AMD RYZEN AI MAX+ 395 w/ Radeon 8060S ollama run SIGSEGV

qianjigui · 2026-01-31 10:52:13

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 0.15.2
± % 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 ***

± % sudo docker logs ollama !2428
[sudo] password for qian:
time=2026-01-31T09:01:12.260Z level=INFO source=routes.go:1631 msg="server config" env="map[CUDA_VISIBLE_DEVICES: GGML_VK_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:4096 OLLAMA_DEBUG:INFO OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://0.0.0.0:11434 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:/root/.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: https_proxy: no_proxy:]"
time=2026-01-31T09:01:12.263Z level=INFO source=images.go:473 msg="total blobs: 12"
time=2026-01-31T09:01:12.263Z level=INFO source=images.go:480 msg="total unused blobs removed: 0"
time=2026-01-31T09:01:12.263Z level=INFO source=routes.go:1684 msg="Listening on [::]:11434 (version 0.15.2)"
time=2026-01-31T09:01:12.264Z level=INFO source=runner.go:67 msg="discovering available GPUs..."
time=2026-01-31T09:01:12.264Z level=INFO source=server.go:429 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 34127"
time=2026-01-31T09:01:12.678Z level=INFO source=server.go:429 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 44307"
time=2026-01-31T09:01:13.201Z 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="94.2 GiB"
[GIN] 2026/01/31 - 09:02:01 | 200 | 45.528µs | 127.0.0.1 | HEAD "/"
[GIN] 2026/01/31 - 09:02:01 | 404 | 286.601µs | 127.0.0.1 | POST "/api/show"
[GIN] 2026/01/31 - 09:02:03 | 200 | 1.668468344s | 127.0.0.1 | POST "/api/pull"
[GIN] 2026/01/31 - 09:02:21 | 200 | 30.409µs | 127.0.0.1 | HEAD "/"
[GIN] 2026/01/31 - 09:02:21 | 200 | 105.895536ms | 127.0.0.1 | POST "/api/show"
[GIN] 2026/01/31 - 09:02:21 | 200 | 90.256386ms | 127.0.0.1 | POST "/api/show"
time=2026-01-31T09:02:21.391Z level=INFO source=server.go:429 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 45575"
time=2026-01-31T09:02:21.758Z level=WARN source=cpu_linux.go:130 msg="failed to parse CPU allowed micro secs" error="strconv.ParseInt: parsing \"max\": invalid syntax"
llama_model_loader: loaded meta data with 29 key-value pairs and 292 tensors from /root/.ollama/models/blobs/sha256-667b0c1932bc6ffc593ed1d03f895bf2dc8dc6df21db3042284a6f4416b06a29 (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 8B 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 = 8B
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 = 32
llama_model_loader: - kv 10: llama.context_length u32 = 131072
llama_model_loader: - kv 11: llama.embedding_length u32 = 4096
llama_model_loader: - kv 12: llama.feed_forward_length u32 = 14336
llama_model_loader: - kv 13: llama.attention.head_count u32 = 32
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: 66 tensors
llama_model_loader: - type q4_K: 193 tensors
llama_model_loader: - type q6_K: 33 tensors
print_info: file format = GGUF V3 (latest)
print_info: file type = Q4_K - Medium
print_info: file size = 4.58 GiB (4.89 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 = 8.03 B
print_info: general.name = Meta Llama 3.1 8B 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=2026-01-31T09:02:21.926Z level=INFO source=server.go:429 msg="starting runner" cmd="/usr/bin/ollama runner --model /root/.ollama/models/blobs/sha256-667b0c1932bc6ffc593ed1d03f895bf2dc8dc6df21db3042284a6f4416b06a29 --port 38963"
time=2026-01-31T09:02:21.926Z level=INFO source=sched.go:452 msg="system memory" total="62.4 GiB" free="62.2 GiB" free_swap="97.7 GiB"
time=2026-01-31T09:02:21.926Z level=INFO source=sched.go:459 msg="gpu memory" id=0 library=ROCm available="93.7 GiB" free="94.2 GiB" minimum="457.0 MiB" overhead="0 B"
time=2026-01-31T09:02:21.926Z level=INFO source=server.go:496 msg="loading model" "model layers"=33 requested=-1
time=2026-01-31T09:02:21.926Z level=INFO source=device.go:240 msg="model weights" device=ROCm0 size="4.3 GiB"
time=2026-01-31T09:02:21.926Z level=INFO source=device.go:251 msg="kv cache" device=ROCm0 size="512.0 MiB"
time=2026-01-31T09:02:21.926Z level=INFO source=device.go:262 msg="compute graph" device=ROCm0 size="296.0 MiB"
time=2026-01-31T09:02:21.926Z level=INFO source=device.go:272 msg="total memory" size="5.1 GiB"
time=2026-01-31T09:02:21.933Z level=INFO source=runner.go:965 msg="starting go runner"
load_backend: loaded CPU backend from /usr/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/lib/ollama/rocm/libggml-hip.so
time=2026-01-31T09:02:22.261Z 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=2026-01-31T09:02:22.261Z level=INFO source=runner.go:1001 msg="Server listening on 127.0.0.1:38963"
time=2026-01-31T09:02:22.263Z level=INFO source=runner.go:895 msg=load request="{Operation:commit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Auto KvSize:4096 KvCacheType: NumThreads:16 GPULayers:33[ID:0 Layers:33(0..32)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:true}"
ggml_hip_get_device_memory searching for device 0000:c6:00.0
time=2026-01-31T09:02:22.263Z level=INFO source=server.go:1347 msg="waiting for llama runner to start responding"
ggml_backend_cuda_device_get_memory device 0000:c6:00.0 utilizing AMD specific memory reporting free: 101124976640 total: 102236356608
llama_model_load_from_file_impl: using device ROCm0 (AMD Radeon Graphics) (0000:c6:00.0) - 96440 MiB free
time=2026-01-31T09:02:22.264Z level=INFO source=server.go:1381 msg="waiting for server to become available" status="llm server loading model"
llama_model_loader: loaded meta data with 29 key-value pairs and 292 tensors from /root/.ollama/models/blobs/sha256-667b0c1932bc6ffc593ed1d03f895bf2dc8dc6df21db3042284a6f4416b06a29 (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 8B 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 = 8B
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 = 32
llama_model_loader: - kv 10: llama.context_length u32 = 131072
llama_model_loader: - kv 11: llama.embedding_length u32 = 4096
llama_model_loader: - kv 12: llama.feed_forward_length u32 = 14336
llama_model_loader: - kv 13: llama.attention.head_count u32 = 32
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: 66 tensors
llama_model_loader: - type q4_K: 193 tensors
llama_model_loader: - type q6_K: 33 tensors
print_info: file format = GGUF V3 (latest)
print_info: file type = Q4_K - Medium
print_info: file size = 4.58 GiB (4.89 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 = 4096
print_info: n_embd_inp = 4096
print_info: n_layer = 32
print_info: n_head = 32
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 = 4
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 = 14336
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 = 8B
print_info: model params = 8.03 B
print_info: general.name = Meta Llama 3.1 8B 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 32 repeating layers to GPU
load_tensors: offloading output layer to GPU
load_tensors: offloaded 33/33 layers to GPU
load_tensors: CPU_Mapped model buffer size = 281.81 MiB
load_tensors: ROCm0 model buffer size = 4403.49 MiB
SIGSEGV: segmentation violation
PC=0x7f48dcec0bf5 m=0 sigcode=1 addr=0x18
signal arrived during cgo execution

goroutine 66 gp=0xc0004c8e00 m=0 mp=0x55c9323c5ba0 [syscall]:
runtime.cgocall(0x55c9311cd960, 0xc00042bb58)
runtime/cgocall.go:167 +0x4b fp=0xc00042bb30 sp=0xc00042baf8 pc=0x55c9303ba94b
github.com/ollama/ollama/llama._Cfunc_llama_model_load_from_file(0x55c942a6e570, {0xc000418f50, 0x0, 0x21, 0x1, 0x0, 0xc000418c58, 0x55c9311cd150, 0xc000418f48, 0x0, ...})
_cgo_gotypes.go:910 +0x4b fp=0xc00042bb58 sp=0xc00042bb30 pc=0x55c9307d07ab
github.com/ollama/ollama/llama.LoadModelFromFile.func1(...)
github.com/ollama/ollama/llama/llama.go:308
github.com/ollama/ollama/llama.LoadModelFromFile({0x7fff65461e02, 0x62}, {{0xc000418c60, 0x1, 0x1}, 0x21, 0x0, 0x1, {0xc000418c58, 0x1, ...}, ...})
github.com/ollama/ollama/llama/llama.go:308 +0x56d fp=0xc00042bda0 sp=0xc00042bb58 pc=0x55c9307d3b2d
github.com/ollama/ollama/runner/llamarunner.(*Server).loadModel(0xc000168f00, {{0xc000418c60, 0x1, 0x1}, 0x21, 0x0, 0x1, {0xc000418c58, 0x1, 0x2}, ...}, ...)
github.com/ollama/ollama/runner/llamarunner/runner.go:841 +0x9e fp=0xc00042bee8 sp=0xc00042bda0 pc=0x55c93088c81e
github.com/ollama/ollama/runner/llamarunner.(*Server).load.gowrap2()
github.com/ollama/ollama/runner/llamarunner/runner.go:934 +0x114 fp=0xc00042bfe0 sp=0xc00042bee8 pc=0x55c93088db14
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc00042bfe8 sp=0xc00042bfe0 pc=0x55c9303c5c61
created by github.com/ollama/ollama/runner/llamarunner.(*Server).load in goroutine 39
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=0xc000125790 sp=0xc000125770 pc=0x55c9303bddce
runtime.netpollblock(0xc0001257e0?, 0x30357506?, 0xc9?)
runtime/netpoll.go:575 +0xf7 fp=0xc0001257c8 sp=0xc000125790 pc=0x55c9303830f7
internal/poll.runtime_pollWait(0x7f48f1644de0, 0x72)
runtime/netpoll.go:351 +0x85 fp=0xc0001257e8 sp=0xc0001257c8 pc=0x55c9303bcfe5
internal/poll.(*pollDesc).wait(0xc000156c00?, 0x900000036?, 0x0)
internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc000125810 sp=0xc0001257e8 pc=0x55c930445167
internal/poll.(*pollDesc).waitRead(...)
internal/poll/fd_poll_runtime.go:89
internal/poll.(*FD).Accept(0xc000156c00)
internal/poll/fd_unix.go:620 +0x295 fp=0xc0001258b8 sp=0xc000125810 pc=0x55c93044a535
net.(*netFD).accept(0xc000156c00)
net/fd_unix.go:172 +0x29 fp=0xc000125970 sp=0xc0001258b8 pc=0x55c9304bd5e9
net.(*TCPListener).accept(0xc000379540)
net/tcpsock_posix.go:159 +0x1b fp=0xc0001259c0 sp=0xc000125970 pc=0x55c9304d34fb
net.(*TCPListener).Accept(0xc000379540)
net/tcpsock.go:380 +0x30 fp=0xc0001259f0 sp=0xc0001259c0 pc=0x55c9304d23b0
net/http.(*onceCloseListener).Accept(0xc000036750?)
<autogenerated>:1 +0x24 fp=0xc000125a08 sp=0xc0001259f0 pc=0x55c9306ea264
net/http.(*Server).Serve(0xc000051300, {0x55c931a846c0, 0xc000379540})
net/http/server.go:3424 +0x30c fp=0xc000125b38 sp=0xc000125a08 pc=0x55c9306c1b2c
github.com/ollama/ollama/runner/llamarunner.Execute({0xc0001801a0, 0x4, 0x4})
github.com/ollama/ollama/runner/llamarunner/runner.go:1002 +0x8f5 fp=0xc000125d08 sp=0xc000125b38 pc=0x55c93088e4d5
github.com/ollama/ollama/runner.Execute({0xc000180190?, 0x0?, 0x0?})
github.com/ollama/ollama/runner/runner.go:30 +0x130 fp=0xc000125d30 sp=0xc000125d08 pc=0x55c93097d650
github.com/ollama/ollama/cmd.NewCLI.func3(0xc000051000?, {0x55c9315160f0?, 0x4?, 0x55c9315160f4?})
github.com/ollama/ollama/cmd/cmd.go:1966 +0x45 fp=0xc000125d58 sp=0xc000125d30 pc=0x55c93114ec65
github.com/spf13/cobra.(*Command).execute(0xc00016b508, {0xc000379340, 0x4, 0x4})
github.com/spf13/cobra@v1.7.0/command.go:940 +0x85c fp=0xc000125e78 sp=0xc000125d58 pc=0x55c93053755c
github.com/spf13/cobra.(*Command).ExecuteC(0xc00013c908)
github.com/spf13/cobra@v1.7.0/command.go:1068 +0x3a5 fp=0xc000125f30 sp=0xc000125e78 pc=0x55c930537da5
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=0xc000125f50 sp=0xc000125f30 pc=0x55c93114f74d
runtime.main()
runtime/proc.go:283 +0x29d fp=0xc000125fe0 sp=0xc000125f50 pc=0x55c93038a77d
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc000125fe8 sp=0xc000125fe0 pc=0x55c9303c5c61

goroutine 2 gp=0xc000002e00 m=nil [force gc (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc0000aafa8 sp=0xc0000aaf88 pc=0x55c9303bddce
runtime.goparkunlock(...)
runtime/proc.go:441
runtime.forcegchelper()
runtime/proc.go:348 +0xb8 fp=0xc0000aafe0 sp=0xc0000aafa8 pc=0x55c93038aab8
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc0000aafe8 sp=0xc0000aafe0 pc=0x55c9303c5c61
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=0xc0000ab780 sp=0xc0000ab760 pc=0x55c9303bddce
runtime.goparkunlock(...)
runtime/proc.go:441
runtime.bgsweep(0xc0000d6000)
runtime/mgcsweep.go:316 +0xdf fp=0xc0000ab7c8 sp=0xc0000ab780 pc=0x55c93037525f
runtime.gcenable.gowrap1()
runtime/mgc.go:204 +0x25 fp=0xc0000ab7e0 sp=0xc0000ab7c8 pc=0x55c930369645
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc0000ab7e8 sp=0xc0000ab7e0 pc=0x55c9303c5c61
created by runtime.gcenable in goroutine 1
runtime/mgc.go:204 +0x66

goroutine 4 gp=0xc000003500 m=nil [GC scavenge wait]:
runtime.gopark(0x10000?, 0x55c9316fff38?, 0x0?, 0x0?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc0000abf78 sp=0xc0000abf58 pc=0x55c9303bddce
runtime.goparkunlock(...)
runtime/proc.go:441
runtime.(*scavengerState).park(0x55c9323c2d80)
runtime/mgcscavenge.go:425 +0x49 fp=0xc0000abfa8 sp=0xc0000abf78 pc=0x55c930372ca9
runtime.bgscavenge(0xc0000d6000)
runtime/mgcscavenge.go:658 +0x59 fp=0xc0000abfc8 sp=0xc0000abfa8 pc=0x55c930373239
runtime.gcenable.gowrap2()
runtime/mgc.go:205 +0x25 fp=0xc0000abfe0 sp=0xc0000abfc8 pc=0x55c9303695e5
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc0000abfe8 sp=0xc0000abfe0 pc=0x55c9303c5c61
created by runtime.gcenable in goroutine 1
runtime/mgc.go:205 +0xa5

goroutine 18 gp=0xc000186380 m=nil [finalizer wait]:
runtime.gopark(0x1b8?, 0xc000002380?, 0x1?, 0x23?, 0xc0000aa688?)
runtime/proc.go:435 +0xce fp=0xc0000aa630 sp=0xc0000aa610 pc=0x55c9303bddce
runtime.runfinq()
runtime/mfinal.go:196 +0x107 fp=0xc0000aa7e0 sp=0xc0000aa630 pc=0x55c930368607
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc0000aa7e8 sp=0xc0000aa7e0 pc=0x55c9303c5c61
created by runtime.createfing in goroutine 1
runtime/mfinal.go:166 +0x3d

goroutine 19 gp=0xc000186e00 m=nil [chan receive]:
runtime.gopark(0xc0002ab860?, 0xc000126018?, 0x60?, 0x67?, 0x55c9304a4228?)
runtime/proc.go:435 +0xce fp=0xc0000a6718 sp=0xc0000a66f8 pc=0x55c9303bddce
runtime.chanrecv(0xc000182310, 0x0, 0x1)
runtime/chan.go:664 +0x445 fp=0xc0000a6790 sp=0xc0000a6718 pc=0x55c93035a0e5
runtime.chanrecv1(0x0?, 0x0?)
runtime/chan.go:506 +0x12 fp=0xc0000a67b8 sp=0xc0000a6790 pc=0x55c930359c72
runtime.unique_runtime_registerUniqueMapCleanup.func2(...)
runtime/mgc.go:1796
runtime.unique_runtime_registerUniqueMapCleanup.gowrap1()
runtime/mgc.go:1799 +0x2f fp=0xc0000a67e0 sp=0xc0000a67b8 pc=0x55c93036c7ef
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc0000a67e8 sp=0xc0000a67e0 pc=0x55c9303c5c61
created by unique.runtime_registerUniqueMapCleanup in goroutine 1
runtime/mgc.go:1794 +0x85

goroutine 20 gp=0xc000187180 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc0000a6f38 sp=0xc0000a6f18 pc=0x55c9303bddce
runtime.gcBgMarkWorker(0xc000183570)
runtime/mgc.go:1423 +0xe9 fp=0xc0000a6fc8 sp=0xc0000a6f38 pc=0x55c93036bb09
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1339 +0x25 fp=0xc0000a6fe0 sp=0xc0000a6fc8 pc=0x55c93036b9e5
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc0000a6fe8 sp=0xc0000a6fe0 pc=0x55c9303c5c61
created by runtime.gcBgMarkStartWorkers in goroutine 1
runtime/mgc.go:1339 +0x105

goroutine 21 gp=0xc000187340 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc0000a7738 sp=0xc0000a7718 pc=0x55c9303bddce
runtime.gcBgMarkWorker(0xc000183570)
runtime/mgc.go:1423 +0xe9 fp=0xc0000a77c8 sp=0xc0000a7738 pc=0x55c93036bb09
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1339 +0x25 fp=0xc0000a77e0 sp=0xc0000a77c8 pc=0x55c93036b9e5
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc0000a77e8 sp=0xc0000a77e0 pc=0x55c9303c5c61
created by runtime.gcBgMarkStartWorkers in goroutine 1
runtime/mgc.go:1339 +0x105

goroutine 5 gp=0xc000003a40 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc0000ac738 sp=0xc0000ac718 pc=0x55c9303bddce
runtime.gcBgMarkWorker(0xc000183570)
runtime/mgc.go:1423 +0xe9 fp=0xc0000ac7c8 sp=0xc0000ac738 pc=0x55c93036bb09
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1339 +0x25 fp=0xc0000ac7e0 sp=0xc0000ac7c8 pc=0x55c93036b9e5
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc0000ac7e8 sp=0xc0000ac7e0 pc=0x55c9303c5c61
created by runtime.gcBgMarkStartWorkers in goroutine 1
runtime/mgc.go:1339 +0x105

goroutine 6 gp=0xc000003c00 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc0000acf38 sp=0xc0000acf18 pc=0x55c9303bddce
runtime.gcBgMarkWorker(0xc000183570)
runtime/mgc.go:1423 +0xe9 fp=0xc0000acfc8 sp=0xc0000acf38 pc=0x55c93036bb09
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1339 +0x25 fp=0xc0000acfe0 sp=0xc0000acfc8 pc=0x55c93036b9e5
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc0000acfe8 sp=0xc0000acfe0 pc=0x55c9303c5c61
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=0x55c9303bddce
runtime.gcBgMarkWorker(0xc000183570)
runtime/mgc.go:1423 +0xe9 fp=0xc00011a7c8 sp=0xc00011a738 pc=0x55c93036bb09
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1339 +0x25 fp=0xc00011a7e0 sp=0xc00011a7c8 pc=0x55c93036b9e5
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc00011a7e8 sp=0xc00011a7e0 pc=0x55c9303c5c61
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=0x55c9303bddce
runtime.gcBgMarkWorker(0xc000183570)
runtime/mgc.go:1423 +0xe9 fp=0xc00011afc8 sp=0xc00011af38 pc=0x55c93036bb09
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1339 +0x25 fp=0xc00011afe0 sp=0xc00011afc8 pc=0x55c93036b9e5
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc00011afe8 sp=0xc00011afe0 pc=0x55c9303c5c61
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=0x55c9303bddce
runtime.gcBgMarkWorker(0xc000183570)
runtime/mgc.go:1423 +0xe9 fp=0xc00011b7c8 sp=0xc00011b738 pc=0x55c93036bb09
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1339 +0x25 fp=0xc00011b7e0 sp=0xc00011b7c8 pc=0x55c93036b9e5
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc00011b7e8 sp=0xc00011b7e0 pc=0x55c9303c5c61
created by runtime.gcBgMarkStartWorkers in goroutine 1
runtime/mgc.go:1339 +0x105

goroutine 22 gp=0xc000187500 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc0000a7f38 sp=0xc0000a7f18 pc=0x55c9303bddce
runtime.gcBgMarkWorker(0xc000183570)
runtime/mgc.go:1423 +0xe9 fp=0xc0000a7fc8 sp=0xc0000a7f38 pc=0x55c93036bb09
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1339 +0x25 fp=0xc0000a7fe0 sp=0xc0000a7fc8 pc=0x55c93036b9e5
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc0000a7fe8 sp=0xc0000a7fe0 pc=0x55c9303c5c61
created by runtime.gcBgMarkStartWorkers in goroutine 1
runtime/mgc.go:1339 +0x105

goroutine 23 gp=0xc0001876c0 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc0000a8738 sp=0xc0000a8718 pc=0x55c9303bddce
runtime.gcBgMarkWorker(0xc000183570)
runtime/mgc.go:1423 +0xe9 fp=0xc0000a87c8 sp=0xc0000a8738 pc=0x55c93036bb09
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1339 +0x25 fp=0xc0000a87e0 sp=0xc0000a87c8 pc=0x55c93036b9e5
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc0000a87e8 sp=0xc0000a87e0 pc=0x55c9303c5c61
created by runtime.gcBgMarkStartWorkers in goroutine 1
runtime/mgc.go:1339 +0x105

goroutine 7 gp=0xc000003dc0 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc0000ad738 sp=0xc0000ad718 pc=0x55c9303bddce
runtime.gcBgMarkWorker(0xc000183570)
runtime/mgc.go:1423 +0xe9 fp=0xc0000ad7c8 sp=0xc0000ad738 pc=0x55c93036bb09
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1339 +0x25 fp=0xc0000ad7e0 sp=0xc0000ad7c8 pc=0x55c93036b9e5
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc0000ad7e8 sp=0xc0000ad7e0 pc=0x55c9303c5c61
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=0x55c9303bddce
runtime.gcBgMarkWorker(0xc000183570)
runtime/mgc.go:1423 +0xe9 fp=0xc00011bfc8 sp=0xc00011bf38 pc=0x55c93036bb09
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1339 +0x25 fp=0xc00011bfe0 sp=0xc00011bfc8 pc=0x55c93036b9e5
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc00011bfe8 sp=0xc00011bfe0 pc=0x55c9303c5c61
created by runtime.gcBgMarkStartWorkers in goroutine 1
runtime/mgc.go:1339 +0x105

goroutine 8 gp=0xc0000e2000 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc0000adf38 sp=0xc0000adf18 pc=0x55c9303bddce
runtime.gcBgMarkWorker(0xc000183570)
runtime/mgc.go:1423 +0xe9 fp=0xc0000adfc8 sp=0xc0000adf38 pc=0x55c93036bb09
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1339 +0x25 fp=0xc0000adfe0 sp=0xc0000adfc8 pc=0x55c93036b9e5
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc0000adfe8 sp=0xc0000adfe0 pc=0x55c9303c5c61
created by runtime.gcBgMarkStartWorkers in goroutine 1
runtime/mgc.go:1339 +0x105

goroutine 9 gp=0xc0000e21c0 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc000116738 sp=0xc000116718 pc=0x55c9303bddce
runtime.gcBgMarkWorker(0xc000183570)
runtime/mgc.go:1423 +0xe9 fp=0xc0001167c8 sp=0xc000116738 pc=0x55c93036bb09
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1339 +0x25 fp=0xc0001167e0 sp=0xc0001167c8 pc=0x55c93036b9e5
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc0001167e8 sp=0xc0001167e0 pc=0x55c9303c5c61
created by runtime.gcBgMarkStartWorkers in goroutine 1
runtime/mgc.go:1339 +0x105

goroutine 10 gp=0xc0000e2380 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc000116f38 sp=0xc000116f18 pc=0x55c9303bddce
runtime.gcBgMarkWorker(0xc000183570)
runtime/mgc.go:1423 +0xe9 fp=0xc000116fc8 sp=0xc000116f38 pc=0x55c93036bb09
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1339 +0x25 fp=0xc000116fe0 sp=0xc000116fc8 pc=0x55c93036b9e5
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc000116fe8 sp=0xc000116fe0 pc=0x55c9303c5c61
created by runtime.gcBgMarkStartWorkers in goroutine 1
runtime/mgc.go:1339 +0x105

goroutine 11 gp=0xc0000e2540 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc000117738 sp=0xc000117718 pc=0x55c9303bddce
runtime.gcBgMarkWorker(0xc000183570)
runtime/mgc.go:1423 +0xe9 fp=0xc0001177c8 sp=0xc000117738 pc=0x55c93036bb09
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1339 +0x25 fp=0xc0001177e0 sp=0xc0001177c8 pc=0x55c93036b9e5
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc0001177e8 sp=0xc0001177e0 pc=0x55c9303c5c61
created by runtime.gcBgMarkStartWorkers in goroutine 1
runtime/mgc.go:1339 +0x105

goroutine 12 gp=0xc0000e2700 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc000117f38 sp=0xc000117f18 pc=0x55c9303bddce
runtime.gcBgMarkWorker(0xc000183570)
runtime/mgc.go:1423 +0xe9 fp=0xc000117fc8 sp=0xc000117f38 pc=0x55c93036bb09
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1339 +0x25 fp=0xc000117fe0 sp=0xc000117fc8 pc=0x55c93036b9e5
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc000117fe8 sp=0xc000117fe0 pc=0x55c9303c5c61
created by runtime.gcBgMarkStartWorkers in goroutine 1
runtime/mgc.go:1339 +0x105

goroutine 13 gp=0xc0000e28c0 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc000118738 sp=0xc000118718 pc=0x55c9303bddce
runtime.gcBgMarkWorker(0xc000183570)
runtime/mgc.go:1423 +0xe9 fp=0xc0001187c8 sp=0xc000118738 pc=0x55c93036bb09
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1339 +0x25 fp=0xc0001187e0 sp=0xc0001187c8 pc=0x55c93036b9e5
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc0001187e8 sp=0xc0001187e0 pc=0x55c9303c5c61
created by runtime.gcBgMarkStartWorkers in goroutine 1
runtime/mgc.go:1339 +0x105

goroutine 14 gp=0xc0000e2a80 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc000118f38 sp=0xc000118f18 pc=0x55c9303bddce
runtime.gcBgMarkWorker(0xc000183570)
runtime/mgc.go:1423 +0xe9 fp=0xc000118fc8 sp=0xc000118f38 pc=0x55c93036bb09
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1339 +0x25 fp=0xc000118fe0 sp=0xc000118fc8 pc=0x55c93036b9e5
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc000118fe8 sp=0xc000118fe0 pc=0x55c9303c5c61
created by runtime.gcBgMarkStartWorkers in goroutine 1
runtime/mgc.go:1339 +0x105

goroutine 15 gp=0xc0000e2c40 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc000119738 sp=0xc000119718 pc=0x55c9303bddce
runtime.gcBgMarkWorker(0xc000183570)
runtime/mgc.go:1423 +0xe9 fp=0xc0001197c8 sp=0xc000119738 pc=0x55c93036bb09
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1339 +0x25 fp=0xc0001197e0 sp=0xc0001197c8 pc=0x55c93036b9e5
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc0001197e8 sp=0xc0001197e0 pc=0x55c9303c5c61
created by runtime.gcBgMarkStartWorkers in goroutine 1
runtime/mgc.go:1339 +0x105

goroutine 16 gp=0xc0000e2e00 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc000119f38 sp=0xc000119f18 pc=0x55c9303bddce
runtime.gcBgMarkWorker(0xc000183570)
runtime/mgc.go:1423 +0xe9 fp=0xc000119fc8 sp=0xc000119f38 pc=0x55c93036bb09
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1339 +0x25 fp=0xc000119fe0 sp=0xc000119fc8 pc=0x55c93036b9e5
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc000119fe8 sp=0xc000119fe0 pc=0x55c9303c5c61
created by runtime.gcBgMarkStartWorkers in goroutine 1
runtime/mgc.go:1339 +0x105

goroutine 50 gp=0xc0000e2fc0 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc0000e8738 sp=0xc0000e8718 pc=0x55c9303bddce
runtime.gcBgMarkWorker(0xc000183570)
runtime/mgc.go:1423 +0xe9 fp=0xc0000e87c8 sp=0xc0000e8738 pc=0x55c93036bb09
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1339 +0x25 fp=0xc0000e87e0 sp=0xc0000e87c8 pc=0x55c93036b9e5
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc0000e87e8 sp=0xc0000e87e0 pc=0x55c9303c5c61
created by runtime.gcBgMarkStartWorkers in goroutine 1
runtime/mgc.go:1339 +0x105

goroutine 51 gp=0xc0000e3180 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc0000e8f38 sp=0xc0000e8f18 pc=0x55c9303bddce
runtime.gcBgMarkWorker(0xc000183570)
runtime/mgc.go:1423 +0xe9 fp=0xc0000e8fc8 sp=0xc0000e8f38 pc=0x55c93036bb09
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1339 +0x25 fp=0xc0000e8fe0 sp=0xc0000e8fc8 pc=0x55c93036b9e5
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc0000e8fe8 sp=0xc0000e8fe0 pc=0x55c9303c5c61
created by runtime.gcBgMarkStartWorkers in goroutine 1
runtime/mgc.go:1339 +0x105

goroutine 52 gp=0xc0000e3340 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc0000e9738 sp=0xc0000e9718 pc=0x55c9303bddce
runtime.gcBgMarkWorker(0xc000183570)
runtime/mgc.go:1423 +0xe9 fp=0xc0000e97c8 sp=0xc0000e9738 pc=0x55c93036bb09
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1339 +0x25 fp=0xc0000e97e0 sp=0xc0000e97c8 pc=0x55c93036b9e5
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc0000e97e8 sp=0xc0000e97e0 pc=0x55c9303c5c61
created by runtime.gcBgMarkStartWorkers in goroutine 1
runtime/mgc.go:1339 +0x105

goroutine 24 gp=0xc000187880 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc0000a8f38 sp=0xc0000a8f18 pc=0x55c9303bddce
runtime.gcBgMarkWorker(0xc000183570)
runtime/mgc.go:1423 +0xe9 fp=0xc0000a8fc8 sp=0xc0000a8f38 pc=0x55c93036bb09
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1339 +0x25 fp=0xc0000a8fe0 sp=0xc0000a8fc8 pc=0x55c93036b9e5
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc0000a8fe8 sp=0xc0000a8fe0 pc=0x55c9303c5c61
created by runtime.gcBgMarkStartWorkers in goroutine 1
runtime/mgc.go:1339 +0x105

goroutine 25 gp=0xc000187a40 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc0000a9738 sp=0xc0000a9718 pc=0x55c9303bddce
runtime.gcBgMarkWorker(0xc000183570)
runtime/mgc.go:1423 +0xe9 fp=0xc0000a97c8 sp=0xc0000a9738 pc=0x55c93036bb09
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1339 +0x25 fp=0xc0000a97e0 sp=0xc0000a97c8 pc=0x55c93036b9e5
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc0000a97e8 sp=0xc0000a97e0 pc=0x55c9303c5c61
created by runtime.gcBgMarkStartWorkers in goroutine 1
runtime/mgc.go:1339 +0x105

goroutine 26 gp=0xc000187c00 m=nil [GC worker (idle)]:
runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc0000a9f38 sp=0xc0000a9f18 pc=0x55c9303bddce
runtime.gcBgMarkWorker(0xc000183570)
runtime/mgc.go:1423 +0xe9 fp=0xc0000a9fc8 sp=0xc0000a9f38 pc=0x55c93036bb09
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1339 +0x25 fp=0xc0000a9fe0 sp=0xc0000a9fc8 pc=0x55c93036b9e5
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc0000a9fe8 sp=0xc0000a9fe0 pc=0x55c9303c5c61
created by runtime.gcBgMarkStartWorkers in goroutine 1
runtime/mgc.go:1339 +0x105

goroutine 27 gp=0xc000187dc0 m=nil [GC worker (idle)]:
runtime.gopark(0x28bdbe4a4a7?, 0x0?, 0x0?, 0x0?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc0000e4738 sp=0xc0000e4718 pc=0x55c9303bddce
runtime.gcBgMarkWorker(0xc000183570)
runtime/mgc.go:1423 +0xe9 fp=0xc0000e47c8 sp=0xc0000e4738 pc=0x55c93036bb09
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1339 +0x25 fp=0xc0000e47e0 sp=0xc0000e47c8 pc=0x55c93036b9e5
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc0000e47e8 sp=0xc0000e47e0 pc=0x55c9303c5c61
created by runtime.gcBgMarkStartWorkers in goroutine 1
runtime/mgc.go:1339 +0x105

goroutine 28 gp=0xc0004c8000 m=nil [GC worker (idle)]:
runtime.gopark(0x28bdbe31176?, 0x1?, 0xf0?, 0xd2?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc0000e4f38 sp=0xc0000e4f18 pc=0x55c9303bddce
runtime.gcBgMarkWorker(0xc000183570)
runtime/mgc.go:1423 +0xe9 fp=0xc0000e4fc8 sp=0xc0000e4f38 pc=0x55c93036bb09
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1339 +0x25 fp=0xc0000e4fe0 sp=0xc0000e4fc8 pc=0x55c93036b9e5
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc0000e4fe8 sp=0xc0000e4fe0 pc=0x55c9303c5c61
created by runtime.gcBgMarkStartWorkers in goroutine 1
runtime/mgc.go:1339 +0x105

goroutine 29 gp=0xc0004c81c0 m=nil [GC worker (idle)]:
runtime.gopark(0x28bdbe302c7?, 0x1?, 0x16?, 0xc?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc0000e5738 sp=0xc0000e5718 pc=0x55c9303bddce
runtime.gcBgMarkWorker(0xc000183570)
runtime/mgc.go:1423 +0xe9 fp=0xc0000e57c8 sp=0xc0000e5738 pc=0x55c93036bb09
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1339 +0x25 fp=0xc0000e57e0 sp=0xc0000e57c8 pc=0x55c93036b9e5
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc0000e57e8 sp=0xc0000e57e0 pc=0x55c9303c5c61
created by runtime.gcBgMarkStartWorkers in goroutine 1
runtime/mgc.go:1339 +0x105

goroutine 30 gp=0xc0004c8380 m=nil [GC worker (idle)]:
runtime.gopark(0x55c932492680?, 0x1?, 0xd5?, 0x43?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc0000e5f38 sp=0xc0000e5f18 pc=0x55c9303bddce
runtime.gcBgMarkWorker(0xc000183570)
runtime/mgc.go:1423 +0xe9 fp=0xc0000e5fc8 sp=0xc0000e5f38 pc=0x55c93036bb09
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1339 +0x25 fp=0xc0000e5fe0 sp=0xc0000e5fc8 pc=0x55c93036b9e5
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc0000e5fe8 sp=0xc0000e5fe0 pc=0x55c9303c5c61
created by runtime.gcBgMarkStartWorkers in goroutine 1
runtime/mgc.go:1339 +0x105

goroutine 31 gp=0xc0004c8540 m=nil [GC worker (idle)]:
runtime.gopark(0x55c932492680?, 0x1?, 0xd8?, 0xe3?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc0000e6738 sp=0xc0000e6718 pc=0x55c9303bddce
runtime.gcBgMarkWorker(0xc000183570)
runtime/mgc.go:1423 +0xe9 fp=0xc0000e67c8 sp=0xc0000e6738 pc=0x55c93036bb09
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1339 +0x25 fp=0xc0000e67e0 sp=0xc0000e67c8 pc=0x55c93036b9e5
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc0000e67e8 sp=0xc0000e67e0 pc=0x55c9303c5c61
created by runtime.gcBgMarkStartWorkers in goroutine 1
runtime/mgc.go:1339 +0x105

goroutine 32 gp=0xc0004c8700 m=nil [GC worker (idle)]:
runtime.gopark(0x55c932492680?, 0x1?, 0x2b?, 0x9e?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc0000e6f38 sp=0xc0000e6f18 pc=0x55c9303bddce
runtime.gcBgMarkWorker(0xc000183570)
runtime/mgc.go:1423 +0xe9 fp=0xc0000e6fc8 sp=0xc0000e6f38 pc=0x55c93036bb09
runtime.gcBgMarkStartWorkers.gowrap1()
runtime/mgc.go:1339 +0x25 fp=0xc0000e6fe0 sp=0xc0000e6fc8 pc=0x55c93036b9e5
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc0000e6fe8 sp=0xc0000e6fe0 pc=0x55c9303c5c61
created by runtime.gcBgMarkStartWorkers in goroutine 1
runtime/mgc.go:1339 +0x105

goroutine 38 gp=0xc0000e3c00 m=nil [sync.WaitGroup.Wait]:
runtime.gopark(0x0?, 0x0?, 0x20?, 0xa1?, 0x0?)
runtime/proc.go:435 +0xce fp=0xc0000eb620 sp=0xc0000eb600 pc=0x55c9303bddce
runtime.goparkunlock(...)
runtime/proc.go:441
runtime.semacquire1(0xc000168f20, 0x0, 0x1, 0x0, 0x18)
runtime/sema.go:188 +0x229 fp=0xc0000eb688 sp=0xc0000eb620 pc=0x55c93039dd49
sync.runtime_SemacquireWaitGroup(0x0?)
runtime/sema.go:110 +0x25 fp=0xc0000eb6c0 sp=0xc0000eb688 pc=0x55c9303bf705
sync.(*WaitGroup).Wait(0x0?)
sync/waitgroup.go:118 +0x48 fp=0xc0000eb6e8 sp=0xc0000eb6c0 pc=0x55c9303d16c8
github.com/ollama/ollama/runner/llamarunner.(*Server).run(0xc000168f00, {0x55c931a86d40, 0xc0001527d0})
github.com/ollama/ollama/runner/llamarunner/runner.go:360 +0x4b fp=0xc0000eb7b8 sp=0xc0000eb6e8 pc=0x55c9308891eb
github.com/ollama/ollama/runner/llamarunner.Execute.gowrap1()
github.com/ollama/ollama/runner/llamarunner/runner.go:981 +0x28 fp=0xc0000eb7e0 sp=0xc0000eb7b8 pc=0x55c93088e748
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc0000eb7e8 sp=0xc0000eb7e0 pc=0x55c9303c5c61
created by github.com/ollama/ollama/runner/llamarunner.Execute in goroutine 1
github.com/ollama/ollama/runner/llamarunner/runner.go:981 +0x4c5

goroutine 39 gp=0xc0000e3dc0 m=nil [IO wait]:
runtime.gopark(0x55c930448765?, 0xc000156c80?, 0x40?, 0x9a?, 0xb?)
runtime/proc.go:435 +0xce fp=0xc000049948 sp=0xc000049928 pc=0x55c9303bddce
runtime.netpollblock(0x55c9303e1598?, 0x30357506?, 0xc9?)
runtime/netpoll.go:575 +0xf7 fp=0xc000049980 sp=0xc000049948 pc=0x55c9303830f7
internal/poll.runtime_pollWait(0x7f48f1644cc8, 0x72)
runtime/netpoll.go:351 +0x85 fp=0xc0000499a0 sp=0xc000049980 pc=0x55c9303bcfe5
internal/poll.(*pollDesc).wait(0xc000156c80?, 0xc000000000?, 0x0)
internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc0000499c8 sp=0xc0000499a0 pc=0x55c930445167
internal/poll.(*pollDesc).waitRead(...)
internal/poll/fd_poll_runtime.go:89
internal/poll.(*FD).Read(0xc000156c80, {0xc000000000, 0x1000, 0x1000})
internal/poll/fd_unix.go:165 +0x27a fp=0xc000049a60 sp=0xc0000499c8 pc=0x55c93044645a
net.(*netFD).Read(0xc000156c80, {0xc000000000?, 0xc000049ad0?, 0x55c930445625?})
net/fd_posix.go:55 +0x25 fp=0xc000049aa8 sp=0xc000049a60 pc=0x55c9304bb645
net.(*conn).Read(0xc000196970, {0xc000000000?, 0x0?, 0x0?})
net/net.go:194 +0x45 fp=0xc000049af0 sp=0xc000049aa8 pc=0x55c9304c9a05
net/http.(*connReader).Read(0xc000167290, {0xc000000000, 0x1000, 0x1000})
net/http/server.go:798 +0x159 fp=0xc000049b40 sp=0xc000049af0 pc=0x55c9306b69d9
bufio.(*Reader).fill(0xc000034660)
bufio/bufio.go:113 +0x103 fp=0xc000049b78 sp=0xc000049b40 pc=0x55c9304e1ac3
bufio.(*Reader).Peek(0xc000034660, 0x4)
bufio/bufio.go:152 +0x53 fp=0xc000049b98 sp=0xc000049b78 pc=0x55c9304e1bf3
net/http.(*conn).serve(0xc000036750, {0x55c931a86d08, 0xc0001671a0})
net/http/server.go:2137 +0x785 fp=0xc000049fb8 sp=0xc000049b98 pc=0x55c9306bc7c5
net/http.(*Server).Serve.gowrap3()
net/http/server.go:3454 +0x28 fp=0xc000049fe0 sp=0xc000049fb8 pc=0x55c9306c1f28
runtime.goexit({})
runtime/asm_amd64.s:1700 +0x1 fp=0xc000049fe8 sp=0xc000049fe0 pc=0x55c9303c5c61
created by net/http.(*Server).Serve in goroutine 1
net/http/server.go:3454 +0x485

rax 0x7f493a1aa698
rbx 0x55c94aa3b660
rcx 0x0
rdx 0x55c94230c100
rdi 0x7f48dd258e48
rsi 0x3
rbp 0x7f493a1aa698
rsp 0x7fff6545f8d0
r8 0x0
r9 0x0
r10 0x55c94aaa7350
r11 0x55c94aa359d0
r12 0x0
r13 0x0
r14 0x18
r15 0x1
rip 0x7f48dcec0bf5
rflags 0x10246
cs 0x33
fs 0x0
gs 0x0
time=2026-01-31T09:02:25.272Z level=INFO source=sched.go:479 msg="Load failed" model=/root/.ollama/models/blobs/sha256-667b0c1932bc6ffc593ed1d03f895bf2dc8dc6df21db3042284a6f4416b06a29 error="llama runner process has terminated: exit status 2"
[GIN] 2026/01/31 - 09:02:25 | 500 | 4.032735214s | 127.0.0.1 | POST "/api/generate"

5hridhyan · 2026-01-31 11:30:40

im not sure about it but kinda, try this, like first run your model and in cli(chat) and then run it

/set parameter num_gpu 12 #either range 9-12

if not some users said forcing to vulkan helped them, but I heard stability>performance

OLLAMA_VULKAN=1 ollama run <your_model>

https://docs.ollama.com/gpu#overrides-on-linux

HSA_OVERRIDE_GFX_VERSION=11.0.0 ollama run <your_model> #sneaky ;)

it has mixed reviews some say unstable, and if ntg helps force CPU mode.

also please use code tags and please edit you #1 post and wrap it up

Last edited by 5hridhyan (2026-01-31 11:43:21)

Luciddream · 2026-01-31 13:23:27

I don't have anything to say right now, but, I'm expecting a Ryzen AI Max+ 395 hopefully on Monday. I'm also maintaining the AUR package for rocm-gfx1151-bin and opencl-amd.
So I will be able to troubleshoot issues like that for stable and preview ROCm versions. Also, hopefully AMD releases a new preview version soon. I will try to ask them on discord about it.

May I suggest you try to use lemonade-server instead? I'm also maintaining that package. And lemonade-desktop for the GUI.

edit: or as a faster potential solution, I would download the nightly ROCm from: https://rocm.nightlies.amd.com/tarball/ … 131.tar.gz - extract it somewhere e.g /home/user/rocm-nightly - and set LD_LIBRARY_PATH=/home/user/rocm-nightly

Last edited by Luciddream (2026-01-31 13:38:58)

Luciddream · 2026-02-04 07:59:12

I got my Ryzen AI Max+ PC yesterday, but didn't have time to set it up. Hopefully I can do it tonight. Did you have any luck with yours ?

qianjigui · 2026-02-15 13:19:03

Luciddream wrote:

I got my Ryzen AI Max+ PC yesterday, but didn't have time to set it up. Hopefully I can do it tonight. Did you have any luck with yours ?

I am using the docker image from https://github.com/phueper/ollama-linux-amd-apu , it works now.
My system is rocm 7.2, and kernel is 6.18.

Docker information:
Docker images: ghcr.io/rjmalagon/ollama-linux-amd-apu:optm-latest
IMAGE ID DISK USAGE CONTENT SIZE EXTRA
ghcr.io/rjmalagon/ollama-linux-amd-apu:optm-latest c7b3ad833172 11.6GB 3.08GB U

Arch Linux

#1 2026-01-31 10:52:13

AMD RYZEN AI MAX+ 395 w/ Radeon 8060S ollama run SIGSEGV

#2 2026-01-31 11:30:40

Re: AMD RYZEN AI MAX+ 395 w/ Radeon 8060S ollama run SIGSEGV

#3 2026-01-31 13:23:27

Re: AMD RYZEN AI MAX+ 395 w/ Radeon 8060S ollama run SIGSEGV

#4 2026-02-04 07:59:12

Re: AMD RYZEN AI MAX+ 395 w/ Radeon 8060S ollama run SIGSEGV

#5 2026-02-15 13:19:03

Re: AMD RYZEN AI MAX+ 395 w/ Radeon 8060S ollama run SIGSEGV

Board footer