❯ OLLAMA_HOST=0.0.0.0 ./ollama serve ggml_sycl_init: found 1 SYCL devices: 2025/03/18 09:29:15 routes.go:1259: INFO server config env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://0.0.0.0:11434 OLLAMA_INTEL_GPU:false 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/billr/.ollama/models OLLAMA_MULTIUSER_CACHE:false 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://* vscode-webview://*] OLLAMA_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:localhost,127.0.0.1]" time=2025-03-18T09:29:15.819-05:00 level=INFO source=images.go:757 msg="total blobs: 41" time=2025-03-18T09:29:15.820-05:00 level=INFO source=images.go:764 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 --> ollama/server.(*Server).PullHandler-fm (5 handlers) [GIN-debug] POST /api/generate --> ollama/server.(*Server).GenerateHandler-fm (5 handlers) [GIN-debug] POST /api/chat --> ollama/server.(*Server).ChatHandler-fm (5 handlers) [GIN-debug] POST /api/embed --> ollama/server.(*Server).EmbedHandler-fm (5 handlers) [GIN-debug] POST /api/embeddings --> ollama/server.(*Server).EmbeddingsHandler-fm (5 handlers) [GIN-debug] POST /api/create --> ollama/server.(*Server).CreateHandler-fm (5 handlers) [GIN-debug] POST /api/push --> ollama/server.(*Server).PushHandler-fm (5 handlers) [GIN-debug] POST /api/copy --> ollama/server.(*Server).CopyHandler-fm (5 handlers) [GIN-debug] DELETE /api/delete --> ollama/server.(*Server).DeleteHandler-fm (5 handlers) [GIN-debug] POST /api/show --> ollama/server.(*Server).ShowHandler-fm (5 handlers) [GIN-debug] POST /api/blobs/:digest --> ollama/server.(*Server).CreateBlobHandler-fm (5 handlers) [GIN-debug] HEAD /api/blobs/:digest --> ollama/server.(*Server).HeadBlobHandler-fm (5 handlers) [GIN-debug] GET /api/ps --> ollama/server.(*Server).PsHandler-fm (5 handlers) [GIN-debug] POST /v1/chat/completions --> ollama/server.(*Server).ChatHandler-fm (6 handlers) [GIN-debug] POST /v1/completions --> ollama/server.(*Server).GenerateHandler-fm (6 handlers) [GIN-debug] POST /v1/embeddings --> ollama/server.(*Server).EmbedHandler-fm (6 handlers) [GIN-debug] GET /v1/models --> ollama/server.(*Server).ListHandler-fm (6 handlers) [GIN-debug] GET /v1/models/:model --> ollama/server.(*Server).ShowHandler-fm (6 handlers) [GIN-debug] GET / --> ollama/server.(*Server).GenerateRoutes.func1 (5 handlers) [GIN-debug] GET /api/tags --> ollama/server.(*Server).ListHandler-fm (5 handlers) [GIN-debug] GET /api/version --> ollama/server.(*Server).GenerateRoutes.func2 (5 handlers) [GIN-debug] HEAD / --> ollama/server.(*Server).GenerateRoutes.func1 (5 handlers) [GIN-debug] HEAD /api/tags --> ollama/server.(*Server).ListHandler-fm (5 handlers) [GIN-debug] HEAD /api/version --> ollama/server.(*Server).GenerateRoutes.func2 (5 handlers) time=2025-03-18T09:29:15.820-05:00 level=INFO source=routes.go:1310 msg="Listening on [::]:11434 (version 0.5.4-ipexllm-20250318)" time=2025-03-18T09:29:15.820-05:00 level=INFO source=routes.go:1339 msg="Dynamic LLM libraries" runners=[ipex_llm] [GIN] 2025/03/18 - 09:29:21 | 200 | 24.018µs | 127.0.0.1 | HEAD "/" [GIN] 2025/03/18 - 09:29:21 | 200 | 19.002954ms | 127.0.0.1 | POST "/api/show" time=2025-03-18T09:29:21.059-05:00 level=INFO source=gpu.go:226 msg="looking for compatible GPUs" time=2025-03-18T09:29:21.136-05:00 level=INFO source=server.go:104 msg="system memory" total="31.2 GiB" free="24.9 GiB" free_swap="0 B" time=2025-03-18T09:29:21.137-05:00 level=INFO source=memory.go:356 msg="offload to device" projector.weights="811.8 MiB" projector.graph="0 B" layers.requested=-1 layers.model=35 layers.offload=0 layers.split="" memory.available="[24.9 GiB]" memory.gpu_overhead="0 B" memory.required.full="3.5 GiB" memory.required.partial="0 B" memory.required.kv="272.0 MiB" memory.required.allocations="[3.5 GiB]" memory.weights.total="2.1 GiB" memory.weights.repeating="1.6 GiB" memory.weights.nonrepeating="525.0 MiB" memory.graph.full="90.7 MiB" memory.graph.partial="90.7 MiB" time=2025-03-18T09:29:21.137-05:00 level=INFO source=server.go:392 msg="starting llama server" cmd="/home/billr/miniconda3/envs/ollama/lib/python3.11/site-packages/bigdl/cpp/libs/ollama-lib runner --model /home/billr/.ollama/models/blobs/sha256-be49949e48422e4547b00af14179a193d3777eea7fbbd7d6e1b0861304628a01 --ctx-size 2048 --batch-size 512 --n-gpu-layers 999 --mmproj /home/billr/.ollama/models/blobs/sha256-8c0fb064b019a6972856aaae2c7e4792858af3ca4561be2dbf649123ba6c40cb --threads 6 --no-mmap --parallel 1 --port 45887" time=2025-03-18T09:29:21.137-05:00 level=INFO source=sched.go:449 msg="loaded runners" count=1 time=2025-03-18T09:29:21.137-05:00 level=INFO source=server.go:571 msg="waiting for llama runner to start responding" time=2025-03-18T09:29:21.137-05:00 level=INFO source=server.go:605 msg="waiting for server to become available" status="llm server error" ggml_sycl_init: found 1 SYCL devices: time=2025-03-18T09:29:21.183-05:00 level=INFO source=runner.go:967 msg="starting go runner" time=2025-03-18T09:29:21.184-05:00 level=INFO source=runner.go:968 msg=system info="CPU : SSE3 = 1 | SSSE3 = 1 | AVX = 1 | AVX_VNNI = 1 | AVX2 = 1 | F16C = 1 | FMA = 1 | LLAMAFILE = 1 | OPENMP = 1 | AARCH64_REPACK = 1 | CPU : SSE3 = 1 | SSSE3 = 1 | AVX = 1 | AVX_VNNI = 1 | AVX2 = 1 | F16C = 1 | FMA = 1 | LLAMAFILE = 1 | OPENMP = 1 | AARCH64_REPACK = 1 | cgo(gcc)" threads=6 time=2025-03-18T09:29:21.184-05:00 level=INFO source=runner.go:1026 msg="Server listening on 127.0.0.1:45887" llama_load_model_from_file: using device SYCL0 (Intel(R) Arc(TM) A770 Graphics) - 15473 MiB free llama_model_loader: loaded meta data with 40 key-value pairs and 444 tensors from /home/billr/.ollama/models/blobs/sha256-be49949e48422e4547b00af14179a193d3777eea7fbbd7d6e1b0861304628a01 (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 = gemma3 llama_model_loader: - kv 1: general.type str = model llama_model_loader: - kv 2: general.name str = Gemma 3 4b It llama_model_loader: - kv 3: general.finetune str = it llama_model_loader: - kv 4: general.basename str = gemma-3 llama_model_loader: - kv 5: general.size_label str = 4B llama_model_loader: - kv 6: general.license str = gemma llama_model_loader: - kv 7: general.base_model.count u32 = 1 llama_model_loader: - kv 8: general.base_model.0.name str = Gemma 3 4b Pt llama_model_loader: - kv 9: general.base_model.0.organization str = Google llama_model_loader: - kv 10: general.base_model.0.repo_url str = https://huggingface.co/google/gemma-3... llama_model_loader: - kv 11: general.tags arr[str,1] = ["image-text-to-text"] llama_model_loader: - kv 12: gemma3.context_length u32 = 131072 llama_model_loader: - kv 13: gemma3.embedding_length u32 = 2560 llama_model_loader: - kv 14: gemma3.block_count u32 = 34 llama_model_loader: - kv 15: gemma3.feed_forward_length u32 = 10240 llama_model_loader: - kv 16: gemma3.attention.head_count u32 = 8 llama_model_loader: - kv 17: gemma3.attention.layer_norm_rms_epsilon f32 = 0.000001 llama_model_loader: - kv 18: gemma3.attention.key_length u32 = 256 llama_model_loader: - kv 19: gemma3.attention.value_length u32 = 256 llama_model_loader: - kv 20: gemma3.rope.freq_base f32 = 1000000.000000 llama_model_loader: - kv 21: gemma3.attention.sliding_window u32 = 1024 llama_model_loader: - kv 22: gemma3.attention.head_count_kv u32 = 4 llama_model_loader: - kv 23: gemma3.rope.scaling.type str = linear llama_model_loader: - kv 24: gemma3.rope.scaling.factor f32 = 8.000000 llama_model_loader: - kv 25: tokenizer.ggml.model str = llama llama_model_loader: - kv 26: tokenizer.ggml.pre str = default llama_model_loader: - kv 27: tokenizer.ggml.tokens arr[str,262144] = ["", "", "", "", ... llama_model_loader: - kv 28: tokenizer.ggml.scores arr[f32,262144] = [-1000.000000, -1000.000000, -1000.00... llama_model_loader: - kv 29: tokenizer.ggml.token_type arr[i32,262144] = [3, 3, 3, 3, 3, 4, 3, 3, 3, 3, 3, 3, ... llama_model_loader: - kv 30: tokenizer.ggml.bos_token_id u32 = 2 llama_model_loader: - kv 31: tokenizer.ggml.eos_token_id u32 = 1 llama_model_loader: - kv 32: tokenizer.ggml.unknown_token_id u32 = 3 llama_model_loader: - kv 33: tokenizer.ggml.padding_token_id u32 = 0 llama_model_loader: - kv 34: tokenizer.ggml.add_bos_token bool = true llama_model_loader: - kv 35: tokenizer.ggml.add_eos_token bool = false llama_model_loader: - kv 36: tokenizer.chat_template str = {{ bos_token }}\n{%- if messages[0]['r... llama_model_loader: - kv 37: tokenizer.ggml.add_space_prefix bool = false llama_model_loader: - kv 38: general.quantization_version u32 = 2 llama_model_loader: - kv 39: general.file_type u32 = 15 llama_model_loader: - type f32: 205 tensors llama_model_loader: - type q4_K: 204 tensors llama_model_loader: - type q6_K: 35 tensors llm_load_vocab: special_eos_id is not in special_eog_ids - the tokenizer config may be incorrect llm_load_vocab: special tokens cache size = 6414 time=2025-03-18T09:29:21.388-05:00 level=INFO source=server.go:605 msg="waiting for server to become available" status="llm server loading model" llm_load_vocab: token to piece cache size = 1.9446 MB llm_load_print_meta: format = GGUF V3 (latest) llm_load_print_meta: arch = gemma3 llm_load_print_meta: vocab type = SPM llm_load_print_meta: n_vocab = 262144 llm_load_print_meta: n_merges = 0 llm_load_print_meta: vocab_only = 0 llm_load_print_meta: n_ctx_train = 131072 llm_load_print_meta: n_embd = 2560 llm_load_print_meta: n_layer = 34 llm_load_print_meta: n_head = 8 llm_load_print_meta: n_head_kv = 4 llm_load_print_meta: n_rot = 256 llm_load_print_meta: n_swa = 1024 llm_load_print_meta: n_embd_head_k = 256 llm_load_print_meta: n_embd_head_v = 256 llm_load_print_meta: n_gqa = 2 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-06 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: f_attn_scale = 6.2e-02 llm_load_print_meta: n_ff = 10240 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 = 2 llm_load_print_meta: rope scaling = linear llm_load_print_meta: freq_base_train = 1000000.0 llm_load_print_meta: freq_scale_train = 0.125 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 = 4B llm_load_print_meta: model ftype = Q4_K - Medium llm_load_print_meta: model params = 3.88 B llm_load_print_meta: model size = 2.31 GiB (5.12 BPW) llm_load_print_meta: general.name = Gemma 3 4b It llm_load_print_meta: BOS token = 2 '' llm_load_print_meta: EOS token = 1 '' llm_load_print_meta: EOT token = 106 '' llm_load_print_meta: UNK token = 3 '' llm_load_print_meta: PAD token = 0 '' llm_load_print_meta: LF token = 248 '<0x0A>' llm_load_print_meta: EOG token = 1 '' llm_load_print_meta: EOG token = 106 '' llm_load_print_meta: max token length = 48 llm_load_tensors: offloading 34 repeating layers to GPU llm_load_tensors: offloading output layer to GPU llm_load_tensors: offloaded 35/35 layers to GPU llm_load_tensors: SYCL0 model buffer size = 2368.18 MiB llm_load_tensors: CPU model buffer size = 525.00 MiB llama_new_context_with_model: n_seq_max = 1 llama_new_context_with_model: n_ctx = 2048 llama_new_context_with_model: n_ctx_per_seq = 2048 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 = 1000000.0 llama_new_context_with_model: freq_scale = 0.125 llama_new_context_with_model: n_ctx_per_seq (2048) < n_ctx_train (131072) -- the full capacity of the model will not be utilized [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 Arc A770 Graphics| 12.55| 512| 1024| 32| 16225M| 1.6.32224+14| llama_kv_cache_init: SYCL0 KV buffer size = 272.00 MiB llama_new_context_with_model: KV self size = 272.00 MiB, K (f16): 136.00 MiB, V (f16): 136.00 MiB llama_new_context_with_model: SYCL_Host output buffer size = 1.01 MiB llama_new_context_with_model: SYCL0 compute buffer size = 517.00 MiB llama_new_context_with_model: SYCL_Host compute buffer size = 13.01 MiB llama_new_context_with_model: graph nodes = 1401 llama_new_context_with_model: graph splits = 2 key general.file_type not found in file terminate called after throwing an instance of 'std::runtime_error' what(): Missing required key: general.file_type SIGABRT: abort PC=0x7688cd40eb2c m=7 sigcode=18446744073709551610 signal arrived during cgo execution goroutine 34 gp=0xc000104380 m=7 mp=0xc000580008 [syscall]: runtime.cgocall(0x5853fd659f00, 0xc0000b5c78) runtime/cgocall.go:167 +0x4b fp=0xc0000b5c50 sp=0xc0000b5c18 pc=0x5853fcab7feb ollama/llama/llamafile._Cfunc_clip_model_load(0x76885401a420, 0x1) _cgo_gotypes.go:315 +0x50 fp=0xc0000b5c78 sp=0xc0000b5c50 pc=0x5853fce796d0 ollama/llama/llamafile.NewClipContext(0xc0003a0060, {0x7ffcca12ae5e, 0x68}) ollama/llama/llamafile/llama.go:488 +0x90 fp=0xc0000b5d38 sp=0xc0000b5c78 pc=0x5853fce80570 ollama/llama/runner.NewImageContext(0xc0003a0060, {0x7ffcca12ae5e, 0x68}) ollama/llama/runner/image.go:37 +0xf8 fp=0xc0000b5db8 sp=0xc0000b5d38 pc=0x5853fce85698 ollama/llama/runner.(*Server).loadModel(0xc000596120, {0x3e7, 0x0, 0x0, 0x0, {0x0, 0x0, 0x0}, 0xc00005b290, 0x0}, ...) ollama/llama/runner/runner.go:881 +0x24f fp=0xc0000b5f10 sp=0xc0000b5db8 pc=0x5853fce8b20f ollama/llama/runner.Execute.gowrap1() ollama/llama/runner/runner.go:1001 +0xda fp=0xc0000b5fe0 sp=0xc0000b5f10 pc=0x5853fce8cc1a runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0000b5fe8 sp=0xc0000b5fe0 pc=0x5853fcac6ac1 created by ollama/llama/runner.Execute in goroutine 1 ollama/llama/runner/runner.go:1001 +0xd0d goroutine 1 gp=0xc0000061c0 m=nil [IO wait]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xce fp=0xc000507560 sp=0xc000507540 pc=0x5853fcabe6ee runtime.netpollblock(0xc00011df80?, 0xfca55506?, 0x53?) runtime/netpoll.go:575 +0xf7 fp=0xc000507598 sp=0xc000507560 pc=0x5853fca82357 internal/poll.runtime_pollWait(0x7688cdbb6680, 0x72) runtime/netpoll.go:351 +0x85 fp=0xc0005075b8 sp=0xc000507598 pc=0x5853fcabd9e5 internal/poll.(*pollDesc).wait(0xc000598280?, 0x2c?, 0x0) internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc0005075e0 sp=0xc0005075b8 pc=0x5853fcb45007 internal/poll.(*pollDesc).waitRead(...) internal/poll/fd_poll_runtime.go:89 internal/poll.(*FD).Accept(0xc000598280) internal/poll/fd_unix.go:620 +0x295 fp=0xc000507688 sp=0xc0005075e0 pc=0x5853fcb4a3d5 net.(*netFD).accept(0xc000598280) net/fd_unix.go:172 +0x29 fp=0xc000507740 sp=0xc000507688 pc=0x5853fcbb2aa9 net.(*TCPListener).accept(0xc0000cff40) net/tcpsock_posix.go:159 +0x1e fp=0xc000507790 sp=0xc000507740 pc=0x5853fcbc871e net.(*TCPListener).Accept(0xc0000cff40) net/tcpsock.go:372 +0x30 fp=0xc0005077c0 sp=0xc000507790 pc=0x5853fcbc75d0 net/http.(*onceCloseListener).Accept(0xc000118000?) :1 +0x24 fp=0xc0005077d8 sp=0xc0005077c0 pc=0x5853fce40d24 net/http.(*Server).Serve(0xc00040e4b0, {0x5853fdc08ee0, 0xc0000cff40}) net/http/server.go:3330 +0x30c fp=0xc000507908 sp=0xc0005077d8 pc=0x5853fce18cac ollama/llama/runner.Execute({0xc000036150?, 0x0?, 0x0?}) ollama/llama/runner/runner.go:1027 +0x11a9 fp=0xc000507ca8 sp=0xc000507908 pc=0x5853fce8c7e9 ollama/cmd.NewCLI.func2(0xc0001eea00?, {0x5853fd65ed1d?, 0x4?, 0x5853fd65ed21?}) ollama/cmd/cmd.go:1430 +0x45 fp=0xc000507cd0 sp=0xc000507ca8 pc=0x5853fd6594e5 github.com/spf13/cobra.(*Command).execute(0xc000592008, {0xc0005c0120, 0x11, 0x11}) github.com/spf13/cobra@v1.8.1/command.go:985 +0xaaa fp=0xc000507e58 sp=0xc000507cd0 pc=0x5853fcc4be8a github.com/spf13/cobra.(*Command).ExecuteC(0xc0004da308) github.com/spf13/cobra@v1.8.1/command.go:1117 +0x3ff fp=0xc000507f30 sp=0xc000507e58 pc=0x5853fcc4c75f github.com/spf13/cobra.(*Command).Execute(...) github.com/spf13/cobra@v1.8.1/command.go:1041 github.com/spf13/cobra.(*Command).ExecuteContext(...) github.com/spf13/cobra@v1.8.1/command.go:1034 main.main() ollama/main.go:12 +0x4d fp=0xc000507f50 sp=0xc000507f30 pc=0x5853fd659b4d runtime.main() runtime/proc.go:272 +0x29d fp=0xc000507fe0 sp=0xc000507f50 pc=0x5853fca899fd runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000507fe8 sp=0xc000507fe0 pc=0x5853fcac6ac1 goroutine 2 gp=0xc000006c40 m=nil [force gc (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xce fp=0xc0000a4fa8 sp=0xc0000a4f88 pc=0x5853fcabe6ee runtime.goparkunlock(...) runtime/proc.go:430 runtime.forcegchelper() runtime/proc.go:337 +0xb8 fp=0xc0000a4fe0 sp=0xc0000a4fa8 pc=0x5853fca89d38 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0000a4fe8 sp=0xc0000a4fe0 pc=0x5853fcac6ac1 created by runtime.init.7 in goroutine 1 runtime/proc.go:325 +0x1a goroutine 3 gp=0xc000007180 m=nil [GC sweep wait]: runtime.gopark(0x1?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xce fp=0xc0000a5780 sp=0xc0000a5760 pc=0x5853fcabe6ee runtime.goparkunlock(...) runtime/proc.go:430 runtime.bgsweep(0xc000052080) runtime/mgcsweep.go:317 +0xdf fp=0xc0000a57c8 sp=0xc0000a5780 pc=0x5853fca743df runtime.gcenable.gowrap1() runtime/mgc.go:204 +0x25 fp=0xc0000a57e0 sp=0xc0000a57c8 pc=0x5853fca68a25 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0000a57e8 sp=0xc0000a57e0 pc=0x5853fcac6ac1 created by runtime.gcenable in goroutine 1 runtime/mgc.go:204 +0x66 goroutine 4 gp=0xc000007340 m=nil [GC scavenge wait]: runtime.gopark(0x10000?, 0x5853fd804ed8?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xce fp=0xc0000a5f78 sp=0xc0000a5f58 pc=0x5853fcabe6ee runtime.goparkunlock(...) runtime/proc.go:430 runtime.(*scavengerState).park(0x5853fe3a2da0) runtime/mgcscavenge.go:425 +0x49 fp=0xc0000a5fa8 sp=0xc0000a5f78 pc=0x5853fca71da9 runtime.bgscavenge(0xc000052080) runtime/mgcscavenge.go:658 +0x59 fp=0xc0000a5fc8 sp=0xc0000a5fa8 pc=0x5853fca72339 runtime.gcenable.gowrap2() runtime/mgc.go:205 +0x25 fp=0xc0000a5fe0 sp=0xc0000a5fc8 pc=0x5853fca689c5 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0000a5fe8 sp=0xc0000a5fe0 pc=0x5853fcac6ac1 created by runtime.gcenable in goroutine 1 runtime/mgc.go:205 +0xa5 goroutine 5 gp=0xc000007c00 m=nil [finalizer wait]: runtime.gopark(0xc0000a4648?, 0x5853fca5ef25?, 0xb0?, 0x1?, 0xc0000061c0?) runtime/proc.go:424 +0xce fp=0xc0000a4620 sp=0xc0000a4600 pc=0x5853fcabe6ee runtime.runfinq() runtime/mfinal.go:193 +0x107 fp=0xc0000a47e0 sp=0xc0000a4620 pc=0x5853fca67aa7 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0000a47e8 sp=0xc0000a47e0 pc=0x5853fcac6ac1 created by runtime.createfing in goroutine 1 runtime/mfinal.go:163 +0x3d goroutine 6 gp=0xc000216e00 m=nil [chan receive]: runtime.gopark(0xc0000a6760?, 0x5853fcb9a125?, 0x40?, 0x28?, 0x5853fdc1c400?) runtime/proc.go:424 +0xce fp=0xc0000a6718 sp=0xc0000a66f8 pc=0x5853fcabe6ee runtime.chanrecv(0xc000050310, 0x0, 0x1) runtime/chan.go:639 +0x41c fp=0xc0000a6790 sp=0xc0000a6718 pc=0x5853fca5811c runtime.chanrecv1(0x0?, 0x0?) runtime/chan.go:489 +0x12 fp=0xc0000a67b8 sp=0xc0000a6790 pc=0x5853fca57cd2 runtime.unique_runtime_registerUniqueMapCleanup.func1(...) runtime/mgc.go:1781 runtime.unique_runtime_registerUniqueMapCleanup.gowrap1() runtime/mgc.go:1784 +0x2f fp=0xc0000a67e0 sp=0xc0000a67b8 pc=0x5853fca6ba8f runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0000a67e8 sp=0xc0000a67e0 pc=0x5853fcac6ac1 created by unique.runtime_registerUniqueMapCleanup in goroutine 1 runtime/mgc.go:1779 +0x96 goroutine 7 gp=0xc000217340 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xce fp=0xc0000a6f38 sp=0xc0000a6f18 pc=0x5853fcabe6ee runtime.gcBgMarkWorker(0xc0000518f0) runtime/mgc.go:1412 +0xe9 fp=0xc0000a6fc8 sp=0xc0000a6f38 pc=0x5853fca6ad89 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x25 fp=0xc0000a6fe0 sp=0xc0000a6fc8 pc=0x5853fca6ac65 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0000a6fe8 sp=0xc0000a6fe0 pc=0x5853fcac6ac1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1328 +0x105 goroutine 8 gp=0xc000217500 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xce fp=0xc0000a7738 sp=0xc0000a7718 pc=0x5853fcabe6ee runtime.gcBgMarkWorker(0xc0000518f0) runtime/mgc.go:1412 +0xe9 fp=0xc0000a77c8 sp=0xc0000a7738 pc=0x5853fca6ad89 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x25 fp=0xc0000a77e0 sp=0xc0000a77c8 pc=0x5853fca6ac65 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0000a77e8 sp=0xc0000a77e0 pc=0x5853fcac6ac1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1328 +0x105 goroutine 9 gp=0xc0002176c0 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xce fp=0xc0000a7f38 sp=0xc0000a7f18 pc=0x5853fcabe6ee runtime.gcBgMarkWorker(0xc0000518f0) runtime/mgc.go:1412 +0xe9 fp=0xc0000a7fc8 sp=0xc0000a7f38 pc=0x5853fca6ad89 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x25 fp=0xc0000a7fe0 sp=0xc0000a7fc8 pc=0x5853fca6ac65 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0000a7fe8 sp=0xc0000a7fe0 pc=0x5853fcac6ac1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1328 +0x105 goroutine 10 gp=0xc000217880 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xce fp=0xc0000a0738 sp=0xc0000a0718 pc=0x5853fcabe6ee runtime.gcBgMarkWorker(0xc0000518f0) runtime/mgc.go:1412 +0xe9 fp=0xc0000a07c8 sp=0xc0000a0738 pc=0x5853fca6ad89 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x25 fp=0xc0000a07e0 sp=0xc0000a07c8 pc=0x5853fca6ac65 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0000a07e8 sp=0xc0000a07e0 pc=0x5853fcac6ac1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1328 +0x105 goroutine 11 gp=0xc000217a40 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xce fp=0xc0000a0f38 sp=0xc0000a0f18 pc=0x5853fcabe6ee runtime.gcBgMarkWorker(0xc0000518f0) runtime/mgc.go:1412 +0xe9 fp=0xc0000a0fc8 sp=0xc0000a0f38 pc=0x5853fca6ad89 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x25 fp=0xc0000a0fe0 sp=0xc0000a0fc8 pc=0x5853fca6ac65 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0000a0fe8 sp=0xc0000a0fe0 pc=0x5853fcac6ac1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1328 +0x105 goroutine 12 gp=0xc000217c00 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xce fp=0xc0000a1738 sp=0xc0000a1718 pc=0x5853fcabe6ee runtime.gcBgMarkWorker(0xc0000518f0) runtime/mgc.go:1412 +0xe9 fp=0xc0000a17c8 sp=0xc0000a1738 pc=0x5853fca6ad89 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x25 fp=0xc0000a17e0 sp=0xc0000a17c8 pc=0x5853fca6ac65 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0000a17e8 sp=0xc0000a17e0 pc=0x5853fcac6ac1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1328 +0x105 goroutine 13 gp=0xc000217dc0 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xce fp=0xc0000a1f38 sp=0xc0000a1f18 pc=0x5853fcabe6ee runtime.gcBgMarkWorker(0xc0000518f0) runtime/mgc.go:1412 +0xe9 fp=0xc0000a1fc8 sp=0xc0000a1f38 pc=0x5853fca6ad89 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x25 fp=0xc0000a1fe0 sp=0xc0000a1fc8 pc=0x5853fca6ac65 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0000a1fe8 sp=0xc0000a1fe0 pc=0x5853fcac6ac1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1328 +0x105 goroutine 14 gp=0xc0004a4000 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xce fp=0xc0000a2738 sp=0xc0000a2718 pc=0x5853fcabe6ee runtime.gcBgMarkWorker(0xc0000518f0) runtime/mgc.go:1412 +0xe9 fp=0xc0000a27c8 sp=0xc0000a2738 pc=0x5853fca6ad89 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x25 fp=0xc0000a27e0 sp=0xc0000a27c8 pc=0x5853fca6ac65 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0000a27e8 sp=0xc0000a27e0 pc=0x5853fcac6ac1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1328 +0x105 goroutine 15 gp=0xc0004a41c0 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xce fp=0xc0000a2f38 sp=0xc0000a2f18 pc=0x5853fcabe6ee runtime.gcBgMarkWorker(0xc0000518f0) runtime/mgc.go:1412 +0xe9 fp=0xc0000a2fc8 sp=0xc0000a2f38 pc=0x5853fca6ad89 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x25 fp=0xc0000a2fe0 sp=0xc0000a2fc8 pc=0x5853fca6ac65 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0000a2fe8 sp=0xc0000a2fe0 pc=0x5853fcac6ac1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1328 +0x105 goroutine 16 gp=0xc0004a4380 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xce fp=0xc0000a3738 sp=0xc0000a3718 pc=0x5853fcabe6ee runtime.gcBgMarkWorker(0xc0000518f0) runtime/mgc.go:1412 +0xe9 fp=0xc0000a37c8 sp=0xc0000a3738 pc=0x5853fca6ad89 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x25 fp=0xc0000a37e0 sp=0xc0000a37c8 pc=0x5853fca6ac65 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0000a37e8 sp=0xc0000a37e0 pc=0x5853fcac6ac1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1328 +0x105 goroutine 18 gp=0xc0004a4540 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xce fp=0xc0000a3f38 sp=0xc0000a3f18 pc=0x5853fcabe6ee runtime.gcBgMarkWorker(0xc0000518f0) runtime/mgc.go:1412 +0xe9 fp=0xc0000a3fc8 sp=0xc0000a3f38 pc=0x5853fca6ad89 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x25 fp=0xc0000a3fe0 sp=0xc0000a3fc8 pc=0x5853fca6ac65 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0000a3fe8 sp=0xc0000a3fe0 pc=0x5853fcac6ac1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1328 +0x105 goroutine 19 gp=0xc0004a4700 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xce fp=0xc0004aa738 sp=0xc0004aa718 pc=0x5853fcabe6ee runtime.gcBgMarkWorker(0xc0000518f0) runtime/mgc.go:1412 +0xe9 fp=0xc0004aa7c8 sp=0xc0004aa738 pc=0x5853fca6ad89 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x25 fp=0xc0004aa7e0 sp=0xc0004aa7c8 pc=0x5853fca6ac65 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0004aa7e8 sp=0xc0004aa7e0 pc=0x5853fcac6ac1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1328 +0x105 goroutine 20 gp=0xc0004a48c0 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xce fp=0xc0004aaf38 sp=0xc0004aaf18 pc=0x5853fcabe6ee runtime.gcBgMarkWorker(0xc0000518f0) runtime/mgc.go:1412 +0xe9 fp=0xc0004aafc8 sp=0xc0004aaf38 pc=0x5853fca6ad89 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x25 fp=0xc0004aafe0 sp=0xc0004aafc8 pc=0x5853fca6ac65 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0004aafe8 sp=0xc0004aafe0 pc=0x5853fcac6ac1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1328 +0x105 goroutine 21 gp=0xc0004a4a80 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xce fp=0xc0004ab738 sp=0xc0004ab718 pc=0x5853fcabe6ee runtime.gcBgMarkWorker(0xc0000518f0) runtime/mgc.go:1412 +0xe9 fp=0xc0004ab7c8 sp=0xc0004ab738 pc=0x5853fca6ad89 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x25 fp=0xc0004ab7e0 sp=0xc0004ab7c8 pc=0x5853fca6ac65 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0004ab7e8 sp=0xc0004ab7e0 pc=0x5853fcac6ac1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1328 +0x105 goroutine 22 gp=0xc0004a4c40 m=nil [GC worker (idle)]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xce fp=0xc0004abf38 sp=0xc0004abf18 pc=0x5853fcabe6ee runtime.gcBgMarkWorker(0xc0000518f0) runtime/mgc.go:1412 +0xe9 fp=0xc0004abfc8 sp=0xc0004abf38 pc=0x5853fca6ad89 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x25 fp=0xc0004abfe0 sp=0xc0004abfc8 pc=0x5853fca6ac65 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0004abfe8 sp=0xc0004abfe0 pc=0x5853fcac6ac1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1328 +0x105 goroutine 23 gp=0xc0004a4e00 m=nil [GC worker (idle)]: runtime.gopark(0x49e26476e721?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xce fp=0xc0004ac738 sp=0xc0004ac718 pc=0x5853fcabe6ee runtime.gcBgMarkWorker(0xc0000518f0) runtime/mgc.go:1412 +0xe9 fp=0xc0004ac7c8 sp=0xc0004ac738 pc=0x5853fca6ad89 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x25 fp=0xc0004ac7e0 sp=0xc0004ac7c8 pc=0x5853fca6ac65 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0004ac7e8 sp=0xc0004ac7e0 pc=0x5853fcac6ac1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1328 +0x105 goroutine 24 gp=0xc0004a4fc0 m=nil [GC worker (idle)]: runtime.gopark(0x49e264783131?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xce fp=0xc0004acf38 sp=0xc0004acf18 pc=0x5853fcabe6ee runtime.gcBgMarkWorker(0xc0000518f0) runtime/mgc.go:1412 +0xe9 fp=0xc0004acfc8 sp=0xc0004acf38 pc=0x5853fca6ad89 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x25 fp=0xc0004acfe0 sp=0xc0004acfc8 pc=0x5853fca6ac65 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0004acfe8 sp=0xc0004acfe0 pc=0x5853fcac6ac1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1328 +0x105 goroutine 25 gp=0xc0004a5180 m=nil [GC worker (idle)]: runtime.gopark(0x5853fe3cc920?, 0x1?, 0x4c?, 0x5?, 0x0?) runtime/proc.go:424 +0xce fp=0xc0004ad738 sp=0xc0004ad718 pc=0x5853fcabe6ee runtime.gcBgMarkWorker(0xc0000518f0) runtime/mgc.go:1412 +0xe9 fp=0xc0004ad7c8 sp=0xc0004ad738 pc=0x5853fca6ad89 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x25 fp=0xc0004ad7e0 sp=0xc0004ad7c8 pc=0x5853fca6ac65 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0004ad7e8 sp=0xc0004ad7e0 pc=0x5853fcac6ac1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1328 +0x105 goroutine 26 gp=0xc0004a5340 m=nil [GC worker (idle)]: runtime.gopark(0x49e26476e643?, 0x1?, 0x3d?, 0xe2?, 0x0?) runtime/proc.go:424 +0xce fp=0xc0004adf38 sp=0xc0004adf18 pc=0x5853fcabe6ee runtime.gcBgMarkWorker(0xc0000518f0) runtime/mgc.go:1412 +0xe9 fp=0xc0004adfc8 sp=0xc0004adf38 pc=0x5853fca6ad89 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x25 fp=0xc0004adfe0 sp=0xc0004adfc8 pc=0x5853fca6ac65 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0004adfe8 sp=0xc0004adfe0 pc=0x5853fcac6ac1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1328 +0x105 goroutine 27 gp=0xc0004a5500 m=nil [GC worker (idle)]: runtime.gopark(0x49e264771de5?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xce fp=0xc0004a6738 sp=0xc0004a6718 pc=0x5853fcabe6ee runtime.gcBgMarkWorker(0xc0000518f0) runtime/mgc.go:1412 +0xe9 fp=0xc0004a67c8 sp=0xc0004a6738 pc=0x5853fca6ad89 runtime.gcBgMarkStartWorkers.gowrap1() runtime/mgc.go:1328 +0x25 fp=0xc0004a67e0 sp=0xc0004a67c8 pc=0x5853fca6ac65 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0004a67e8 sp=0xc0004a67e0 pc=0x5853fcac6ac1 created by runtime.gcBgMarkStartWorkers in goroutine 1 runtime/mgc.go:1328 +0x105 goroutine 35 gp=0xc000104540 m=nil [semacquire]: runtime.gopark(0x0?, 0x0?, 0x0?, 0x0?, 0x0?) runtime/proc.go:424 +0xce fp=0xc0004a6e18 sp=0xc0004a6df8 pc=0x5853fcabe6ee runtime.goparkunlock(...) runtime/proc.go:430 runtime.semacquire1(0xc000596128, 0x0, 0x1, 0x0, 0x12) runtime/sema.go:178 +0x22c fp=0xc0004a6e80 sp=0xc0004a6e18 pc=0x5853fca9caac sync.runtime_Semacquire(0x0?) runtime/sema.go:71 +0x25 fp=0xc0004a6eb8 sp=0xc0004a6e80 pc=0x5853fcabff05 sync.(*WaitGroup).Wait(0x0?) sync/waitgroup.go:118 +0x48 fp=0xc0004a6ee0 sp=0xc0004a6eb8 pc=0x5853fcad52e8 ollama/llama/runner.(*Server).run(0xc000596120, {0x5853fdc0b1d0, 0xc000192640}) ollama/llama/runner/runner.go:315 +0x47 fp=0xc0004a6fb8 sp=0xc0004a6ee0 pc=0x5853fce87707 ollama/llama/runner.Execute.gowrap2() ollama/llama/runner/runner.go:1006 +0x28 fp=0xc0004a6fe0 sp=0xc0004a6fb8 pc=0x5853fce8cb08 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc0004a6fe8 sp=0xc0004a6fe0 pc=0x5853fcac6ac1 created by ollama/llama/runner.Execute in goroutine 1 ollama/llama/runner/runner.go:1006 +0xde5 goroutine 50 gp=0xc000604380 m=nil [IO wait]: runtime.gopark(0xc00041e3c0?, 0xc000116000?, 0x10?, 0x7a?, 0xb?) runtime/proc.go:424 +0xce fp=0xc000227918 sp=0xc0002278f8 pc=0x5853fcabe6ee runtime.netpollblock(0x5853fcae1918?, 0xfca55506?, 0x53?) runtime/netpoll.go:575 +0xf7 fp=0xc000227950 sp=0xc000227918 pc=0x5853fca82357 internal/poll.runtime_pollWait(0x7688cdbb6568, 0x72) runtime/netpoll.go:351 +0x85 fp=0xc000227970 sp=0xc000227950 pc=0x5853fcabd9e5 internal/poll.(*pollDesc).wait(0xc000116000?, 0xc000120000?, 0x0) internal/poll/fd_poll_runtime.go:84 +0x27 fp=0xc000227998 sp=0xc000227970 pc=0x5853fcb45007 internal/poll.(*pollDesc).waitRead(...) internal/poll/fd_poll_runtime.go:89 internal/poll.(*FD).Read(0xc000116000, {0xc000120000, 0x1000, 0x1000}) internal/poll/fd_unix.go:165 +0x27a fp=0xc000227a30 sp=0xc000227998 pc=0x5853fcb462fa net.(*netFD).Read(0xc000116000, {0xc000120000?, 0xc000227aa0?, 0x5853fcb454c5?}) net/fd_posix.go:55 +0x25 fp=0xc000227a78 sp=0xc000227a30 pc=0x5853fcbb0ae5 net.(*conn).Read(0xc000018008, {0xc000120000?, 0x0?, 0xc0000160f8?}) net/net.go:189 +0x45 fp=0xc000227ac0 sp=0xc000227a78 pc=0x5853fcbbf0e5 net.(*TCPConn).Read(0xc0000160f0?, {0xc000120000?, 0xc000116000?, 0xc000227af8?}) :1 +0x25 fp=0xc000227af0 sp=0xc000227ac0 pc=0x5853fcbd22e5 net/http.(*connReader).Read(0xc0000160f0, {0xc000120000, 0x1000, 0x1000}) net/http/server.go:798 +0x14b fp=0xc000227b40 sp=0xc000227af0 pc=0x5853fce0ea6b bufio.(*Reader).fill(0xc000612060) bufio/bufio.go:110 +0x103 fp=0xc000227b78 sp=0xc000227b40 pc=0x5853fcbd69e3 bufio.(*Reader).Peek(0xc000612060, 0x4) bufio/bufio.go:148 +0x53 fp=0xc000227b98 sp=0xc000227b78 pc=0x5853fcbd6b13 net/http.(*conn).serve(0xc000118000, {0x5853fdc0b198, 0xc0005944b0}) net/http/server.go:2127 +0x738 fp=0xc000227fb8 sp=0xc000227b98 pc=0x5853fce13db8 net/http.(*Server).Serve.gowrap3() net/http/server.go:3360 +0x28 fp=0xc000227fe0 sp=0xc000227fb8 pc=0x5853fce190a8 runtime.goexit({}) runtime/asm_amd64.s:1700 +0x1 fp=0xc000227fe8 sp=0xc000227fe0 pc=0x5853fcac6ac1 created by net/http.(*Server).Serve in goroutine 1 net/http/server.go:3360 +0x485 rax 0x0 rbx 0x36a21 rcx 0x7688cd40eb2c rdx 0x6 rdi 0x36a1b rsi 0x36a21 rbp 0x76886e1f8ac0 rsp 0x76886e1f8a80 r8 0x0 r9 0x76886e1f8610 r10 0x8 r11 0x246 r12 0x6 r13 0x768854155bc0 r14 0x16 r15 0x1fffffffffffffff rip 0x7688cd40eb2c rflags 0x246 cs 0x33 fs 0x0 gs 0x0 time=2025-03-18T09:29:22.892-05:00 level=ERROR source=sched.go:455 msg="error loading llama server" error="llama runner process has terminated: exit status 2" [GIN] 2025/03/18 - 09:29:22 | 500 | 1.855564063s | 127.0.0.1 | POST "/api/generate"