x556d1a19d510, 0xc000218000}, 0xc000204000)
Dec 18 02:31:29 ksy ollama[2877902]:         github.com/ollama/ollama/llama/runner/runner.go:793 +0x746 fp=0xc0000f3ab8 sp=0xc0000f38f8 pc=0x556d19e4dc66
Dec 18 02:31:29 ksy ollama[2877902]: main.(*Server).embeddings-fm({0x556d1a19d510?, 0xc000218000?}, 0x556d19e2738d?)
Dec 18 02:31:29 ksy ollama[2877902]:         <autogenerated>:1 +0x36 fp=0xc0000f3ae8 sp=0xc0000f3ab8 pc=0x556d19e50236
Dec 18 02:31:29 ksy ollama[2877902]: net/http.HandlerFunc.ServeHTTP(0xc0000b4d00?, {0x556d1a19d510?, 0xc000218000?}, 0x10?)
Dec 18 02:31:29 ksy ollama[2877902]:         net/http/server.go:2171 +0x29 fp=0xc0000f3b10 sp=0xc0000f3ae8 pc=0x556d19e1fe29
Dec 18 02:31:29 ksy ollama[2877902]: net/http.(*ServeMux).ServeHTTP(0x556d19bdb465?, {0x556d1a19d510, 0xc000218000}, 0xc000204000)
Dec 18 02:31:29 ksy ollama[2877902]:         net/http/server.go:2688 +0x1ad fp=0xc0000f3b60 sp=0xc0000f3b10 pc=0x556d19e21cad
Dec 18 02:31:29 ksy ollama[2877902]: net/http.serverHandler.ServeHTTP({0x556d1a19c860?}, {0x556d1a19d510?, 0xc000218000?}, 0x6?)
Dec 18 02:31:29 ksy ollama[2877902]:         net/http/server.go:3142 +0x8e fp=0xc0000f3b90 sp=0xc0000f3b60 pc=0x556d19e22cce
Dec 18 02:31:29 ksy ollama[2877902]: net/http.(*conn).serve(0xc000122000, {0x556d1a19d968, 0xc0000b2db0})
Dec 18 02:31:29 ksy ollama[2877902]:         net/http/server.go:2044 +0x5e8 fp=0xc0000f3fb8 sp=0xc0000f3b90 pc=0x556d19e1ea68
Dec 18 02:31:29 ksy ollama[2877902]: net/http.(*Server).Serve.gowrap3()
Dec 18 02:31:29 ksy ollama[2877902]:         net/http/server.go:3290 +0x28 fp=0xc0000f3fe0 sp=0xc0000f3fb8 pc=0x556d19e23448
Dec 18 02:31:29 ksy ollama[2877902]: runtime.goexit({})
Dec 18 02:31:29 ksy ollama[2877902]:         runtime/asm_amd64.s:1695 +0x1 fp=0xc0000f3fe8 sp=0xc0000f3fe0 pc=0x556d19c3a2c1
Dec 18 02:31:29 ksy ollama[2877902]: created by net/http.(*Server).Serve in goroutine 1
Dec 18 02:31:29 ksy ollama[2877902]:         net/http/server.go:3290 +0x4b4
Dec 18 02:31:29 ksy ollama[2877902]: goroutine 34 gp=0xc000224000 m=nil [IO wait]:
Dec 18 02:31:29 ksy ollama[2877902]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0xb?)
Dec 18 02:31:29 ksy ollama[2877902]:         runtime/proc.go:402 +0xce fp=0xc0000685a8 sp=0xc000068588 pc=0x556d19c084ee
Dec 18 02:31:29 ksy ollama[2877902]: runtime.netpollblock(0x556d19c6ea38?, 0x19bd1006?, 0x6d?)
Dec 18 02:31:29 ksy ollama[2877902]:         runtime/netpoll.go:573 +0xf7 fp=0xc0000685e0 sp=0xc0000685a8 pc=0x556d19c00737
Dec 18 02:31:29 ksy ollama[2877902]: internal/poll.runtime_pollWait(0x7f7cba9c7f28, 0x72)
Dec 18 02:31:29 ksy ollama[2877902]:         runtime/netpoll.go:345 +0x85 fp=0xc000068600 sp=0xc0000685e0 pc=0x556d19c34f85
Dec 18 02:31:29 ksy ollama[2877902]: internal/poll.(*pollDesc).wait(0xc000120000?, 0xc0000b2e21?, 0x0)
Dec 18 02:31:29 ksy ollama[2877902]:         internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc000068628 sp=0xc000068600 pc=0x556d19c84ea7
Dec 18 02:31:29 ksy ollama[2877902]: internal/poll.(*pollDesc).waitRead(...)
Dec 18 02:31:29 ksy ollama[2877902]:         internal/poll/fd_poll_runtime.go:89
Dec 18 02:31:29 ksy ollama[2877902]: internal/poll.(*FD).Read(0xc000120000, {0xc0000b2e21, 0x1, 0x1})
Dec 18 02:31:29 ksy ollama[2877902]:         internal/poll/fd_unix.go:164 +0x27a fp=0xc0000686c0 sp=0xc000068628 pc=0x556d19c859fa
Dec 18 02:31:29 ksy ollama[2877902]: net.(*netFD).Read(0xc000120000, {0xc0000b2e21?, 0x0?, 0x0?})
Dec 18 02:31:29 ksy ollama[2877902]:         net/fd_posix.go:55 +0x25 fp=0xc000068708 sp=0xc0000686c0 pc=0x556d19cf3ea5
Dec 18 02:31:29 ksy ollama[2877902]: net.(*conn).Read(0xc000114008, {0xc0000b2e21?, 0x0?, 0x0?})
Dec 18 02:31:29 ksy ollama[2877902]:         net/net.go:185 +0x45 fp=0xc000068750 sp=0xc000068708 pc=0x556d19cfe165
Dec 18 02:31:29 ksy ollama[2877902]: net.(*TCPConn).Read(0x0?, {0xc0000b2e21?, 0x0?, 0x0?})
Dec 18 02:31:29 ksy ollama[2877902]:         <autogenerated>:1 +0x25 fp=0xc000068780 sp=0xc000068750 pc=0x556d19d09b45
Dec 18 02:31:29 ksy ollama[2877902]: net/http.(*connReader).backgroundRead(0xc0000b2e10)
Dec 18 02:31:29 ksy ollama[2877902]:         net/http/server.go:681 +0x37 fp=0xc0000687c8 sp=0xc000068780 pc=0x556d19e189d7
Dec 18 02:31:29 ksy ollama[2877902]: net/http.(*connReader).startBackgroundRead.gowrap2()
Dec 18 02:31:29 ksy ollama[2877902]:         net/http/server.go:677 +0x25 fp=0xc0000687e0 sp=0xc0000687c8 pc=0x556d19e18905
Dec 18 02:31:29 ksy ollama[2877902]: runtime.goexit({})
Dec 18 02:31:29 ksy ollama[2877902]:         runtime/asm_amd64.s:1695 +0x1 fp=0xc0000687e8 sp=0xc0000687e0 pc=0x556d19c3a2c1
Dec 18 02:31:29 ksy ollama[2877902]: created by net/http.(*connReader).startBackgroundRead in goroutine 18
Dec 18 02:31:29 ksy ollama[2877902]:         net/http/server.go:677 +0xba
Dec 18 02:31:29 ksy ollama[2877902]: rax    0x204a03fd8
Dec 18 02:31:29 ksy ollama[2877902]: rbx    0x7f7c485e5370
Dec 18 02:31:29 ksy ollama[2877902]: rcx    0xff6
Dec 18 02:31:29 ksy ollama[2877902]: rdx    0x7f7c483fe430
Dec 18 02:31:29 ksy ollama[2877902]: rdi    0x7f7c483fe440
Dec 18 02:31:29 ksy ollama[2877902]: rsi    0x0
Dec 18 02:31:29 ksy ollama[2877902]: rbp    0x7ffd316fc660
Dec 18 02:31:29 ksy ollama[2877902]: rsp    0x7ffd316fc640
Dec 18 02:31:29 ksy ollama[2877902]: r8     0x4
Dec 18 02:31:29 ksy ollama[2877902]: r9     0x0
Dec 18 02:31:29 ksy ollama[2877902]: r10    0x4
Dec 18 02:31:29 ksy ollama[2877902]: r11    0x8
Dec 18 02:31:29 ksy ollama[2877902]: r12    0x556d1ae4f830
Dec 18 02:31:29 ksy ollama[2877902]: r13    0x7f7c483fe440
Dec 18 02:31:29 ksy ollama[2877902]: r14    0x0
Dec 18 02:31:29 ksy ollama[2877902]: r15    0x7f7d0d1557e0
Dec 18 02:31:29 ksy ollama[2877902]: rip    0x7f7cc1f06f77
Dec 18 02:31:29 ksy ollama[2877902]: rflags 0x10297
Dec 18 02:31:29 ksy ollama[2877902]: cs     0x33
Dec 18 02:31:29 ksy ollama[2877902]: fs     0x0
Dec 18 02:31:29 ksy ollama[2877902]: gs     0x0
Dec 18 02:31:29 ksy ollama[2877902]: SIGABRT: abort
Dec 18 02:31:29 ksy ollama[2877902]: PC=0x7f7c9c6419fc m=0 sigcode=18446744073709551610
Dec 18 02:31:29 ksy ollama[2877902]: signal arrived during cgo execution
Dec 18 02:31:29 ksy ollama[2877902]: goroutine 7 gp=0xc000184000 m=0 mp=0x556d1a36cf20 [syscall]:
Dec 18 02:31:29 ksy ollama[2877902]: runtime.cgocall(0x556d19e50a90, 0xc000080b48)
Dec 18 02:31:29 ksy ollama[2877902]:         runtime/cgocall.go:157 +0x4b fp=0xc000080b20 sp=0xc000080ae8 pc=0x556d19bd18ab
Dec 18 02:31:29 ksy ollama[2877902]: github.com/ollama/ollama/llama._Cfunc_llama_decode(0x7f7c48006490, {0x200, 0x7f7c4804a260, 0x0, 0x0, 0x7f7c4804aa70, 0x7f7c4804b280, 0x7f7c4804ba90, 0x7f7c487873d0, 0x0, ...})
Dec 18 02:31:29 ksy ollama[2877902]:         _cgo_gotypes.go:548 +0x52 fp=0xc000080b48 sp=0xc000080b20 pc=0x556d19ccee32
Dec 18 02:31:29 ksy ollama[2877902]: github.com/ollama/ollama/llama.(*Context).Decode.func1(0x556d19e4c4eb?, 0x7f7c48006490?)
Dec 18 02:31:29 ksy ollama[2877902]:         github.com/ollama/ollama/llama/llama.go:189 +0xd8 fp=0xc000080c68 sp=0xc000080b48 pc=0x556d19cd1518
Dec 18 02:31:29 ksy ollama[2877902]: github.com/ollama/ollama/llama.(*Context).Decode(0xc000080d58?, 0x0?)
Dec 18 02:31:29 ksy ollama[2877902]:         github.com/ollama/ollama/llama/llama.go:189 +0x13 fp=0xc000080cb0 sp=0xc000080c68 pc=0x556d19cd13b3
Dec 18 02:31:29 ksy ollama[2877902]: main.(*Server).processBatch(0xc0000ce120, 0xc00011a000, 0xc000080f10)
Dec 18 02:31:29 ksy ollama[2877902]:         github.com/ollama/ollama/llama/runner/runner.go:434 +0x24d fp=0xc000080ed0 sp=0xc000080cb0 pc=0x556d19e4b1ad
Dec 18 02:31:29 ksy ollama[2877902]: main.(*Server).run(0xc0000ce120, {0x556d1a19d9a0, 0xc0000a40a0})
Dec 18 02:31:29 ksy ollama[2877902]:         github.com/ollama/ollama/llama/runner/runner.go:342 +0x1e5 fp=0xc000080fb8 sp=0xc000080ed0 pc=0x556d19e4ac25
Dec 18 02:31:29 ksy ollama[2877902]: main.main.gowrap2()
Dec 18 02:31:29 ksy ollama[2877902]:         github.com/ollama/ollama/llama/runner/runner.go:980 +0x28 fp=0xc000080fe0 sp=0xc000080fb8 pc=0x556d19e4fa88
Dec 18 02:31:29 ksy ollama[2877902]: runtime.goexit({})
Dec 18 02:31:29 ksy ollama[2877902]:         runtime/asm_amd64.s:1695 +0x1 fp=0xc000080fe8 sp=0xc000080fe0 pc=0x556d19c3a2c1
Dec 18 02:31:29 ksy ollama[2877902]: created by main.main in goroutine 1
Dec 18 02:31:29 ksy ollama[2877902]:         github.com/ollama/ollama/llama/runner/runner.go:980 +0xd3e
Dec 18 02:31:29 ksy ollama[2877902]: goroutine 1 gp=0xc0000061c0 m=nil [IO wait]:
Dec 18 02:31:29 ksy ollama[2877902]: runtime.gopark(0x1?, 0xc0000298e0?, 0xd4?, 0x82?, 0xc0000298c0?)
Dec 18 02:31:29 ksy ollama[2877902]:         runtime/proc.go:402 +0xce fp=0xc000029860 sp=0xc000029840 pc=0x556d19c084ee
Dec 18 02:31:29 ksy ollama[2877902]: runtime.netpollblock(0x10?, 0x19bd1006?, 0x6d?)
Dec 18 02:31:29 ksy ollama[2877902]:         runtime/netpoll.go:573 +0xf7 fp=0xc000029898 sp=0xc000029860 pc=0x556d19c00737
Dec 18 02:31:29 ksy ollama[2877902]: internal/poll.runtime_pollWait(0x7f7cba9c8020, 0x72)
Dec 18 02:31:29 ksy ollama[2877902]:         runtime/netpoll.go:345 +0x85 fp=0xc0000298b8 sp=0xc000029898 pc=0x556d19c34f85
Dec 18 02:31:29 ksy ollama[2877902]: internal/poll.(*pollDesc).wait(0x3?, 0x7f7cc14c1368?, 0x0)
Dec 18 02:31:29 ksy ollama[2877902]:         internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc0000298e0 sp=0xc0000298b8 pc=0x556d19c84ea7
Dec 18 02:31:29 ksy ollama[2877902]: internal/poll.(*pollDesc).waitRead(...)
Dec 18 02:31:29 ksy ollama[2877902]:         internal/poll/fd_poll_runtime.go:89
Dec 18 02:31:29 ksy ollama[2877902]: internal/poll.(*FD).Accept(0xc0000fe080)
Dec 18 02:31:29 ksy ollama[2877902]:         internal/poll/fd_unix.go:611 +0x2ac fp=0xc000029988 sp=0xc0000298e0 pc=0x556d19c8636c
Dec 18 02:31:29 ksy ollama[2877902]: net.(*netFD).accept(0xc0000fe080)
Dec 18 02:31:29 ksy ollama[2877902]:         net/fd_unix.go:172 +0x29 fp=0xc000029a40 sp=0xc000029988 pc=0x556d19cf4fa9
Dec 18 02:31:29 ksy ollama[2877902]: net.(*TCPListener).accept(0xc00007c1c0)
Dec 18 02:31:29 ksy ollama[2877902]:         net/tcpsock_posix.go:159 +0x1e fp=0xc000029a68 sp=0xc000029a40 pc=0x556d19d05cde
Dec 18 02:31:29 ksy ollama[2877902]: net.(*TCPListener).Accept(0xc00007c1c0)
Dec 18 02:31:29 ksy ollama[2877902]:         net/tcpsock.go:327 +0x30 fp=0xc000029a98 sp=0xc000029a68 pc=0x556d19d05030
Dec 18 02:31:29 ksy ollama[2877902]: net/http.(*onceCloseListener).Accept(0xc000122000?)
Dec 18 02:31:29 ksy ollama[2877902]:         <autogenerated>:1 +0x24 fp=0xc000029ab0 sp=0xc000029a98 pc=0x556d19e2c244
Dec 18 02:31:29 ksy ollama[2877902]: net/http.(*Server).Serve(0xc0000181e0, {0x556d1a19d360, 0xc00007c1c0})
Dec 18 02:31:29 ksy ollama[2877902]:         net/http/server.go:3260 +0x33e fp=0xc000029be0 sp=0xc000029ab0 pc=0x556d19e2305e
Dec 18 02:31:29 ksy ollama[2877902]: main.main()
Dec 18 02:31:29 ksy ollama[2877902]:         github.com/ollama/ollama/llama/runner/runner.go:1000 +0x10cd fp=0xc000029f50 sp=0xc000029be0 pc=0x556d19e4f80d
Dec 18 02:31:29 ksy ollama[2877902]: runtime.main()
Dec 18 02:31:29 ksy ollama[2877902]:         runtime/proc.go:271 +0x29d fp=0xc000029fe0 sp=0xc000029f50 pc=0x556d19c080bd
Dec 18 02:31:29 ksy ollama[2877902]: runtime.goexit({})
Dec 18 02:31:29 ksy ollama[2877902]:         runtime/asm_amd64.s:1695 +0x1 fp=0xc000029fe8 sp=0xc000029fe0 pc=0x556d19c3a2c1
Dec 18 02:31:29 ksy ollama[2877902]: goroutine 2 gp=0xc000006c40 m=nil [force gc (idle)]:
Dec 18 02:31:29 ksy ollama[2877902]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
Dec 18 02:31:29 ksy ollama[2877902]:         runtime/proc.go:402 +0xce fp=0xc00006cfa8 sp=0xc00006cf88 pc=0x556d19c084ee
Dec 18 02:31:29 ksy ollama[2877902]: runtime.goparkunlock(...)
Dec 18 02:31:29 ksy ollama[2877902]:         runtime/proc.go:408
Dec 18 02:31:29 ksy ollama[2877902]: runtime.forcegchelper()
Dec 18 02:31:29 ksy ollama[2877902]:         runtime/proc.go:326 +0xb8 fp=0xc00006cfe0 sp=0xc00006cfa8 pc=0x556d19c08378
Dec 18 02:31:29 ksy ollama[2877902]: runtime.goexit({})
Dec 18 02:31:29 ksy ollama[2877902]:         runtime/asm_amd64.s:1695 +0x1 fp=0xc00006cfe8 sp=0xc00006cfe0 pc=0x556d19c3a2c1
Dec 18 02:31:29 ksy ollama[2877902]: created by runtime.init.6 in goroutine 1
Dec 18 02:31:29 ksy ollama[2877902]:         runtime/proc.go:314 +0x1a
Dec 18 02:31:29 ksy ollama[2877902]: goroutine 3 gp=0xc000007180 m=nil [GC sweep wait]:
Dec 18 02:31:29 ksy ollama[2877902]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
Dec 18 02:31:29 ksy ollama[2877902]:         runtime/proc.go:402 +0xce fp=0xc00006d780 sp=0xc00006d760 pc=0x556d19c084ee
Dec 18 02:31:29 ksy ollama[2877902]: runtime.goparkunlock(...)
Dec 18 02:31:29 ksy ollama[2877902]:         runtime/proc.go:408
Dec 18 02:31:29 ksy ollama[2877902]: runtime.bgsweep(0xc00007e000)
Dec 18 02:31:29 ksy ollama[2877902]:         runtime/mgcsweep.go:278 +0x94 fp=0xc00006d7c8 sp=0xc00006d780 pc=0x556d19bf3034
Dec 18 02:31:29 ksy ollama[2877902]: runtime.gcenable.gowrap1()
Dec 18 02:31:29 ksy ollama[2877902]:         runtime/mgc.go:203 +0x25 fp=0xc00006d7e0 sp=0xc00006d7c8 pc=0x556d19be7b65
Dec 18 02:31:29 ksy ollama[2877902]: runtime.goexit({})
Dec 18 02:31:29 ksy ollama[2877902]:         runtime/asm_amd64.s:1695 +0x1 fp=0xc00006d7e8 sp=0xc00006d7e0 pc=0x556d19c3a2c1
Dec 18 02:31:29 ksy ollama[2877902]: created by runtime.gcenable in goroutine 1
Dec 18 02:31:29 ksy ollama[2877902]:         runtime/mgc.go:203 +0x66
Dec 18 02:31:29 ksy ollama[2877902]: goroutine 4 gp=0xc000007340 m=nil [GC scavenge wait]:
Dec 18 02:31:29 ksy ollama[2877902]: runtime.gopark(0xc00007e000?, 0x556d1a09a4f0?, 0x1?, 0x0?, 0xc000007340?)
Dec 18 02:31:29 ksy ollama[2877902]:         runtime/proc.go:402 +0xce fp=0xc00006df78 sp=0xc00006df58 pc=0x556d19c084ee
Dec 18 02:31:29 ksy ollama[2877902]: runtime.goparkunlock(...)
Dec 18 02:31:29 ksy ollama[2877902]:         runtime/proc.go:408
Dec 18 02:31:29 ksy ollama[2877902]: runtime.(*scavengerState).park(0x556d1a36c560)
Dec 18 02:31:29 ksy ollama[2877902]:         runtime/mgcscavenge.go:425 +0x49 fp=0xc00006dfa8 sp=0xc00006df78 pc=0x556d19bf0a29
Dec 18 02:31:29 ksy ollama[2877902]: runtime.bgscavenge(0xc00007e000)
Dec 18 02:31:29 ksy ollama[2877902]:         runtime/mgcscavenge.go:653 +0x3c fp=0xc00006dfc8 sp=0xc00006dfa8 pc=0x556d19bf0fbc
Dec 18 02:31:29 ksy ollama[2877902]: runtime.gcenable.gowrap2()
Dec 18 02:31:29 ksy ollama[2877902]:         runtime/mgc.go:204 +0x25 fp=0xc00006dfe0 sp=0xc00006dfc8 pc=0x556d19be7b05
Dec 18 02:31:29 ksy ollama[2877902]: runtime.goexit({})
Dec 18 02:31:29 ksy ollama[2877902]:         runtime/asm_amd64.s:1695 +0x1 fp=0xc00006dfe8 sp=0xc00006dfe0 pc=0x556d19c3a2c1
Dec 18 02:31:29 ksy ollama[2877902]: created by runtime.gcenable in goroutine 1
Dec 18 02:31:29 ksy ollama[2877902]:         runtime/mgc.go:204 +0xa5
Dec 18 02:31:29 ksy ollama[2877902]: goroutine 5 gp=0xc000007c00 m=nil [finalizer wait]:
Dec 18 02:31:29 ksy ollama[2877902]: runtime.gopark(0xc00006c648?, 0x556d19bdb465?, 0xa8?, 0x1?, 0xc0000061c0?)
Dec 18 02:31:29 ksy ollama[2877902]:         runtime/proc.go:402 +0xce fp=0xc00006c620 sp=0xc00006c600 pc=0x556d19c084ee
Dec 18 02:31:29 ksy ollama[2877902]: runtime.runfinq()
Dec 18 02:31:29 ksy ollama[2877902]:         runtime/mfinal.go:194 +0x107 fp=0xc00006c7e0 sp=0xc00006c620 pc=0x556d19be6ba7
Dec 18 02:31:29 ksy ollama[2877902]: runtime.goexit({})
Dec 18 02:31:29 ksy ollama[2877902]:         runtime/asm_amd64.s:1695 +0x1 fp=0xc00006c7e8 sp=0xc00006c7e0 pc=0x556d19c3a2c1
Dec 18 02:31:29 ksy ollama[2877902]: created by runtime.createfing in goroutine 1
Dec 18 02:31:29 ksy ollama[2877902]:         runtime/mfinal.go:164 +0x3d
Dec 18 02:31:29 ksy ollama[2877902]: goroutine 18 gp=0xc000007dc0 m=nil [chan receive]:
Dec 18 02:31:29 ksy ollama[2877902]: runtime.gopark(0x556d19c382d4?, 0xc0000f3890?, 0x65?, 0xa6?, 0xc0000f3878?)
Dec 18 02:31:29 ksy ollama[2877902]:         runtime/proc.go:402 +0xce fp=0xc0000f3858 sp=0xc0000f3838 pc=0x556d19c084ee
Dec 18 02:31:29 ksy ollama[2877902]: runtime.chanrecv(0xc0002000c0, 0xc0000f3a08, 0x1)
Dec 18 02:31:29 ksy ollama[2877902]:         runtime/chan.go:583 +0x3bf fp=0xc0000f38d0 sp=0xc0000f3858 pc=0x556d19bd3ebf
Dec 18 02:31:29 ksy ollama[2877902]: runtime.chanrecv1(0xc000112030?, 0xc00029e000?)
Dec 18 02:31:29 ksy ollama[2877902]:         runtime/chan.go:442 +0x12 fp=0xc0000f38f8 sp=0xc0000f38d0 pc=0x556d19bd3af2
Dec 18 02:31:29 ksy ollama[2877902]: main.(*Server).embeddings(0xc0000ce120, {0x556d1a19d510, 0xc000218000}, 0xc000204000)
Dec 18 02:31:29 ksy ollama[2877902]:         github.com/ollama/ollama/llama/runner/runner.go:793 +0x746 fp=0xc0000f3ab8 sp=0xc0000f38f8 pc=0x556d19e4dc66
Dec 18 02:31:29 ksy ollama[2877902]: main.(*Server).embeddings-fm({0x556d1a19d510?, 0xc000218000?}, 0x556d19e2738d?)
Dec 18 02:31:29 ksy ollama[2877902]:         <autogenerated>:1 +0x36 fp=0xc0000f3ae8 sp=0xc0000f3ab8 pc=0x556d19e50236
Dec 18 02:31:29 ksy ollama[2877902]: net/http.HandlerFunc.ServeHTTP(0xc0000b4d00?, {0x556d1a19d510?, 0xc000218000?}, 0x10?)
Dec 18 02:31:29 ksy ollama[2877902]:         net/http/server.go:2171 +0x29 fp=0xc0000f3b10 sp=0xc0000f3ae8 pc=0x556d19e1fe29
Dec 18 02:31:29 ksy ollama[2877902]: net/http.(*ServeMux).ServeHTTP(0x556d19bdb465?, {0x556d1a19d510, 0xc000218000}, 0xc000204000)
Dec 18 02:31:29 ksy ollama[2877902]:         net/http/server.go:2688 +0x1ad fp=0xc0000f3b60 sp=0xc0000f3b10 pc=0x556d19e21cad
Dec 18 02:31:29 ksy ollama[2877902]: net/http.serverHandler.ServeHTTP({0x556d1a19c860?}, {0x556d1a19d510?, 0xc000218000?}, 0x6?)
Dec 18 02:31:29 ksy ollama[2877902]:         net/http/server.go:3142 +0x8e fp=0xc0000f3b90 sp=0xc0000f3b60 pc=0x556d19e22cce
Dec 18 02:31:29 ksy ollama[2877902]: net/http.(*conn).serve(0xc000122000, {0x556d1a19d968, 0xc0000b2db0})
Dec 18 02:31:29 ksy ollama[2877902]:         net/http/server.go:2044 +0x5e8 fp=0xc0000f3fb8 sp=0xc0000f3b90 pc=0x556d19e1ea68
Dec 18 02:31:29 ksy ollama[2877902]: net/http.(*Server).Serve.gowrap3()
Dec 18 02:31:29 ksy ollama[2877902]:         net/http/server.go:3290 +0x28 fp=0xc0000f3fe0 sp=0xc0000f3fb8 pc=0x556d19e23448
Dec 18 02:31:29 ksy ollama[2877902]: runtime.goexit({})
Dec 18 02:31:29 ksy ollama[2877902]:         runtime/asm_amd64.s:1695 +0x1 fp=0xc0000f3fe8 sp=0xc0000f3fe0 pc=0x556d19c3a2c1
Dec 18 02:31:29 ksy ollama[2877902]: created by net/http.(*Server).Serve in goroutine 1
Dec 18 02:31:29 ksy ollama[2877902]:         net/http/server.go:3290 +0x4b4
Dec 18 02:31:29 ksy ollama[2877902]: goroutine 34 gp=0xc000224000 m=nil [IO wait]:
Dec 18 02:31:29 ksy ollama[2877902]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0xb?)
Dec 18 02:31:29 ksy ollama[2877902]:         runtime/proc.go:402 +0xce fp=0xc0000685a8 sp=0xc000068588 pc=0x556d19c084ee
Dec 18 02:31:29 ksy ollama[2877902]: runtime.netpollblock(0x556d19c6ea38?, 0x19bd1006?, 0x6d?)
Dec 18 02:31:29 ksy ollama[2877902]:         runtime/netpoll.go:573 +0xf7 fp=0xc0000685e0 sp=0xc0000685a8 pc=0x556d19c00737
Dec 18 02:31:29 ksy ollama[2877902]: internal/poll.runtime_pollWait(0x7f7cba9c7f28, 0x72)
Dec 18 02:31:29 ksy ollama[2877902]:         runtime/netpoll.go:345 +0x85 fp=0xc000068600 sp=0xc0000685e0 pc=0x556d19c34f85
Dec 18 02:31:29 ksy ollama[2877902]: internal/poll.(*pollDesc).wait(0xc000120000?, 0xc0000b2e21?, 0x0)
Dec 18 02:31:29 ksy ollama[2877902]:         internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc000068628 sp=0xc000068600 pc=0x556d19c84ea7
Dec 18 02:31:29 ksy ollama[2877902]: internal/poll.(*pollDesc).waitRead(...)
Dec 18 02:31:29 ksy ollama[2877902]:         internal/poll/fd_poll_runtime.go:89
Dec 18 02:31:29 ksy ollama[2877902]: internal/poll.(*FD).Read(0xc000120000, {0xc0000b2e21, 0x1, 0x1})
Dec 18 02:31:29 ksy ollama[2877902]:         internal/poll/fd_unix.go:164 +0x27a fp=0xc0000686c0 sp=0xc000068628 pc=0x556d19c859fa
Dec 18 02:31:29 ksy ollama[2877902]: net.(*netFD).Read(0xc000120000, {0xc0000b2e21?, 0x0?, 0x0?})
Dec 18 02:31:29 ksy ollama[2877902]:         net/fd_posix.go:55 +0x25 fp=0xc000068708 sp=0xc0000686c0 pc=0x556d19cf3ea5
Dec 18 02:31:29 ksy ollama[2877902]: net.(*conn).Read(0xc000114008, {0xc0000b2e21?, 0x0?, 0x0?})
Dec 18 02:31:29 ksy ollama[2877902]:         net/net.go:185 +0x45 fp=0xc000068750 sp=0xc000068708 pc=0x556d19cfe165
Dec 18 02:31:29 ksy ollama[2877902]: net.(*TCPConn).Read(0x0?, {0xc0000b2e21?, 0x0?, 0x0?})
Dec 18 02:31:29 ksy ollama[2877902]:         <autogenerated>:1 +0x25 fp=0xc000068780 sp=0xc000068750 pc=0x556d19d09b45
Dec 18 02:31:29 ksy ollama[2877902]: net/http.(*connReader).backgroundRead(0xc0000b2e10)
Dec 18 02:31:29 ksy ollama[2877902]:         net/http/server.go:681 +0x37 fp=0xc0000687c8 sp=0xc000068780 pc=0x556d19e189d7
Dec 18 02:31:29 ksy ollama[2877902]: net/http.(*connReader).startBackgroundRead.gowrap2()
Dec 18 02:31:29 ksy ollama[2877902]:         net/http/server.go:677 +0x25 fp=0xc0000687e0 sp=0xc0000687c8 pc=0x556d19e18905
Dec 18 02:31:29 ksy ollama[2877902]: runtime.goexit({})
Dec 18 02:31:29 ksy ollama[2877902]:         runtime/asm_amd64.s:1695 +0x1 fp=0xc0000687e8 sp=0xc0000687e0 pc=0x556d19c3a2c1
Dec 18 02:31:29 ksy ollama[2877902]: created by net/http.(*connReader).startBackgroundRead in goroutine 18
Dec 18 02:31:29 ksy ollama[2877902]:         net/http/server.go:677 +0xba
Dec 18 02:31:29 ksy ollama[2877902]: rax    0x0
Dec 18 02:31:29 ksy ollama[2877902]: rbx    0x7f7cc1974000
Dec 18 02:31:29 ksy ollama[2877902]: rcx    0x7f7c9c6419fc
Dec 18 02:31:29 ksy ollama[2877902]: rdx    0x6
Dec 18 02:31:29 ksy ollama[2877902]: rdi    0x2c0d82
Dec 18 02:31:29 ksy ollama[2877902]: rsi    0x2c0d82
Dec 18 02:31:29 ksy ollama[2877902]: rbp    0x2c0d82
Dec 18 02:31:29 ksy ollama[2877902]: rsp    0x7ffd316fc6b0
Dec 18 02:31:29 ksy ollama[2877902]: r8     0x7ffd316fc780
Dec 18 02:31:29 ksy ollama[2877902]: r9     0x7ffd316fc750
Dec 18 02:31:29 ksy ollama[2877902]: r10    0x8
Dec 18 02:31:29 ksy ollama[2877902]: r11    0x246
Dec 18 02:31:29 ksy ollama[2877902]: r12    0x6
Dec 18 02:31:29 ksy ollama[2877902]: r13    0x16
Dec 18 02:31:29 ksy ollama[2877902]: r14    0x0
Dec 18 02:31:29 ksy ollama[2877902]: r15    0x0
Dec 18 02:31:29 ksy ollama[2877902]: rip    0x7f7c9c6419fc
Dec 18 02:31:29 ksy ollama[2877902]: rflags 0x246
Dec 18 02:31:29 ksy ollama[2877902]: cs     0x33
Dec 18 02:31:29 ksy ollama[2877902]: fs     0x0
Dec 18 02:31:29 ksy ollama[2877902]: gs     0x0
Dec 18 02:31:29 ksy ollama[2877902]: time=2024-12-18T02:31:29.804+08:00 level=INFO source=routes.go:507 msg="embedding generation failed: do embedding request: Post \"http://127.0.0.1:45295/embedding\": EOF"
Dec 18 02:31:29 ksy ollama[2877902]: [GIN] 2024/12/18 - 02:31:29 | 500 |  5.564875389s |   192.168.176.6 | POST     "/api/embeddings"
Dec 18 02:31:29 ksy ollama[2877902]: time=2024-12-18T02:31:29.804+08:00 level=DEBUG source=sched.go:466 msg="context for request finished"
Dec 18 02:31:29 ksy ollama[2877902]: time=2024-12-18T02:31:29.804+08:00 level=DEBUG source=sched.go:339 msg="runner with non-zero duration has gone idle, adding timer" modelPath=/data/ollama/blobs/sha256-3757be8630cc587da3948fe2f1fbb646770a18fa04adc57f1c8977dd0e6281fa duration=5m0s
Dec 18 02:31:29 ksy ollama[2877902]: time=2024-12-18T02:31:29.804+08:00 level=DEBUG source=sched.go:357 msg="after processing request finished event" modelPath=/data/ollama/blobs/sha256-3757be8630cc587da3948fe2f1fbb646770a18fa04adc57f1c8977dd0e6281fa refCount=0
Dec 18 02:31:29 ksy ollama[2877902]: time=2024-12-18T02:31:29.815+08:00 level=DEBUG source=server.go:437 msg="llama runner terminated" error="exit status 2"

OS

Linux

GPU

Nvidia

CPU

Intel

Ollama version

0.5.1 (client version is 0.5.3)

Originally created by @9suns on GitHub (Dec 17, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/8140 ### What is the issue? ``` text Dec 18 02:31:29 ksy ollama[2877902]: time=2024-12-18T02:31:29.468+08:00 level=INFO source=.:0 msg="Server listening on 127.0.0.1:45295" Dec 18 02:31:29 ksy ollama[2877902]: llama_model_loader: loaded meta data with 23 key-value pairs and 197 tensors from /data/ollama/blobs/sha256-3757be8630cc587da3948fe2f1fbb646770a18fa04adc57f1c8977dd0e6281fa (version GGUF V3 (latest)) Dec 18 02:31:29 ksy ollama[2877902]: llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output. Dec 18 02:31:29 ksy ollama[2877902]: llama_model_loader: - kv 0: general.architecture str = bert Dec 18 02:31:29 ksy ollama[2877902]: llama_model_loader: - kv 1: general.name str = Dmeta-embedding-zh Dec 18 02:31:29 ksy ollama[2877902]: llama_model_loader: - kv 2: bert.block_count u32 = 12 Dec 18 02:31:29 ksy ollama[2877902]: llama_model_loader: - kv 3: bert.context_length u32 = 1024 Dec 18 02:31:29 ksy ollama[2877902]: llama_model_loader: - kv 4: bert.embedding_length u32 = 768 Dec 18 02:31:29 ksy ollama[2877902]: llama_model_loader: - kv 5: bert.feed_forward_length u32 = 3072 Dec 18 02:31:29 ksy ollama[2877902]: llama_model_loader: - kv 6: bert.attention.head_count u32 = 12 Dec 18 02:31:29 ksy ollama[2877902]: llama_model_loader: - kv 7: bert.attention.layer_norm_epsilon f32 = 0.000000 Dec 18 02:31:29 ksy ollama[2877902]: llama_model_loader: - kv 8: general.file_type u32 = 1 Dec 18 02:31:29 ksy ollama[2877902]: llama_model_loader: - kv 9: bert.attention.causal bool = false Dec 18 02:31:29 ksy ollama[2877902]: llama_model_loader: - kv 10: bert.pooling_type u32 = 2 Dec 18 02:31:29 ksy ollama[2877902]: llama_model_loader: - kv 11: tokenizer.ggml.token_type_count u32 = 2 Dec 18 02:31:29 ksy ollama[2877902]: llama_model_loader: - kv 12: tokenizer.ggml.model str = bert Dec 18 02:31:29 ksy ollama[2877902]: llama_model_loader: - kv 13: tokenizer.ggml.pre str = Dmeta-embedding-zh Dec 18 02:31:29 ksy ollama[2877902]: llama_model_loader: - kv 14: tokenizer.ggml.tokens arr[str,21128] = ["[PAD]", "[unused1]", "[unused2]", "... Dec 18 02:31:29 ksy ollama[2877902]: llama_model_loader: - kv 15: tokenizer.ggml.token_type arr[i32,21128] = [3, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... Dec 18 02:31:29 ksy ollama[2877902]: llama_model_loader: - kv 16: tokenizer.ggml.unknown_token_id u32 = 100 Dec 18 02:31:29 ksy ollama[2877902]: llama_model_loader: - kv 17: tokenizer.ggml.seperator_token_id u32 = 102 Dec 18 02:31:29 ksy ollama[2877902]: llama_model_loader: - kv 18: tokenizer.ggml.padding_token_id u32 = 0 Dec 18 02:31:29 ksy ollama[2877902]: llama_model_loader: - kv 19: tokenizer.ggml.cls_token_id u32 = 101 Dec 18 02:31:29 ksy ollama[2877902]: llama_model_loader: - kv 20: tokenizer.ggml.mask_token_id u32 = 103 Dec 18 02:31:29 ksy ollama[2877902]: llama_model_loader: - kv 21: tokenizer.ggml.bos_token_id u32 = 0 Dec 18 02:31:29 ksy ollama[2877902]: llama_model_loader: - kv 22: tokenizer.ggml.eos_token_id u32 = 2 Dec 18 02:31:29 ksy ollama[2877902]: llama_model_loader: - type f32: 123 tensors Dec 18 02:31:29 ksy ollama[2877902]: llama_model_loader: - type f16: 74 tensors Dec 18 02:31:29 ksy ollama[2877902]: llm_load_vocab: special_eos_id is not in special_eog_ids - the tokenizer config may be incorrect Dec 18 02:31:29 ksy ollama[2877902]: llm_load_vocab: special tokens cache size = 5 Dec 18 02:31:29 ksy ollama[2877902]: llm_load_vocab: token to piece cache size = 0.0769 MB Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: format = GGUF V3 (latest) Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: arch = bert Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: vocab type = WPM Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: n_vocab = 21128 Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: n_merges = 0 Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: vocab_only = 0 Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: n_ctx_train = 1024 Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: n_embd = 768 Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: n_layer = 12 Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: n_head = 12 Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: n_head_kv = 12 Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: n_rot = 64 Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: n_swa = 0 Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: n_embd_head_k = 64 Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: n_embd_head_v = 64 Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: n_gqa = 1 Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: n_embd_k_gqa = 768 Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: n_embd_v_gqa = 768 Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: f_norm_eps = 1.0e-12 Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: f_norm_rms_eps = 0.0e+00 Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: f_clamp_kqv = 0.0e+00 Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: f_max_alibi_bias = 0.0e+00 Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: f_logit_scale = 0.0e+00 Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: n_ff = 3072 Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: n_expert = 0 Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: n_expert_used = 0 Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: causal attn = 0 Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: pooling type = 2 Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: rope type = 2 Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: rope scaling = linear Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: freq_base_train = 10000.0 Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: freq_scale_train = 1 Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: n_ctx_orig_yarn = 1024 Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: rope_finetuned = unknown Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: ssm_d_conv = 0 Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: ssm_d_inner = 0 Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: ssm_d_state = 0 Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: ssm_dt_rank = 0 Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: ssm_dt_b_c_rms = 0 Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: model type = 109M Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: model ftype = F16 Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: model params = 102.07 M Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: model size = 194.92 MiB (16.02 BPW) Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: general.name = Dmeta-embedding-zh Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: BOS token = 0 '[PAD]' Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: EOS token = 2 '[unused2]' Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: UNK token = 100 '[UNK]' Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: SEP token = 102 '[SEP]' Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: PAD token = 0 '[PAD]' Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: CLS token = 101 '[CLS]' Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: MASK token = 103 '[MASK]' Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: LF token = 0 '[PAD]' Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: EOG token = 2 '[unused2]' Dec 18 02:31:29 ksy ollama[2877902]: llm_load_print_meta: max token length = 48 Dec 18 02:31:29 ksy ollama[2877902]: ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no Dec 18 02:31:29 ksy ollama[2877902]: ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no Dec 18 02:31:29 ksy ollama[2877902]: ggml_cuda_init: found 1 CUDA devices: Dec 18 02:31:29 ksy ollama[2877902]: Device 0: NVIDIA GeForce RTX 3090, compute capability 8.6, VMM: yes Dec 18 02:31:29 ksy ollama[2877902]: time=2024-12-18T02:31:29.550+08:00 level=WARN source=sched.go:646 msg="gpu VRAM usage didn't recover within timeout" seconds=5.309635673 model=/data/ollama/blobs/sha256-3757be8630cc587da3948fe2f1fbb646770a18fa04adc57f1c8977dd0e6281fa Dec 18 02:31:29 ksy ollama[2877902]: time=2024-12-18T02:31:29.550+08:00 level=DEBUG source=gpu.go:398 msg="updating system memory data" before.total="31.2 GiB" before.free="22.2 GiB" before.free_swap="7.1 GiB" now.total="31.2 GiB" now.free="22.0 GiB" now.free_swap="7.1 GiB" Dec 18 02:31:29 ksy ollama[2877902]: initializing /usr/lib/x86_64-linux-gnu/libcuda.so.535.161.07 Dec 18 02:31:29 ksy ollama[2877902]: dlsym: cuInit - 0x7f2482655430 Dec 18 02:31:29 ksy ollama[2877902]: dlsym: cuDriverGetVersion - 0x7f2482655450 Dec 18 02:31:29 ksy ollama[2877902]: dlsym: cuDeviceGetCount - 0x7f2482655490 Dec 18 02:31:29 ksy ollama[2877902]: dlsym: cuDeviceGet - 0x7f2482655470 Dec 18 02:31:29 ksy ollama[2877902]: dlsym: cuDeviceGetAttribute - 0x7f2482655570 Dec 18 02:31:29 ksy ollama[2877902]: dlsym: cuDeviceGetUuid - 0x7f24826554d0 Dec 18 02:31:29 ksy ollama[2877902]: dlsym: cuDeviceGetName - 0x7f24826554b0 Dec 18 02:31:29 ksy ollama[2877902]: dlsym: cuCtxCreate_v3 - 0x7f248265d130 Dec 18 02:31:29 ksy ollama[2877902]: dlsym: cuMemGetInfo_v2 - 0x7f2482668600 Dec 18 02:31:29 ksy ollama[2877902]: dlsym: cuCtxDestroy - 0x7f24826b7600 Dec 18 02:31:29 ksy ollama[2877902]: calling cuInit Dec 18 02:31:29 ksy ollama[2877902]: calling cuDriverGetVersion Dec 18 02:31:29 ksy ollama[2877902]: raw version 0x2ef4 Dec 18 02:31:29 ksy ollama[2877902]: CUDA driver version: 12.2 Dec 18 02:31:29 ksy ollama[2877902]: calling cuDeviceGetCount Dec 18 02:31:29 ksy ollama[2877902]: device count 1 Dec 18 02:31:29 ksy ollama[2877902]: llm_load_tensors: ggml ctx size = 0.16 MiB Dec 18 02:31:29 ksy ollama[2877902]: llm_load_tensors: offloading 12 repeating layers to GPU Dec 18 02:31:29 ksy ollama[2877902]: llm_load_tensors: offloading non-repeating layers to GPU Dec 18 02:31:29 ksy ollama[2877902]: llm_load_tensors: offloaded 13/13 layers to GPU Dec 18 02:31:29 ksy ollama[2877902]: llm_load_tensors: CPU buffer size = 32.46 MiB Dec 18 02:31:29 ksy ollama[2877902]: llm_load_tensors: CUDA0 buffer size = 162.46 MiB Dec 18 02:31:29 ksy ollama[2877902]: llama_new_context_with_model: n_ctx = 2048 Dec 18 02:31:29 ksy ollama[2877902]: llama_new_context_with_model: n_batch = 512 Dec 18 02:31:29 ksy ollama[2877902]: llama_new_context_with_model: n_ubatch = 512 Dec 18 02:31:29 ksy ollama[2877902]: llama_new_context_with_model: flash_attn = 0 Dec 18 02:31:29 ksy ollama[2877902]: llama_new_context_with_model: freq_base = 10000.0 Dec 18 02:31:29 ksy ollama[2877902]: llama_new_context_with_model: freq_scale = 1 Dec 18 02:31:29 ksy ollama[2877902]: llama_kv_cache_init: CUDA0 KV buffer size = 72.00 MiB Dec 18 02:31:29 ksy ollama[2877902]: llama_new_context_with_model: KV self size = 72.00 MiB, K (f16): 36.00 MiB, V (f16): 36.00 MiB Dec 18 02:31:29 ksy ollama[2877902]: llama_new_context_with_model: CPU output buffer size = 0.00 MiB Dec 18 02:31:29 ksy ollama[2877902]: llama_new_context_with_model: CUDA0 compute buffer size = 19.00 MiB Dec 18 02:31:29 ksy ollama[2877902]: llama_new_context_with_model: CUDA_Host compute buffer size = 4.01 MiB Dec 18 02:31:29 ksy ollama[2877902]: llama_new_context_with_model: graph nodes = 429 Dec 18 02:31:29 ksy ollama[2877902]: llama_new_context_with_model: graph splits = 2 Dec 18 02:31:29 ksy ollama[2877902]: time=2024-12-18T02:31:29.598+08:00 level=DEBUG source=gpu.go:448 msg="updating cuda memory data" gpu=GPU-f4ac237a-4252-ac0e-b006-d7ae4f03cbf9 name="NVIDIA GeForce RTX 3090" overhead="0 B" before.total="23.7 GiB" before.free="23.4 GiB" now.total="23.7 GiB" now.free="23.0 GiB" now.used="681.8 MiB" Dec 18 02:31:29 ksy ollama[2877902]: releasing cuda driver library Dec 18 02:31:29 ksy ollama[2877902]: time=2024-12-18T02:31:29.598+08:00 level=DEBUG source=sched.go:659 msg="gpu VRAM free memory converged after 5.36 seconds" model=/data/ollama/blobs/sha256-3757be8630cc587da3948fe2f1fbb646770a18fa04adc57f1c8977dd0e6281fa Dec 18 02:31:29 ksy ollama[2877902]: time=2024-12-18T02:31:29.700+08:00 level=INFO source=server.go:615 msg="llama runner started in 0.25 seconds" Dec 18 02:31:29 ksy ollama[2877902]: time=2024-12-18T02:31:29.700+08:00 level=DEBUG source=sched.go:462 msg="finished setting up runner" model=/data/ollama/blobs/sha256-3757be8630cc587da3948fe2f1fbb646770a18fa04adc57f1c8977dd0e6281fa Dec 18 02:31:29 ksy ollama[2877902]: time=2024-12-18T02:31:29.701+08:00 level=DEBUG source=runner.go:752 msg="embedding request" content="I\r\n目录\r\n第 1 章 概述.......................................................................................................................................................... 1\r\n1.1 适用范围.................................................................................................................................................. 1\r\n1.2 遵照标准.................................................................................................................................................. 1\r\n1.3 数据库说明.............................................................................................................................................. 1\r\n1.4 数据同步频率......................................................................................................................................... 2\r\n1.5 数据校验规则说明................................................................................................................................. 3\r\n1.6 数据表常见数据类型说明..................................................................................................................... 3\r\n第 2 章 数据采集内容 ......................................................................................................................................... 5\r\n2.1 实时采集数据表说明............................................................................................................................. 5\r\n2.1.1 患者基本信息表 emr_patient_info ............................................................................................. 5\r\n2.1.2 诊疗活动信息表 emr_activity_info ............................................................................................. 9\r\n2.1.3 传染病报告卡 emr_inf_report ................................................................................................... 14\r\n2.2 常规监测数据表说明........................................................................................................................... 36\r\n2.2.1 门(急)诊病历 emr_outpatient_record ................................................................................. 36\r\n2.2.2 门(急)诊留 观记录 emr_outpatient_obs ............................................................................. 42\r\n2.2.3 入院记录 emr_admission_info .................................................................................................." Dec 18 02:31:29 ksy ollama[2877902]: time=2024-12-18T02:31:29.707+08:00 level=WARN source=runner.go:129 msg="truncating input prompt" limit=2048 prompt=2131 keep=1 new=2048 Dec 18 02:31:29 ksy ollama[2877902]: time=2024-12-18T02:31:29.707+08:00 level=DEBUG source=cache.go:104 msg="loading cache slot" id=0 cache=0 prompt=2048 used=0 remaining=2048 Dec 18 02:31:29 ksy ollama[2877902]: ggml.c:13343: GGML_ASSERT(i01 >= 0 && i01 < ne01) failed Dec 18 02:31:29 ksy ollama[2877902]: SIGSEGV: segmentation violation Dec 18 02:31:29 ksy ollama[2877902]: PC=0x7f7cc1f06f77 m=0 sigcode=1 addr=0x204a03fd8 Dec 18 02:31:29 ksy ollama[2877902]: signal arrived during cgo execution Dec 18 02:31:29 ksy ollama[2877902]: goroutine 7 gp=0xc000184000 m=0 mp=0x556d1a36cf20 [syscall]: Dec 18 02:31:29 ksy ollama[2877902]: runtime.cgocall(0x556d19e50a90, 0xc000080b48) Dec 18 02:31:29 ksy ollama[2877902]: runtime/cgocall.go:157 +0x4b fp=0xc000080b20 sp=0xc000080ae8 pc=0x556d19bd18ab Dec 18 02:31:29 ksy ollama[2877902]: github.com/ollama/ollama/llama._Cfunc_llama_decode(0x7f7c48006490, {0x200, 0x7f7c4804a260, 0x0, 0x0, 0x7f7c4804aa70, 0x7f7c4804b280, 0x7f7c4804ba90, 0x7f7c487873d0, 0x0, ...}) Dec 18 02:31:29 ksy ollama[2877902]: _cgo_gotypes.go:548 +0x52 fp=0xc000080b48 sp=0xc000080b20 pc=0x556d19ccee32 Dec 18 02:31:29 ksy ollama[2877902]: github.com/ollama/ollama/llama.(*Context).Decode.func1(0x556d19e4c4eb?, 0x7f7c48006490?) Dec 18 02:31:29 ksy ollama[2877902]: github.com/ollama/ollama/llama/llama.go:189 +0xd8 fp=0xc000080c68 sp=0xc000080b48 pc=0x556d19cd1518 Dec 18 02:31:29 ksy ollama[2877902]: github.com/ollama/ollama/llama.(*Context).Decode(0xc000080d58?, 0x0?) Dec 18 02:31:29 ksy ollama[2877902]: github.com/ollama/ollama/llama/llama.go:189 +0x13 fp=0xc000080cb0 sp=0xc000080c68 pc=0x556d19cd13b3 Dec 18 02:31:29 ksy ollama[2877902]: main.(*Server).processBatch(0xc0000ce120, 0xc00011a000, 0xc000080f10) Dec 18 02:31:29 ksy ollama[2877902]: github.com/ollama/ollama/llama/runner/runner.go:434 +0x24d fp=0xc000080ed0 sp=0xc000080cb0 pc=0x556d19e4b1ad Dec 18 02:31:29 ksy ollama[2877902]: main.(*Server).run(0xc0000ce120, {0x556d1a19d9a0, 0xc0000a40a0}) Dec 18 02:31:29 ksy ollama[2877902]: github.com/ollama/ollama/llama/runner/runner.go:342 +0x1e5 fp=0xc000080fb8 sp=0xc000080ed0 pc=0x556d19e4ac25 Dec 18 02:31:29 ksy ollama[2877902]: main.main.gowrap2() Dec 18 02:31:29 ksy ollama[2877902]: github.com/ollama/ollama/llama/runner/runner.go:980 +0x28 fp=0xc000080fe0 sp=0xc000080fb8 pc=0x556d19e4fa88 Dec 18 02:31:29 ksy ollama[2877902]: runtime.goexit({}) Dec 18 02:31:29 ksy ollama[2877902]: runtime/asm_amd64.s:1695 +0x1 fp=0xc000080fe8 sp=0xc000080fe0 pc=0x556d19c3a2c1 Dec 18 02:31:29 ksy ollama[2877902]: created by main.main in goroutine 1 Dec 18 02:31:29 ksy ollama[2877902]: github.com/ollama/ollama/llama/runner/runner.go:980 +0xd3e Dec 18 02:31:29 ksy ollama[2877902]: goroutine 1 gp=0xc0000061c0 m=nil [IO wait]: Dec 18 02:31:29 ksy ollama[2877902]: runtime.gopark(0x1?, 0xc0000298e0?, 0xd4?, 0x82?, 0xc0000298c0?) Dec 18 02:31:29 ksy ollama[2877902]: runtime/proc.go:402 +0xce fp=0xc000029860 sp=0xc000029840 pc=0x556d19c084ee Dec 18 02:31:29 ksy ollama[2877902]: runtime.netpollblock(0x10?, 0x19bd1006?, 0x6d?) Dec 18 02:31:29 ksy ollama[2877902]: runtime/netpoll.go:573 +0xf7 fp=0xc000029898 sp=0xc000029860 pc=0x556d19c00737 Dec 18 02:31:29 ksy ollama[2877902]: internal/poll.runtime_pollWait(0x7f7cba9c8020, 0x72) Dec 18 02:31:29 ksy ollama[2877902]: runtime/netpoll.go:345 +0x85 fp=0xc0000298b8 sp=0xc000029898 pc=0x556d19c34f85 Dec 18 02:31:29 ksy ollama[2877902]: internal/poll.(*pollDesc).wait(0x3?, 0x7f7cc14c1368?, 0x0) Dec 18 02:31:29 ksy ollama[2877902]: internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc0000298e0 sp=0xc0000298b8 pc=0x556d19c84ea7 Dec 18 02:31:29 ksy ollama[2877902]: internal/poll.(*pollDesc).waitRead(...) Dec 18 02:31:29 ksy ollama[2877902]: internal/poll/fd_poll_runtime.go:89 Dec 18 02:31:29 ksy ollama[2877902]: internal/poll.(*FD).Accept(0xc0000fe080) Dec 18 02:31:29 ksy ollama[2877902]: internal/poll/fd_unix.go:611 +0x2ac fp=0xc000029988 sp=0xc0000298e0 pc=0x556d19c8636c Dec 18 02:31:29 ksy ollama[2877902]: net.(*netFD).accept(0xc0000fe080) Dec 18 02:31:29 ksy ollama[2877902]: net/fd_unix.go:172 +0x29 fp=0xc000029a40 sp=0xc000029988 pc=0x556d19cf4fa9 Dec 18 02:31:29 ksy ollama[2877902]: net.(*TCPListener).accept(0xc00007c1c0) Dec 18 02:31:29 ksy ollama[2877902]: net/tcpsock_posix.go:159 +0x1e fp=0xc000029a68 sp=0xc000029a40 pc=0x556d19d05cde Dec 18 02:31:29 ksy ollama[2877902]: net.(*TCPListener).Accept(0xc00007c1c0) Dec 18 02:31:29 ksy ollama[2877902]: net/tcpsock.go:327 +0x30 fp=0xc000029a98 sp=0xc000029a68 pc=0x556d19d05030 Dec 18 02:31:29 ksy ollama[2877902]: net/http.(*onceCloseListener).Accept(0xc000122000?) Dec 18 02:31:29 ksy ollama[2877902]: <autogenerated>:1 +0x24 fp=0xc000029ab0 sp=0xc000029a98 pc=0x556d19e2c244 Dec 18 02:31:29 ksy ollama[2877902]: net/http.(*Server).Serve(0xc0000181e0, {0x556d1a19d360, 0xc00007c1c0}) Dec 18 02:31:29 ksy ollama[2877902]: net/http/server.go:3260 +0x33e fp=0xc000029be0 sp=0xc000029ab0 pc=0x556d19e2305e Dec 18 02:31:29 ksy ollama[2877902]: main.main() Dec 18 02:31:29 ksy ollama[2877902]: github.com/ollama/ollama/llama/runner/runner.go:1000 +0x10cd fp=0xc000029f50 sp=0xc000029be0 pc=0x556d19e4f80d Dec 18 02:31:29 ksy ollama[2877902]: runtime.main() Dec 18 02:31:29 ksy ollama[2877902]: runtime/proc.go:271 +0x29d fp=0xc000029fe0 sp=0xc000029f50 pc=0x556d19c080bd Dec 18 02:31:29 ksy ollama[2877902]: runtime.goexit({}) Dec 18 02:31:29 ksy ollama[2877902]: runtime/asm_amd64.s:1695 +0x1 fp=0xc000029fe8 sp=0xc000029fe0 pc=0x556d19c3a2c1 Dec 18 02:31:29 ksy ollama[2877902]: goroutine 2 gp=0xc000006c40 m=nil [force gc (idle)]: Dec 18 02:31:29 ksy ollama[2877902]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) Dec 18 02:31:29 ksy ollama[2877902]: runtime/proc.go:402 +0xce fp=0xc00006cfa8 sp=0xc00006cf88 pc=0x556d19c084ee Dec 18 02:31:29 ksy ollama[2877902]: runtime.goparkunlock(...) Dec 18 02:31:29 ksy ollama[2877902]: runtime/proc.go:408 Dec 18 02:31:29 ksy ollama[2877902]: runtime.forcegchelper() Dec 18 02:31:29 ksy ollama[2877902]: runtime/proc.go:326 +0xb8 fp=0xc00006cfe0 sp=0xc00006cfa8 pc=0x556d19c08378 Dec 18 02:31:29 ksy ollama[2877902]: runtime.goexit({}) Dec 18 02:31:29 ksy ollama[2877902]: runtime/asm_amd64.s:1695 +0x1 fp=0xc00006cfe8 sp=0xc00006cfe0 pc=0x556d19c3a2c1 Dec 18 02:31:29 ksy ollama[2877902]: created by runtime.init.6 in goroutine 1 Dec 18 02:31:29 ksy ollama[2877902]: runtime/proc.go:314 +0x1a Dec 18 02:31:29 ksy ollama[2877902]: goroutine 3 gp=0xc000007180 m=nil [GC sweep wait]: Dec 18 02:31:29 ksy ollama[2877902]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) Dec 18 02:31:29 ksy ollama[2877902]: runtime/proc.go:402 +0xce fp=0xc00006d780 sp=0xc00006d760 pc=0x556d19c084ee Dec 18 02:31:29 ksy ollama[2877902]: runtime.goparkunlock(...) Dec 18 02:31:29 ksy ollama[2877902]: runtime/proc.go:408 Dec 18 02:31:29 ksy ollama[2877902]: runtime.bgsweep(0xc00007e000) Dec 18 02:31:29 ksy ollama[2877902]: runtime/mgcsweep.go:278 +0x94 fp=0xc00006d7c8 sp=0xc00006d780 pc=0x556d19bf3034 Dec 18 02:31:29 ksy ollama[2877902]: runtime.gcenable.gowrap1() Dec 18 02:31:29 ksy ollama[2877902]: runtime/mgc.go:203 +0x25 fp=0xc00006d7e0 sp=0xc00006d7c8 pc=0x556d19be7b65 Dec 18 02:31:29 ksy ollama[2877902]: runtime.goexit({}) Dec 18 02:31:29 ksy ollama[2877902]: runtime/asm_amd64.s:1695 +0x1 fp=0xc00006d7e8 sp=0xc00006d7e0 pc=0x556d19c3a2c1 Dec 18 02:31:29 ksy ollama[2877902]: created by runtime.gcenable in goroutine 1 Dec 18 02:31:29 ksy ollama[2877902]: runtime/mgc.go:203 +0x66 Dec 18 02:31:29 ksy ollama[2877902]: goroutine 4 gp=0xc000007340 m=nil [GC scavenge wait]: Dec 18 02:31:29 ksy ollama[2877902]: runtime.gopark(0xc00007e000?, 0x556d1a09a4f0?, 0x1?, 0x0?, 0xc000007340?) Dec 18 02:31:29 ksy ollama[2877902]: runtime/proc.go:402 +0xce fp=0xc00006df78 sp=0xc00006df58 pc=0x556d19c084ee Dec 18 02:31:29 ksy ollama[2877902]: runtime.goparkunlock(...) Dec 18 02:31:29 ksy ollama[2877902]: runtime/proc.go:408 Dec 18 02:31:29 ksy ollama[2877902]: runtime.(*scavengerState).park(0x556d1a36c560) Dec 18 02:31:29 ksy ollama[2877902]: runtime/mgcscavenge.go:425 +0x49 fp=0xc00006dfa8 sp=0xc00006df78 pc=0x556d19bf0a29 Dec 18 02:31:29 ksy ollama[2877902]: runtime.bgscavenge(0xc00007e000) Dec 18 02:31:29 ksy ollama[2877902]: runtime/mgcscavenge.go:653 +0x3c fp=0xc00006dfc8 sp=0xc00006dfa8 pc=0x556d19bf0fbc Dec 18 02:31:29 ksy ollama[2877902]: runtime.gcenable.gowrap2() Dec 18 02:31:29 ksy ollama[2877902]: runtime/mgc.go:204 +0x25 fp=0xc00006dfe0 sp=0xc00006dfc8 pc=0x556d19be7b05 Dec 18 02:31:29 ksy ollama[2877902]: runtime.goexit({}) Dec 18 02:31:29 ksy ollama[2877902]: runtime/asm_amd64.s:1695 +0x1 fp=0xc00006dfe8 sp=0xc00006dfe0 pc=0x556d19c3a2c1 Dec 18 02:31:29 ksy ollama[2877902]: created by runtime.gcenable in goroutine 1 Dec 18 02:31:29 ksy ollama[2877902]: runtime/mgc.go:204 +0xa5 Dec 18 02:31:29 ksy ollama[2877902]: goroutine 5 gp=0xc000007c00 m=nil [finalizer wait]: Dec 18 02:31:29 ksy ollama[2877902]: runtime.gopark(0xc00006c648?, 0x556d19bdb465?, 0xa8?, 0x1?, 0xc0000061c0?) Dec 18 02:31:29 ksy ollama[2877902]: runtime/proc.go:402 +0xce fp=0xc00006c620 sp=0xc00006c600 pc=0x556d19c084ee Dec 18 02:31:29 ksy ollama[2877902]: runtime.runfinq() Dec 18 02:31:29 ksy ollama[2877902]: runtime/mfinal.go:194 +0x107 fp=0xc00006c7e0 sp=0xc00006c620 pc=0x556d19be6ba7 Dec 18 02:31:29 ksy ollama[2877902]: runtime.goexit({}) Dec 18 02:31:29 ksy ollama[2877902]: runtime/asm_amd64.s:1695 +0x1 fp=0xc00006c7e8 sp=0xc00006c7e0 pc=0x556d19c3a2c1 Dec 18 02:31:29 ksy ollama[2877902]: created by runtime.createfing in goroutine 1 Dec 18 02:31:29 ksy ollama[2877902]: runtime/mfinal.go:164 +0x3d Dec 18 02:31:29 ksy ollama[2877902]: goroutine 18 gp=0xc000007dc0 m=nil [chan receive]: Dec 18 02:31:29 ksy ollama[2877902]: runtime.gopark(0x556d19c382d4?, 0xc0000f3890?, 0x65?, 0xa6?, 0xc0000f3878?) Dec 18 02:31:29 ksy ollama[2877902]: runtime/proc.go:402 +0xce fp=0xc0000f3858 sp=0xc0000f3838 pc=0x556d19c084ee Dec 18 02:31:29 ksy ollama[2877902]: runtime.chanrecv(0xc0002000c0, 0xc0000f3a08, 0x1) Dec 18 02:31:29 ksy ollama[2877902]: runtime/chan.go:583 +0x3bf fp=0xc0000f38d0 sp=0xc0000f3858 pc=0x556d19bd3ebf Dec 18 02:31:29 ksy ollama[2877902]: runtime.chanrecv1(0xc000112030?, 0xc00029e000?) Dec 18 02:31:29 ksy ollama[2877902]: runtime/chan.go:442 +0x12 fp=0xc0000f38f8 sp=0xc0000f38d0 pc=0x556d19bd3af2 Dec 18 02:31:29 ksy ollama[2877902]: main.(*Server).embeddings(0xc0000ce120, {0x556d1a19d510, 0xc000218000}, 0xc000204000) Dec 18 02:31:29 ksy ollama[2877902]: github.com/ollama/ollama/llama/runner/runner.go:793 +0x746 fp=0xc0000f3ab8 sp=0xc0000f38f8 pc=0x556d19e4dc66 Dec 18 02:31:29 ksy ollama[2877902]: main.(*Server).embeddings-fm({0x556d1a19d510?, 0xc000218000?}, 0x556d19e2738d?) Dec 18 02:31:29 ksy ollama[2877902]: <autogenerated>:1 +0x36 fp=0xc0000f3ae8 sp=0xc0000f3ab8 pc=0x556d19e50236 Dec 18 02:31:29 ksy ollama[2877902]: net/http.HandlerFunc.ServeHTTP(0xc0000b4d00?, {0x556d1a19d510?, 0xc000218000?}, 0x10?) Dec 18 02:31:29 ksy ollama[2877902]: net/http/server.go:2171 +0x29 fp=0xc0000f3b10 sp=0xc0000f3ae8 pc=0x556d19e1fe29 Dec 18 02:31:29 ksy ollama[2877902]: net/http.(*ServeMux).ServeHTTP(0x556d19bdb465?, {0x556d1a19d510, 0xc000218000}, 0xc000204000) Dec 18 02:31:29 ksy ollama[2877902]: net/http/server.go:2688 +0x1ad fp=0xc0000f3b60 sp=0xc0000f3b10 pc=0x556d19e21cad Dec 18 02:31:29 ksy ollama[2877902]: net/http.serverHandler.ServeHTTP({0x556d1a19c860?}, {0x556d1a19d510?, 0xc000218000?}, 0x6?) Dec 18 02:31:29 ksy ollama[2877902]: net/http/server.go:3142 +0x8e fp=0xc0000f3b90 sp=0xc0000f3b60 pc=0x556d19e22cce Dec 18 02:31:29 ksy ollama[2877902]: net/http.(*conn).serve(0xc000122000, {0x556d1a19d968, 0xc0000b2db0}) Dec 18 02:31:29 ksy ollama[2877902]: net/http/server.go:2044 +0x5e8 fp=0xc0000f3fb8 sp=0xc0000f3b90 pc=0x556d19e1ea68 Dec 18 02:31:29 ksy ollama[2877902]: net/http.(*Server).Serve.gowrap3() Dec 18 02:31:29 ksy ollama[2877902]: net/http/server.go:3290 +0x28 fp=0xc0000f3fe0 sp=0xc0000f3fb8 pc=0x556d19e23448 Dec 18 02:31:29 ksy ollama[2877902]: runtime.goexit({}) Dec 18 02:31:29 ksy ollama[2877902]: runtime/asm_amd64.s:1695 +0x1 fp=0xc0000f3fe8 sp=0xc0000f3fe0 pc=0x556d19c3a2c1 Dec 18 02:31:29 ksy ollama[2877902]: created by net/http.(*Server).Serve in goroutine 1 Dec 18 02:31:29 ksy ollama[2877902]: net/http/server.go:3290 +0x4b4 Dec 18 02:31:29 ksy ollama[2877902]: goroutine 34 gp=0xc000224000 m=nil [IO wait]: Dec 18 02:31:29 ksy ollama[2877902]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0xb?) Dec 18 02:31:29 ksy ollama[2877902]: runtime/proc.go:402 +0xce fp=0xc0000685a8 sp=0xc000068588 pc=0x556d19c084ee Dec 18 02:31:29 ksy ollama[2877902]: runtime.netpollblock(0x556d19c6ea38?, 0x19bd1006?, 0x6d?) Dec 18 02:31:29 ksy ollama[2877902]: runtime/netpoll.go:573 +0xf7 fp=0xc0000685e0 sp=0xc0000685a8 pc=0x556d19c00737 Dec 18 02:31:29 ksy ollama[2877902]: internal/poll.runtime_pollWait(0x7f7cba9c7f28, 0x72) Dec 18 02:31:29 ksy ollama[2877902]: runtime/netpoll.go:345 +0x85 fp=0xc000068600 sp=0xc0000685e0 pc=0x556d19c34f85 Dec 18 02:31:29 ksy ollama[2877902]: internal/poll.(*pollDesc).wait(0xc000120000?, 0xc0000b2e21?, 0x0) Dec 18 02:31:29 ksy ollama[2877902]: internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc000068628 sp=0xc000068600 pc=0x556d19c84ea7 Dec 18 02:31:29 ksy ollama[2877902]: internal/poll.(*pollDesc).waitRead(...) Dec 18 02:31:29 ksy ollama[2877902]: internal/poll/fd_poll_runtime.go:89 Dec 18 02:31:29 ksy ollama[2877902]: internal/poll.(*FD).Read(0xc000120000, {0xc0000b2e21, 0x1, 0x1}) Dec 18 02:31:29 ksy ollama[2877902]: internal/poll/fd_unix.go:164 +0x27a fp=0xc0000686c0 sp=0xc000068628 pc=0x556d19c859fa Dec 18 02:31:29 ksy ollama[2877902]: net.(*netFD).Read(0xc000120000, {0xc0000b2e21?, 0x0?, 0x0?}) Dec 18 02:31:29 ksy ollama[2877902]: net/fd_posix.go:55 +0x25 fp=0xc000068708 sp=0xc0000686c0 pc=0x556d19cf3ea5 Dec 18 02:31:29 ksy ollama[2877902]: net.(*conn).Read(0xc000114008, {0xc0000b2e21?, 0x0?, 0x0?}) Dec 18 02:31:29 ksy ollama[2877902]: net/net.go:185 +0x45 fp=0xc000068750 sp=0xc000068708 pc=0x556d19cfe165 Dec 18 02:31:29 ksy ollama[2877902]: net.(*TCPConn).Read(0x0?, {0xc0000b2e21?, 0x0?, 0x0?}) Dec 18 02:31:29 ksy ollama[2877902]: <autogenerated>:1 +0x25 fp=0xc000068780 sp=0xc000068750 pc=0x556d19d09b45 Dec 18 02:31:29 ksy ollama[2877902]: net/http.(*connReader).backgroundRead(0xc0000b2e10) Dec 18 02:31:29 ksy ollama[2877902]: net/http/server.go:681 +0x37 fp=0xc0000687c8 sp=0xc000068780 pc=0x556d19e189d7 Dec 18 02:31:29 ksy ollama[2877902]: net/http.(*connReader).startBackgroundRead.gowrap2() Dec 18 02:31:29 ksy ollama[2877902]: net/http/server.go:677 +0x25 fp=0xc0000687e0 sp=0xc0000687c8 pc=0x556d19e18905 Dec 18 02:31:29 ksy ollama[2877902]: runtime.goexit({}) Dec 18 02:31:29 ksy ollama[2877902]: runtime/asm_amd64.s:1695 +0x1 fp=0xc0000687e8 sp=0xc0000687e0 pc=0x556d19c3a2c1 Dec 18 02:31:29 ksy ollama[2877902]: created by net/http.(*connReader).startBackgroundRead in goroutine 18 Dec 18 02:31:29 ksy ollama[2877902]: net/http/server.go:677 +0xba Dec 18 02:31:29 ksy ollama[2877902]: rax 0x204a03fd8 Dec 18 02:31:29 ksy ollama[2877902]: rbx 0x7f7c485e5370 Dec 18 02:31:29 ksy ollama[2877902]: rcx 0xff6 Dec 18 02:31:29 ksy ollama[2877902]: rdx 0x7f7c483fe430 Dec 18 02:31:29 ksy ollama[2877902]: rdi 0x7f7c483fe440 Dec 18 02:31:29 ksy ollama[2877902]: rsi 0x0 Dec 18 02:31:29 ksy ollama[2877902]: rbp 0x7ffd316fc660 Dec 18 02:31:29 ksy ollama[2877902]: rsp 0x7ffd316fc640 Dec 18 02:31:29 ksy ollama[2877902]: r8 0x4 Dec 18 02:31:29 ksy ollama[2877902]: r9 0x0 Dec 18 02:31:29 ksy ollama[2877902]: r10 0x4 Dec 18 02:31:29 ksy ollama[2877902]: r11 0x8 Dec 18 02:31:29 ksy ollama[2877902]: r12 0x556d1ae4f830 Dec 18 02:31:29 ksy ollama[2877902]: r13 0x7f7c483fe440 Dec 18 02:31:29 ksy ollama[2877902]: r14 0x0 Dec 18 02:31:29 ksy ollama[2877902]: r15 0x7f7d0d1557e0 Dec 18 02:31:29 ksy ollama[2877902]: rip 0x7f7cc1f06f77 Dec 18 02:31:29 ksy ollama[2877902]: rflags 0x10297 Dec 18 02:31:29 ksy ollama[2877902]: cs 0x33 Dec 18 02:31:29 ksy ollama[2877902]: fs 0x0 Dec 18 02:31:29 ksy ollama[2877902]: gs 0x0 Dec 18 02:31:29 ksy ollama[2877902]: SIGABRT: abort Dec 18 02:31:29 ksy ollama[2877902]: PC=0x7f7c9c6419fc m=0 sigcode=18446744073709551610 Dec 18 02:31:29 ksy ollama[2877902]: signal arrived during cgo execution Dec 18 02:31:29 ksy ollama[2877902]: goroutine 7 gp=0xc000184000 m=0 mp=0x556d1a36cf20 [syscall]: Dec 18 02:31:29 ksy ollama[2877902]: runtime.cgocall(0x556d19e50a90, 0xc000080b48) Dec 18 02:31:29 ksy ollama[2877902]: runtime/cgocall.go:157 +0x4b fp=0xc000080b20 sp=0xc000080ae8 pc=0x556d19bd18ab Dec 18 02:31:29 ksy ollama[2877902]: github.com/ollama/ollama/llama._Cfunc_llama_decode(0x7f7c48006490, {0x200, 0x7f7c4804a260, 0x0, 0x0, 0x7f7c4804aa70, 0x7f7c4804b280, 0x7f7c4804ba90, 0x7f7c487873d0, 0x0, ...}) Dec 18 02:31:29 ksy ollama[2877902]: _cgo_gotypes.go:548 +0x52 fp=0xc000080b48 sp=0xc000080b20 pc=0x556d19ccee32 Dec 18 02:31:29 ksy ollama[2877902]: github.com/ollama/ollama/llama.(*Context).Decode.func1(0x556d19e4c4eb?, 0x7f7c48006490?) Dec 18 02:31:29 ksy ollama[2877902]: github.com/ollama/ollama/llama/llama.go:189 +0xd8 fp=0xc000080c68 sp=0xc000080b48 pc=0x556d19cd1518 Dec 18 02:31:29 ksy ollama[2877902]: github.com/ollama/ollama/llama.(*Context).Decode(0xc000080d58?, 0x0?) Dec 18 02:31:29 ksy ollama[2877902]: github.com/ollama/ollama/llama/llama.go:189 +0x13 fp=0xc000080cb0 sp=0xc000080c68 pc=0x556d19cd13b3 Dec 18 02:31:29 ksy ollama[2877902]: main.(*Server).processBatch(0xc0000ce120, 0xc00011a000, 0xc000080f10) Dec 18 02:31:29 ksy ollama[2877902]: github.com/ollama/ollama/llama/runner/runner.go:434 +0x24d fp=0xc000080ed0 sp=0xc000080cb0 pc=0x556d19e4b1ad Dec 18 02:31:29 ksy ollama[2877902]: main.(*Server).run(0xc0000ce120, {0x556d1a19d9a0, 0xc0000a40a0}) Dec 18 02:31:29 ksy ollama[2877902]: github.com/ollama/ollama/llama/runner/runner.go:342 +0x1e5 fp=0xc000080fb8 sp=0xc000080ed0 pc=0x556d19e4ac25 Dec 18 02:31:29 ksy ollama[2877902]: main.main.gowrap2() Dec 18 02:31:29 ksy ollama[2877902]: github.com/ollama/ollama/llama/runner/runner.go:980 +0x28 fp=0xc000080fe0 sp=0xc000080fb8 pc=0x556d19e4fa88 Dec 18 02:31:29 ksy ollama[2877902]: runtime.goexit({}) Dec 18 02:31:29 ksy ollama[2877902]: runtime/asm_amd64.s:1695 +0x1 fp=0xc000080fe8 sp=0xc000080fe0 pc=0x556d19c3a2c1 Dec 18 02:31:29 ksy ollama[2877902]: created by main.main in goroutine 1 Dec 18 02:31:29 ksy ollama[2877902]: github.com/ollama/ollama/llama/runner/runner.go:980 +0xd3e Dec 18 02:31:29 ksy ollama[2877902]: goroutine 1 gp=0xc0000061c0 m=nil [IO wait]: Dec 18 02:31:29 ksy ollama[2877902]: runtime.gopark(0x1?, 0xc0000298e0?, 0xd4?, 0x82?, 0xc0000298c0?) Dec 18 02:31:29 ksy ollama[2877902]: runtime/proc.go:402 +0xce fp=0xc000029860 sp=0xc000029840 pc=0x556d19c084ee Dec 18 02:31:29 ksy ollama[2877902]: runtime.netpollblock(0x10?, 0x19bd1006?, 0x6d?) Dec 18 02:31:29 ksy ollama[2877902]: runtime/netpoll.go:573 +0xf7 fp=0xc000029898 sp=0xc000029860 pc=0x556d19c00737 Dec 18 02:31:29 ksy ollama[2877902]: internal/poll.runtime_pollWait(0x7f7cba9c8020, 0x72) Dec 18 02:31:29 ksy ollama[2877902]: runtime/netpoll.go:345 +0x85 fp=0xc0000298b8 sp=0xc000029898 pc=0x556d19c34f85 Dec 18 02:31:29 ksy ollama[2877902]: internal/poll.(*pollDesc).wait(0x3?, 0x7f7cc14c1368?, 0x0) Dec 18 02:31:29 ksy ollama[2877902]: internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc0000298e0 sp=0xc0000298b8 pc=0x556d19c84ea7 Dec 18 02:31:29 ksy ollama[2877902]: internal/poll.(*pollDesc).waitRead(...) Dec 18 02:31:29 ksy ollama[2877902]: internal/poll/fd_poll_runtime.go:89 Dec 18 02:31:29 ksy ollama[2877902]: internal/poll.(*FD).Accept(0xc0000fe080) Dec 18 02:31:29 ksy ollama[2877902]: internal/poll/fd_unix.go:611 +0x2ac fp=0xc000029988 sp=0xc0000298e0 pc=0x556d19c8636c Dec 18 02:31:29 ksy ollama[2877902]: net.(*netFD).accept(0xc0000fe080) Dec 18 02:31:29 ksy ollama[2877902]: net/fd_unix.go:172 +0x29 fp=0xc000029a40 sp=0xc000029988 pc=0x556d19cf4fa9 Dec 18 02:31:29 ksy ollama[2877902]: net.(*TCPListener).accept(0xc00007c1c0) Dec 18 02:31:29 ksy ollama[2877902]: net/tcpsock_posix.go:159 +0x1e fp=0xc000029a68 sp=0xc000029a40 pc=0x556d19d05cde Dec 18 02:31:29 ksy ollama[2877902]: net.(*TCPListener).Accept(0xc00007c1c0) Dec 18 02:31:29 ksy ollama[2877902]: net/tcpsock.go:327 +0x30 fp=0xc000029a98 sp=0xc000029a68 pc=0x556d19d05030 Dec 18 02:31:29 ksy ollama[2877902]: net/http.(*onceCloseListener).Accept(0xc000122000?) Dec 18 02:31:29 ksy ollama[2877902]: <autogenerated>:1 +0x24 fp=0xc000029ab0 sp=0xc000029a98 pc=0x556d19e2c244 Dec 18 02:31:29 ksy ollama[2877902]: net/http.(*Server).Serve(0xc0000181e0, {0x556d1a19d360, 0xc00007c1c0}) Dec 18 02:31:29 ksy ollama[2877902]: net/http/server.go:3260 +0x33e fp=0xc000029be0 sp=0xc000029ab0 pc=0x556d19e2305e Dec 18 02:31:29 ksy ollama[2877902]: main.main() Dec 18 02:31:29 ksy ollama[2877902]: github.com/ollama/ollama/llama/runner/runner.go:1000 +0x10cd fp=0xc000029f50 sp=0xc000029be0 pc=0x556d19e4f80d Dec 18 02:31:29 ksy ollama[2877902]: runtime.main() Dec 18 02:31:29 ksy ollama[2877902]: runtime/proc.go:271 +0x29d fp=0xc000029fe0 sp=0xc000029f50 pc=0x556d19c080bd Dec 18 02:31:29 ksy ollama[2877902]: runtime.goexit({}) Dec 18 02:31:29 ksy ollama[2877902]: runtime/asm_amd64.s:1695 +0x1 fp=0xc000029fe8 sp=0xc000029fe0 pc=0x556d19c3a2c1 Dec 18 02:31:29 ksy ollama[2877902]: goroutine 2 gp=0xc000006c40 m=nil [force gc (idle)]: Dec 18 02:31:29 ksy ollama[2877902]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) Dec 18 02:31:29 ksy ollama[2877902]: runtime/proc.go:402 +0xce fp=0xc00006cfa8 sp=0xc00006cf88 pc=0x556d19c084ee Dec 18 02:31:29 ksy ollama[2877902]: runtime.goparkunlock(...) Dec 18 02:31:29 ksy ollama[2877902]: runtime/proc.go:408 Dec 18 02:31:29 ksy ollama[2877902]: runtime.forcegchelper() Dec 18 02:31:29 ksy ollama[2877902]: runtime/proc.go:326 +0xb8 fp=0xc00006cfe0 sp=0xc00006cfa8 pc=0x556d19c08378 Dec 18 02:31:29 ksy ollama[2877902]: runtime.goexit({}) Dec 18 02:31:29 ksy ollama[2877902]: runtime/asm_amd64.s:1695 +0x1 fp=0xc00006cfe8 sp=0xc00006cfe0 pc=0x556d19c3a2c1 Dec 18 02:31:29 ksy ollama[2877902]: created by runtime.init.6 in goroutine 1 Dec 18 02:31:29 ksy ollama[2877902]: runtime/proc.go:314 +0x1a Dec 18 02:31:29 ksy ollama[2877902]: goroutine 3 gp=0xc000007180 m=nil [GC sweep wait]: Dec 18 02:31:29 ksy ollama[2877902]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) Dec 18 02:31:29 ksy ollama[2877902]: runtime/proc.go:402 +0xce fp=0xc00006d780 sp=0xc00006d760 pc=0x556d19c084ee Dec 18 02:31:29 ksy ollama[2877902]: runtime.goparkunlock(...) Dec 18 02:31:29 ksy ollama[2877902]: runtime/proc.go:408 Dec 18 02:31:29 ksy ollama[2877902]: runtime.bgsweep(0xc00007e000) Dec 18 02:31:29 ksy ollama[2877902]: runtime/mgcsweep.go:278 +0x94 fp=0xc00006d7c8 sp=0xc00006d780 pc=0x556d19bf3034 Dec 18 02:31:29 ksy ollama[2877902]: runtime.gcenable.gowrap1() Dec 18 02:31:29 ksy ollama[2877902]: runtime/mgc.go:203 +0x25 fp=0xc00006d7e0 sp=0xc00006d7c8 pc=0x556d19be7b65 Dec 18 02:31:29 ksy ollama[2877902]: runtime.goexit({}) Dec 18 02:31:29 ksy ollama[2877902]: runtime/asm_amd64.s:1695 +0x1 fp=0xc00006d7e8 sp=0xc00006d7e0 pc=0x556d19c3a2c1 Dec 18 02:31:29 ksy ollama[2877902]: created by runtime.gcenable in goroutine 1 Dec 18 02:31:29 ksy ollama[2877902]: runtime/mgc.go:203 +0x66 Dec 18 02:31:29 ksy ollama[2877902]: goroutine 4 gp=0xc000007340 m=nil [GC scavenge wait]: Dec 18 02:31:29 ksy ollama[2877902]: runtime.gopark(0xc00007e000?, 0x556d1a09a4f0?, 0x1?, 0x0?, 0xc000007340?) Dec 18 02:31:29 ksy ollama[2877902]: runtime/proc.go:402 +0xce fp=0xc00006df78 sp=0xc00006df58 pc=0x556d19c084ee Dec 18 02:31:29 ksy ollama[2877902]: runtime.goparkunlock(...) Dec 18 02:31:29 ksy ollama[2877902]: runtime/proc.go:408 Dec 18 02:31:29 ksy ollama[2877902]: runtime.(*scavengerState).park(0x556d1a36c560) Dec 18 02:31:29 ksy ollama[2877902]: runtime/mgcscavenge.go:425 +0x49 fp=0xc00006dfa8 sp=0xc00006df78 pc=0x556d19bf0a29 Dec 18 02:31:29 ksy ollama[2877902]: runtime.bgscavenge(0xc00007e000) Dec 18 02:31:29 ksy ollama[2877902]: runtime/mgcscavenge.go:653 +0x3c fp=0xc00006dfc8 sp=0xc00006dfa8 pc=0x556d19bf0fbc Dec 18 02:31:29 ksy ollama[2877902]: runtime.gcenable.gowrap2() Dec 18 02:31:29 ksy ollama[2877902]: runtime/mgc.go:204 +0x25 fp=0xc00006dfe0 sp=0xc00006dfc8 pc=0x556d19be7b05 Dec 18 02:31:29 ksy ollama[2877902]: runtime.goexit({}) Dec 18 02:31:29 ksy ollama[2877902]: runtime/asm_amd64.s:1695 +0x1 fp=0xc00006dfe8 sp=0xc00006dfe0 pc=0x556d19c3a2c1 Dec 18 02:31:29 ksy ollama[2877902]: created by runtime.gcenable in goroutine 1 Dec 18 02:31:29 ksy ollama[2877902]: runtime/mgc.go:204 +0xa5 Dec 18 02:31:29 ksy ollama[2877902]: goroutine 5 gp=0xc000007c00 m=nil [finalizer wait]: Dec 18 02:31:29 ksy ollama[2877902]: runtime.gopark(0xc00006c648?, 0x556d19bdb465?, 0xa8?, 0x1?, 0xc0000061c0?) Dec 18 02:31:29 ksy ollama[2877902]: runtime/proc.go:402 +0xce fp=0xc00006c620 sp=0xc00006c600 pc=0x556d19c084ee Dec 18 02:31:29 ksy ollama[2877902]: runtime.runfinq() Dec 18 02:31:29 ksy ollama[2877902]: runtime/mfinal.go:194 +0x107 fp=0xc00006c7e0 sp=0xc00006c620 pc=0x556d19be6ba7 Dec 18 02:31:29 ksy ollama[2877902]: runtime.goexit({}) Dec 18 02:31:29 ksy ollama[2877902]: runtime/asm_amd64.s:1695 +0x1 fp=0xc00006c7e8 sp=0xc00006c7e0 pc=0x556d19c3a2c1 Dec 18 02:31:29 ksy ollama[2877902]: created by runtime.createfing in goroutine 1 Dec 18 02:31:29 ksy ollama[2877902]: runtime/mfinal.go:164 +0x3d Dec 18 02:31:29 ksy ollama[2877902]: goroutine 18 gp=0xc000007dc0 m=nil [chan receive]: Dec 18 02:31:29 ksy ollama[2877902]: runtime.gopark(0x556d19c382d4?, 0xc0000f3890?, 0x65?, 0xa6?, 0xc0000f3878?) Dec 18 02:31:29 ksy ollama[2877902]: runtime/proc.go:402 +0xce fp=0xc0000f3858 sp=0xc0000f3838 pc=0x556d19c084ee Dec 18 02:31:29 ksy ollama[2877902]: runtime.chanrecv(0xc0002000c0, 0xc0000f3a08, 0x1) Dec 18 02:31:29 ksy ollama[2877902]: runtime/chan.go:583 +0x3bf fp=0xc0000f38d0 sp=0xc0000f3858 pc=0x556d19bd3ebf Dec 18 02:31:29 ksy ollama[2877902]: runtime.chanrecv1(0xc000112030?, 0xc00029e000?) Dec 18 02:31:29 ksy ollama[2877902]: runtime/chan.go:442 +0x12 fp=0xc0000f38f8 sp=0xc0000f38d0 pc=0x556d19bd3af2 Dec 18 02:31:29 ksy ollama[2877902]: main.(*Server).embeddings(0xc0000ce120, {0x556d1a19d510, 0xc000218000}, 0xc000204000) Dec 18 02:31:29 ksy ollama[2877902]: github.com/ollama/ollama/llama/runner/runner.go:793 +0x746 fp=0xc0000f3ab8 sp=0xc0000f38f8 pc=0x556d19e4dc66 Dec 18 02:31:29 ksy ollama[2877902]: main.(*Server).embeddings-fm({0x556d1a19d510?, 0xc000218000?}, 0x556d19e2738d?) Dec 18 02:31:29 ksy ollama[2877902]: <autogenerated>:1 +0x36 fp=0xc0000f3ae8 sp=0xc0000f3ab8 pc=0x556d19e50236 Dec 18 02:31:29 ksy ollama[2877902]: net/http.HandlerFunc.ServeHTTP(0xc0000b4d00?, {0x556d1a19d510?, 0xc000218000?}, 0x10?) Dec 18 02:31:29 ksy ollama[2877902]: net/http/server.go:2171 +0x29 fp=0xc0000f3b10 sp=0xc0000f3ae8 pc=0x556d19e1fe29 Dec 18 02:31:29 ksy ollama[2877902]: net/http.(*ServeMux).ServeHTTP(0x556d19bdb465?, {0x556d1a19d510, 0xc000218000}, 0xc000204000) Dec 18 02:31:29 ksy ollama[2877902]: net/http/server.go:2688 +0x1ad fp=0xc0000f3b60 sp=0xc0000f3b10 pc=0x556d19e21cad Dec 18 02:31:29 ksy ollama[2877902]: net/http.serverHandler.ServeHTTP({0x556d1a19c860?}, {0x556d1a19d510?, 0xc000218000?}, 0x6?) Dec 18 02:31:29 ksy ollama[2877902]: net/http/server.go:3142 +0x8e fp=0xc0000f3b90 sp=0xc0000f3b60 pc=0x556d19e22cce Dec 18 02:31:29 ksy ollama[2877902]: net/http.(*conn).serve(0xc000122000, {0x556d1a19d968, 0xc0000b2db0}) Dec 18 02:31:29 ksy ollama[2877902]: net/http/server.go:2044 +0x5e8 fp=0xc0000f3fb8 sp=0xc0000f3b90 pc=0x556d19e1ea68 Dec 18 02:31:29 ksy ollama[2877902]: net/http.(*Server).Serve.gowrap3() Dec 18 02:31:29 ksy ollama[2877902]: net/http/server.go:3290 +0x28 fp=0xc0000f3fe0 sp=0xc0000f3fb8 pc=0x556d19e23448 Dec 18 02:31:29 ksy ollama[2877902]: runtime.goexit({}) Dec 18 02:31:29 ksy ollama[2877902]: runtime/asm_amd64.s:1695 +0x1 fp=0xc0000f3fe8 sp=0xc0000f3fe0 pc=0x556d19c3a2c1 Dec 18 02:31:29 ksy ollama[2877902]: created by net/http.(*Server).Serve in goroutine 1 Dec 18 02:31:29 ksy ollama[2877902]: net/http/server.go:3290 +0x4b4 Dec 18 02:31:29 ksy ollama[2877902]: goroutine 34 gp=0xc000224000 m=nil [IO wait]: Dec 18 02:31:29 ksy ollama[2877902]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0xb?) Dec 18 02:31:29 ksy ollama[2877902]: runtime/proc.go:402 +0xce fp=0xc0000685a8 sp=0xc000068588 pc=0x556d19c084ee Dec 18 02:31:29 ksy ollama[2877902]: runtime.netpollblock(0x556d19c6ea38?, 0x19bd1006?, 0x6d?) Dec 18 02:31:29 ksy ollama[2877902]: runtime/netpoll.go:573 +0xf7 fp=0xc0000685e0 sp=0xc0000685a8 pc=0x556d19c00737 Dec 18 02:31:29 ksy ollama[2877902]: internal/poll.runtime_pollWait(0x7f7cba9c7f28, 0x72) Dec 18 02:31:29 ksy ollama[2877902]: runtime/netpoll.go:345 +0x85 fp=0xc000068600 sp=0xc0000685e0 pc=0x556d19c34f85 Dec 18 02:31:29 ksy ollama[2877902]: internal/poll.(*pollDesc).wait(0xc000120000?, 0xc0000b2e21?, 0x0) Dec 18 02:31:29 ksy ollama[2877902]: internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc000068628 sp=0xc000068600 pc=0x556d19c84ea7 Dec 18 02:31:29 ksy ollama[2877902]: internal/poll.(*pollDesc).waitRead(...) Dec 18 02:31:29 ksy ollama[2877902]: internal/poll/fd_poll_runtime.go:89 Dec 18 02:31:29 ksy ollama[2877902]: internal/poll.(*FD).Read(0xc000120000, {0xc0000b2e21, 0x1, 0x1}) Dec 18 02:31:29 ksy ollama[2877902]: internal/poll/fd_unix.go:164 +0x27a fp=0xc0000686c0 sp=0xc000068628 pc=0x556d19c859fa Dec 18 02:31:29 ksy ollama[2877902]: net.(*netFD).Read(0xc000120000, {0xc0000b2e21?, 0x0?, 0x0?}) Dec 18 02:31:29 ksy ollama[2877902]: net/fd_posix.go:55 +0x25 fp=0xc000068708 sp=0xc0000686c0 pc=0x556d19cf3ea5 Dec 18 02:31:29 ksy ollama[2877902]: net.(*conn).Read(0xc000114008, {0xc0000b2e21?, 0x0?, 0x0?}) Dec 18 02:31:29 ksy ollama[2877902]: net/net.go:185 +0x45 fp=0xc000068750 sp=0xc000068708 pc=0x556d19cfe165 Dec 18 02:31:29 ksy ollama[2877902]: net.(*TCPConn).Read(0x0?, {0xc0000b2e21?, 0x0?, 0x0?}) Dec 18 02:31:29 ksy ollama[2877902]: <autogenerated>:1 +0x25 fp=0xc000068780 sp=0xc000068750 pc=0x556d19d09b45 Dec 18 02:31:29 ksy ollama[2877902]: net/http.(*connReader).backgroundRead(0xc0000b2e10) Dec 18 02:31:29 ksy ollama[2877902]: net/http/server.go:681 +0x37 fp=0xc0000687c8 sp=0xc000068780 pc=0x556d19e189d7 Dec 18 02:31:29 ksy ollama[2877902]: net/http.(*connReader).startBackgroundRead.gowrap2() Dec 18 02:31:29 ksy ollama[2877902]: net/http/server.go:677 +0x25 fp=0xc0000687e0 sp=0xc0000687c8 pc=0x556d19e18905 Dec 18 02:31:29 ksy ollama[2877902]: runtime.goexit({}) Dec 18 02:31:29 ksy ollama[2877902]: runtime/asm_amd64.s:1695 +0x1 fp=0xc0000687e8 sp=0xc0000687e0 pc=0x556d19c3a2c1 Dec 18 02:31:29 ksy ollama[2877902]: created by net/http.(*connReader).startBackgroundRead in goroutine 18 Dec 18 02:31:29 ksy ollama[2877902]: net/http/server.go:677 +0xba Dec 18 02:31:29 ksy ollama[2877902]: rax 0x0 Dec 18 02:31:29 ksy ollama[2877902]: rbx 0x7f7cc1974000 Dec 18 02:31:29 ksy ollama[2877902]: rcx 0x7f7c9c6419fc Dec 18 02:31:29 ksy ollama[2877902]: rdx 0x6 Dec 18 02:31:29 ksy ollama[2877902]: rdi 0x2c0d82 Dec 18 02:31:29 ksy ollama[2877902]: rsi 0x2c0d82 Dec 18 02:31:29 ksy ollama[2877902]: rbp 0x2c0d82 Dec 18 02:31:29 ksy ollama[2877902]: rsp 0x7ffd316fc6b0 Dec 18 02:31:29 ksy ollama[2877902]: r8 0x7ffd316fc780 Dec 18 02:31:29 ksy ollama[2877902]: r9 0x7ffd316fc750 Dec 18 02:31:29 ksy ollama[2877902]: r10 0x8 Dec 18 02:31:29 ksy ollama[2877902]: r11 0x246 Dec 18 02:31:29 ksy ollama[2877902]: r12 0x6 Dec 18 02:31:29 ksy ollama[2877902]: r13 0x16 Dec 18 02:31:29 ksy ollama[2877902]: r14 0x0 Dec 18 02:31:29 ksy ollama[2877902]: r15 0x0 Dec 18 02:31:29 ksy ollama[2877902]: rip 0x7f7c9c6419fc Dec 18 02:31:29 ksy ollama[2877902]: rflags 0x246 Dec 18 02:31:29 ksy ollama[2877902]: cs 0x33 Dec 18 02:31:29 ksy ollama[2877902]: fs 0x0 Dec 18 02:31:29 ksy ollama[2877902]: gs 0x0 Dec 18 02:31:29 ksy ollama[2877902]: time=2024-12-18T02:31:29.804+08:00 level=INFO source=routes.go:507 msg="embedding generation failed: do embedding request: Post \"http://127.0.0.1:45295/embedding\": EOF" Dec 18 02:31:29 ksy ollama[2877902]: [GIN] 2024/12/18 - 02:31:29 | 500 | 5.564875389s | 192.168.176.6 | POST "/api/embeddings" Dec 18 02:31:29 ksy ollama[2877902]: time=2024-12-18T02:31:29.804+08:00 level=DEBUG source=sched.go:466 msg="context for request finished" Dec 18 02:31:29 ksy ollama[2877902]: time=2024-12-18T02:31:29.804+08:00 level=DEBUG source=sched.go:339 msg="runner with non-zero duration has gone idle, adding timer" modelPath=/data/ollama/blobs/sha256-3757be8630cc587da3948fe2f1fbb646770a18fa04adc57f1c8977dd0e6281fa duration=5m0s Dec 18 02:31:29 ksy ollama[2877902]: time=2024-12-18T02:31:29.804+08:00 level=DEBUG source=sched.go:357 msg="after processing request finished event" modelPath=/data/ollama/blobs/sha256-3757be8630cc587da3948fe2f1fbb646770a18fa04adc57f1c8977dd0e6281fa refCount=0 Dec 18 02:31:29 ksy ollama[2877902]: time=2024-12-18T02:31:29.815+08:00 level=DEBUG source=server.go:437 msg="llama runner terminated" error="exit status 2" ``` ### OS Linux ### GPU Nvidia ### CPU Intel ### Ollama version 0.5.1 (client version is 0.5.3)
GiteaMirror added the bug label 2026-05-04 09:43:52 -05:00
Author
Owner

@jessegross commented on GitHub (Dec 18, 2024):

Does it help it you set num_ctx to 1024 or less?

<!-- gh-comment-id:2550189199 --> @jessegross commented on GitHub (Dec 18, 2024): Does it help it you set num_ctx to 1024 or less?
Author
Owner

@9suns commented on GitHub (Dec 18, 2024):

Does it help it you set num_ctx to 1024 or less?

The default value should be 1024.
But success after config the num_ctx to 512.

Thanks for your help, this issue can be closed now.

<!-- gh-comment-id:2550214091 --> @9suns commented on GitHub (Dec 18, 2024): > Does it help it you set num_ctx to 1024 or less? The default value should be 1024. But success after config the num_ctx to 512. Thanks for your help, this issue can be closed now.
Author
Owner

@shaozi commented on GitHub (Jun 24, 2025):

I ran into the same issue when using the embedding api. changing num_ctx to 512 fixed the crash. But WHY? @jessegross

<!-- gh-comment-id:3001698834 --> @shaozi commented on GitHub (Jun 24, 2025): I ran into the same issue when using the embedding api. changing num_ctx to 512 fixed the crash. But WHY? @jessegross
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#67251