github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-15 12:48:05 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #13873] Linux X86_64 AMD RYZEN AI MAX+ 395 w/ Radeon 8060S ollama run SIGSEGV #9079

New Issue
Closed
opened 2026-04-12 21:55:19 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-12 21:55:19 -05:00
Owner
Copy Link

Originally created by @qjgwork on GitHub (Jan 24, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/13873

What is the issue?

Install the ollama by curl -fsSL https://ollama.com/install.sh | sh
Install the rocm bin: 1 aur/rocm-gfx1151-bin 7.10.0pre-2 (+0 0.00) (Installed) ROCm Core SDK and TheRock Build System - Ryzen AI Max

run the ollama and then load the model , I got the SIGSEGV

System information

± % ollama -v                                                                                  !381
ollama version is 0.14.3


± % rocminfo                                                                                   !422
ROCk module is loaded
=====================
HSA System Attributes
=====================
Runtime Version:         1.18
Runtime Ext Version:     1.15
System Timestamp Freq.:  1000.000000MHz
Sig. Max Wait Duration:  18446744073709551615 (0xFFFFFFFFFFFFFFFF) (timestamp count)
Machine Model:           LARGE
System Endianness:       LITTLE
Mwaitx:                  DISABLED
XNACK enabled:           NO
DMAbuf Support:          YES
VMM Support:             YES

==========
HSA Agents
==========
*******
Agent 1
*******
  Name:                    AMD RYZEN AI MAX+ 395 w/ Radeon 8060S
  Uuid:                    CPU-XX
  Marketing Name:          AMD RYZEN AI MAX+ 395 w/ Radeon 8060S
  Vendor Name:             CPU
  Feature:                 None specified
  Profile:                 FULL_PROFILE
  Float Round Mode:        NEAR
  Max Queue Number:        0(0x0)
  Queue Min Size:          0(0x0)
  Queue Max Size:          0(0x0)
  Queue Type:              MULTI
  Node:                    0
  Device Type:             CPU
  Cache Info:
    L1:                      49152(0xc000) KB
  Chip ID:                 0(0x0)
  ASIC Revision:           0(0x0)
  Cacheline Size:          64(0x40)
  Max Clock Freq. (MHz):   5187
  BDFID:                   0
  Internal Node ID:        0
  Compute Unit:            32
  SIMDs per CU:            0
  Shader Engines:          0
  Shader Arrs. per Eng.:   0
  WatchPts on Addr. Ranges:1
  Memory Properties:
  Features:                None
  Pool Info:
    Pool 1
      Segment:                 GLOBAL; FLAGS: FINE GRAINED
      Size:                    65462660(0x3e6e184) KB
      Allocatable:             TRUE
      Alloc Granule:           4KB
      Alloc Recommended Granule:4KB
      Alloc Alignment:         4KB
      Accessible by all:       TRUE
    Pool 2
      Segment:                 GLOBAL; FLAGS: EXTENDED FINE GRAINED
      Size:                    65462660(0x3e6e184) KB
      Allocatable:             TRUE
      Alloc Granule:           4KB
      Alloc Recommended Granule:4KB
      Alloc Alignment:         4KB
      Accessible by all:       TRUE
    Pool 3
      Segment:                 GLOBAL; FLAGS: KERNARG, FINE GRAINED
      Size:                    65462660(0x3e6e184) KB
      Allocatable:             TRUE
      Alloc Granule:           4KB
      Alloc Recommended Granule:4KB
      Alloc Alignment:         4KB
      Accessible by all:       TRUE
    Pool 4
      Segment:                 GLOBAL; FLAGS: COARSE GRAINED
      Size:                    65462660(0x3e6e184) KB
      Allocatable:             TRUE
      Alloc Granule:           4KB
      Alloc Recommended Granule:4KB
      Alloc Alignment:         4KB
      Accessible by all:       TRUE
  ISA Info:
*******
Agent 2
*******
  Name:                    gfx1151
  Uuid:                    GPU-XX
  Marketing Name:          Radeon 8060S Graphics
  Vendor Name:             AMD
  Feature:                 KERNEL_DISPATCH
  Profile:                 BASE_PROFILE
  Float Round Mode:        NEAR
  Max Queue Number:        128(0x80)
  Queue Min Size:          64(0x40)
  Queue Max Size:          131072(0x20000)
  Queue Type:              MULTI
  Node:                    1
  Device Type:             GPU
  Cache Info:
    L1:                      32(0x20) KB
    L2:                      2048(0x800) KB
    L3:                      32768(0x8000) KB
  Chip ID:                 5510(0x1586)
  ASIC Revision:           0(0x0)
  Cacheline Size:          128(0x80)
  Max Clock Freq. (MHz):   2900
  BDFID:                   50688
  Internal Node ID:        1
  Compute Unit:            40
  SIMDs per CU:            2
  Shader Engines:          2
  Shader Arrs. per Eng.:   2
  WatchPts on Addr. Ranges:4
  Coherent Host Access:    FALSE
  Memory Properties:       APU
  Features:                KERNEL_DISPATCH
  Fast F16 Operation:      TRUE
  Wavefront Size:          32(0x20)
  Workgroup Max Size:      1024(0x400)
  Workgroup Max Size per Dimension:
    x                        1024(0x400)
    y                        1024(0x400)
    z                        1024(0x400)
  Max Waves Per CU:        32(0x20)
  Max Work-item Per CU:    1024(0x400)
  Grid Max Size:           4294967295(0xffffffff)
  Grid Max Size per Dimension:
    x                        2147483647(0x7fffffff)
    y                        65535(0xffff)
    z                        65535(0xffff)
  Max fbarriers/Workgrp:   32
  Packet Processor uCode:: 32
  SDMA engine uCode::      17
  IOMMU Support::          None
  Pool Info:
    Pool 1
      Segment:                 GLOBAL; FLAGS: COARSE GRAINED
      Size:                    67108864(0x4000000) KB
      Allocatable:             TRUE
      Alloc Granule:           4KB
      Alloc Recommended Granule:2048KB
      Alloc Alignment:         4KB
      Accessible by all:       FALSE
    Pool 2
      Segment:                 GLOBAL; FLAGS: EXTENDED FINE GRAINED
      Size:                    67108864(0x4000000) KB
      Allocatable:             TRUE
      Alloc Granule:           4KB
      Alloc Recommended Granule:2048KB
      Alloc Alignment:         4KB
      Accessible by all:       FALSE
    Pool 3
      Segment:                 GROUP
      Size:                    64(0x40) KB
      Allocatable:             FALSE
      Alloc Granule:           0KB
      Alloc Recommended Granule:0KB
      Alloc Alignment:         0KB
      Accessible by all:       FALSE
  ISA Info:
    ISA 1
      Name:                    amdgcn-amd-amdhsa--gfx1151
      Machine Models:          HSA_MACHINE_MODEL_LARGE
      Profiles:                HSA_PROFILE_BASE
      Default Rounding Mode:   NEAR
      Default Rounding Mode:   NEAR
      Fast f16:                TRUE
      Workgroup Max Size:      1024(0x400)
      Workgroup Max Size per Dimension:
        x                        1024(0x400)
        y                        1024(0x400)
        z                        1024(0x400)
      Grid Max Size:           4294967295(0xffffffff)
      Grid Max Size per Dimension:
        x                        2147483647(0x7fffffff)
        y                        65535(0xffff)
        z                        65535(0xffff)
      FBarrier Max Size:       32
    ISA 2
      Name:                    amdgcn-amd-amdhsa--gfx11-generic
      Machine Models:          HSA_MACHINE_MODEL_LARGE
      Profiles:                HSA_PROFILE_BASE
      Default Rounding Mode:   NEAR
      Default Rounding Mode:   NEAR
      Fast f16:                TRUE
      Workgroup Max Size:      1024(0x400)
      Workgroup Max Size per Dimension:
        x                        1024(0x400)
        y                        1024(0x400)
        z                        1024(0x400)
      Grid Max Size:           4294967295(0xffffffff)
      Grid Max Size per Dimension:
        x                        2147483647(0x7fffffff)
        y                        65535(0xffff)
        z                        65535(0xffff)
      FBarrier Max Size:       32
*** Done ***

Relevant log output

± % ollama serve                                                                               !421
time=2026-01-24T11:07:37.024+08:00 level=INFO source=routes.go:1629 msg="server config" env="map[CUDA_VISIBLE_DEVICES: GGML_VK_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION:11.5.1 HTTPS_PROXY:http://127.0.0.1:7890 HTTP_PROXY:http://127.0.0.1:7890 NO_PROXY: OLLAMA_CONTEXT_LENGTH:4096 OLLAMA_DEBUG:INFO OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/home/qian/.ollama/models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:1 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://* vscode-file://*] OLLAMA_REMOTES:[ollama.com] OLLAMA_SCHED_SPREAD:false OLLAMA_VULKAN:false ROCR_VISIBLE_DEVICES: http_proxy:http://127.0.0.1:7890 https_proxy:http://127.0.0.1:7890 no_proxy:]"
time=2026-01-24T11:07:37.025+08:00 level=INFO source=images.go:501 msg="total blobs: 10"
time=2026-01-24T11:07:37.025+08:00 level=INFO source=images.go:508 msg="total unused blobs removed: 0"
time=2026-01-24T11:07:37.025+08:00 level=INFO source=routes.go:1682 msg="Listening on 127.0.0.1:11434 (version 0.14.3)"
time=2026-01-24T11:07:37.026+08:00 level=INFO source=runner.go:67 msg="discovering available GPUs..."
time=2026-01-24T11:07:37.026+08:00 level=WARN source=runner.go:485 msg="user overrode visible devices" HSA_OVERRIDE_GFX_VERSION=11.5.1
time=2026-01-24T11:07:37.026+08:00 level=WARN source=runner.go:489 msg="if GPUs are not correctly discovered, unset and try again"
time=2026-01-24T11:07:37.027+08:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 38159"
time=2026-01-24T11:07:37.543+08:00 level=INFO source=runner.go:106 msg="experimental Vulkan support disabled.  To enable, set OLLAMA_VULKAN=1"
time=2026-01-24T11:07:37.543+08:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 41889"
time=2026-01-24T11:07:37.558+08:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 33065"
time=2026-01-24T11:07:37.573+08:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 36325"
time=2026-01-24T11:07:38.071+08:00 level=INFO source=types.go:42 msg="inference compute" id=0 filter_id=0 library=ROCm compute=gfx1151 name=ROCm0 description="AMD Radeon Graphics" libdirs=ollama,rocm driver=60342.13 pci_id=0000:c6:00.0 type=iGPU total="95.2 GiB" available="93.9 GiB"
[GIN] 2026/01/24 - 11:07:44 | 200 |      42.648µs |       127.0.0.1 | HEAD     "/"
[GIN] 2026/01/24 - 11:07:44 | 200 |   94.241383ms |       127.0.0.1 | POST     "/api/show"
[GIN] 2026/01/24 - 11:07:44 | 200 |   98.052397ms |       127.0.0.1 | POST     "/api/show"
time=2026-01-24T11:07:44.855+08:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 42379"
llama_model_loader: loaded meta data with 29 key-value pairs and 724 tensors from /home/qian/.ollama/models/blobs/sha256-de20d2cf2dc430b1717a8b07a9df029d651f3895dbffec4729a3902a6fe344c9 (version GGUF V3 (latest))
llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
llama_model_loader: - kv   0:                       general.architecture str              = llama
llama_model_loader: - kv   1:                               general.type str              = model
llama_model_loader: - kv   2:                               general.name str              = Meta Llama 3.1 70B Instruct
llama_model_loader: - kv   3:                           general.finetune str              = Instruct
llama_model_loader: - kv   4:                           general.basename str              = Meta-Llama-3.1
llama_model_loader: - kv   5:                         general.size_label str              = 70B
llama_model_loader: - kv   6:                            general.license str              = llama3.1
llama_model_loader: - kv   7:                               general.tags arr[str,6]       = ["facebook", "meta", "pytorch", "llam...
llama_model_loader: - kv   8:                          general.languages arr[str,8]       = ["en", "de", "fr", "it", "pt", "hi", ...
llama_model_loader: - kv   9:                          llama.block_count u32              = 80
llama_model_loader: - kv  10:                       llama.context_length u32              = 131072
llama_model_loader: - kv  11:                     llama.embedding_length u32              = 8192
llama_model_loader: - kv  12:                  llama.feed_forward_length u32              = 28672
llama_model_loader: - kv  13:                 llama.attention.head_count u32              = 64
llama_model_loader: - kv  14:              llama.attention.head_count_kv u32              = 8
llama_model_loader: - kv  15:                       llama.rope.freq_base f32              = 500000.000000
llama_model_loader: - kv  16:     llama.attention.layer_norm_rms_epsilon f32              = 0.000010
llama_model_loader: - kv  17:                          general.file_type u32              = 15
llama_model_loader: - kv  18:                           llama.vocab_size u32              = 128256
llama_model_loader: - kv  19:                 llama.rope.dimension_count u32              = 128
llama_model_loader: - kv  20:                       tokenizer.ggml.model str              = gpt2
llama_model_loader: - kv  21:                         tokenizer.ggml.pre str              = llama-bpe
llama_model_loader: - kv  22:                      tokenizer.ggml.tokens arr[str,128256]  = ["!", "\"", "#", "$", "%", "&", "'", ...
llama_model_loader: - kv  23:                  tokenizer.ggml.token_type arr[i32,128256]  = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv  24:                      tokenizer.ggml.merges arr[str,280147]  = ["Ġ Ġ", "Ġ ĠĠĠ", "ĠĠ ĠĠ", "...
llama_model_loader: - kv  25:                tokenizer.ggml.bos_token_id u32              = 128000
llama_model_loader: - kv  26:                tokenizer.ggml.eos_token_id u32              = 128009
llama_model_loader: - kv  27:                    tokenizer.chat_template str              = {{- bos_token }}\n{%- if custom_tools ...
llama_model_loader: - kv  28:               general.quantization_version u32              = 2
llama_model_loader: - type  f32:  162 tensors
llama_model_loader: - type q4_K:  441 tensors
llama_model_loader: - type q5_K:   40 tensors
llama_model_loader: - type q6_K:   81 tensors
print_info: file format = GGUF V3 (latest)
print_info: file type   = Q4_K - Medium
print_info: file size   = 39.59 GiB (4.82 BPW)
load: printing all EOG tokens:
load:   - 128001 ('<|end_of_text|>')
load:   - 128008 ('<|eom_id|>')
load:   - 128009 ('<|eot_id|>')
load: special tokens cache size = 256
load: token to piece cache size = 0.7999 MB
print_info: arch             = llama
print_info: vocab_only       = 1
print_info: no_alloc         = 0
print_info: model type       = ?B
print_info: model params     = 70.55 B
print_info: general.name     = Meta Llama 3.1 70B Instruct
print_info: vocab type       = BPE
print_info: n_vocab          = 128256
print_info: n_merges         = 280147
print_info: BOS token        = 128000 '<|begin_of_text|>'
print_info: EOS token        = 128009 '<|eot_id|>'
print_info: EOT token        = 128009 '<|eot_id|>'
print_info: EOM token        = 128008 '<|eom_id|>'
print_info: LF token         = 198 'Ċ'
print_info: EOG token        = 128001 '<|end_of_text|>'
print_info: EOG token        = 128008 '<|eom_id|>'
print_info: EOG token        = 128009 '<|eot_id|>'
print_info: max token length = 256
llama_model_load: vocab only - skipping tensors
time=2026-01-24T11:07:45.477+08:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --model /home/qian/.ollama/models/blobs/sha256-de20d2cf2dc430b1717a8b07a9df029d651f3895dbffec4729a3902a6fe344c9 --port 37749"
time=2026-01-24T11:07:45.478+08:00 level=INFO source=sched.go:452 msg="system memory" total="62.4 GiB" free="57.1 GiB" free_swap="97.2 GiB"
time=2026-01-24T11:07:45.478+08:00 level=INFO source=sched.go:459 msg="gpu memory" id=0 library=ROCm available="93.5 GiB" free="93.9 GiB" minimum="457.0 MiB" overhead="0 B"
time=2026-01-24T11:07:45.478+08:00 level=INFO source=server.go:496 msg="loading model" "model layers"=81 requested=-1
time=2026-01-24T11:07:45.478+08:00 level=INFO source=device.go:240 msg="model weights" device=ROCm0 size="39.0 GiB"
time=2026-01-24T11:07:45.478+08:00 level=INFO source=device.go:251 msg="kv cache" device=ROCm0 size="1.2 GiB"
time=2026-01-24T11:07:45.478+08:00 level=INFO source=device.go:262 msg="compute graph" device=ROCm0 size="584.0 MiB"
time=2026-01-24T11:07:45.478+08:00 level=INFO source=device.go:272 msg="total memory" size="40.9 GiB"
time=2026-01-24T11:07:45.486+08:00 level=INFO source=runner.go:965 msg="starting go runner"
load_backend: loaded CPU backend from /usr/local/lib/ollama/libggml-cpu-icelake.so
/opt/amdgpu/share/libdrm/amdgpu.ids: No such file or directory
ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
  Device 0: AMD Radeon Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32, ID: 0
load_backend: loaded ROCm backend from /usr/local/lib/ollama/rocm/libggml-hip.so
time=2026-01-24T11:07:45.822+08:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.AVX512=1 CPU.0.AVX512_VBMI=1 CPU.0.AVX512_VNNI=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 ROCm.0.NO_VMM=1 ROCm.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(gcc)
time=2026-01-24T11:07:45.823+08:00 level=INFO source=runner.go:1001 msg="Server listening on 127.0.0.1:37749"
time=2026-01-24T11:07:45.825+08:00 level=INFO source=runner.go:895 msg=load request="{Operation:commit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Auto KvSize:4096 KvCacheType: NumThreads:16 GPULayers:81[ID:0 Layers:81(0..80)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:true}"
ggml_hip_get_device_memory searching for device 0000:c6:00.0
time=2026-01-24T11:07:45.825+08:00 level=INFO source=server.go:1347 msg="waiting for llama runner to start responding"
time=2026-01-24T11:07:45.825+08:00 level=INFO source=server.go:1381 msg="waiting for server to become available" status="llm server loading model"
ggml_backend_cuda_device_get_memory device 0000:c6:00.0 utilizing AMD specific memory reporting free: 100868141056 total: 102236356608
llama_model_load_from_file_impl: using device ROCm0 (AMD Radeon Graphics) (0000:c6:00.0) - 96195 MiB free
llama_model_loader: loaded meta data with 29 key-value pairs and 724 tensors from /home/qian/.ollama/models/blobs/sha256-de20d2cf2dc430b1717a8b07a9df029d651f3895dbffec4729a3902a6fe344c9 (version GGUF V3 (latest))
llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
llama_model_loader: - kv   0:                       general.architecture str              = llama
llama_model_loader: - kv   1:                               general.type str              = model
llama_model_loader: - kv   2:                               general.name str              = Meta Llama 3.1 70B Instruct
llama_model_loader: - kv   3:                           general.finetune str              = Instruct
llama_model_loader: - kv   4:                           general.basename str              = Meta-Llama-3.1
llama_model_loader: - kv   5:                         general.size_label str              = 70B
llama_model_loader: - kv   6:                            general.license str              = llama3.1
llama_model_loader: - kv   7:                               general.tags arr[str,6]       = ["facebook", "meta", "pytorch", "llam...
llama_model_loader: - kv   8:                          general.languages arr[str,8]       = ["en", "de", "fr", "it", "pt", "hi", ...
llama_model_loader: - kv   9:                          llama.block_count u32              = 80
llama_model_loader: - kv  10:                       llama.context_length u32              = 131072
llama_model_loader: - kv  11:                     llama.embedding_length u32              = 8192
llama_model_loader: - kv  12:                  llama.feed_forward_length u32              = 28672
llama_model_loader: - kv  13:                 llama.attention.head_count u32              = 64
llama_model_loader: - kv  14:              llama.attention.head_count_kv u32              = 8
llama_model_loader: - kv  15:                       llama.rope.freq_base f32              = 500000.000000
llama_model_loader: - kv  16:     llama.attention.layer_norm_rms_epsilon f32              = 0.000010
llama_model_loader: - kv  17:                          general.file_type u32              = 15
llama_model_loader: - kv  18:                           llama.vocab_size u32              = 128256
llama_model_loader: - kv  19:                 llama.rope.dimension_count u32              = 128
llama_model_loader: - kv  20:                       tokenizer.ggml.model str              = gpt2
llama_model_loader: - kv  21:                         tokenizer.ggml.pre str              = llama-bpe
llama_model_loader: - kv  22:                      tokenizer.ggml.tokens arr[str,128256]  = ["!", "\"", "#", "$", "%", "&", "'", ...
llama_model_loader: - kv  23:                  tokenizer.ggml.token_type arr[i32,128256]  = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv  24:                      tokenizer.ggml.merges arr[str,280147]  = ["Ġ Ġ", "Ġ ĠĠĠ", "ĠĠ ĠĠ", "...
llama_model_loader: - kv  25:                tokenizer.ggml.bos_token_id u32              = 128000
llama_model_loader: - kv  26:                tokenizer.ggml.eos_token_id u32              = 128009
llama_model_loader: - kv  27:                    tokenizer.chat_template str              = {{- bos_token }}\n{%- if custom_tools ...
llama_model_loader: - kv  28:               general.quantization_version u32              = 2
llama_model_loader: - type  f32:  162 tensors
llama_model_loader: - type q4_K:  441 tensors
llama_model_loader: - type q5_K:   40 tensors
llama_model_loader: - type q6_K:   81 tensors
print_info: file format = GGUF V3 (latest)
print_info: file type   = Q4_K - Medium
print_info: file size   = 39.59 GiB (4.82 BPW)
load: printing all EOG tokens:
load:   - 128001 ('<|end_of_text|>')
load:   - 128008 ('<|eom_id|>')
load:   - 128009 ('<|eot_id|>')
load: special tokens cache size = 256
load: token to piece cache size = 0.7999 MB
print_info: arch             = llama
print_info: vocab_only       = 0
print_info: no_alloc         = 0
print_info: n_ctx_train      = 131072
print_info: n_embd           = 8192
print_info: n_embd_inp       = 8192
print_info: n_layer          = 80
print_info: n_head           = 64
print_info: n_head_kv        = 8
print_info: n_rot            = 128
print_info: n_swa            = 0
print_info: is_swa_any       = 0
print_info: n_embd_head_k    = 128
print_info: n_embd_head_v    = 128
print_info: n_gqa            = 8
print_info: n_embd_k_gqa     = 1024
print_info: n_embd_v_gqa     = 1024
print_info: f_norm_eps       = 0.0e+00
print_info: f_norm_rms_eps   = 1.0e-05
print_info: f_clamp_kqv      = 0.0e+00
print_info: f_max_alibi_bias = 0.0e+00
print_info: f_logit_scale    = 0.0e+00
print_info: f_attn_scale     = 0.0e+00
print_info: n_ff             = 28672
print_info: n_expert         = 0
print_info: n_expert_used    = 0
print_info: n_expert_groups  = 0
print_info: n_group_used     = 0
print_info: causal attn      = 1
print_info: pooling type     = 0
print_info: rope type        = 0
print_info: rope scaling     = linear
print_info: freq_base_train  = 500000.0
print_info: freq_scale_train = 1
print_info: n_ctx_orig_yarn  = 131072
print_info: rope_yarn_log_mul= 0.0000
print_info: rope_finetuned   = unknown
print_info: model type       = 70B
print_info: model params     = 70.55 B
print_info: general.name     = Meta Llama 3.1 70B Instruct
print_info: vocab type       = BPE
print_info: n_vocab          = 128256
print_info: n_merges         = 280147
print_info: BOS token        = 128000 '<|begin_of_text|>'
print_info: EOS token        = 128009 '<|eot_id|>'
print_info: EOT token        = 128009 '<|eot_id|>'
print_info: EOM token        = 128008 '<|eom_id|>'
print_info: LF token         = 198 'Ċ'
print_info: EOG token        = 128001 '<|end_of_text|>'
print_info: EOG token        = 128008 '<|eom_id|>'
print_info: EOG token        = 128009 '<|eot_id|>'
print_info: max token length = 256
load_tensors: loading model tensors, this can take a while... (mmap = true)
load_tensors: offloading 80 repeating layers to GPU
load_tensors: offloading output layer to GPU
load_tensors: offloaded 81/81 layers to GPU
load_tensors:   CPU_Mapped model buffer size =   563.62 MiB
load_tensors:        ROCm0 model buffer size = 39979.48 MiB
SIGSEGV: segmentation violation
PC=0x7f31e06c0bf5 m=0 sigcode=1 addr=0x18
signal arrived during cgo execution

goroutine 13 gp=0xc000504e00 m=0 mp=0x5631ae294080 [syscall]:
runtime.cgocall(0x5631ad0b60d2, 0xc0000c7b58)
	runtime/cgocall.go:167 +0x4b fp=0xc0000c7b30 sp=0xc0000c7af8 pc=0x5631ac2b28ab
github.com/ollama/ollama/llama._Cfunc_llama_model_load_from_file(0x5631e2a8cbc0, {0xc0003880a0, 0x0, 0x51, 0x1, 0x0, 0xc0003634f8, 0x5631ad0b5315, 0xc000388028, 0x0, ...})
	_cgo_gotypes.go:910 +0x4b fp=0xc0000c7b58 sp=0xc0000c7b30 pc=0x5631ac6b3d6b
github.com/ollama/ollama/llama.LoadModelFromFile.func1(...)
	github.com/ollama/ollama/llama/llama.go:308
github.com/ollama/ollama/llama.LoadModelFromFile({0x7fff3f3ac82b, 0x67}, {{0xc000363580, 0x1, 0x1}, 0x51, 0x0, 0x1, {0xc0003634f8, 0x1, ...}, ...})
	github.com/ollama/ollama/llama/llama.go:308 +0x56d fp=0xc0000c7da0 sp=0xc0000c7b58 pc=0x5631ac6b70ed
github.com/ollama/ollama/runner/llamarunner.(*Server).loadModel(0xc0004c8820, {{0xc000363580, 0x1, 0x1}, 0x51, 0x0, 0x1, {0xc0003634f8, 0x1, 0x2}, ...}, ...)
	github.com/ollama/ollama/runner/llamarunner/runner.go:841 +0x9e fp=0xc0000c7ee8 sp=0xc0000c7da0 pc=0x5631ac7754be
github.com/ollama/ollama/runner/llamarunner.(*Server).load.gowrap2()
	github.com/ollama/ollama/runner/llamarunner/runner.go:934 +0x114 fp=0xc0000c7fe0 sp=0xc0000c7ee8 pc=0x5631ac7767b4
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc0000c7fe8 sp=0xc0000c7fe0 pc=0x5631ac2bdbc1
created by github.com/ollama/ollama/runner/llamarunner.(*Server).load in goroutine 10
	github.com/ollama/ollama/runner/llamarunner/runner.go:934 +0x889

goroutine 1 gp=0xc000002380 m=nil [IO wait]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
	runtime/proc.go:435 +0xce fp=0xc000139790 sp=0xc000139770 pc=0x5631ac2b5d2e
runtime.netpollblock(0xc0001397e0?, 0xac24f466?, 0x31?)
	runtime/netpoll.go:575 +0xf7 fp=0xc0001397c8 sp=0xc000139790 pc=0x5631ac27b057
internal/poll.runtime_pollWait(0x7f3262ec7eb0, 0x72)
	runtime/netpoll.go:351 +0x85 fp=0xc0001397e8 sp=0xc0001397c8 pc=0x5631ac2b4f45
internal/poll.(*pollDesc).wait(0xc0003b5e00?, 0x900000036?, 0x0)
	internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc000139810 sp=0xc0001397e8 pc=0x5631ac33d0c7
internal/poll.(*pollDesc).waitRead(...)
	internal/poll/fd_poll_runtime.go:89
internal/poll.(*FD).Accept(0xc0003b5e00)
	internal/poll/fd_unix.go:620 +0x295 fp=0xc0001398b8 sp=0xc000139810 pc=0x5631ac342495
net.(*netFD).accept(0xc0003b5e00)
	net/fd_unix.go:172 +0x29 fp=0xc000139970 sp=0xc0001398b8 pc=0x5631ac3b5549
net.(*TCPListener).accept(0xc0005b7600)
	net/tcpsock_posix.go:159 +0x1b fp=0xc0001399c0 sp=0xc000139970 pc=0x5631ac3cb45b
net.(*TCPListener).Accept(0xc0005b7600)
	net/tcpsock.go:380 +0x30 fp=0xc0001399f0 sp=0xc0001399c0 pc=0x5631ac3ca310
net/http.(*onceCloseListener).Accept(0xc0004c6480?)
	<autogenerated>:1 +0x24 fp=0xc000139a08 sp=0xc0001399f0 pc=0x5631ac5e21c4
net/http.(*Server).Serve(0xc00005b900, {0x5631ad95ade0, 0xc0005b7600})
	net/http/server.go:3424 +0x30c fp=0xc000139b38 sp=0xc000139a08 pc=0x5631ac5b9a8c
github.com/ollama/ollama/runner/llamarunner.Execute({0xc000034260, 0x4, 0x4})
	github.com/ollama/ollama/runner/llamarunner/runner.go:1002 +0x8f5 fp=0xc000139d08 sp=0xc000139b38 pc=0x5631ac777175
github.com/ollama/ollama/runner.Execute({0xc000034250?, 0x0?, 0x0?})
	github.com/ollama/ollama/runner/runner.go:30 +0x130 fp=0xc000139d30 sp=0xc000139d08 pc=0x5631ac8645d0
github.com/ollama/ollama/cmd.NewCLI.func3(0xc00005b600?, {0x5631ad3e90df?, 0x4?, 0x5631ad3e90e3?})
	github.com/ollama/ollama/cmd/cmd.go:1961 +0x45 fp=0xc000139d58 sp=0xc000139d30 pc=0x5631ad035025
github.com/spf13/cobra.(*Command).execute(0xc000243208, {0xc0005b7400, 0x4, 0x4})
	github.com/spf13/cobra@v1.7.0/command.go:940 +0x85c fp=0xc000139e78 sp=0xc000139d58 pc=0x5631ac42f4bc
github.com/spf13/cobra.(*Command).ExecuteC(0xc000646f08)
	github.com/spf13/cobra@v1.7.0/command.go:1068 +0x3a5 fp=0xc000139f30 sp=0xc000139e78 pc=0x5631ac42fd05
github.com/spf13/cobra.(*Command).Execute(...)
	github.com/spf13/cobra@v1.7.0/command.go:992
github.com/spf13/cobra.(*Command).ExecuteContext(...)
	github.com/spf13/cobra@v1.7.0/command.go:985
main.main()
	github.com/ollama/ollama/main.go:12 +0x4d fp=0xc000139f50 sp=0xc000139f30 pc=0x5631ad035b0d
runtime.main()
	runtime/proc.go:283 +0x29d fp=0xc000139fe0 sp=0xc000139f50 pc=0x5631ac2826dd
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc000139fe8 sp=0xc000139fe0 pc=0x5631ac2bdbc1

goroutine 2 gp=0xc000002e00 m=nil [force gc (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
	runtime/proc.go:435 +0xce fp=0xc0000b4fa8 sp=0xc0000b4f88 pc=0x5631ac2b5d2e
runtime.goparkunlock(...)
	runtime/proc.go:441
runtime.forcegchelper()
	runtime/proc.go:348 +0xb8 fp=0xc0000b4fe0 sp=0xc0000b4fa8 pc=0x5631ac282a18
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc0000b4fe8 sp=0xc0000b4fe0 pc=0x5631ac2bdbc1
created by runtime.init.7 in goroutine 1
	runtime/proc.go:336 +0x1a

goroutine 3 gp=0xc000003340 m=nil [GC sweep wait]:
runtime.gopark(0x1?, 0x0?, 0x0?, 0x0?, 0x0?)
	runtime/proc.go:435 +0xce fp=0xc0000b5780 sp=0xc0000b5760 pc=0x5631ac2b5d2e
runtime.goparkunlock(...)
	runtime/proc.go:441
runtime.bgsweep(0xc0000e0000)
	runtime/mgcsweep.go:316 +0xdf fp=0xc0000b57c8 sp=0xc0000b5780 pc=0x5631ac26d1bf
runtime.gcenable.gowrap1()
	runtime/mgc.go:204 +0x25 fp=0xc0000b57e0 sp=0xc0000b57c8 pc=0x5631ac2615a5
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc0000b57e8 sp=0xc0000b57e0 pc=0x5631ac2bdbc1
created by runtime.gcenable in goroutine 1
	runtime/mgc.go:204 +0x66

goroutine 4 gp=0xc000003500 m=nil [GC scavenge wait]:
runtime.gopark(0x10000?, 0x5631ad5d0730?, 0x0?, 0x0?, 0x0?)
	runtime/proc.go:435 +0xce fp=0xc0000b5f78 sp=0xc0000b5f58 pc=0x5631ac2b5d2e
runtime.goparkunlock(...)
	runtime/proc.go:441
runtime.(*scavengerState).park(0x5631ae291260)
	runtime/mgcscavenge.go:425 +0x49 fp=0xc0000b5fa8 sp=0xc0000b5f78 pc=0x5631ac26ac09
runtime.bgscavenge(0xc0000e0000)
	runtime/mgcscavenge.go:658 +0x59 fp=0xc0000b5fc8 sp=0xc0000b5fa8 pc=0x5631ac26b199
runtime.gcenable.gowrap2()
	runtime/mgc.go:205 +0x25 fp=0xc0000b5fe0 sp=0xc0000b5fc8 pc=0x5631ac261545
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc0000b5fe8 sp=0xc0000b5fe0 pc=0x5631ac2bdbc1
created by runtime.gcenable in goroutine 1
	runtime/mgc.go:205 +0xa5

goroutine 5 gp=0xc000003dc0 m=nil [finalizer wait]:
runtime.gopark(0x1b8?, 0xc000002380?, 0x1?, 0x23?, 0xc0000b4688?)
	runtime/proc.go:435 +0xce fp=0xc0000b4630 sp=0xc0000b4610 pc=0x5631ac2b5d2e
runtime.runfinq()
	runtime/mfinal.go:196 +0x107 fp=0xc0000b47e0 sp=0xc0000b4630 pc=0x5631ac260567
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc0000b47e8 sp=0xc0000b47e0 pc=0x5631ac2bdbc1
created by runtime.createfing in goroutine 1
	runtime/mfinal.go:166 +0x3d

goroutine 6 gp=0xc0001f88c0 m=nil [chan receive]:
runtime.gopark(0xc000271540?, 0xc00050a018?, 0x60?, 0x67?, 0x5631ac39c188?)
	runtime/proc.go:435 +0xce fp=0xc0000b6718 sp=0xc0000b66f8 pc=0x5631ac2b5d2e
runtime.chanrecv(0xc00003c380, 0x0, 0x1)
	runtime/chan.go:664 +0x445 fp=0xc0000b6790 sp=0xc0000b6718 pc=0x5631ac252045
runtime.chanrecv1(0x0?, 0x0?)
	runtime/chan.go:506 +0x12 fp=0xc0000b67b8 sp=0xc0000b6790 pc=0x5631ac251bd2
runtime.unique_runtime_registerUniqueMapCleanup.func2(...)
	runtime/mgc.go:1796
runtime.unique_runtime_registerUniqueMapCleanup.gowrap1()
	runtime/mgc.go:1799 +0x2f fp=0xc0000b67e0 sp=0xc0000b67b8 pc=0x5631ac26474f
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc0000b67e8 sp=0xc0000b67e0 pc=0x5631ac2bdbc1
created by unique.runtime_registerUniqueMapCleanup in goroutine 1
	runtime/mgc.go:1794 +0x85

goroutine 7 gp=0xc0001f8c40 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
	runtime/proc.go:435 +0xce fp=0xc0000b6f38 sp=0xc0000b6f18 pc=0x5631ac2b5d2e
runtime.gcBgMarkWorker(0xc00003d7a0)
	runtime/mgc.go:1423 +0xe9 fp=0xc0000b6fc8 sp=0xc0000b6f38 pc=0x5631ac263a69
runtime.gcBgMarkStartWorkers.gowrap1()
	runtime/mgc.go:1339 +0x25 fp=0xc0000b6fe0 sp=0xc0000b6fc8 pc=0x5631ac263945
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc0000b6fe8 sp=0xc0000b6fe0 pc=0x5631ac2bdbc1
created by runtime.gcBgMarkStartWorkers in goroutine 1
	runtime/mgc.go:1339 +0x105

goroutine 18 gp=0xc000504000 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
	runtime/proc.go:435 +0xce fp=0xc0000b0738 sp=0xc0000b0718 pc=0x5631ac2b5d2e
runtime.gcBgMarkWorker(0xc00003d7a0)
	runtime/mgc.go:1423 +0xe9 fp=0xc0000b07c8 sp=0xc0000b0738 pc=0x5631ac263a69
runtime.gcBgMarkStartWorkers.gowrap1()
	runtime/mgc.go:1339 +0x25 fp=0xc0000b07e0 sp=0xc0000b07c8 pc=0x5631ac263945
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc0000b07e8 sp=0xc0000b07e0 pc=0x5631ac2bdbc1
created by runtime.gcBgMarkStartWorkers in goroutine 1
	runtime/mgc.go:1339 +0x105

goroutine 34 gp=0xc000102380 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
	runtime/proc.go:435 +0xce fp=0xc00011a738 sp=0xc00011a718 pc=0x5631ac2b5d2e
runtime.gcBgMarkWorker(0xc00003d7a0)
	runtime/mgc.go:1423 +0xe9 fp=0xc00011a7c8 sp=0xc00011a738 pc=0x5631ac263a69
runtime.gcBgMarkStartWorkers.gowrap1()
	runtime/mgc.go:1339 +0x25 fp=0xc00011a7e0 sp=0xc00011a7c8 pc=0x5631ac263945
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc00011a7e8 sp=0xc00011a7e0 pc=0x5631ac2bdbc1
created by runtime.gcBgMarkStartWorkers in goroutine 1
	runtime/mgc.go:1339 +0x105

goroutine 35 gp=0xc000102540 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
	runtime/proc.go:435 +0xce fp=0xc00011af38 sp=0xc00011af18 pc=0x5631ac2b5d2e
runtime.gcBgMarkWorker(0xc00003d7a0)
	runtime/mgc.go:1423 +0xe9 fp=0xc00011afc8 sp=0xc00011af38 pc=0x5631ac263a69
runtime.gcBgMarkStartWorkers.gowrap1()
	runtime/mgc.go:1339 +0x25 fp=0xc00011afe0 sp=0xc00011afc8 pc=0x5631ac263945
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc00011afe8 sp=0xc00011afe0 pc=0x5631ac2bdbc1
created by runtime.gcBgMarkStartWorkers in goroutine 1
	runtime/mgc.go:1339 +0x105

goroutine 8 gp=0xc0001f8e00 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
	runtime/proc.go:435 +0xce fp=0xc0000b7738 sp=0xc0000b7718 pc=0x5631ac2b5d2e
runtime.gcBgMarkWorker(0xc00003d7a0)
	runtime/mgc.go:1423 +0xe9 fp=0xc0000b77c8 sp=0xc0000b7738 pc=0x5631ac263a69
runtime.gcBgMarkStartWorkers.gowrap1()
	runtime/mgc.go:1339 +0x25 fp=0xc0000b77e0 sp=0xc0000b77c8 pc=0x5631ac263945
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc0000b77e8 sp=0xc0000b77e0 pc=0x5631ac2bdbc1
created by runtime.gcBgMarkStartWorkers in goroutine 1
	runtime/mgc.go:1339 +0x105

goroutine 19 gp=0xc0005041c0 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
	runtime/proc.go:435 +0xce fp=0xc0000b0f38 sp=0xc0000b0f18 pc=0x5631ac2b5d2e
runtime.gcBgMarkWorker(0xc00003d7a0)
	runtime/mgc.go:1423 +0xe9 fp=0xc0000b0fc8 sp=0xc0000b0f38 pc=0x5631ac263a69
runtime.gcBgMarkStartWorkers.gowrap1()
	runtime/mgc.go:1339 +0x25 fp=0xc0000b0fe0 sp=0xc0000b0fc8 pc=0x5631ac263945
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc0000b0fe8 sp=0xc0000b0fe0 pc=0x5631ac2bdbc1
created by runtime.gcBgMarkStartWorkers in goroutine 1
	runtime/mgc.go:1339 +0x105

goroutine 36 gp=0xc000102700 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
	runtime/proc.go:435 +0xce fp=0xc00011b738 sp=0xc00011b718 pc=0x5631ac2b5d2e
runtime.gcBgMarkWorker(0xc00003d7a0)
	runtime/mgc.go:1423 +0xe9 fp=0xc00011b7c8 sp=0xc00011b738 pc=0x5631ac263a69
runtime.gcBgMarkStartWorkers.gowrap1()
	runtime/mgc.go:1339 +0x25 fp=0xc00011b7e0 sp=0xc00011b7c8 pc=0x5631ac263945
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc00011b7e8 sp=0xc00011b7e0 pc=0x5631ac2bdbc1
created by runtime.gcBgMarkStartWorkers in goroutine 1
	runtime/mgc.go:1339 +0x105

goroutine 20 gp=0xc000504380 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
	runtime/proc.go:435 +0xce fp=0xc0000b1738 sp=0xc0000b1718 pc=0x5631ac2b5d2e
runtime.gcBgMarkWorker(0xc00003d7a0)
	runtime/mgc.go:1423 +0xe9 fp=0xc0000b17c8 sp=0xc0000b1738 pc=0x5631ac263a69
runtime.gcBgMarkStartWorkers.gowrap1()
	runtime/mgc.go:1339 +0x25 fp=0xc0000b17e0 sp=0xc0000b17c8 pc=0x5631ac263945
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc0000b17e8 sp=0xc0000b17e0 pc=0x5631ac2bdbc1
created by runtime.gcBgMarkStartWorkers in goroutine 1
	runtime/mgc.go:1339 +0x105

goroutine 37 gp=0xc0001028c0 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
	runtime/proc.go:435 +0xce fp=0xc00011bf38 sp=0xc00011bf18 pc=0x5631ac2b5d2e
runtime.gcBgMarkWorker(0xc00003d7a0)
	runtime/mgc.go:1423 +0xe9 fp=0xc00011bfc8 sp=0xc00011bf38 pc=0x5631ac263a69
runtime.gcBgMarkStartWorkers.gowrap1()
	runtime/mgc.go:1339 +0x25 fp=0xc00011bfe0 sp=0xc00011bfc8 pc=0x5631ac263945
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc00011bfe8 sp=0xc00011bfe0 pc=0x5631ac2bdbc1
created by runtime.gcBgMarkStartWorkers in goroutine 1
	runtime/mgc.go:1339 +0x105

goroutine 21 gp=0xc000504540 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
	runtime/proc.go:435 +0xce fp=0xc0000b1f38 sp=0xc0000b1f18 pc=0x5631ac2b5d2e
runtime.gcBgMarkWorker(0xc00003d7a0)
	runtime/mgc.go:1423 +0xe9 fp=0xc0000b1fc8 sp=0xc0000b1f38 pc=0x5631ac263a69
runtime.gcBgMarkStartWorkers.gowrap1()
	runtime/mgc.go:1339 +0x25 fp=0xc0000b1fe0 sp=0xc0000b1fc8 pc=0x5631ac263945
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc0000b1fe8 sp=0xc0000b1fe0 pc=0x5631ac2bdbc1
created by runtime.gcBgMarkStartWorkers in goroutine 1
	runtime/mgc.go:1339 +0x105

goroutine 38 gp=0xc000102a80 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
	runtime/proc.go:435 +0xce fp=0xc00011c738 sp=0xc00011c718 pc=0x5631ac2b5d2e
runtime.gcBgMarkWorker(0xc00003d7a0)
	runtime/mgc.go:1423 +0xe9 fp=0xc00011c7c8 sp=0xc00011c738 pc=0x5631ac263a69
runtime.gcBgMarkStartWorkers.gowrap1()
	runtime/mgc.go:1339 +0x25 fp=0xc00011c7e0 sp=0xc00011c7c8 pc=0x5631ac263945
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc00011c7e8 sp=0xc00011c7e0 pc=0x5631ac2bdbc1
created by runtime.gcBgMarkStartWorkers in goroutine 1
	runtime/mgc.go:1339 +0x105

goroutine 22 gp=0xc000504700 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
	runtime/proc.go:435 +0xce fp=0xc0000b2738 sp=0xc0000b2718 pc=0x5631ac2b5d2e
runtime.gcBgMarkWorker(0xc00003d7a0)
	runtime/mgc.go:1423 +0xe9 fp=0xc0000b27c8 sp=0xc0000b2738 pc=0x5631ac263a69
runtime.gcBgMarkStartWorkers.gowrap1()
	runtime/mgc.go:1339 +0x25 fp=0xc0000b27e0 sp=0xc0000b27c8 pc=0x5631ac263945
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc0000b27e8 sp=0xc0000b27e0 pc=0x5631ac2bdbc1
created by runtime.gcBgMarkStartWorkers in goroutine 1
	runtime/mgc.go:1339 +0x105

goroutine 39 gp=0xc000102c40 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
	runtime/proc.go:435 +0xce fp=0xc00011cf38 sp=0xc00011cf18 pc=0x5631ac2b5d2e
runtime.gcBgMarkWorker(0xc00003d7a0)
	runtime/mgc.go:1423 +0xe9 fp=0xc00011cfc8 sp=0xc00011cf38 pc=0x5631ac263a69
runtime.gcBgMarkStartWorkers.gowrap1()
	runtime/mgc.go:1339 +0x25 fp=0xc00011cfe0 sp=0xc00011cfc8 pc=0x5631ac263945
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc00011cfe8 sp=0xc00011cfe0 pc=0x5631ac2bdbc1
created by runtime.gcBgMarkStartWorkers in goroutine 1
	runtime/mgc.go:1339 +0x105

goroutine 40 gp=0xc000102e00 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
	runtime/proc.go:435 +0xce fp=0xc00011d738 sp=0xc00011d718 pc=0x5631ac2b5d2e
runtime.gcBgMarkWorker(0xc00003d7a0)
	runtime/mgc.go:1423 +0xe9 fp=0xc00011d7c8 sp=0xc00011d738 pc=0x5631ac263a69
runtime.gcBgMarkStartWorkers.gowrap1()
	runtime/mgc.go:1339 +0x25 fp=0xc00011d7e0 sp=0xc00011d7c8 pc=0x5631ac263945
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc00011d7e8 sp=0xc00011d7e0 pc=0x5631ac2bdbc1
created by runtime.gcBgMarkStartWorkers in goroutine 1
	runtime/mgc.go:1339 +0x105

goroutine 41 gp=0xc000102fc0 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
	runtime/proc.go:435 +0xce fp=0xc00011df38 sp=0xc00011df18 pc=0x5631ac2b5d2e
runtime.gcBgMarkWorker(0xc00003d7a0)
	runtime/mgc.go:1423 +0xe9 fp=0xc00011dfc8 sp=0xc00011df38 pc=0x5631ac263a69
runtime.gcBgMarkStartWorkers.gowrap1()
	runtime/mgc.go:1339 +0x25 fp=0xc00011dfe0 sp=0xc00011dfc8 pc=0x5631ac263945
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc00011dfe8 sp=0xc00011dfe0 pc=0x5631ac2bdbc1
created by runtime.gcBgMarkStartWorkers in goroutine 1
	runtime/mgc.go:1339 +0x105

goroutine 42 gp=0xc000103180 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
	runtime/proc.go:435 +0xce fp=0xc000116738 sp=0xc000116718 pc=0x5631ac2b5d2e
runtime.gcBgMarkWorker(0xc00003d7a0)
	runtime/mgc.go:1423 +0xe9 fp=0xc0001167c8 sp=0xc000116738 pc=0x5631ac263a69
runtime.gcBgMarkStartWorkers.gowrap1()
	runtime/mgc.go:1339 +0x25 fp=0xc0001167e0 sp=0xc0001167c8 pc=0x5631ac263945
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc0001167e8 sp=0xc0001167e0 pc=0x5631ac2bdbc1
created by runtime.gcBgMarkStartWorkers in goroutine 1
	runtime/mgc.go:1339 +0x105

goroutine 43 gp=0xc000103340 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
	runtime/proc.go:435 +0xce fp=0xc000116f38 sp=0xc000116f18 pc=0x5631ac2b5d2e
runtime.gcBgMarkWorker(0xc00003d7a0)
	runtime/mgc.go:1423 +0xe9 fp=0xc000116fc8 sp=0xc000116f38 pc=0x5631ac263a69
runtime.gcBgMarkStartWorkers.gowrap1()
	runtime/mgc.go:1339 +0x25 fp=0xc000116fe0 sp=0xc000116fc8 pc=0x5631ac263945
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc000116fe8 sp=0xc000116fe0 pc=0x5631ac2bdbc1
created by runtime.gcBgMarkStartWorkers in goroutine 1
	runtime/mgc.go:1339 +0x105

goroutine 44 gp=0xc000103500 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
	runtime/proc.go:435 +0xce fp=0xc000117738 sp=0xc000117718 pc=0x5631ac2b5d2e
runtime.gcBgMarkWorker(0xc00003d7a0)
	runtime/mgc.go:1423 +0xe9 fp=0xc0001177c8 sp=0xc000117738 pc=0x5631ac263a69
runtime.gcBgMarkStartWorkers.gowrap1()
	runtime/mgc.go:1339 +0x25 fp=0xc0001177e0 sp=0xc0001177c8 pc=0x5631ac263945
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc0001177e8 sp=0xc0001177e0 pc=0x5631ac2bdbc1
created by runtime.gcBgMarkStartWorkers in goroutine 1
	runtime/mgc.go:1339 +0x105

goroutine 45 gp=0xc0001036c0 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
	runtime/proc.go:435 +0xce fp=0xc000117f38 sp=0xc000117f18 pc=0x5631ac2b5d2e
runtime.gcBgMarkWorker(0xc00003d7a0)
	runtime/mgc.go:1423 +0xe9 fp=0xc000117fc8 sp=0xc000117f38 pc=0x5631ac263a69
runtime.gcBgMarkStartWorkers.gowrap1()
	runtime/mgc.go:1339 +0x25 fp=0xc000117fe0 sp=0xc000117fc8 pc=0x5631ac263945
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc000117fe8 sp=0xc000117fe0 pc=0x5631ac2bdbc1
created by runtime.gcBgMarkStartWorkers in goroutine 1
	runtime/mgc.go:1339 +0x105

goroutine 46 gp=0xc000103880 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
	runtime/proc.go:435 +0xce fp=0xc000118738 sp=0xc000118718 pc=0x5631ac2b5d2e
runtime.gcBgMarkWorker(0xc00003d7a0)
	runtime/mgc.go:1423 +0xe9 fp=0xc0001187c8 sp=0xc000118738 pc=0x5631ac263a69
runtime.gcBgMarkStartWorkers.gowrap1()
	runtime/mgc.go:1339 +0x25 fp=0xc0001187e0 sp=0xc0001187c8 pc=0x5631ac263945
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc0001187e8 sp=0xc0001187e0 pc=0x5631ac2bdbc1
created by runtime.gcBgMarkStartWorkers in goroutine 1
	runtime/mgc.go:1339 +0x105

goroutine 47 gp=0xc000103a40 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
	runtime/proc.go:435 +0xce fp=0xc000118f38 sp=0xc000118f18 pc=0x5631ac2b5d2e
runtime.gcBgMarkWorker(0xc00003d7a0)
	runtime/mgc.go:1423 +0xe9 fp=0xc000118fc8 sp=0xc000118f38 pc=0x5631ac263a69
runtime.gcBgMarkStartWorkers.gowrap1()
	runtime/mgc.go:1339 +0x25 fp=0xc000118fe0 sp=0xc000118fc8 pc=0x5631ac263945
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc000118fe8 sp=0xc000118fe0 pc=0x5631ac2bdbc1
created by runtime.gcBgMarkStartWorkers in goroutine 1
	runtime/mgc.go:1339 +0x105

goroutine 48 gp=0xc000103c00 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
	runtime/proc.go:435 +0xce fp=0xc000119738 sp=0xc000119718 pc=0x5631ac2b5d2e
runtime.gcBgMarkWorker(0xc00003d7a0)
	runtime/mgc.go:1423 +0xe9 fp=0xc0001197c8 sp=0xc000119738 pc=0x5631ac263a69
runtime.gcBgMarkStartWorkers.gowrap1()
	runtime/mgc.go:1339 +0x25 fp=0xc0001197e0 sp=0xc0001197c8 pc=0x5631ac263945
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc0001197e8 sp=0xc0001197e0 pc=0x5631ac2bdbc1
created by runtime.gcBgMarkStartWorkers in goroutine 1
	runtime/mgc.go:1339 +0x105

goroutine 49 gp=0xc000103dc0 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
	runtime/proc.go:435 +0xce fp=0xc000119f38 sp=0xc000119f18 pc=0x5631ac2b5d2e
runtime.gcBgMarkWorker(0xc00003d7a0)
	runtime/mgc.go:1423 +0xe9 fp=0xc000119fc8 sp=0xc000119f38 pc=0x5631ac263a69
runtime.gcBgMarkStartWorkers.gowrap1()
	runtime/mgc.go:1339 +0x25 fp=0xc000119fe0 sp=0xc000119fc8 pc=0x5631ac263945
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc000119fe8 sp=0xc000119fe0 pc=0x5631ac2bdbc1
created by runtime.gcBgMarkStartWorkers in goroutine 1
	runtime/mgc.go:1339 +0x105

goroutine 50 gp=0xc00011e000 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
	runtime/proc.go:435 +0xce fp=0xc000124738 sp=0xc000124718 pc=0x5631ac2b5d2e
runtime.gcBgMarkWorker(0xc00003d7a0)
	runtime/mgc.go:1423 +0xe9 fp=0xc0001247c8 sp=0xc000124738 pc=0x5631ac263a69
runtime.gcBgMarkStartWorkers.gowrap1()
	runtime/mgc.go:1339 +0x25 fp=0xc0001247e0 sp=0xc0001247c8 pc=0x5631ac263945
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc0001247e8 sp=0xc0001247e0 pc=0x5631ac2bdbc1
created by runtime.gcBgMarkStartWorkers in goroutine 1
	runtime/mgc.go:1339 +0x105

goroutine 51 gp=0xc00011e1c0 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
	runtime/proc.go:435 +0xce fp=0xc000124f38 sp=0xc000124f18 pc=0x5631ac2b5d2e
runtime.gcBgMarkWorker(0xc00003d7a0)
	runtime/mgc.go:1423 +0xe9 fp=0xc000124fc8 sp=0xc000124f38 pc=0x5631ac263a69
runtime.gcBgMarkStartWorkers.gowrap1()
	runtime/mgc.go:1339 +0x25 fp=0xc000124fe0 sp=0xc000124fc8 pc=0x5631ac263945
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc000124fe8 sp=0xc000124fe0 pc=0x5631ac2bdbc1
created by runtime.gcBgMarkStartWorkers in goroutine 1
	runtime/mgc.go:1339 +0x105

goroutine 52 gp=0xc00011e380 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
	runtime/proc.go:435 +0xce fp=0xc000125738 sp=0xc000125718 pc=0x5631ac2b5d2e
runtime.gcBgMarkWorker(0xc00003d7a0)
	runtime/mgc.go:1423 +0xe9 fp=0xc0001257c8 sp=0xc000125738 pc=0x5631ac263a69
runtime.gcBgMarkStartWorkers.gowrap1()
	runtime/mgc.go:1339 +0x25 fp=0xc0001257e0 sp=0xc0001257c8 pc=0x5631ac263945
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc0001257e8 sp=0xc0001257e0 pc=0x5631ac2bdbc1
created by runtime.gcBgMarkStartWorkers in goroutine 1
	runtime/mgc.go:1339 +0x105

goroutine 53 gp=0xc00011e540 m=nil [GC worker (idle)]:
runtime.gopark(0x3e7d4204531?, 0x0?, 0x0?, 0x0?, 0x0?)
	runtime/proc.go:435 +0xce fp=0xc000125f38 sp=0xc000125f18 pc=0x5631ac2b5d2e
runtime.gcBgMarkWorker(0xc00003d7a0)
	runtime/mgc.go:1423 +0xe9 fp=0xc000125fc8 sp=0xc000125f38 pc=0x5631ac263a69
runtime.gcBgMarkStartWorkers.gowrap1()
	runtime/mgc.go:1339 +0x25 fp=0xc000125fe0 sp=0xc000125fc8 pc=0x5631ac263945
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc000125fe8 sp=0xc000125fe0 pc=0x5631ac2bdbc1
created by runtime.gcBgMarkStartWorkers in goroutine 1
	runtime/mgc.go:1339 +0x105

goroutine 54 gp=0xc00011e700 m=nil [GC worker (idle)]:
runtime.gopark(0x3e7d41fbc55?, 0x0?, 0x0?, 0x0?, 0x0?)
	runtime/proc.go:435 +0xce fp=0xc000126738 sp=0xc000126718 pc=0x5631ac2b5d2e
runtime.gcBgMarkWorker(0xc00003d7a0)
	runtime/mgc.go:1423 +0xe9 fp=0xc0001267c8 sp=0xc000126738 pc=0x5631ac263a69
runtime.gcBgMarkStartWorkers.gowrap1()
	runtime/mgc.go:1339 +0x25 fp=0xc0001267e0 sp=0xc0001267c8 pc=0x5631ac263945
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc0001267e8 sp=0xc0001267e0 pc=0x5631ac2bdbc1
created by runtime.gcBgMarkStartWorkers in goroutine 1
	runtime/mgc.go:1339 +0x105

goroutine 55 gp=0xc00011e8c0 m=nil [GC worker (idle)]:
runtime.gopark(0x3e7d41fd4f2?, 0x1?, 0x93?, 0x9b?, 0x0?)
	runtime/proc.go:435 +0xce fp=0xc000126f38 sp=0xc000126f18 pc=0x5631ac2b5d2e
runtime.gcBgMarkWorker(0xc00003d7a0)
	runtime/mgc.go:1423 +0xe9 fp=0xc000126fc8 sp=0xc000126f38 pc=0x5631ac263a69
runtime.gcBgMarkStartWorkers.gowrap1()
	runtime/mgc.go:1339 +0x25 fp=0xc000126fe0 sp=0xc000126fc8 pc=0x5631ac263945
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc000126fe8 sp=0xc000126fe0 pc=0x5631ac2bdbc1
created by runtime.gcBgMarkStartWorkers in goroutine 1
	runtime/mgc.go:1339 +0x105

goroutine 56 gp=0xc00011ea80 m=nil [GC worker (idle)]:
runtime.gopark(0x5631ae360ba0?, 0x1?, 0x2e?, 0x4e?, 0x0?)
	runtime/proc.go:435 +0xce fp=0xc000127738 sp=0xc000127718 pc=0x5631ac2b5d2e
runtime.gcBgMarkWorker(0xc00003d7a0)
	runtime/mgc.go:1423 +0xe9 fp=0xc0001277c8 sp=0xc000127738 pc=0x5631ac263a69
runtime.gcBgMarkStartWorkers.gowrap1()
	runtime/mgc.go:1339 +0x25 fp=0xc0001277e0 sp=0xc0001277c8 pc=0x5631ac263945
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc0001277e8 sp=0xc0001277e0 pc=0x5631ac2bdbc1
created by runtime.gcBgMarkStartWorkers in goroutine 1
	runtime/mgc.go:1339 +0x105

goroutine 57 gp=0xc00011ec40 m=nil [GC worker (idle)]:
runtime.gopark(0x5631ae360ba0?, 0x1?, 0xf8?, 0x9b?, 0x0?)
	runtime/proc.go:435 +0xce fp=0xc000127f38 sp=0xc000127f18 pc=0x5631ac2b5d2e
runtime.gcBgMarkWorker(0xc00003d7a0)
	runtime/mgc.go:1423 +0xe9 fp=0xc000127fc8 sp=0xc000127f38 pc=0x5631ac263a69
runtime.gcBgMarkStartWorkers.gowrap1()
	runtime/mgc.go:1339 +0x25 fp=0xc000127fe0 sp=0xc000127fc8 pc=0x5631ac263945
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc000127fe8 sp=0xc000127fe0 pc=0x5631ac2bdbc1
created by runtime.gcBgMarkStartWorkers in goroutine 1
	runtime/mgc.go:1339 +0x105

goroutine 58 gp=0xc00011ee00 m=nil [GC worker (idle)]:
runtime.gopark(0x3e7d41fd68c?, 0x1?, 0x74?, 0x79?, 0x0?)
	runtime/proc.go:435 +0xce fp=0xc000120738 sp=0xc000120718 pc=0x5631ac2b5d2e
runtime.gcBgMarkWorker(0xc00003d7a0)
	runtime/mgc.go:1423 +0xe9 fp=0xc0001207c8 sp=0xc000120738 pc=0x5631ac263a69
runtime.gcBgMarkStartWorkers.gowrap1()
	runtime/mgc.go:1339 +0x25 fp=0xc0001207e0 sp=0xc0001207c8 pc=0x5631ac263945
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc0001207e8 sp=0xc0001207e0 pc=0x5631ac2bdbc1
created by runtime.gcBgMarkStartWorkers in goroutine 1
	runtime/mgc.go:1339 +0x105

goroutine 9 gp=0xc0005048c0 m=nil [sync.WaitGroup.Wait]:
runtime.gopark(0x0?, 0x0?, 0x60?, 0x40?, 0x0?)
	runtime/proc.go:435 +0xce fp=0xc000122620 sp=0xc000122600 pc=0x5631ac2b5d2e
runtime.goparkunlock(...)
	runtime/proc.go:441
runtime.semacquire1(0xc0004c8840, 0x0, 0x1, 0x0, 0x18)
	runtime/sema.go:188 +0x229 fp=0xc000122688 sp=0xc000122620 pc=0x5631ac295ca9
sync.runtime_SemacquireWaitGroup(0x0?)
	runtime/sema.go:110 +0x25 fp=0xc0001226c0 sp=0xc000122688 pc=0x5631ac2b7665
sync.(*WaitGroup).Wait(0x0?)
	sync/waitgroup.go:118 +0x48 fp=0xc0001226e8 sp=0xc0001226c0 pc=0x5631ac2c9628
github.com/ollama/ollama/runner/llamarunner.(*Server).run(0xc0004c8820, {0x5631ad95d470, 0xc00059f400})
	github.com/ollama/ollama/runner/llamarunner/runner.go:360 +0x4b fp=0xc0001227b8 sp=0xc0001226e8 pc=0x5631ac771e8b
github.com/ollama/ollama/runner/llamarunner.Execute.gowrap1()
	github.com/ollama/ollama/runner/llamarunner/runner.go:981 +0x28 fp=0xc0001227e0 sp=0xc0001227b8 pc=0x5631ac7773e8
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc0001227e8 sp=0xc0001227e0 pc=0x5631ac2bdbc1
created by github.com/ollama/ollama/runner/llamarunner.Execute in goroutine 1
	github.com/ollama/ollama/runner/llamarunner/runner.go:981 +0x4c5

goroutine 10 gp=0xc000504a80 m=nil [IO wait]:
runtime.gopark(0x5631ac3406c5?, 0xc0003b5e80?, 0x40?, 0x3a?, 0xb?)
	runtime/proc.go:435 +0xce fp=0xc000053948 sp=0xc000053928 pc=0x5631ac2b5d2e
runtime.netpollblock(0x5631ac2d94f8?, 0xac24f466?, 0x31?)
	runtime/netpoll.go:575 +0xf7 fp=0xc000053980 sp=0xc000053948 pc=0x5631ac27b057
internal/poll.runtime_pollWait(0x7f3262ec7d98, 0x72)
	runtime/netpoll.go:351 +0x85 fp=0xc0000539a0 sp=0xc000053980 pc=0x5631ac2b4f45
internal/poll.(*pollDesc).wait(0xc0003b5e80?, 0xc000295000?, 0x0)
	internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc0000539c8 sp=0xc0000539a0 pc=0x5631ac33d0c7
internal/poll.(*pollDesc).waitRead(...)
	internal/poll/fd_poll_runtime.go:89
internal/poll.(*FD).Read(0xc0003b5e80, {0xc000295000, 0x1000, 0x1000})
	internal/poll/fd_unix.go:165 +0x27a fp=0xc000053a60 sp=0xc0000539c8 pc=0x5631ac33e3ba
net.(*netFD).Read(0xc0003b5e80, {0xc000295000?, 0xc000053ad0?, 0x5631ac33d585?})
	net/fd_posix.go:55 +0x25 fp=0xc000053aa8 sp=0xc000053a60 pc=0x5631ac3b35a5
net.(*conn).Read(0xc000176560, {0xc000295000?, 0x0?, 0x0?})
	net/net.go:194 +0x45 fp=0xc000053af0 sp=0xc000053aa8 pc=0x5631ac3c1965
net/http.(*connReader).Read(0xc0004c3140, {0xc000295000, 0x1000, 0x1000})
	net/http/server.go:798 +0x159 fp=0xc000053b40 sp=0xc000053af0 pc=0x5631ac5ae939
bufio.(*Reader).fill(0xc000110780)
	bufio/bufio.go:113 +0x103 fp=0xc000053b78 sp=0xc000053b40 pc=0x5631ac3d9a23
bufio.(*Reader).Peek(0xc000110780, 0x4)
	bufio/bufio.go:152 +0x53 fp=0xc000053b98 sp=0xc000053b78 pc=0x5631ac3d9b53
net/http.(*conn).serve(0xc0004c6480, {0x5631ad95d438, 0xc0004c3050})
	net/http/server.go:2137 +0x785 fp=0xc000053fb8 sp=0xc000053b98 pc=0x5631ac5b4725
net/http.(*Server).Serve.gowrap3()
	net/http/server.go:3454 +0x28 fp=0xc000053fe0 sp=0xc000053fb8 pc=0x5631ac5b9e88
runtime.goexit({})
	runtime/asm_amd64.s:1700 +0x1 fp=0xc000053fe8 sp=0xc000053fe0 pc=0x5631ac2bdbc1
created by net/http.(*Server).Serve in goroutine 1
	net/http/server.go:3454 +0x485

rax    0x7f326332a670
rbx    0x5631eb0782c0
rcx    0x0
rdx    0x5631e232d170
rdi    0x7f31e0a58e48
rsi    0x3
rbp    0x7f326332a670
rsp    0x7fff3f3aa850
r8     0x0
r9     0x0
r10    0x2b1
r11    0x5631e2a295fc
r12    0x0
r13    0x0
r14    0x18
r15    0x1
rip    0x7f31e06c0bf5
rflags 0x10246
cs     0x33
fs     0x0
gs     0x0
time=2026-01-24T11:07:46.327+08:00 level=INFO source=sched.go:479 msg="Load failed" model=/home/qian/.ollama/models/blobs/sha256-de20d2cf2dc430b1717a8b07a9df029d651f3895dbffec4729a3902a6fe344c9 error="llama runner process has terminated: exit status 2"
[GIN] 2026/01/24 - 11:07:46 | 500 |  1.618251058s |       127.0.0.1 | POST     "/api/generate"

OS

EndeavourOS
KDE Plasma Version: 6.5.4
KDE Frameworks Version: 6.22.0
Qt Version: 6.10.1
Kernel Version: 6.18.4-arch1-1(64-bit)
Graphics Platform: X11

GPU

Radeon 8060s Graphics

CPU

32 × AMD RYZEN AI MAX+ 395 w/ Radeon 8060S
128 GiB of RAM (62.4 GiB usable)

Ollama version

client version is 0.14.3

Originally created by @qjgwork on GitHub (Jan 24, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/13873 ### What is the issue? Install the ollama by `curl -fsSL https://ollama.com/install.sh | sh` Install the rocm bin: `1 aur/rocm-gfx1151-bin 7.10.0pre-2 (+0 0.00) (Installed) ROCm Core SDK and TheRock Build System - Ryzen AI Max` run the ollama and then load the model , I got the SIGSEGV ### System information ``` ± % ollama -v !381 ollama version is 0.14.3 ± % rocminfo !422 ROCk module is loaded ===================== HSA System Attributes ===================== Runtime Version: 1.18 Runtime Ext Version: 1.15 System Timestamp Freq.: 1000.000000MHz Sig. Max Wait Duration: 18446744073709551615 (0xFFFFFFFFFFFFFFFF) (timestamp count) Machine Model: LARGE System Endianness: LITTLE Mwaitx: DISABLED XNACK enabled: NO DMAbuf Support: YES VMM Support: YES ========== HSA Agents ========== ******* Agent 1 ******* Name: AMD RYZEN AI MAX+ 395 w/ Radeon 8060S Uuid: CPU-XX Marketing Name: AMD RYZEN AI MAX+ 395 w/ Radeon 8060S Vendor Name: CPU Feature: None specified Profile: FULL_PROFILE Float Round Mode: NEAR Max Queue Number: 0(0x0) Queue Min Size: 0(0x0) Queue Max Size: 0(0x0) Queue Type: MULTI Node: 0 Device Type: CPU Cache Info: L1: 49152(0xc000) KB Chip ID: 0(0x0) ASIC Revision: 0(0x0) Cacheline Size: 64(0x40) Max Clock Freq. (MHz): 5187 BDFID: 0 Internal Node ID: 0 Compute Unit: 32 SIMDs per CU: 0 Shader Engines: 0 Shader Arrs. per Eng.: 0 WatchPts on Addr. Ranges:1 Memory Properties: Features: None Pool Info: Pool 1 Segment: GLOBAL; FLAGS: FINE GRAINED Size: 65462660(0x3e6e184) KB Allocatable: TRUE Alloc Granule: 4KB Alloc Recommended Granule:4KB Alloc Alignment: 4KB Accessible by all: TRUE Pool 2 Segment: GLOBAL; FLAGS: EXTENDED FINE GRAINED Size: 65462660(0x3e6e184) KB Allocatable: TRUE Alloc Granule: 4KB Alloc Recommended Granule:4KB Alloc Alignment: 4KB Accessible by all: TRUE Pool 3 Segment: GLOBAL; FLAGS: KERNARG, FINE GRAINED Size: 65462660(0x3e6e184) KB Allocatable: TRUE Alloc Granule: 4KB Alloc Recommended Granule:4KB Alloc Alignment: 4KB Accessible by all: TRUE Pool 4 Segment: GLOBAL; FLAGS: COARSE GRAINED Size: 65462660(0x3e6e184) KB Allocatable: TRUE Alloc Granule: 4KB Alloc Recommended Granule:4KB Alloc Alignment: 4KB Accessible by all: TRUE ISA Info: ******* Agent 2 ******* Name: gfx1151 Uuid: GPU-XX Marketing Name: Radeon 8060S Graphics Vendor Name: AMD Feature: KERNEL_DISPATCH Profile: BASE_PROFILE Float Round Mode: NEAR Max Queue Number: 128(0x80) Queue Min Size: 64(0x40) Queue Max Size: 131072(0x20000) Queue Type: MULTI Node: 1 Device Type: GPU Cache Info: L1: 32(0x20) KB L2: 2048(0x800) KB L3: 32768(0x8000) KB Chip ID: 5510(0x1586) ASIC Revision: 0(0x0) Cacheline Size: 128(0x80) Max Clock Freq. (MHz): 2900 BDFID: 50688 Internal Node ID: 1 Compute Unit: 40 SIMDs per CU: 2 Shader Engines: 2 Shader Arrs. per Eng.: 2 WatchPts on Addr. Ranges:4 Coherent Host Access: FALSE Memory Properties: APU Features: KERNEL_DISPATCH Fast F16 Operation: TRUE Wavefront Size: 32(0x20) Workgroup Max Size: 1024(0x400) Workgroup Max Size per Dimension: x 1024(0x400) y 1024(0x400) z 1024(0x400) Max Waves Per CU: 32(0x20) Max Work-item Per CU: 1024(0x400) Grid Max Size: 4294967295(0xffffffff) Grid Max Size per Dimension: x 2147483647(0x7fffffff) y 65535(0xffff) z 65535(0xffff) Max fbarriers/Workgrp: 32 Packet Processor uCode:: 32 SDMA engine uCode:: 17 IOMMU Support:: None Pool Info: Pool 1 Segment: GLOBAL; FLAGS: COARSE GRAINED Size: 67108864(0x4000000) KB Allocatable: TRUE Alloc Granule: 4KB Alloc Recommended Granule:2048KB Alloc Alignment: 4KB Accessible by all: FALSE Pool 2 Segment: GLOBAL; FLAGS: EXTENDED FINE GRAINED Size: 67108864(0x4000000) KB Allocatable: TRUE Alloc Granule: 4KB Alloc Recommended Granule:2048KB Alloc Alignment: 4KB Accessible by all: FALSE Pool 3 Segment: GROUP Size: 64(0x40) KB Allocatable: FALSE Alloc Granule: 0KB Alloc Recommended Granule:0KB Alloc Alignment: 0KB Accessible by all: FALSE ISA Info: ISA 1 Name: amdgcn-amd-amdhsa--gfx1151 Machine Models: HSA_MACHINE_MODEL_LARGE Profiles: HSA_PROFILE_BASE Default Rounding Mode: NEAR Default Rounding Mode: NEAR Fast f16: TRUE Workgroup Max Size: 1024(0x400) Workgroup Max Size per Dimension: x 1024(0x400) y 1024(0x400) z 1024(0x400) Grid Max Size: 4294967295(0xffffffff) Grid Max Size per Dimension: x 2147483647(0x7fffffff) y 65535(0xffff) z 65535(0xffff) FBarrier Max Size: 32 ISA 2 Name: amdgcn-amd-amdhsa--gfx11-generic Machine Models: HSA_MACHINE_MODEL_LARGE Profiles: HSA_PROFILE_BASE Default Rounding Mode: NEAR Default Rounding Mode: NEAR Fast f16: TRUE Workgroup Max Size: 1024(0x400) Workgroup Max Size per Dimension: x 1024(0x400) y 1024(0x400) z 1024(0x400) Grid Max Size: 4294967295(0xffffffff) Grid Max Size per Dimension: x 2147483647(0x7fffffff) y 65535(0xffff) z 65535(0xffff) FBarrier Max Size: 32 *** Done *** ``` ### Relevant log output ```shell ± % ollama serve !421 time=2026-01-24T11:07:37.024+08:00 level=INFO source=routes.go:1629 msg="server config" env="map[CUDA_VISIBLE_DEVICES: GGML_VK_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION:11.5.1 HTTPS_PROXY:http://127.0.0.1:7890 HTTP_PROXY:http://127.0.0.1:7890 NO_PROXY: OLLAMA_CONTEXT_LENGTH:4096 OLLAMA_DEBUG:INFO OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/home/qian/.ollama/models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:1 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://* vscode-file://*] OLLAMA_REMOTES:[ollama.com] OLLAMA_SCHED_SPREAD:false OLLAMA_VULKAN:false ROCR_VISIBLE_DEVICES: http_proxy:http://127.0.0.1:7890 https_proxy:http://127.0.0.1:7890 no_proxy:]" time=2026-01-24T11:07:37.025+08:00 level=INFO source=images.go:501 msg="total blobs: 10" time=2026-01-24T11:07:37.025+08:00 level=INFO source=images.go:508 msg="total unused blobs removed: 0" time=2026-01-24T11:07:37.025+08:00 level=INFO source=routes.go:1682 msg="Listening on 127.0.0.1:11434 (version 0.14.3)" time=2026-01-24T11:07:37.026+08:00 level=INFO source=runner.go:67 msg="discovering available GPUs..." time=2026-01-24T11:07:37.026+08:00 level=WARN source=runner.go:485 msg="user overrode visible devices" HSA_OVERRIDE_GFX_VERSION=11.5.1 time=2026-01-24T11:07:37.026+08:00 level=WARN source=runner.go:489 msg="if GPUs are not correctly discovered, unset and try again" time=2026-01-24T11:07:37.027+08:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 38159" time=2026-01-24T11:07:37.543+08:00 level=INFO source=runner.go:106 msg="experimental Vulkan support disabled. To enable, set OLLAMA_VULKAN=1" time=2026-01-24T11:07:37.543+08:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 41889" time=2026-01-24T11:07:37.558+08:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 33065" time=2026-01-24T11:07:37.573+08:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 36325" time=2026-01-24T11:07:38.071+08:00 level=INFO source=types.go:42 msg="inference compute" id=0 filter_id=0 library=ROCm compute=gfx1151 name=ROCm0 description="AMD Radeon Graphics" libdirs=ollama,rocm driver=60342.13 pci_id=0000:c6:00.0 type=iGPU total="95.2 GiB" available="93.9 GiB" [GIN] 2026/01/24 - 11:07:44 | 200 | 42.648µs | 127.0.0.1 | HEAD "/" [GIN] 2026/01/24 - 11:07:44 | 200 | 94.241383ms | 127.0.0.1 | POST "/api/show" [GIN] 2026/01/24 - 11:07:44 | 200 | 98.052397ms | 127.0.0.1 | POST "/api/show" time=2026-01-24T11:07:44.855+08:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 42379" llama_model_loader: loaded meta data with 29 key-value pairs and 724 tensors from /home/qian/.ollama/models/blobs/sha256-de20d2cf2dc430b1717a8b07a9df029d651f3895dbffec4729a3902a6fe344c9 (version GGUF V3 (latest)) llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output. llama_model_loader: - kv 0: general.architecture str = llama llama_model_loader: - kv 1: general.type str = model llama_model_loader: - kv 2: general.name str = Meta Llama 3.1 70B Instruct llama_model_loader: - kv 3: general.finetune str = Instruct llama_model_loader: - kv 4: general.basename str = Meta-Llama-3.1 llama_model_loader: - kv 5: general.size_label str = 70B llama_model_loader: - kv 6: general.license str = llama3.1 llama_model_loader: - kv 7: general.tags arr[str,6] = ["facebook", "meta", "pytorch", "llam... llama_model_loader: - kv 8: general.languages arr[str,8] = ["en", "de", "fr", "it", "pt", "hi", ... llama_model_loader: - kv 9: llama.block_count u32 = 80 llama_model_loader: - kv 10: llama.context_length u32 = 131072 llama_model_loader: - kv 11: llama.embedding_length u32 = 8192 llama_model_loader: - kv 12: llama.feed_forward_length u32 = 28672 llama_model_loader: - kv 13: llama.attention.head_count u32 = 64 llama_model_loader: - kv 14: llama.attention.head_count_kv u32 = 8 llama_model_loader: - kv 15: llama.rope.freq_base f32 = 500000.000000 llama_model_loader: - kv 16: llama.attention.layer_norm_rms_epsilon f32 = 0.000010 llama_model_loader: - kv 17: general.file_type u32 = 15 llama_model_loader: - kv 18: llama.vocab_size u32 = 128256 llama_model_loader: - kv 19: llama.rope.dimension_count u32 = 128 llama_model_loader: - kv 20: tokenizer.ggml.model str = gpt2 llama_model_loader: - kv 21: tokenizer.ggml.pre str = llama-bpe llama_model_loader: - kv 22: tokenizer.ggml.tokens arr[str,128256] = ["!", "\"", "#", "$", "%", "&", "'", ... llama_model_loader: - kv 23: tokenizer.ggml.token_type arr[i32,128256] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... llama_model_loader: - kv 24: tokenizer.ggml.merges arr[str,280147] = ["Ġ Ġ", "Ġ ĠĠĠ", "ĠĠ ĠĠ", "... llama_model_loader: - kv 25: tokenizer.ggml.bos_token_id u32 = 128000 llama_model_loader: - kv 26: tokenizer.ggml.eos_token_id u32 = 128009 llama_model_loader: - kv 27: tokenizer.chat_template str = {{- bos_token }}\n{%- if custom_tools ... llama_model_loader: - kv 28: general.quantization_version u32 = 2 llama_model_loader: - type f32: 162 tensors llama_model_loader: - type q4_K: 441 tensors llama_model_loader: - type q5_K: 40 tensors llama_model_loader: - type q6_K: 81 tensors print_info: file format = GGUF V3 (latest) print_info: file type = Q4_K - Medium print_info: file size = 39.59 GiB (4.82 BPW) load: printing all EOG tokens: load: - 128001 ('<|end_of_text|>') load: - 128008 ('<|eom_id|>') load: - 128009 ('<|eot_id|>') load: special tokens cache size = 256 load: token to piece cache size = 0.7999 MB print_info: arch = llama print_info: vocab_only = 1 print_info: no_alloc = 0 print_info: model type = ?B print_info: model params = 70.55 B print_info: general.name = Meta Llama 3.1 70B Instruct print_info: vocab type = BPE print_info: n_vocab = 128256 print_info: n_merges = 280147 print_info: BOS token = 128000 '<|begin_of_text|>' print_info: EOS token = 128009 '<|eot_id|>' print_info: EOT token = 128009 '<|eot_id|>' print_info: EOM token = 128008 '<|eom_id|>' print_info: LF token = 198 'Ċ' print_info: EOG token = 128001 '<|end_of_text|>' print_info: EOG token = 128008 '<|eom_id|>' print_info: EOG token = 128009 '<|eot_id|>' print_info: max token length = 256 llama_model_load: vocab only - skipping tensors time=2026-01-24T11:07:45.477+08:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --model /home/qian/.ollama/models/blobs/sha256-de20d2cf2dc430b1717a8b07a9df029d651f3895dbffec4729a3902a6fe344c9 --port 37749" time=2026-01-24T11:07:45.478+08:00 level=INFO source=sched.go:452 msg="system memory" total="62.4 GiB" free="57.1 GiB" free_swap="97.2 GiB" time=2026-01-24T11:07:45.478+08:00 level=INFO source=sched.go:459 msg="gpu memory" id=0 library=ROCm available="93.5 GiB" free="93.9 GiB" minimum="457.0 MiB" overhead="0 B" time=2026-01-24T11:07:45.478+08:00 level=INFO source=server.go:496 msg="loading model" "model layers"=81 requested=-1 time=2026-01-24T11:07:45.478+08:00 level=INFO source=device.go:240 msg="model weights" device=ROCm0 size="39.0 GiB" time=2026-01-24T11:07:45.478+08:00 level=INFO source=device.go:251 msg="kv cache" device=ROCm0 size="1.2 GiB" time=2026-01-24T11:07:45.478+08:00 level=INFO source=device.go:262 msg="compute graph" device=ROCm0 size="584.0 MiB" time=2026-01-24T11:07:45.478+08:00 level=INFO source=device.go:272 msg="total memory" size="40.9 GiB" time=2026-01-24T11:07:45.486+08:00 level=INFO source=runner.go:965 msg="starting go runner" load_backend: loaded CPU backend from /usr/local/lib/ollama/libggml-cpu-icelake.so /opt/amdgpu/share/libdrm/amdgpu.ids: No such file or directory ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no ggml_cuda_init: found 1 ROCm devices: Device 0: AMD Radeon Graphics, gfx1151 (0x1151), VMM: no, Wave Size: 32, ID: 0 load_backend: loaded ROCm backend from /usr/local/lib/ollama/rocm/libggml-hip.so time=2026-01-24T11:07:45.822+08:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.AVX512=1 CPU.0.AVX512_VBMI=1 CPU.0.AVX512_VNNI=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 ROCm.0.NO_VMM=1 ROCm.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(gcc) time=2026-01-24T11:07:45.823+08:00 level=INFO source=runner.go:1001 msg="Server listening on 127.0.0.1:37749" time=2026-01-24T11:07:45.825+08:00 level=INFO source=runner.go:895 msg=load request="{Operation:commit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Auto KvSize:4096 KvCacheType: NumThreads:16 GPULayers:81[ID:0 Layers:81(0..80)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:true}" ggml_hip_get_device_memory searching for device 0000:c6:00.0 time=2026-01-24T11:07:45.825+08:00 level=INFO source=server.go:1347 msg="waiting for llama runner to start responding" time=2026-01-24T11:07:45.825+08:00 level=INFO source=server.go:1381 msg="waiting for server to become available" status="llm server loading model" ggml_backend_cuda_device_get_memory device 0000:c6:00.0 utilizing AMD specific memory reporting free: 100868141056 total: 102236356608 llama_model_load_from_file_impl: using device ROCm0 (AMD Radeon Graphics) (0000:c6:00.0) - 96195 MiB free llama_model_loader: loaded meta data with 29 key-value pairs and 724 tensors from /home/qian/.ollama/models/blobs/sha256-de20d2cf2dc430b1717a8b07a9df029d651f3895dbffec4729a3902a6fe344c9 (version GGUF V3 (latest)) llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output. llama_model_loader: - kv 0: general.architecture str = llama llama_model_loader: - kv 1: general.type str = model llama_model_loader: - kv 2: general.name str = Meta Llama 3.1 70B Instruct llama_model_loader: - kv 3: general.finetune str = Instruct llama_model_loader: - kv 4: general.basename str = Meta-Llama-3.1 llama_model_loader: - kv 5: general.size_label str = 70B llama_model_loader: - kv 6: general.license str = llama3.1 llama_model_loader: - kv 7: general.tags arr[str,6] = ["facebook", "meta", "pytorch", "llam... llama_model_loader: - kv 8: general.languages arr[str,8] = ["en", "de", "fr", "it", "pt", "hi", ... llama_model_loader: - kv 9: llama.block_count u32 = 80 llama_model_loader: - kv 10: llama.context_length u32 = 131072 llama_model_loader: - kv 11: llama.embedding_length u32 = 8192 llama_model_loader: - kv 12: llama.feed_forward_length u32 = 28672 llama_model_loader: - kv 13: llama.attention.head_count u32 = 64 llama_model_loader: - kv 14: llama.attention.head_count_kv u32 = 8 llama_model_loader: - kv 15: llama.rope.freq_base f32 = 500000.000000 llama_model_loader: - kv 16: llama.attention.layer_norm_rms_epsilon f32 = 0.000010 llama_model_loader: - kv 17: general.file_type u32 = 15 llama_model_loader: - kv 18: llama.vocab_size u32 = 128256 llama_model_loader: - kv 19: llama.rope.dimension_count u32 = 128 llama_model_loader: - kv 20: tokenizer.ggml.model str = gpt2 llama_model_loader: - kv 21: tokenizer.ggml.pre str = llama-bpe llama_model_loader: - kv 22: tokenizer.ggml.tokens arr[str,128256] = ["!", "\"", "#", "$", "%", "&", "'", ... llama_model_loader: - kv 23: tokenizer.ggml.token_type arr[i32,128256] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... llama_model_loader: - kv 24: tokenizer.ggml.merges arr[str,280147] = ["Ġ Ġ", "Ġ ĠĠĠ", "ĠĠ ĠĠ", "... llama_model_loader: - kv 25: tokenizer.ggml.bos_token_id u32 = 128000 llama_model_loader: - kv 26: tokenizer.ggml.eos_token_id u32 = 128009 llama_model_loader: - kv 27: tokenizer.chat_template str = {{- bos_token }}\n{%- if custom_tools ... llama_model_loader: - kv 28: general.quantization_version u32 = 2 llama_model_loader: - type f32: 162 tensors llama_model_loader: - type q4_K: 441 tensors llama_model_loader: - type q5_K: 40 tensors llama_model_loader: - type q6_K: 81 tensors print_info: file format = GGUF V3 (latest) print_info: file type = Q4_K - Medium print_info: file size = 39.59 GiB (4.82 BPW) load: printing all EOG tokens: load: - 128001 ('<|end_of_text|>') load: - 128008 ('<|eom_id|>') load: - 128009 ('<|eot_id|>') load: special tokens cache size = 256 load: token to piece cache size = 0.7999 MB print_info: arch = llama print_info: vocab_only = 0 print_info: no_alloc = 0 print_info: n_ctx_train = 131072 print_info: n_embd = 8192 print_info: n_embd_inp = 8192 print_info: n_layer = 80 print_info: n_head = 64 print_info: n_head_kv = 8 print_info: n_rot = 128 print_info: n_swa = 0 print_info: is_swa_any = 0 print_info: n_embd_head_k = 128 print_info: n_embd_head_v = 128 print_info: n_gqa = 8 print_info: n_embd_k_gqa = 1024 print_info: n_embd_v_gqa = 1024 print_info: f_norm_eps = 0.0e+00 print_info: f_norm_rms_eps = 1.0e-05 print_info: f_clamp_kqv = 0.0e+00 print_info: f_max_alibi_bias = 0.0e+00 print_info: f_logit_scale = 0.0e+00 print_info: f_attn_scale = 0.0e+00 print_info: n_ff = 28672 print_info: n_expert = 0 print_info: n_expert_used = 0 print_info: n_expert_groups = 0 print_info: n_group_used = 0 print_info: causal attn = 1 print_info: pooling type = 0 print_info: rope type = 0 print_info: rope scaling = linear print_info: freq_base_train = 500000.0 print_info: freq_scale_train = 1 print_info: n_ctx_orig_yarn = 131072 print_info: rope_yarn_log_mul= 0.0000 print_info: rope_finetuned = unknown print_info: model type = 70B print_info: model params = 70.55 B print_info: general.name = Meta Llama 3.1 70B Instruct print_info: vocab type = BPE print_info: n_vocab = 128256 print_info: n_merges = 280147 print_info: BOS token = 128000 '<|begin_of_text|>' print_info: EOS token = 128009 '<|eot_id|>' print_info: EOT token = 128009 '<|eot_id|>' print_info: EOM token = 128008 '<|eom_id|>' print_info: LF token = 198 'Ċ' print_info: EOG token = 128001 '<|end_of_text|>' print_info: EOG token = 128008 '<|eom_id|>' print_info: EOG token = 128009 '<|eot_id|>' print_info: max token length = 256 load_tensors: loading model tensors, this can take a while... (mmap = true) load_tensors: offloading 80 repeating layers to GPU load_tensors: offloading output layer to GPU load_tensors: offloaded 81/81 layers to GPU load_tensors: CPU_Mapped model buffer size = 563.62 MiB load_tensors: ROCm0 model buffer size = 39979.48 MiB SIGSEGV: segmentation violation PC=0x7f31e06c0bf5 m=0 sigcode=1 addr=0x18 signal arrived during cgo execution goroutine 13 gp=0xc000504e00 m=0 mp=0x5631ae294080 [syscall]: runtime.cgocall(0x5631ad0b60d2, 0xc0000c7b58) runtime/cgocall.go:167 +0x4b fp=0xc0000c7b30 sp=0xc0000c7af8 pc=0x5631ac2b28ab github.com/ollama/ollama/llama._Cfunc_llama_model_load_from_file(0x5631e2a8cbc0, {0xc0003880a0, 0x0, 0x51, 0x1, 0x0, 0xc0003634f8, 0x5631ad0b5315, 0xc000388028, 0x0, ...}) _cgo_gotypes.go:910 +0x4b fp=0xc0000c7b58 sp=0xc0000c7b30 pc=0x5631ac6b3d6b github.com/ollama/ollama/llama.LoadModelFromFile.func1(...) github.com/ollama/ollama/llama/llama.go:308 github.com/ollama/ollama/llama.LoadModelFromFile({0x7fff3f3ac82b, 0x67}, {{0xc000363580, 0x1, 0x1}, 0x51, 0x0, 0x1, {0xc0003634f8, 0x1, ...}, ...}) github.com/ollama/ollama/llama/llama.go:308 +0x56d fp=0xc0000c7da0 sp=0xc0000c7b58 pc=0x5631ac6b70ed github.com/ollama/ollama/runner/llamarunner.(*Server).loadModel(0xc0004c8820, {{0xc000363580, 0x1, 0x1}, 0x51, 0x0, 0x1, {0xc0003634f8, 0x1, 0x2}, ...}, ...) github.com/ollama/ollama/runner/llamarunner/runner.go:841 +0x9e fp=0xc0000c7ee8 sp=0xc0000c7da0 pc=0x5631ac7754be github.com/ollama/ollama/runner/llamarunner.(*Server).load.gowrap2() github.com/ollama/ollama/runner/llamarunner/runner.go:934 +0x114 fp=0xc0000c7fe0 sp=0xc0000c7ee8 pc=0x5631ac7767b4 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0000c7fe8 sp=0xc0000c7fe0 pc=0x5631ac2bdbc1 created by github.com/ollama/ollama/runner/llamarunner.(*Server).load in goroutine 10 github.com/ollama/ollama/runner/llamarunner/runner.go:934 +0x889 goroutine 1 gp=0xc000002380 m=nil [IO wait]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000139790 sp=0xc000139770 pc=0x5631ac2b5d2e runtime.netpollblock(0xc0001397e0?, 0xac24f466?, 0x31?) runtime/netpoll.go:575 +0xf7 fp=0xc0001397c8 sp=0xc000139790 pc=0x5631ac27b057 internal/poll.runtime_pollWait(0x7f3262ec7eb0, 0x72) runtime/netpoll.go:351 +0x85 fp=0xc0001397e8 sp=0xc0001397c8 pc=0x5631ac2b4f45 internal/poll.(*pollDesc).wait(0xc0003b5e00?, 0x900000036?, 0x0) internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc000139810 sp=0xc0001397e8 pc=0x5631ac33d0c7 internal/poll.(*pollDesc).waitRead(...) internal/poll/fd_poll_runtime.go:89 internal/poll.(*FD).Accept(0xc0003b5e00) internal/poll/fd_unix.go:620 +0x295 fp=0xc0001398b8 sp=0xc000139810 pc=0x5631ac342495 net.(*netFD).accept(0xc0003b5e00) net/fd_unix.go:172 +0x29 fp=0xc000139970 sp=0xc0001398b8 pc=0x5631ac3b5549 net.(*TCPListener).accept(0xc0005b7600) net/tcpsock_posix.go:159 +0x1b fp=0xc0001399c0 sp=0xc000139970 pc=0x5631ac3cb45b net.(*TCPListener).Accept(0xc0005b7600) net/tcpsock.go:380 +0x30 fp=0xc0001399f0 sp=0xc0001399c0 pc=0x5631ac3ca310 net/http.(*onceCloseListener).Accept(0xc0004c6480?) <autogenerated>:1 +0x24 fp=0xc000139a08 sp=0xc0001399f0 pc=0x5631ac5e21c4 net/http.(*Server).Serve(0xc00005b900, {0x5631ad95ade0, 0xc0005b7600}) net/http/server.go:3424 +0x30c fp=0xc000139b38 sp=0xc000139a08 pc=0x5631ac5b9a8c github.com/ollama/ollama/runner/llamarunner.Execute({0xc000034260, 0x4, 0x4}) github.com/ollama/ollama/runner/llamarunner/runner.go:1002 +0x8f5 fp=0xc000139d08 sp=0xc000139b38 pc=0x5631ac777175 github.com/ollama/ollama/runner.Execute({0xc000034250?, 0x0?, 0x0?}) github.com/ollama/ollama/runner/runner.go:30 +0x130 fp=0xc000139d30 sp=0xc000139d08 pc=0x5631ac8645d0 github.com/ollama/ollama/cmd.NewCLI.func3(0xc00005b600?, {0x5631ad3e90df?, 0x4?, 0x5631ad3e90e3?}) github.com/ollama/ollama/cmd/cmd.go:1961 +0x45 fp=0xc000139d58 sp=0xc000139d30 pc=0x5631ad035025 github.com/spf13/cobra.(*Command).execute(0xc000243208, {0xc0005b7400, 0x4, 0x4}) github.com/spf13/cobra@v1.7.0/command.go:940 +0x85c fp=0xc000139e78 sp=0xc000139d58 pc=0x5631ac42f4bc github.com/spf13/cobra.(*Command).ExecuteC(0xc000646f08) github.com/spf13/cobra@v1.7.0/command.go:1068 +0x3a5 fp=0xc000139f30 sp=0xc000139e78 pc=0x5631ac42fd05 github.com/spf13/cobra.(*Command).Execute(...) github.com/spf13/cobra@v1.7.0/command.go:992 github.com/spf13/cobra.(*Command).ExecuteContext(...) github.com/spf13/cobra@v1.7.0/command.go:985 main.main() github.com/ollama/ollama/main.go:12 +0x4d fp=0xc000139f50 sp=0xc000139f30 pc=0x5631ad035b0d runtime.main() runtime/proc.go:283 +0x29d fp=0xc000139fe0 sp=0xc000139f50 pc=0x5631ac2826dd runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000139fe8 sp=0xc000139fe0 pc=0x5631ac2bdbc1 goroutine 2 gp=0xc000002e00 m=nil [force gc (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc0000b4fa8 sp=0xc0000b4f88 pc=0x5631ac2b5d2e runtime.goparkunlock(...) runtime/proc.go:441 runtime.forcegchelper() runtime/proc.go:348 +0xb8 fp=0xc0000b4fe0 sp=0xc0000b4fa8 pc=0x5631ac282a18 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0000b4fe8 sp=0xc0000b4fe0 pc=0x5631ac2bdbc1 created by runtime.init.7 in goroutine 1 runtime/proc.go:336 +0x1a goroutine 3 gp=0xc000003340 m=nil [GC sweep wait]: runtime.gopark(0x1?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc0000b5780 sp=0xc0000b5760 pc=0x5631ac2b5d2e runtime.goparkunlock(...) runtime/proc.go:441 runtime.bgsweep(0xc0000e0000) runtime/mgcsweep.go:316 +0xdf fp=0xc0000b57c8 sp=0xc0000b5780 pc=0x5631ac26d1bf runtime.gcenable.gowrap1() runtime/mgc.go:204 +0x25 fp=0xc0000b57e0 sp=0xc0000b57c8 pc=0x5631ac2615a5 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0000b57e8 sp=0xc0000b57e0 pc=0x5631ac2bdbc1 created by runtime.gcenable in goroutine 1 runtime/mgc.go:204 +0x66 goroutine 4 gp=0xc000003500 m=nil [GC scavenge wait]: runtime.gopark(0x10000?, 0x5631ad5d0730?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc0000b5f78 sp=0xc0000b5f58 pc=0x5631ac2b5d2e runtime.goparkunlock(...) runtime/proc.go:441 runtime.(*scavengerState).park(0x5631ae291260) runtime/mgcscavenge.go:425 +0x49 fp=0xc0000b5fa8 sp=0xc0000b5f78 pc=0x5631ac26ac09 runtime.bgscavenge(0xc0000e0000) runtime/mgcscavenge.go:658 +0x59 fp=0xc0000b5fc8 sp=0xc0000b5fa8 pc=0x5631ac26b199 runtime.gcenable.gowrap2() runtime/mgc.go:205 +0x25 fp=0xc0000b5fe0 sp=0xc0000b5fc8 pc=0x5631ac261545 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0000b5fe8 sp=0xc0000b5fe0 pc=0x5631ac2bdbc1 created by runtime.gcenable in goroutine 1 runtime/mgc.go:205 +0xa5 goroutine 5 gp=0xc000003dc0 m=nil [finalizer wait]: runtime.gopark(0x1b8?, 0xc000002380?, 0x1?, 0x23?, 0xc0000b4688?) runtime/proc.go:435 +0xce fp=0xc0000b4630 sp=0xc0000b4610 pc=0x5631ac2b5d2e runtime.runfinq() runtime/mfinal.go:196 +0x107 fp=0xc0000b47e0 sp=0xc0000b4630 pc=0x5631ac260567 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0000b47e8 sp=0xc0000b47e0 pc=0x5631ac2bdbc1 created by runtime.createfing in goroutine 1 runtime/mfinal.go:166 +0x3d goroutine 6 gp=0xc0001f88c0 m=nil [chan receive]: runtime.gopark(0xc000271540?, 0xc00050a018?, 0x60?, 0x67?, 0x5631ac39c188?) runtime/proc.go:435 +0xce fp=0xc0000b6718 sp=0xc0000b66f8 pc=0x5631ac2b5d2e runtime.chanrecv(0xc00003c380, 0x0, 0x1) runtime/chan.go:664 +0x445 fp=0xc0000b6790 sp=0xc0000b6718 pc=0x5631ac252045 runtime.chanrecv1(0x0?, 0x0?) runtime/chan.go:506 +0x12 fp=0xc0000b67b8 sp=0xc0000b6790 pc=0x5631ac251bd2 runtime.unique_runtime_registerUniqueMapCleanup.func2(...) runtime/mgc.go:1796 runtime.unique_runtime_registerUniqueMapCleanup.gowrap1() runtime/mgc.go:1799 +0x2f fp=0xc0000b67e0 sp=0xc0000b67b8 pc=0x5631ac26474f runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0000b67e8 sp=0xc0000b67e0 pc=0x5631ac2bdbc1 created by unique.runtime_registerUniqueMapCleanup in goroutine 1 runtime/mgc.go:1794 +0x85 goroutine 7 gp=0xc0001f8c40 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc0000b6f38 sp=0xc0000b6f18 pc=0x5631ac2b5d2e runtime.gcBgMarkWorker(0xc00003d7a0) runtime/mgc.go:1423 +0xe9 fp=0xc0000b6fc8 sp=0xc0000b6f38 pc=0x5631ac263a69 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc0000b6fe0 sp=0xc0000b6fc8 pc=0x5631ac263945 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0000b6fe8 sp=0xc0000b6fe0 pc=0x5631ac2bdbc1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 18 gp=0xc000504000 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc0000b0738 sp=0xc0000b0718 pc=0x5631ac2b5d2e runtime.gcBgMarkWorker(0xc00003d7a0) runtime/mgc.go:1423 +0xe9 fp=0xc0000b07c8 sp=0xc0000b0738 pc=0x5631ac263a69 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc0000b07e0 sp=0xc0000b07c8 pc=0x5631ac263945 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0000b07e8 sp=0xc0000b07e0 pc=0x5631ac2bdbc1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 34 gp=0xc000102380 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc00011a738 sp=0xc00011a718 pc=0x5631ac2b5d2e runtime.gcBgMarkWorker(0xc00003d7a0) runtime/mgc.go:1423 +0xe9 fp=0xc00011a7c8 sp=0xc00011a738 pc=0x5631ac263a69 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc00011a7e0 sp=0xc00011a7c8 pc=0x5631ac263945 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc00011a7e8 sp=0xc00011a7e0 pc=0x5631ac2bdbc1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 35 gp=0xc000102540 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc00011af38 sp=0xc00011af18 pc=0x5631ac2b5d2e runtime.gcBgMarkWorker(0xc00003d7a0) runtime/mgc.go:1423 +0xe9 fp=0xc00011afc8 sp=0xc00011af38 pc=0x5631ac263a69 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc00011afe0 sp=0xc00011afc8 pc=0x5631ac263945 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc00011afe8 sp=0xc00011afe0 pc=0x5631ac2bdbc1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 8 gp=0xc0001f8e00 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc0000b7738 sp=0xc0000b7718 pc=0x5631ac2b5d2e runtime.gcBgMarkWorker(0xc00003d7a0) runtime/mgc.go:1423 +0xe9 fp=0xc0000b77c8 sp=0xc0000b7738 pc=0x5631ac263a69 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc0000b77e0 sp=0xc0000b77c8 pc=0x5631ac263945 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0000b77e8 sp=0xc0000b77e0 pc=0x5631ac2bdbc1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 19 gp=0xc0005041c0 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc0000b0f38 sp=0xc0000b0f18 pc=0x5631ac2b5d2e runtime.gcBgMarkWorker(0xc00003d7a0) runtime/mgc.go:1423 +0xe9 fp=0xc0000b0fc8 sp=0xc0000b0f38 pc=0x5631ac263a69 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc0000b0fe0 sp=0xc0000b0fc8 pc=0x5631ac263945 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0000b0fe8 sp=0xc0000b0fe0 pc=0x5631ac2bdbc1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 36 gp=0xc000102700 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc00011b738 sp=0xc00011b718 pc=0x5631ac2b5d2e runtime.gcBgMarkWorker(0xc00003d7a0) runtime/mgc.go:1423 +0xe9 fp=0xc00011b7c8 sp=0xc00011b738 pc=0x5631ac263a69 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc00011b7e0 sp=0xc00011b7c8 pc=0x5631ac263945 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc00011b7e8 sp=0xc00011b7e0 pc=0x5631ac2bdbc1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 20 gp=0xc000504380 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc0000b1738 sp=0xc0000b1718 pc=0x5631ac2b5d2e runtime.gcBgMarkWorker(0xc00003d7a0) runtime/mgc.go:1423 +0xe9 fp=0xc0000b17c8 sp=0xc0000b1738 pc=0x5631ac263a69 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc0000b17e0 sp=0xc0000b17c8 pc=0x5631ac263945 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0000b17e8 sp=0xc0000b17e0 pc=0x5631ac2bdbc1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 37 gp=0xc0001028c0 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc00011bf38 sp=0xc00011bf18 pc=0x5631ac2b5d2e runtime.gcBgMarkWorker(0xc00003d7a0) runtime/mgc.go:1423 +0xe9 fp=0xc00011bfc8 sp=0xc00011bf38 pc=0x5631ac263a69 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc00011bfe0 sp=0xc00011bfc8 pc=0x5631ac263945 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc00011bfe8 sp=0xc00011bfe0 pc=0x5631ac2bdbc1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 21 gp=0xc000504540 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc0000b1f38 sp=0xc0000b1f18 pc=0x5631ac2b5d2e runtime.gcBgMarkWorker(0xc00003d7a0) runtime/mgc.go:1423 +0xe9 fp=0xc0000b1fc8 sp=0xc0000b1f38 pc=0x5631ac263a69 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc0000b1fe0 sp=0xc0000b1fc8 pc=0x5631ac263945 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0000b1fe8 sp=0xc0000b1fe0 pc=0x5631ac2bdbc1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 38 gp=0xc000102a80 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc00011c738 sp=0xc00011c718 pc=0x5631ac2b5d2e runtime.gcBgMarkWorker(0xc00003d7a0) runtime/mgc.go:1423 +0xe9 fp=0xc00011c7c8 sp=0xc00011c738 pc=0x5631ac263a69 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc00011c7e0 sp=0xc00011c7c8 pc=0x5631ac263945 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc00011c7e8 sp=0xc00011c7e0 pc=0x5631ac2bdbc1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 22 gp=0xc000504700 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc0000b2738 sp=0xc0000b2718 pc=0x5631ac2b5d2e runtime.gcBgMarkWorker(0xc00003d7a0) runtime/mgc.go:1423 +0xe9 fp=0xc0000b27c8 sp=0xc0000b2738 pc=0x5631ac263a69 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc0000b27e0 sp=0xc0000b27c8 pc=0x5631ac263945 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0000b27e8 sp=0xc0000b27e0 pc=0x5631ac2bdbc1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 39 gp=0xc000102c40 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc00011cf38 sp=0xc00011cf18 pc=0x5631ac2b5d2e runtime.gcBgMarkWorker(0xc00003d7a0) runtime/mgc.go:1423 +0xe9 fp=0xc00011cfc8 sp=0xc00011cf38 pc=0x5631ac263a69 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc00011cfe0 sp=0xc00011cfc8 pc=0x5631ac263945 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc00011cfe8 sp=0xc00011cfe0 pc=0x5631ac2bdbc1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 40 gp=0xc000102e00 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc00011d738 sp=0xc00011d718 pc=0x5631ac2b5d2e runtime.gcBgMarkWorker(0xc00003d7a0) runtime/mgc.go:1423 +0xe9 fp=0xc00011d7c8 sp=0xc00011d738 pc=0x5631ac263a69 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc00011d7e0 sp=0xc00011d7c8 pc=0x5631ac263945 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc00011d7e8 sp=0xc00011d7e0 pc=0x5631ac2bdbc1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 41 gp=0xc000102fc0 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc00011df38 sp=0xc00011df18 pc=0x5631ac2b5d2e runtime.gcBgMarkWorker(0xc00003d7a0) runtime/mgc.go:1423 +0xe9 fp=0xc00011dfc8 sp=0xc00011df38 pc=0x5631ac263a69 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc00011dfe0 sp=0xc00011dfc8 pc=0x5631ac263945 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc00011dfe8 sp=0xc00011dfe0 pc=0x5631ac2bdbc1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 42 gp=0xc000103180 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000116738 sp=0xc000116718 pc=0x5631ac2b5d2e runtime.gcBgMarkWorker(0xc00003d7a0) runtime/mgc.go:1423 +0xe9 fp=0xc0001167c8 sp=0xc000116738 pc=0x5631ac263a69 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc0001167e0 sp=0xc0001167c8 pc=0x5631ac263945 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0001167e8 sp=0xc0001167e0 pc=0x5631ac2bdbc1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 43 gp=0xc000103340 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000116f38 sp=0xc000116f18 pc=0x5631ac2b5d2e runtime.gcBgMarkWorker(0xc00003d7a0) runtime/mgc.go:1423 +0xe9 fp=0xc000116fc8 sp=0xc000116f38 pc=0x5631ac263a69 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc000116fe0 sp=0xc000116fc8 pc=0x5631ac263945 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000116fe8 sp=0xc000116fe0 pc=0x5631ac2bdbc1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 44 gp=0xc000103500 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000117738 sp=0xc000117718 pc=0x5631ac2b5d2e runtime.gcBgMarkWorker(0xc00003d7a0) runtime/mgc.go:1423 +0xe9 fp=0xc0001177c8 sp=0xc000117738 pc=0x5631ac263a69 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc0001177e0 sp=0xc0001177c8 pc=0x5631ac263945 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0001177e8 sp=0xc0001177e0 pc=0x5631ac2bdbc1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 45 gp=0xc0001036c0 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000117f38 sp=0xc000117f18 pc=0x5631ac2b5d2e runtime.gcBgMarkWorker(0xc00003d7a0) runtime/mgc.go:1423 +0xe9 fp=0xc000117fc8 sp=0xc000117f38 pc=0x5631ac263a69 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc000117fe0 sp=0xc000117fc8 pc=0x5631ac263945 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000117fe8 sp=0xc000117fe0 pc=0x5631ac2bdbc1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 46 gp=0xc000103880 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000118738 sp=0xc000118718 pc=0x5631ac2b5d2e runtime.gcBgMarkWorker(0xc00003d7a0) runtime/mgc.go:1423 +0xe9 fp=0xc0001187c8 sp=0xc000118738 pc=0x5631ac263a69 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc0001187e0 sp=0xc0001187c8 pc=0x5631ac263945 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0001187e8 sp=0xc0001187e0 pc=0x5631ac2bdbc1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 47 gp=0xc000103a40 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000118f38 sp=0xc000118f18 pc=0x5631ac2b5d2e runtime.gcBgMarkWorker(0xc00003d7a0) runtime/mgc.go:1423 +0xe9 fp=0xc000118fc8 sp=0xc000118f38 pc=0x5631ac263a69 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc000118fe0 sp=0xc000118fc8 pc=0x5631ac263945 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000118fe8 sp=0xc000118fe0 pc=0x5631ac2bdbc1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 48 gp=0xc000103c00 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000119738 sp=0xc000119718 pc=0x5631ac2b5d2e runtime.gcBgMarkWorker(0xc00003d7a0) runtime/mgc.go:1423 +0xe9 fp=0xc0001197c8 sp=0xc000119738 pc=0x5631ac263a69 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc0001197e0 sp=0xc0001197c8 pc=0x5631ac263945 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0001197e8 sp=0xc0001197e0 pc=0x5631ac2bdbc1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 49 gp=0xc000103dc0 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000119f38 sp=0xc000119f18 pc=0x5631ac2b5d2e runtime.gcBgMarkWorker(0xc00003d7a0) runtime/mgc.go:1423 +0xe9 fp=0xc000119fc8 sp=0xc000119f38 pc=0x5631ac263a69 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc000119fe0 sp=0xc000119fc8 pc=0x5631ac263945 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000119fe8 sp=0xc000119fe0 pc=0x5631ac2bdbc1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 50 gp=0xc00011e000 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000124738 sp=0xc000124718 pc=0x5631ac2b5d2e runtime.gcBgMarkWorker(0xc00003d7a0) runtime/mgc.go:1423 +0xe9 fp=0xc0001247c8 sp=0xc000124738 pc=0x5631ac263a69 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc0001247e0 sp=0xc0001247c8 pc=0x5631ac263945 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0001247e8 sp=0xc0001247e0 pc=0x5631ac2bdbc1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 51 gp=0xc00011e1c0 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000124f38 sp=0xc000124f18 pc=0x5631ac2b5d2e runtime.gcBgMarkWorker(0xc00003d7a0) runtime/mgc.go:1423 +0xe9 fp=0xc000124fc8 sp=0xc000124f38 pc=0x5631ac263a69 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc000124fe0 sp=0xc000124fc8 pc=0x5631ac263945 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000124fe8 sp=0xc000124fe0 pc=0x5631ac2bdbc1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 52 gp=0xc00011e380 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000125738 sp=0xc000125718 pc=0x5631ac2b5d2e runtime.gcBgMarkWorker(0xc00003d7a0) runtime/mgc.go:1423 +0xe9 fp=0xc0001257c8 sp=0xc000125738 pc=0x5631ac263a69 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc0001257e0 sp=0xc0001257c8 pc=0x5631ac263945 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0001257e8 sp=0xc0001257e0 pc=0x5631ac2bdbc1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 53 gp=0xc00011e540 m=nil [GC worker (idle)]: runtime.gopark(0x3e7d4204531?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000125f38 sp=0xc000125f18 pc=0x5631ac2b5d2e runtime.gcBgMarkWorker(0xc00003d7a0) runtime/mgc.go:1423 +0xe9 fp=0xc000125fc8 sp=0xc000125f38 pc=0x5631ac263a69 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc000125fe0 sp=0xc000125fc8 pc=0x5631ac263945 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000125fe8 sp=0xc000125fe0 pc=0x5631ac2bdbc1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 54 gp=0xc00011e700 m=nil [GC worker (idle)]: runtime.gopark(0x3e7d41fbc55?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000126738 sp=0xc000126718 pc=0x5631ac2b5d2e runtime.gcBgMarkWorker(0xc00003d7a0) runtime/mgc.go:1423 +0xe9 fp=0xc0001267c8 sp=0xc000126738 pc=0x5631ac263a69 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc0001267e0 sp=0xc0001267c8 pc=0x5631ac263945 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0001267e8 sp=0xc0001267e0 pc=0x5631ac2bdbc1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 55 gp=0xc00011e8c0 m=nil [GC worker (idle)]: runtime.gopark(0x3e7d41fd4f2?, 0x1?, 0x93?, 0x9b?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000126f38 sp=0xc000126f18 pc=0x5631ac2b5d2e runtime.gcBgMarkWorker(0xc00003d7a0) runtime/mgc.go:1423 +0xe9 fp=0xc000126fc8 sp=0xc000126f38 pc=0x5631ac263a69 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc000126fe0 sp=0xc000126fc8 pc=0x5631ac263945 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000126fe8 sp=0xc000126fe0 pc=0x5631ac2bdbc1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 56 gp=0xc00011ea80 m=nil [GC worker (idle)]: runtime.gopark(0x5631ae360ba0?, 0x1?, 0x2e?, 0x4e?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000127738 sp=0xc000127718 pc=0x5631ac2b5d2e runtime.gcBgMarkWorker(0xc00003d7a0) runtime/mgc.go:1423 +0xe9 fp=0xc0001277c8 sp=0xc000127738 pc=0x5631ac263a69 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc0001277e0 sp=0xc0001277c8 pc=0x5631ac263945 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0001277e8 sp=0xc0001277e0 pc=0x5631ac2bdbc1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 57 gp=0xc00011ec40 m=nil [GC worker (idle)]: runtime.gopark(0x5631ae360ba0?, 0x1?, 0xf8?, 0x9b?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000127f38 sp=0xc000127f18 pc=0x5631ac2b5d2e runtime.gcBgMarkWorker(0xc00003d7a0) runtime/mgc.go:1423 +0xe9 fp=0xc000127fc8 sp=0xc000127f38 pc=0x5631ac263a69 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc000127fe0 sp=0xc000127fc8 pc=0x5631ac263945 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000127fe8 sp=0xc000127fe0 pc=0x5631ac2bdbc1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 58 gp=0xc00011ee00 m=nil [GC worker (idle)]: runtime.gopark(0x3e7d41fd68c?, 0x1?, 0x74?, 0x79?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000120738 sp=0xc000120718 pc=0x5631ac2b5d2e runtime.gcBgMarkWorker(0xc00003d7a0) runtime/mgc.go:1423 +0xe9 fp=0xc0001207c8 sp=0xc000120738 pc=0x5631ac263a69 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1339 +0x25 fp=0xc0001207e0 sp=0xc0001207c8 pc=0x5631ac263945 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0001207e8 sp=0xc0001207e0 pc=0x5631ac2bdbc1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1339 +0x105 goroutine 9 gp=0xc0005048c0 m=nil [sync.WaitGroup.Wait]: runtime.gopark(0x0?, 0x0?, 0x60?, 0x40?, 0x0?) runtime/proc.go:435 +0xce fp=0xc000122620 sp=0xc000122600 pc=0x5631ac2b5d2e runtime.goparkunlock(...) runtime/proc.go:441 runtime.semacquire1(0xc0004c8840, 0x0, 0x1, 0x0, 0x18) runtime/sema.go:188 +0x229 fp=0xc000122688 sp=0xc000122620 pc=0x5631ac295ca9 sync.runtime_SemacquireWaitGroup(0x0?) runtime/sema.go:110 +0x25 fp=0xc0001226c0 sp=0xc000122688 pc=0x5631ac2b7665 sync.(*WaitGroup).Wait(0x0?) sync/waitgroup.go:118 +0x48 fp=0xc0001226e8 sp=0xc0001226c0 pc=0x5631ac2c9628 github.com/ollama/ollama/runner/llamarunner.(*Server).run(0xc0004c8820, {0x5631ad95d470, 0xc00059f400}) github.com/ollama/ollama/runner/llamarunner/runner.go:360 +0x4b fp=0xc0001227b8 sp=0xc0001226e8 pc=0x5631ac771e8b github.com/ollama/ollama/runner/llamarunner.Execute.gowrap1() github.com/ollama/ollama/runner/llamarunner/runner.go:981 +0x28 fp=0xc0001227e0 sp=0xc0001227b8 pc=0x5631ac7773e8 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0001227e8 sp=0xc0001227e0 pc=0x5631ac2bdbc1 created by github.com/ollama/ollama/runner/llamarunner.Execute in goroutine 1 github.com/ollama/ollama/runner/llamarunner/runner.go:981 +0x4c5 goroutine 10 gp=0xc000504a80 m=nil [IO wait]: runtime.gopark(0x5631ac3406c5?, 0xc0003b5e80?, 0x40?, 0x3a?, 0xb?) runtime/proc.go:435 +0xce fp=0xc000053948 sp=0xc000053928 pc=0x5631ac2b5d2e runtime.netpollblock(0x5631ac2d94f8?, 0xac24f466?, 0x31?) runtime/netpoll.go:575 +0xf7 fp=0xc000053980 sp=0xc000053948 pc=0x5631ac27b057 internal/poll.runtime_pollWait(0x7f3262ec7d98, 0x72) runtime/netpoll.go:351 +0x85 fp=0xc0000539a0 sp=0xc000053980 pc=0x5631ac2b4f45 internal/poll.(*pollDesc).wait(0xc0003b5e80?, 0xc000295000?, 0x0) internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc0000539c8 sp=0xc0000539a0 pc=0x5631ac33d0c7 internal/poll.(*pollDesc).waitRead(...) internal/poll/fd_poll_runtime.go:89 internal/poll.(*FD).Read(0xc0003b5e80, {0xc000295000, 0x1000, 0x1000}) internal/poll/fd_unix.go:165 +0x27a fp=0xc000053a60 sp=0xc0000539c8 pc=0x5631ac33e3ba net.(*netFD).Read(0xc0003b5e80, {0xc000295000?, 0xc000053ad0?, 0x5631ac33d585?}) net/fd_posix.go:55 +0x25 fp=0xc000053aa8 sp=0xc000053a60 pc=0x5631ac3b35a5 net.(*conn).Read(0xc000176560, {0xc000295000?, 0x0?, 0x0?}) net/net.go:194 +0x45 fp=0xc000053af0 sp=0xc000053aa8 pc=0x5631ac3c1965 net/http.(*connReader).Read(0xc0004c3140, {0xc000295000, 0x1000, 0x1000}) net/http/server.go:798 +0x159 fp=0xc000053b40 sp=0xc000053af0 pc=0x5631ac5ae939 bufio.(*Reader).fill(0xc000110780) bufio/bufio.go:113 +0x103 fp=0xc000053b78 sp=0xc000053b40 pc=0x5631ac3d9a23 bufio.(*Reader).Peek(0xc000110780, 0x4) bufio/bufio.go:152 +0x53 fp=0xc000053b98 sp=0xc000053b78 pc=0x5631ac3d9b53 net/http.(*conn).serve(0xc0004c6480, {0x5631ad95d438, 0xc0004c3050}) net/http/server.go:2137 +0x785 fp=0xc000053fb8 sp=0xc000053b98 pc=0x5631ac5b4725 net/http.(*Server).Serve.gowrap3() net/http/server.go:3454 +0x28 fp=0xc000053fe0 sp=0xc000053fb8 pc=0x5631ac5b9e88 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000053fe8 sp=0xc000053fe0 pc=0x5631ac2bdbc1 created by net/http.(*Server).Serve in goroutine 1 net/http/server.go:3454 +0x485 rax 0x7f326332a670 rbx 0x5631eb0782c0 rcx 0x0 rdx 0x5631e232d170 rdi 0x7f31e0a58e48 rsi 0x3 rbp 0x7f326332a670 rsp 0x7fff3f3aa850 r8 0x0 r9 0x0 r10 0x2b1 r11 0x5631e2a295fc r12 0x0 r13 0x0 r14 0x18 r15 0x1 rip 0x7f31e06c0bf5 rflags 0x10246 cs 0x33 fs 0x0 gs 0x0 time=2026-01-24T11:07:46.327+08:00 level=INFO source=sched.go:479 msg="Load failed" model=/home/qian/.ollama/models/blobs/sha256-de20d2cf2dc430b1717a8b07a9df029d651f3895dbffec4729a3902a6fe344c9 error="llama runner process has terminated: exit status 2" [GIN] 2026/01/24 - 11:07:46 | 500 | 1.618251058s | 127.0.0.1 | POST "/api/generate" ``` ### OS EndeavourOS KDE Plasma Version: 6.5.4 KDE Frameworks Version: 6.22.0 Qt Version: 6.10.1 Kernel Version: 6.18.4-arch1-1(64-bit) Graphics Platform: X11 ### GPU Radeon 8060s Graphics ### CPU 32 × AMD RYZEN AI MAX+ 395 w/ Radeon 8060S 128 GiB of RAM (62.4 GiB usable) ### Ollama version client version is 0.14.3
GiteaMirror added the linuxbugamd labels 2026-04-12 21:55:20 -05:00
GiteaMirror commented 2026-04-12 21:55:22 -05:00
Author
Owner
Copy Link

@mykeelium commented on GitHub (Jan 31, 2026):

I believe I have the same issue. I think it might due to the issue that is referencing this issue. Take a look at this video they linked, and it may help to explain the situation, as well as possible solutions for you:

https://www.youtube.com/watch?v=Hdg7zL3pcIs

<!-- gh-comment-id:3829301837 --> @mykeelium commented on GitHub (Jan 31, 2026): I believe I have the same issue. I think it might due to the issue that is referencing this issue. Take a look at this video they linked, and it may help to explain the situation, as well as possible solutions for you: https://www.youtube.com/watch?v=Hdg7zL3pcIs
GiteaMirror commented 2026-04-12 21:55:23 -05:00
Author
Owner
Copy Link

@qjgwork commented on GitHub (Feb 28, 2026):

I build one docker in my system, and it works now.

https://github.com/qjgwork/ollama-linux-amd-apu/tree/build/rocm7

<!-- gh-comment-id:3976591406 --> @qjgwork commented on GitHub (Feb 28, 2026): I build one docker in my system, and it works now. https://github.com/qjgwork/ollama-linux-amd-apu/tree/build/rocm7
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label amd bug linux
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#9079
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?