cant run ollama using llm-cpp on 12th igpu under linux

[user7z]

i start serving with this script :

bash

export OLLAMA_NUM_GPU=999 export no_proxy=localhost,127.0.0.1 export ZES_ENABLE_SYSMAN=1 source /opt/intel/oneapi/setvars.sh ./ollama serve

end

here is serve log :

`:: initializing oneAPI environment ... ollama-lunch: BASH_VERSION = 5.2.32(1)-release args: Using "$@" for setvars.sh arguments: :: advisor -- latest :: ccl -- latest :: compiler -- latest :: dal -- latest :: debugger -- latest :: dev-utilities -- latest :: dnnl -- latest :: dpcpp-ct -- latest :: dpl -- latest :: ipp -- latest :: ippcp -- latest :: mkl -- latest :: mpi -- latest :: tbb -- latest :: vtune -- latest :: oneAPI environment initialized ::

2024/09/25 15:24:58 routes.go:1125: INFO server config env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_LLM_LIBRARY: OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/home/user/.ollama/models OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:0 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://*] OLLAMA_RUNNERS_DIR: OLLAMA_SCHED_SPREAD:false OLLAMA_TMPDIR: ROCR_VISIBLE_DEVICES:]" time=2024-09-25T15:24:58.093Z level=INFO source=images.go:753 msg="total blobs: 5" time=2024-09-25T15:24:58.093Z level=INFO source=images.go:760 msg="total unused blobs removed: 0" [GIN-debug] [WARNING] Creating an Engine instance with the Logger and Recovery middleware already attached.

[GIN-debug] [WARNING] Running in "debug" mode. Switch to "release" mode in production.

• using env: export GIN_MODE=release
• using code: gin.SetMode(gin.ReleaseMode)

[GIN-debug] POST /api/pull --> github.com/ollama/ollama/server.(Server).PullModelHandler-fm (5 handlers) [GIN-debug] POST /api/generate --> github.com/ollama/ollama/server.(Server).GenerateHandler-fm (5 handlers) [GIN-debug] POST /api/chat --> github.com/ollama/ollama/server.(Server).ChatHandler-fm (5 handlers) [GIN-debug] POST /api/embed --> github.com/ollama/ollama/server.(Server).EmbedHandler-fm (5 handlers) [GIN-debug] POST /api/embeddings --> github.com/ollama/ollama/server.(Server).EmbeddingsHandler-fm (5 handlers) [GIN-debug] POST /api/create --> github.com/ollama/ollama/server.(Server).CreateModelHandler-fm (5 handlers) [GIN-debug] POST /api/push --> github.com/ollama/ollama/server.(Server).PushModelHandler-fm (5 handlers) [GIN-debug] POST /api/copy --> github.com/ollama/ollama/server.(Server).CopyModelHandler-fm (5 handlers) [GIN-debug] DELETE /api/delete --> github.com/ollama/ollama/server.(Server).DeleteModelHandler-fm (5 handlers) [GIN-debug] POST /api/show --> github.com/ollama/ollama/server.(Server).ShowModelHandler-fm (5 handlers) [GIN-debug] POST /api/blobs/:digest --> github.com/ollama/ollama/server.(Server).CreateBlobHandler-fm (5 handlers) [GIN-debug] HEAD /api/blobs/:digest --> github.com/ollama/ollama/server.(Server).HeadBlobHandler-fm (5 handlers) [GIN-debug] GET /api/ps --> github.com/ollama/ollama/server.(Server).ProcessHandler-fm (5 handlers) [GIN-debug] POST /v1/chat/completions --> github.com/ollama/ollama/server.(Server).ChatHandler-fm (6 handlers) [GIN-debug] POST /v1/completions --> github.com/ollama/ollama/server.(Server).GenerateHandler-fm (6 handlers) [GIN-debug] POST /v1/embeddings --> github.com/ollama/ollama/server.(Server).EmbedHandler-fm (6 handlers) [GIN-debug] GET /v1/models --> github.com/ollama/ollama/server.(Server).ListModelsHandler-fm (6 handlers) [GIN-debug] GET /v1/models/:model --> github.com/ollama/ollama/server.(Server).ShowModelHandler-fm (6 handlers) [GIN-debug] GET / --> github.com/ollama/ollama/server.(Server).GenerateRoutes.func1 (5 handlers) [GIN-debug] GET /api/tags --> github.com/ollama/ollama/server.(Server).ListModelsHandler-fm (5 handlers) [GIN-debug] GET /api/version --> github.com/ollama/ollama/server.(Server).GenerateRoutes.func2 (5 handlers) [GIN-debug] HEAD / --> github.com/ollama/ollama/server.(Server).GenerateRoutes.func1 (5 handlers) [GIN-debug] HEAD /api/tags --> github.com/ollama/ollama/server.(Server).ListModelsHandler-fm (5 handlers) [GIN-debug] HEAD /api/version --> github.com/ollama/ollama/server.(Server).GenerateRoutes.func2 (5 handlers) time=2024-09-25T15:24:58.093Z level=INFO source=routes.go:1172 msg="Listening on 127.0.0.1:11434 (version 0.3.6-ipexllm-20240925)" time=2024-09-25T15:24:58.099Z level=INFO source=payload.go:30 msg="extracting embedded files" dir=/tmp/ollama719758347/runners time=2024-09-25T15:24:58.232Z level=INFO source=payload.go:44 msg="Dynamic LLM libraries [cpu cpu_avx cpu_avx2]"`

wheny i try to : ollama run llama3.1:latest

i get am error with this log :

`[GIN] 2024/09/25 - 15:28:23	200	47.421µs	127.0.0.1	HEAD "/" [GIN] 2024/09/25 - 15:28:23	200	22.833375ms	127.0.0.1	POST "/api/show" time=2024-09-25T15:28:23.254Z level=INFO source=gpu.go:168 msg="looking for compatible GPUs" time=2024-09-25T15:28:23.254Z level=WARN source=gpu.go:560 msg="unable to locate gpu dependency libraries" time=2024-09-25T15:28:23.254Z level=WARN source=gpu.go:560 msg="unable to locate gpu dependency libraries" time=2024-09-25T15:28:23.274Z level=WARN source=gpu.go:560 msg="unable to locate gpu dependency libraries" time=2024-09-25T15:28:23.283Z level=INFO source=gpu.go:280 msg="no compatible GPUs were discovered" time=2024-09-25T15:28:23.330Z level=INFO source=memory.go:309 msg="offload to cpu" layers.requested=-1 layers.model=33 layers.offload=0 layers.split="" memory.available="[25.1 GiB]" memory.required.full="5.8 GiB" memory.required.partial="0 B" memory.required.kv="1.0 GiB" memory.required.allocations="[5.8 GiB]" memory.weights.total="4.7 GiB" memory.weights.repeating="4.3 GiB" memory.weights.nonrepeating="411.0 MiB" memory.graph.full="560.0 MiB" memory.graph.partial="677.5 MiB" time=2024-09-25T15:28:23.332Z level=INFO source=server.go:395 msg="starting llama server" cmd="/tmp/ollama719758347/runners/cpu_avx2/ollama_llama_server --model /home/user/.ollama/models/blobs/sha256-8eeb52dfb3bb9aefdf9d1ef24b3bdbcfbe82238798c4b918278320b6fcef18fe --ctx-size 8192 --batch-size 512 --embedding --log-disable --n-gpu-layers 999 --no-mmap --parallel 4 --port 43871" time=2024-09-25T15:28:23.334Z level=INFO source=sched.go:450 msg="loaded runners" count=1 time=2024-09-25T15:28:23.334Z level=INFO source=server.go:595 msg="waiting for llama runner to start responding" time=2024-09-25T15:28:23.334Z level=INFO source=server.go:629 msg="waiting for server to become available" status="llm server error" INFO [main] build info	build=1 commit="7cec8b8" tid="137492451709312" timestamp=1727278103 INFO [main] system info	n_threads=2 n_threads_batch=-1 system_info="AVX = 0	AVX_VNNI = 0	AVX2 = 0	AVX512 = 0	AVX512_VBMI = 0	AVX512_VNNI = 0	AVX512_BF16 = 0	FMA = 0	NEON = 0	SVE = 0	ARM_FMA = 0	F16C = 0	FP16_VA = 0	WASM_SIMD = 0	BLAS = 1	SSE3 = 0	SSSE3 = 0	VSX = 0	MATMUL_INT8 = 0	LLAMAFILE = 1	" tid="137492451709312" timestamp=1727278103 total_threads=12 INFO [main] HTTP server listening	hostname="127.0.0.1" n_threads_http="11" port="43871" tid="137492451709312" timestamp=1727278103 llama_model_loader: loaded meta data with 29 key-value pairs and 292 tensors from /home/user/.ollama/models/blobs/sha256-8eeb52dfb3bb9aefdf9d1ef24b3bdbcfbe82238798c4b918278320b6fcef18fe (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 = 2 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_0: 225 tensors llama_model_loader: - type q6_K: 1 tensors time=2024-09-25T15:28:23.586Z level=INFO source=server.go:629 msg="waiting for server to become available" status="llm server loading model" llm_load_vocab: special tokens cache size = 256 llm_load_vocab: token to piece cache size = 0.7999 MB llm_load_print_meta: format = GGUF V3 (latest) llm_load_print_meta: arch = llama llm_load_print_meta: vocab type = BPE llm_load_print_meta: n_vocab = 128256 llm_load_print_meta: n_merges = 280147 llm_load_print_meta: vocab_only = 0 llm_load_print_meta: n_ctx_train = 131072 llm_load_print_meta: n_embd = 4096 llm_load_print_meta: n_layer = 32 llm_load_print_meta: n_head = 32 llm_load_print_meta: n_head_kv = 8 llm_load_print_meta: n_rot = 128 llm_load_print_meta: n_swa = 0 llm_load_print_meta: n_embd_head_k = 128 llm_load_print_meta: n_embd_head_v = 128 llm_load_print_meta: n_gqa = 4 llm_load_print_meta: n_embd_k_gqa = 1024 llm_load_print_meta: n_embd_v_gqa = 1024 llm_load_print_meta: f_norm_eps = 0.0e+00 llm_load_print_meta: f_norm_rms_eps = 1.0e-05 llm_load_print_meta: f_clamp_kqv = 0.0e+00 llm_load_print_meta: f_max_alibi_bias = 0.0e+00 llm_load_print_meta: f_logit_scale = 0.0e+00 llm_load_print_meta: n_ff = 14336 llm_load_print_meta: n_expert = 0 llm_load_print_meta: n_expert_used = 0 llm_load_print_meta: causal attn = 1 llm_load_print_meta: pooling type = 0 llm_load_print_meta: rope type = 0 llm_load_print_meta: rope scaling = linear llm_load_print_meta: freq_base_train = 500000.0 llm_load_print_meta: freq_scale_train = 1 llm_load_print_meta: n_ctx_orig_yarn = 131072 llm_load_print_meta: rope_finetuned = unknown llm_load_print_meta: ssm_d_conv = 0 llm_load_print_meta: ssm_d_inner = 0 llm_load_print_meta: ssm_d_state = 0 llm_load_print_meta: ssm_dt_rank = 0 llm_load_print_meta: ssm_dt_b_c_rms = 0 llm_load_print_meta: model type = 8B llm_load_print_meta: model ftype = Q4_0 llm_load_print_meta: model params = 8.03 B llm_load_print_meta: model size = 4.33 GiB (4.64 BPW) llm_load_print_meta: general.name = Meta Llama 3.1 8B Instruct llm_load_print_meta: BOS token = 128000 '<	begin_of_text	>' llm_load_print_meta: EOS token = 128009 '<	eot_id	>' llm_load_print_meta: LF token = 128 'Ä' llm_load_print_meta: EOT token = 128009 '<	eot_id	>' llm_load_print_meta: max token length = 256 ZE_LOADER_DEBUG_TRACE:Using Loader Library Path: ZE_LOADER_DEBUG_TRACE:Tracing Layer Library Path: libze_tracing_layer.so.1 ggml_sycl_init: GGML_SYCL_FORCE_MMQ: no ggml_sycl_init: SYCL_USE_XMX: yes ggml_sycl_init: found 1 SYCL devices: llm_load_tensors: ggml ctx size = 0.27 MiB llm_load_tensors: offloading 32 repeating layers to GPU llm_load_tensors: offloading non-repeating layers to GPU llm_load_tensors: offloaded 33/33 layers to GPU llm_load_tensors: SYCL0 buffer size = 4156.00 MiB llm_load_tensors: SYCL_Host buffer size = 281.81 MiB llama_new_context_with_model: n_ctx = 8192 llama_new_context_with_model: n_batch = 512 llama_new_context_with_model: n_ubatch = 512 llama_new_context_with_model: flash_attn = 0 llama_new_context_with_model: freq_base = 500000.0 llama_new_context_with_model: freq_scale = 1 [SYCL] call ggml_check_sycl ggml_check_sycl: GGML_SYCL_DEBUG: 0 ggml_check_sycl: GGML_SYCL_F16: no found 1 SYCL devices:					Max		Max	Global							compute	Max work	sub	mem			ID	Device Type	Name	Version	units	group	group	size	Driver version
0	[level_zero:gpu:0]	Intel Iris Xe Graphics	1.5	80	512	32	30843M	1.3.30872

llama_kv_cache_init: SYCL0 KV buffer size = 1024.00 MiB llama_new_context_with_model: KV self size = 1024.00 MiB, K (f16): 512.00 MiB, V (f16): 512.00 MiB llama_new_context_with_model: SYCL_Host output buffer size = 2.02 MiB [1727278109] warming up the model with an empty run llama_new_context_with_model: SYCL0 compute buffer size = 576.00 MiB llama_new_context_with_model: SYCL_Host compute buffer size = 24.01 MiB llama_new_context_with_model: graph nodes = 1062 llama_new_context_with_model: graph splits = 2 ollama_llama_server: /home/runner/_work/llm.cpp/llm.cpp/llm.cpp/bigdl-core-xe/llama_backend/sdp_xmx_kernel.cpp:429: auto ggml_sycl_op_sdp_xmx_casual(fp16 , fp16 , fp16 , fp16 , fp16 , float , size_t, size_t, size_t, size_t, size_t, size_t, size_t, size_t, size_t, size_t, size_t, size_t, size_t, size_t, size_t, size_t, size_t, size_t, float *, float, bool, sycl::queue &)::(anonymous class)::operator()() const: Assertion `false' failed. time=2024-09-25T15:28:29.632Z level=INFO source=server.go:629 msg="waiting for server to become available" status="llm server error" time=2024-09-25T15:28:29.883Z level=ERROR source=sched.go:456 msg="error loading llama server" error="llama runner process has terminated: signal: aborted (core dumped)" [GIN] 2024/09/25 - 15:28:29 | 500 | 6.649310166s | 127.0.0.1 | POST "/api/generate"

`

[lzivan]

Hi, we are trying to reproduce your issue.

[casperfrx]

Running in the same issue here. open-webui:git-3ad003b used to work fine but after trying the latest releases, none of them work anymore. Reverting back to 3ad003b now also runs in sysctl issues. I can't figure out for the life of me what it could be.

[lzivan]

Hi @user7z , which version of oneApi are you using?

I'm testing fine on Linux, ipex-llm[cpp] == 2.2.0b20240925, oneApi 2024.0

[user7z]

@lzivan , i am using the latest ipex-llm , for oneapi i tried with 2024.1.0 & also 2024.2.1-1 Linux Kernel 6.10.10

[lzivan]

Hi @user7z , ipex-llm[cpp] currently supports oneAPI 2024.0 on Linux. You may use oneAPI 2024.0 and have a try again.

Here is the guide regarding installing oneAPI 2024.0 on Linux: https://github.com/intel-analytics/ipex-llm/blob/main/docs/mddocs/Quickstart/install_linux_gpu.md#install-oneapi

Feel free to point out if you still have any problems.

[user7z]

Hi @lzivan, i install the intel-oneapi-basekit 2024.0.0.49564-3 , since my package manager is not apt , i was lucky the distro has an archive for old packages, however it gives me the same core dump , here is our distrbution packaging_script.

Is it strictlly needed to be on a debian based distrbution to accelerate ollama on an intel platform ? I think that the pkg manager shouldnt be a probleme & if packages needs to be in a certain way let me know plz , so we could modify what can be. Also is there a known version of llm-cpp know for it to be working , i think that necessairy to identify the source of the issue here.

[lzivan]

Hi @user7z , regarding the installation of intel oneapi, we have some more installation methods.

Follow this link: https://github.com/intel-analytics/ipex-llm/blob/main/docs/mddocs/Overview/install_gpu.md#linux

Under step 2, you can see there are also PIP installer and Offline installer. You can have a try to install your oneApi.

For the llm-cpp version, I'm still trying to test it out. Will get back to you once I figured it out.

[user7z]

@lzivan is there any progress ?

[lzivan]

Hi @user7z , did you rechange your oneApi based on my previous link?

We successfully ran this on our Arc Linux machine, will try to reproduce it on our Iris Linux machine.

[user7z]

@lzivan yes i think its obvious , oneapi isnot the probleme , were toaking here about iris xe machine as i mention

[lzivan]

Hi @user7z , sorry for the late response. We have reproduced this issue and will fix it soon. You can try to use ipex-llm version 2.2.0b20240917 first through pip install --pre --upgrade ipex-llm[cpp]==2.2.0b20240917 and init-ollama again. It's the latest version we tested on our Iris Linux machine that won't cause a core-dump problem.

We will also update here when this issue is fixed :)

[Oscilloscope98]

Hi @user7z,

We have resolved this issue :) You could have a try on the latest ipex-llm[cpp] through pip install --pre --upgrade ipex-llm[cpp] and init-ollama again.

You could also refer to our QuickStart for more information regarding Ollama with ipex-llm acceleration on Intel GPU.

Please let us know for any further problems :)

[user7z]

thank you @lzivan @Oscilloscope98 , i know have it working under Arch Linux using alder lake integrated graphics , the results are very promising . thank you , and if you can plz offer us a systemd service script with the guide , so one wouldnt need to each time run a script , thank you again

[user7z]

update : using it with llama3.2-1b gives very amazing results in conjunction with a browser extension for ollama page assiste, with a systemd service ,it faster than chatgpt, i am just like using chatgpt without privacy concerns and localy , its dramatically fast with 1b models , i dont recommend for higher , i think the cause is the memory , for lunar lake with more than 8000 MT/s it well give more performance , for me i have all what i need for a day to day task , thank you guys here for making this hapen , you make those selicon devices more useful , thank you all

[moophlo]

I'm using iGPU on Intel Core i9 9900K and I'm getting this error in the container console (running on kubernetes pod):

ollama_llama_server: /home/runner/_work/llm.cpp/llm.cpp/llm.cpp/bigdl-core-xe/llama_backend/sdp_kernel.cpp:343: void sdp_fp16_casual_kernel(const void *, const void *, const void *, void *, const size_t, const size_t, const size_t, const size_t, const size_t, const size_t, const size_t, const size_t, const size_t, const size_t, const size_t, const size_t, const size_t, const size_t, const size_t, const size_t, const size_t, float *, float, sycl::queue &) [GS = 32, HD = 64]: Assertion `(context_length-seq_len)%GS==0 && "ubatch must be set as the times of GS\n"' failed.

On the host from syslog I'm getting:

systemd-coredump[34488]: Process 33194 (ollama_llama_se) of user 0 dumped core.#012#012Module /tmp/ollama2041968349/runners/cpu_avx2/ollama_llama_server without build-id.#012Module /tmp/ollama2041968349/runners/cpu_avx2/ollama_llama_server#012Module /opt/intel/oneapi/compiler/2024.2/lib/libcommon_clang.so.2024.18.7.0 without build-id.#012Module /opt/intel/oneapi/compiler/2024.2/lib/libcommon_clang.so.2024.18.7.0#012Module /opt/intel/oneapi/compiler/2024.2/lib/libintelocl.so.2024.18.7.0 without build-id.#012Module /opt/intel/oneapi/compiler/2024.2/lib/libintelocl.so.2024.18.7.0#012Module /opt/intel/oneapi/compiler/2024.0/lib/libintelocl.so.2023.16.12.0 without build-id.#012Module /opt/intel/oneapi/compiler/2024.0/lib/libintelocl.so.2023.16.12.0#012Module /opt/intel/oneapi/compiler/2024.0/lib/libonnxruntime.1.12.22.721.so without build-id.#012Module /opt/intel/oneapi/compiler/2024.0/lib/libonnxruntime.1.12.22.721.so#012Module /opt/intel/oneapi/compiler/2024.0/lib/libcommon_clang.so.2023.16.12.0 without build-id.#012Module /opt/intel/oneapi/compiler/2024.0/lib/libcommon_clang.so.2023.16.12.0#012Module /opt/intel/oneapi/compiler/2024.0/lib/libintelocl_emu.so.2023.16.12.0 without build-id.#012Module /opt/intel/oneapi/compiler/2024.0/lib/libintelocl_emu.so.2023.16.12.0#012Module /opt/intel/oneapi/compiler/2024.0/lib/libur_adapter_level_zero.so.0 without build-id.#012Module /opt/intel/oneapi/compiler/2024.0/lib/libur_adapter_level_zero.so.0#012Module /opt/intel/oneapi/compiler/2024.0/lib/libur_loader.so.0 without build-id.#012Module /opt/intel/oneapi/compiler/2024.0/lib/libur_loader.so.0#012Module /opt/intel/oneapi/compiler/2024.0/lib/libpi_level_zero.so without build-id.#012Module /opt/intel/oneapi/compiler/2024.0/lib/libpi_level_zero.so#012Module /opt/intel/oneapi/compiler/2024.0/lib/libsycl.so.7.0.0 without build-id.#012Module /opt/intel/oneapi/compiler/2024.0/lib/libsycl.so.7.0.0#012Module /opt/intel/oneapi/dnnl/2024.0/lib/libdnnl.so.3.3 without build-id.#012Module /opt/intel/oneapi/dnnl/2024.0/lib/libdnnl.so.3.3#012Module /opt/intel/oneapi/mkl/2024.0/lib/libmkl_sycl_blas.so.4 without build-id.#012Module /opt/intel/oneapi/mkl/2024.0/lib/libmkl_sycl_blas.so.4#012Module /opt/intel/oneapi/compiler/2024.0/opt/oclfpga/host/linux64/lib/libOpenCL.so.1 without build-id.#012Module /opt/intel/oneapi/compiler/2024.0/opt/oclfpga/host/linux64/lib/libOpenCL.so.1#012Module /opt/intel/oneapi/compiler/2024.0/lib/libintlc.so.5 without build-id.#012Module /opt/intel/oneapi/compiler/2024.0/lib/libintlc.so.5#012Module /opt/intel/oneapi/compiler/2024.0/lib/libimf.so without build-id.#012Module /opt/intel/oneapi/compiler/2024.0/lib/libimf.so#012Module /opt/intel/oneapi/compiler/2024.0/lib/libsvml.so without build-id.#012Module /opt/intel/oneapi/compiler/2024.0/lib/libsvml.so#012Module /tmp/ollama2041968349/runners/cpu_avx2/libggml.so without build-id.#012Module /tmp/ollama2041968349/runners/cpu_avx2/libggml.so#012Module /opt/intel/oneapi/compiler/2024.0/lib/libirng.so without build-id.#012Module /opt/intel/oneapi/compiler/2024.0/lib/libirng.so#012Module /tmp/ollama2041968349/runners/cpu_avx2/libllama.so without build-id.#012Module /tmp/ollama2041968349/runners/cpu_avx2/libllama.so#012Module /opt/intel/oneapi/compiler/2024.0/lib/libpi_unified_runtime.so without build-id.#012Module /opt/intel/oneapi/compiler/2024.0/lib/libpi_unified_runtime.so#012Stack trace of thread 67:#012#0  0x000079a68086d9fc n/a (/usr/lib/x86_64-linux-gnu/libc.so.6 + 0x969fc)#012ELF object binary architecture: AMD x86-64

[sgwhat]

Hi @moophlo , could you please open a new issue for us? We will keep to track your issue then.