github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-08 00:51:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #9994] ollama cannot running until restrat it #32309

New Issue
Open
opened 2026-04-22 13:26:35 -05:00 by GiteaMirror · 8 comments
GiteaMirror commented 2026-04-22 13:26:35 -05:00
Owner
Copy Link

Originally created by @Liuyuan0803 on GitHub (Mar 26, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/9994

What is the issue?

In sometimes,ollama cannot chat or embed successfully (I only use these two api), but in localhost:11434, it shows Ollama is running.

Relevant log output

2025/03/26 15:03:39 routes.go:1230: INFO server config env="map[CUDA_VISIBLE_DEVICES:GPU-d8040dfd-0bc8-ad27-6eaf-8a27a2b07beb GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:2048 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:24h0m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:D:\\lipuyun\\Ollama_Model OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE: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://* vscode-file://*] OLLAMA_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES:]"
time=2025-03-26T15:03:39.139+08:00 level=INFO source=images.go:432 msg="total blobs: 10"
time=2025-03-26T15:03:39.143+08:00 level=INFO source=images.go:439 msg="total unused blobs removed: 0"
time=2025-03-26T15:03:39.146+08:00 level=INFO source=routes.go:1297 msg="Listening on [::]:11434 (version 0.6.1)"
time=2025-03-26T15:03:39.147+08:00 level=INFO source=gpu.go:217 msg="looking for compatible GPUs"
time=2025-03-26T15:03:39.147+08:00 level=INFO source=gpu_windows.go:167 msg=packages count=2
time=2025-03-26T15:03:39.147+08:00 level=INFO source=gpu_windows.go:214 msg="" package=0 cores=48 efficiency=0 threads=96
time=2025-03-26T15:03:39.148+08:00 level=INFO source=gpu_windows.go:214 msg="" package=1 cores=48 efficiency=0 threads=96
time=2025-03-26T15:03:39.638+08:00 level=INFO source=gpu.go:319 msg="detected OS VRAM overhead" id=GPU-d8040dfd-0bc8-ad27-6eaf-8a27a2b07beb library=cuda compute=8.9 driver=12.4 name="NVIDIA GeForce RTX 4090" overhead="2.2 GiB"
time=2025-03-26T15:03:39.642+08:00 level=INFO source=types.go:130 msg="inference compute" id=GPU-d8040dfd-0bc8-ad27-6eaf-8a27a2b07beb library=cuda variant=v12 compute=8.9 driver=12.4 name="NVIDIA GeForce RTX 4090" total="24.0 GiB" available="19.7 GiB"
time=2025-03-26T15:09:56.581+08:00 level=WARN source=ggml.go:149 msg="key not found" key=qwen2.vision.block_count default=0
time=2025-03-26T15:09:56.582+08:00 level=WARN source=ggml.go:149 msg="key not found" key=qwen2.attention.key_length default=128
time=2025-03-26T15:09:56.583+08:00 level=WARN source=ggml.go:149 msg="key not found" key=qwen2.attention.value_length default=128
time=2025-03-26T15:09:56.584+08:00 level=INFO source=sched.go:715 msg="new model will fit in available VRAM in single GPU, loading" model=D:\lipuyun\Ollama_Model\blobs\sha256-2049f5674b1e92b4464e5729975c9689fcfbf0b0e4443ccf10b5339f370f9a54 gpu=GPU-d8040dfd-0bc8-ad27-6eaf-8a27a2b07beb parallel=4 available=21116650291 required="10.8 GiB"
time=2025-03-26T15:09:56.598+08:00 level=INFO source=server.go:105 msg="system memory" total="127.5 GiB" free="73.9 GiB" free_swap="117.1 GiB"
time=2025-03-26T15:09:56.598+08:00 level=WARN source=ggml.go:149 msg="key not found" key=qwen2.vision.block_count default=0
time=2025-03-26T15:09:56.600+08:00 level=WARN source=ggml.go:149 msg="key not found" key=qwen2.attention.key_length default=128
time=2025-03-26T15:09:56.601+08:00 level=WARN source=ggml.go:149 msg="key not found" key=qwen2.attention.value_length default=128
time=2025-03-26T15:09:56.603+08:00 level=INFO source=server.go:138 msg=offload library=cuda layers.requested=-1 layers.model=49 layers.offload=49 layers.split="" memory.available="[19.7 GiB]" memory.gpu_overhead="0 B" memory.required.full="10.8 GiB" memory.required.partial="10.8 GiB" memory.required.kv="1.5 GiB" memory.required.allocations="[10.8 GiB]" memory.weights.total="7.4 GiB" memory.weights.repeating="7.4 GiB" memory.weights.nonrepeating="609.1 MiB" memory.graph.full="676.0 MiB" memory.graph.partial="916.1 MiB"
llama_model_loader: loaded meta data with 34 key-value pairs and 579 tensors from D:\lipuyun\Ollama_Model\blobs\sha256-2049f5674b1e92b4464e5729975c9689fcfbf0b0e4443ccf10b5339f370f9a54 (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              = qwen2
llama_model_loader: - kv   1:                               general.type str              = model
llama_model_loader: - kv   2:                               general.name str              = Qwen2.5 14B Instruct
llama_model_loader: - kv   3:                           general.finetune str              = Instruct
llama_model_loader: - kv   4:                           general.basename str              = Qwen2.5
llama_model_loader: - kv   5:                         general.size_label str              = 14B
llama_model_loader: - kv   6:                            general.license str              = apache-2.0
llama_model_loader: - kv   7:                       general.license.link str              = https://huggingface.co/Qwen/Qwen2.5-1...
llama_model_loader: - kv   8:                   general.base_model.count u32              = 1
llama_model_loader: - kv   9:                  general.base_model.0.name str              = Qwen2.5 14B
llama_model_loader: - kv  10:          general.base_model.0.organization str              = Qwen
llama_model_loader: - kv  11:              general.base_model.0.repo_url str              = https://huggingface.co/Qwen/Qwen2.5-14B
llama_model_loader: - kv  12:                               general.tags arr[str,2]       = ["chat", "text-generation"]
llama_model_loader: - kv  13:                          general.languages arr[str,1]       = ["en"]
llama_model_loader: - kv  14:                          qwen2.block_count u32              = 48
llama_model_loader: - kv  15:                       qwen2.context_length u32              = 32768
llama_model_loader: - kv  16:                     qwen2.embedding_length u32              = 5120
llama_model_loader: - kv  17:                  qwen2.feed_forward_length u32              = 13824
llama_model_loader: - kv  18:                 qwen2.attention.head_count u32              = 40
llama_model_loader: - kv  19:              qwen2.attention.head_count_kv u32              = 8
llama_model_loader: - kv  20:                       qwen2.rope.freq_base f32              = 1000000.000000
llama_model_loader: - kv  21:     qwen2.attention.layer_norm_rms_epsilon f32              = 0.000001
llama_model_loader: - kv  22:                          general.file_type u32              = 15
llama_model_loader: - kv  23:                       tokenizer.ggml.model str              = gpt2
llama_model_loader: - kv  24:                         tokenizer.ggml.pre str              = qwen2
llama_model_loader: - kv  25:                      tokenizer.ggml.tokens arr[str,152064]  = ["!", "\"", "#", "$", "%", "&", "'", ...
llama_model_loader: - kv  26:                  tokenizer.ggml.token_type arr[i32,152064]  = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv  27:                      tokenizer.ggml.merges arr[str,151387]  = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
llama_model_loader: - kv  28:                tokenizer.ggml.eos_token_id u32              = 151645
llama_model_loader: - kv  29:            tokenizer.ggml.padding_token_id u32              = 151643
llama_model_loader: - kv  30:                tokenizer.ggml.bos_token_id u32              = 151643
llama_model_loader: - kv  31:               tokenizer.ggml.add_bos_token bool             = false
llama_model_loader: - kv  32:                    tokenizer.chat_template str              = {%- if tools %}\n    {{- '<|im_start|>...
llama_model_loader: - kv  33:               general.quantization_version u32              = 2
llama_model_loader: - type  f32:  241 tensors
llama_model_loader: - type q4_K:  289 tensors
llama_model_loader: - type q6_K:   49 tensors
print_info: file format = GGUF V3 (latest)
print_info: file type   = Q4_K - Medium
print_info: file size   = 8.37 GiB (4.87 BPW)
load: special tokens cache size = 22
load: token to piece cache size = 0.9310 MB
print_info: arch             = qwen2
print_info: vocab_only       = 1
print_info: model type       = ?B
print_info: model params     = 14.77 B
print_info: general.name     = Qwen2.5 14B Instruct
print_info: vocab type       = BPE
print_info: n_vocab          = 152064
print_info: n_merges         = 151387
print_info: BOS token        = 151643 '<|endoftext|>'
print_info: EOS token        = 151645 '<|im_end|>'
print_info: EOT token        = 151645 '<|im_end|>'
print_info: PAD token        = 151643 '<|endoftext|>'
print_info: LF token         = 198 'Ċ'
print_info: FIM PRE token    = 151659 '<|fim_prefix|>'
print_info: FIM SUF token    = 151661 '<|fim_suffix|>'
print_info: FIM MID token    = 151660 '<|fim_middle|>'
print_info: FIM PAD token    = 151662 '<|fim_pad|>'
print_info: FIM REP token    = 151663 '<|repo_name|>'
print_info: FIM SEP token    = 151664 '<|file_sep|>'
print_info: EOG token        = 151643 '<|endoftext|>'
print_info: EOG token        = 151645 '<|im_end|>'
print_info: EOG token        = 151662 '<|fim_pad|>'
print_info: EOG token        = 151663 '<|repo_name|>'
print_info: EOG token        = 151664 '<|file_sep|>'
print_info: max token length = 256
llama_model_load: vocab only - skipping tensors
time=2025-03-26T15:09:56.986+08:00 level=INFO source=server.go:405 msg="starting llama server" cmd="D:\\lipuyun\\Ollama\\ollama.exe runner --model D:\\lipuyun\\Ollama_Model\\blobs\\sha256-2049f5674b1e92b4464e5729975c9689fcfbf0b0e4443ccf10b5339f370f9a54 --ctx-size 8192 --batch-size 512 --n-gpu-layers 49 --threads 96 --no-mmap --parallel 4 --port 58610"
time=2025-03-26T15:09:56.990+08:00 level=INFO source=sched.go:450 msg="loaded runners" count=1
time=2025-03-26T15:09:56.991+08:00 level=INFO source=server.go:585 msg="waiting for llama runner to start responding"
time=2025-03-26T15:09:56.993+08:00 level=INFO source=server.go:619 msg="waiting for server to become available" status="llm server error"
time=2025-03-26T15:09:57.101+08:00 level=INFO source=runner.go:931 msg="starting go runner"
ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 CUDA devices:
  Device 0: NVIDIA GeForce RTX 4090, compute capability 8.9, VMM: yes
load_backend: loaded CUDA backend from D:\lipuyun\Ollama\lib\ollama\cuda_v12\ggml-cuda.dll
load_backend: loaded CPU backend from D:\lipuyun\Ollama\lib\ollama\ggml-cpu-icelake.dll
time=2025-03-26T15:09:57.283+08:00 level=INFO source=ggml.go:109 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.AVX512=1 CPU.0.AVX512_VBMI=1 CPU.0.AVX512_VNNI=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 CUDA.0.ARCHS=500,600,610,700,750,800,860,870,890,900,1200 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(clang)
time=2025-03-26T15:09:57.292+08:00 level=INFO source=runner.go:991 msg="Server listening on 127.0.0.1:58610"
time=2025-03-26T15:09:57.505+08:00 level=INFO source=server.go:619 msg="waiting for server to become available" status="llm server loading model"
llama_model_load_from_file_impl: using device CUDA0 (NVIDIA GeForce RTX 4090) - 20140 MiB free
llama_model_loader: loaded meta data with 34 key-value pairs and 579 tensors from D:\lipuyun\Ollama_Model\blobs\sha256-2049f5674b1e92b4464e5729975c9689fcfbf0b0e4443ccf10b5339f370f9a54 (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              = qwen2
llama_model_loader: - kv   1:                               general.type str              = model
llama_model_loader: - kv   2:                               general.name str              = Qwen2.5 14B Instruct
llama_model_loader: - kv   3:                           general.finetune str              = Instruct
llama_model_loader: - kv   4:                           general.basename str              = Qwen2.5
llama_model_loader: - kv   5:                         general.size_label str              = 14B
llama_model_loader: - kv   6:                            general.license str              = apache-2.0
llama_model_loader: - kv   7:                       general.license.link str              = https://huggingface.co/Qwen/Qwen2.5-1...
llama_model_loader: - kv   8:                   general.base_model.count u32              = 1
llama_model_loader: - kv   9:                  general.base_model.0.name str              = Qwen2.5 14B
llama_model_loader: - kv  10:          general.base_model.0.organization str              = Qwen
llama_model_loader: - kv  11:              general.base_model.0.repo_url str              = https://huggingface.co/Qwen/Qwen2.5-14B
llama_model_loader: - kv  12:                               general.tags arr[str,2]       = ["chat", "text-generation"]
llama_model_loader: - kv  13:                          general.languages arr[str,1]       = ["en"]
llama_model_loader: - kv  14:                          qwen2.block_count u32              = 48
llama_model_loader: - kv  15:                       qwen2.context_length u32              = 32768
llama_model_loader: - kv  16:                     qwen2.embedding_length u32              = 5120
llama_model_loader: - kv  17:                  qwen2.feed_forward_length u32              = 13824
llama_model_loader: - kv  18:                 qwen2.attention.head_count u32              = 40
llama_model_loader: - kv  19:              qwen2.attention.head_count_kv u32              = 8
llama_model_loader: - kv  20:                       qwen2.rope.freq_base f32              = 1000000.000000
llama_model_loader: - kv  21:     qwen2.attention.layer_norm_rms_epsilon f32              = 0.000001
llama_model_loader: - kv  22:                          general.file_type u32              = 15
llama_model_loader: - kv  23:                       tokenizer.ggml.model str              = gpt2
llama_model_loader: - kv  24:                         tokenizer.ggml.pre str              = qwen2
llama_model_loader: - kv  25:                      tokenizer.ggml.tokens arr[str,152064]  = ["!", "\"", "#", "$", "%", "&", "'", ...
llama_model_loader: - kv  26:                  tokenizer.ggml.token_type arr[i32,152064]  = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv  27:                      tokenizer.ggml.merges arr[str,151387]  = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
llama_model_loader: - kv  28:                tokenizer.ggml.eos_token_id u32              = 151645
llama_model_loader: - kv  29:            tokenizer.ggml.padding_token_id u32              = 151643
llama_model_loader: - kv  30:                tokenizer.ggml.bos_token_id u32              = 151643
llama_model_loader: - kv  31:               tokenizer.ggml.add_bos_token bool             = false
llama_model_loader: - kv  32:                    tokenizer.chat_template str              = {%- if tools %}\n    {{- '<|im_start|>...
llama_model_loader: - kv  33:               general.quantization_version u32              = 2
llama_model_loader: - type  f32:  241 tensors
llama_model_loader: - type q4_K:  289 tensors
llama_model_loader: - type q6_K:   49 tensors
print_info: file format = GGUF V3 (latest)
print_info: file type   = Q4_K - Medium
print_info: file size   = 8.37 GiB (4.87 BPW)
load: special tokens cache size = 22
load: token to piece cache size = 0.9310 MB
print_info: arch             = qwen2
print_info: vocab_only       = 0
print_info: n_ctx_train      = 32768
print_info: n_embd           = 5120
print_info: n_layer          = 48
print_info: n_head           = 40
print_info: n_head_kv        = 8
print_info: n_rot            = 128
print_info: n_swa            = 0
print_info: n_embd_head_k    = 128
print_info: n_embd_head_v    = 128
print_info: n_gqa            = 5
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-06
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: n_ff             = 13824
print_info: n_expert         = 0
print_info: n_expert_used    = 0
print_info: causal attn      = 1
print_info: pooling type     = 0
print_info: rope type        = 2
print_info: rope scaling     = linear
print_info: freq_base_train  = 1000000.0
print_info: freq_scale_train = 1
print_info: n_ctx_orig_yarn  = 32768
print_info: rope_finetuned   = unknown
print_info: ssm_d_conv       = 0
print_info: ssm_d_inner      = 0
print_info: ssm_d_state      = 0
print_info: ssm_dt_rank      = 0
print_info: ssm_dt_b_c_rms   = 0
print_info: model type       = 14B
print_info: model params     = 14.77 B
print_info: general.name     = Qwen2.5 14B Instruct
print_info: vocab type       = BPE
print_info: n_vocab          = 152064
print_info: n_merges         = 151387
print_info: BOS token        = 151643 '<|endoftext|>'
print_info: EOS token        = 151645 '<|im_end|>'
print_info: EOT token        = 151645 '<|im_end|>'
print_info: PAD token        = 151643 '<|endoftext|>'
print_info: LF token         = 198 'Ċ'
print_info: FIM PRE token    = 151659 '<|fim_prefix|>'
print_info: FIM SUF token    = 151661 '<|fim_suffix|>'
print_info: FIM MID token    = 151660 '<|fim_middle|>'
print_info: FIM PAD token    = 151662 '<|fim_pad|>'
print_info: FIM REP token    = 151663 '<|repo_name|>'
print_info: FIM SEP token    = 151664 '<|file_sep|>'
print_info: EOG token        = 151643 '<|endoftext|>'
print_info: EOG token        = 151645 '<|im_end|>'
print_info: EOG token        = 151662 '<|fim_pad|>'
print_info: EOG token        = 151663 '<|repo_name|>'
print_info: EOG token        = 151664 '<|file_sep|>'
print_info: max token length = 256
load_tensors: loading model tensors, this can take a while... (mmap = false)
load_tensors: offloading 48 repeating layers to GPU
load_tensors: offloading output layer to GPU
load_tensors: offloaded 49/49 layers to GPU
load_tensors:        CUDA0 model buffer size =  8148.38 MiB
load_tensors:          CPU model buffer size =   417.66 MiB
llama_init_from_model: n_seq_max     = 4
llama_init_from_model: n_ctx         = 8192
llama_init_from_model: n_ctx_per_seq = 2048
llama_init_from_model: n_batch       = 2048
llama_init_from_model: n_ubatch      = 512
llama_init_from_model: flash_attn    = 0
llama_init_from_model: freq_base     = 1000000.0
llama_init_from_model: freq_scale    = 1
llama_init_from_model: n_ctx_per_seq (2048) < n_ctx_train (32768) -- the full capacity of the model will not be utilized
llama_kv_cache_init: kv_size = 8192, offload = 1, type_k = 'f16', type_v = 'f16', n_layer = 48, can_shift = 1
llama_kv_cache_init:      CUDA0 KV buffer size =  1536.00 MiB
llama_init_from_model: KV self size  = 1536.00 MiB, K (f16):  768.00 MiB, V (f16):  768.00 MiB
llama_init_from_model:  CUDA_Host  output buffer size =     2.40 MiB
llama_init_from_model:      CUDA0 compute buffer size =   696.00 MiB
llama_init_from_model:  CUDA_Host compute buffer size =    26.01 MiB
llama_init_from_model: graph nodes  = 1686
llama_init_from_model: graph splits = 2
time=2025-03-26T15:10:01.790+08:00 level=INFO source=server.go:624 msg="llama runner started in 4.80 seconds"
time=2025-03-26T15:10:01.860+08:00 level=WARN source=runner.go:130 msg="truncating input prompt" limit=2048 prompt=6023 keep=4 new=2048
[GIN] 2025/03/26 - 15:10:08 | 200 |   12.4676306s |             ::1 | POST     "/v1/chat/completions"
time=2025-03-26T15:11:17.787+08:00 level=WARN source=runner.go:130 msg="truncating input prompt" limit=2048 prompt=4652 keep=4 new=2048
[GIN] 2025/03/26 - 15:11:20 | 200 |    2.5896677s |             ::1 | POST     "/v1/chat/completions"
[GIN] 2025/03/26 - 15:22:41 | 200 |         202µs |       127.0.0.1 | HEAD     "/"
[GIN] 2025/03/26 - 15:22:41 | 200 |       494.2µs |       127.0.0.1 | GET      "/api/ps"
[GIN] 2025/03/26 - 15:27:18 | 200 |            0s |       127.0.0.1 | HEAD     "/"
[GIN] 2025/03/26 - 15:27:18 | 200 |       362.6µs |       127.0.0.1 | GET      "/api/ps"

OS

No response

GPU

No response

CPU

No response

Ollama version

No response

Originally created by @Liuyuan0803 on GitHub (Mar 26, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/9994 ### What is the issue? In sometimes,ollama cannot chat or embed successfully (I only use these two api), but in localhost:11434, it shows Ollama is running. ### Relevant log output ```shell 2025/03/26 15:03:39 routes.go:1230: INFO server config env="map[CUDA_VISIBLE_DEVICES:GPU-d8040dfd-0bc8-ad27-6eaf-8a27a2b07beb GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:2048 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:24h0m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:D:\\lipuyun\\Ollama_Model OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE: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://* vscode-file://*] OLLAMA_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES:]" time=2025-03-26T15:03:39.139+08:00 level=INFO source=images.go:432 msg="total blobs: 10" time=2025-03-26T15:03:39.143+08:00 level=INFO source=images.go:439 msg="total unused blobs removed: 0" time=2025-03-26T15:03:39.146+08:00 level=INFO source=routes.go:1297 msg="Listening on [::]:11434 (version 0.6.1)" time=2025-03-26T15:03:39.147+08:00 level=INFO source=gpu.go:217 msg="looking for compatible GPUs" time=2025-03-26T15:03:39.147+08:00 level=INFO source=gpu_windows.go:167 msg=packages count=2 time=2025-03-26T15:03:39.147+08:00 level=INFO source=gpu_windows.go:214 msg="" package=0 cores=48 efficiency=0 threads=96 time=2025-03-26T15:03:39.148+08:00 level=INFO source=gpu_windows.go:214 msg="" package=1 cores=48 efficiency=0 threads=96 time=2025-03-26T15:03:39.638+08:00 level=INFO source=gpu.go:319 msg="detected OS VRAM overhead" id=GPU-d8040dfd-0bc8-ad27-6eaf-8a27a2b07beb library=cuda compute=8.9 driver=12.4 name="NVIDIA GeForce RTX 4090" overhead="2.2 GiB" time=2025-03-26T15:03:39.642+08:00 level=INFO source=types.go:130 msg="inference compute" id=GPU-d8040dfd-0bc8-ad27-6eaf-8a27a2b07beb library=cuda variant=v12 compute=8.9 driver=12.4 name="NVIDIA GeForce RTX 4090" total="24.0 GiB" available="19.7 GiB" time=2025-03-26T15:09:56.581+08:00 level=WARN source=ggml.go:149 msg="key not found" key=qwen2.vision.block_count default=0 time=2025-03-26T15:09:56.582+08:00 level=WARN source=ggml.go:149 msg="key not found" key=qwen2.attention.key_length default=128 time=2025-03-26T15:09:56.583+08:00 level=WARN source=ggml.go:149 msg="key not found" key=qwen2.attention.value_length default=128 time=2025-03-26T15:09:56.584+08:00 level=INFO source=sched.go:715 msg="new model will fit in available VRAM in single GPU, loading" model=D:\lipuyun\Ollama_Model\blobs\sha256-2049f5674b1e92b4464e5729975c9689fcfbf0b0e4443ccf10b5339f370f9a54 gpu=GPU-d8040dfd-0bc8-ad27-6eaf-8a27a2b07beb parallel=4 available=21116650291 required="10.8 GiB" time=2025-03-26T15:09:56.598+08:00 level=INFO source=server.go:105 msg="system memory" total="127.5 GiB" free="73.9 GiB" free_swap="117.1 GiB" time=2025-03-26T15:09:56.598+08:00 level=WARN source=ggml.go:149 msg="key not found" key=qwen2.vision.block_count default=0 time=2025-03-26T15:09:56.600+08:00 level=WARN source=ggml.go:149 msg="key not found" key=qwen2.attention.key_length default=128 time=2025-03-26T15:09:56.601+08:00 level=WARN source=ggml.go:149 msg="key not found" key=qwen2.attention.value_length default=128 time=2025-03-26T15:09:56.603+08:00 level=INFO source=server.go:138 msg=offload library=cuda layers.requested=-1 layers.model=49 layers.offload=49 layers.split="" memory.available="[19.7 GiB]" memory.gpu_overhead="0 B" memory.required.full="10.8 GiB" memory.required.partial="10.8 GiB" memory.required.kv="1.5 GiB" memory.required.allocations="[10.8 GiB]" memory.weights.total="7.4 GiB" memory.weights.repeating="7.4 GiB" memory.weights.nonrepeating="609.1 MiB" memory.graph.full="676.0 MiB" memory.graph.partial="916.1 MiB" llama_model_loader: loaded meta data with 34 key-value pairs and 579 tensors from D:\lipuyun\Ollama_Model\blobs\sha256-2049f5674b1e92b4464e5729975c9689fcfbf0b0e4443ccf10b5339f370f9a54 (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 = qwen2 llama_model_loader: - kv 1: general.type str = model llama_model_loader: - kv 2: general.name str = Qwen2.5 14B Instruct llama_model_loader: - kv 3: general.finetune str = Instruct llama_model_loader: - kv 4: general.basename str = Qwen2.5 llama_model_loader: - kv 5: general.size_label str = 14B llama_model_loader: - kv 6: general.license str = apache-2.0 llama_model_loader: - kv 7: general.license.link str = https://huggingface.co/Qwen/Qwen2.5-1... llama_model_loader: - kv 8: general.base_model.count u32 = 1 llama_model_loader: - kv 9: general.base_model.0.name str = Qwen2.5 14B llama_model_loader: - kv 10: general.base_model.0.organization str = Qwen llama_model_loader: - kv 11: general.base_model.0.repo_url str = https://huggingface.co/Qwen/Qwen2.5-14B llama_model_loader: - kv 12: general.tags arr[str,2] = ["chat", "text-generation"] llama_model_loader: - kv 13: general.languages arr[str,1] = ["en"] llama_model_loader: - kv 14: qwen2.block_count u32 = 48 llama_model_loader: - kv 15: qwen2.context_length u32 = 32768 llama_model_loader: - kv 16: qwen2.embedding_length u32 = 5120 llama_model_loader: - kv 17: qwen2.feed_forward_length u32 = 13824 llama_model_loader: - kv 18: qwen2.attention.head_count u32 = 40 llama_model_loader: - kv 19: qwen2.attention.head_count_kv u32 = 8 llama_model_loader: - kv 20: qwen2.rope.freq_base f32 = 1000000.000000 llama_model_loader: - kv 21: qwen2.attention.layer_norm_rms_epsilon f32 = 0.000001 llama_model_loader: - kv 22: general.file_type u32 = 15 llama_model_loader: - kv 23: tokenizer.ggml.model str = gpt2 llama_model_loader: - kv 24: tokenizer.ggml.pre str = qwen2 llama_model_loader: - kv 25: tokenizer.ggml.tokens arr[str,152064] = ["!", "\"", "#", "$", "%", "&", "'", ... llama_model_loader: - kv 26: tokenizer.ggml.token_type arr[i32,152064] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... llama_model_loader: - kv 27: tokenizer.ggml.merges arr[str,151387] = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",... llama_model_loader: - kv 28: tokenizer.ggml.eos_token_id u32 = 151645 llama_model_loader: - kv 29: tokenizer.ggml.padding_token_id u32 = 151643 llama_model_loader: - kv 30: tokenizer.ggml.bos_token_id u32 = 151643 llama_model_loader: - kv 31: tokenizer.ggml.add_bos_token bool = false llama_model_loader: - kv 32: tokenizer.chat_template str = {%- if tools %}\n {{- '<|im_start|>... llama_model_loader: - kv 33: general.quantization_version u32 = 2 llama_model_loader: - type f32: 241 tensors llama_model_loader: - type q4_K: 289 tensors llama_model_loader: - type q6_K: 49 tensors print_info: file format = GGUF V3 (latest) print_info: file type = Q4_K - Medium print_info: file size = 8.37 GiB (4.87 BPW) load: special tokens cache size = 22 load: token to piece cache size = 0.9310 MB print_info: arch = qwen2 print_info: vocab_only = 1 print_info: model type = ?B print_info: model params = 14.77 B print_info: general.name = Qwen2.5 14B Instruct print_info: vocab type = BPE print_info: n_vocab = 152064 print_info: n_merges = 151387 print_info: BOS token = 151643 '<|endoftext|>' print_info: EOS token = 151645 '<|im_end|>' print_info: EOT token = 151645 '<|im_end|>' print_info: PAD token = 151643 '<|endoftext|>' print_info: LF token = 198 'Ċ' print_info: FIM PRE token = 151659 '<|fim_prefix|>' print_info: FIM SUF token = 151661 '<|fim_suffix|>' print_info: FIM MID token = 151660 '<|fim_middle|>' print_info: FIM PAD token = 151662 '<|fim_pad|>' print_info: FIM REP token = 151663 '<|repo_name|>' print_info: FIM SEP token = 151664 '<|file_sep|>' print_info: EOG token = 151643 '<|endoftext|>' print_info: EOG token = 151645 '<|im_end|>' print_info: EOG token = 151662 '<|fim_pad|>' print_info: EOG token = 151663 '<|repo_name|>' print_info: EOG token = 151664 '<|file_sep|>' print_info: max token length = 256 llama_model_load: vocab only - skipping tensors time=2025-03-26T15:09:56.986+08:00 level=INFO source=server.go:405 msg="starting llama server" cmd="D:\\lipuyun\\Ollama\\ollama.exe runner --model D:\\lipuyun\\Ollama_Model\\blobs\\sha256-2049f5674b1e92b4464e5729975c9689fcfbf0b0e4443ccf10b5339f370f9a54 --ctx-size 8192 --batch-size 512 --n-gpu-layers 49 --threads 96 --no-mmap --parallel 4 --port 58610" time=2025-03-26T15:09:56.990+08:00 level=INFO source=sched.go:450 msg="loaded runners" count=1 time=2025-03-26T15:09:56.991+08:00 level=INFO source=server.go:585 msg="waiting for llama runner to start responding" time=2025-03-26T15:09:56.993+08:00 level=INFO source=server.go:619 msg="waiting for server to become available" status="llm server error" time=2025-03-26T15:09:57.101+08:00 level=INFO source=runner.go:931 msg="starting go runner" ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no ggml_cuda_init: found 1 CUDA devices: Device 0: NVIDIA GeForce RTX 4090, compute capability 8.9, VMM: yes load_backend: loaded CUDA backend from D:\lipuyun\Ollama\lib\ollama\cuda_v12\ggml-cuda.dll load_backend: loaded CPU backend from D:\lipuyun\Ollama\lib\ollama\ggml-cpu-icelake.dll time=2025-03-26T15:09:57.283+08:00 level=INFO source=ggml.go:109 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.AVX512=1 CPU.0.AVX512_VBMI=1 CPU.0.AVX512_VNNI=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 CUDA.0.ARCHS=500,600,610,700,750,800,860,870,890,900,1200 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(clang) time=2025-03-26T15:09:57.292+08:00 level=INFO source=runner.go:991 msg="Server listening on 127.0.0.1:58610" time=2025-03-26T15:09:57.505+08:00 level=INFO source=server.go:619 msg="waiting for server to become available" status="llm server loading model" llama_model_load_from_file_impl: using device CUDA0 (NVIDIA GeForce RTX 4090) - 20140 MiB free llama_model_loader: loaded meta data with 34 key-value pairs and 579 tensors from D:\lipuyun\Ollama_Model\blobs\sha256-2049f5674b1e92b4464e5729975c9689fcfbf0b0e4443ccf10b5339f370f9a54 (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 = qwen2 llama_model_loader: - kv 1: general.type str = model llama_model_loader: - kv 2: general.name str = Qwen2.5 14B Instruct llama_model_loader: - kv 3: general.finetune str = Instruct llama_model_loader: - kv 4: general.basename str = Qwen2.5 llama_model_loader: - kv 5: general.size_label str = 14B llama_model_loader: - kv 6: general.license str = apache-2.0 llama_model_loader: - kv 7: general.license.link str = https://huggingface.co/Qwen/Qwen2.5-1... llama_model_loader: - kv 8: general.base_model.count u32 = 1 llama_model_loader: - kv 9: general.base_model.0.name str = Qwen2.5 14B llama_model_loader: - kv 10: general.base_model.0.organization str = Qwen llama_model_loader: - kv 11: general.base_model.0.repo_url str = https://huggingface.co/Qwen/Qwen2.5-14B llama_model_loader: - kv 12: general.tags arr[str,2] = ["chat", "text-generation"] llama_model_loader: - kv 13: general.languages arr[str,1] = ["en"] llama_model_loader: - kv 14: qwen2.block_count u32 = 48 llama_model_loader: - kv 15: qwen2.context_length u32 = 32768 llama_model_loader: - kv 16: qwen2.embedding_length u32 = 5120 llama_model_loader: - kv 17: qwen2.feed_forward_length u32 = 13824 llama_model_loader: - kv 18: qwen2.attention.head_count u32 = 40 llama_model_loader: - kv 19: qwen2.attention.head_count_kv u32 = 8 llama_model_loader: - kv 20: qwen2.rope.freq_base f32 = 1000000.000000 llama_model_loader: - kv 21: qwen2.attention.layer_norm_rms_epsilon f32 = 0.000001 llama_model_loader: - kv 22: general.file_type u32 = 15 llama_model_loader: - kv 23: tokenizer.ggml.model str = gpt2 llama_model_loader: - kv 24: tokenizer.ggml.pre str = qwen2 llama_model_loader: - kv 25: tokenizer.ggml.tokens arr[str,152064] = ["!", "\"", "#", "$", "%", "&", "'", ... llama_model_loader: - kv 26: tokenizer.ggml.token_type arr[i32,152064] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... llama_model_loader: - kv 27: tokenizer.ggml.merges arr[str,151387] = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",... llama_model_loader: - kv 28: tokenizer.ggml.eos_token_id u32 = 151645 llama_model_loader: - kv 29: tokenizer.ggml.padding_token_id u32 = 151643 llama_model_loader: - kv 30: tokenizer.ggml.bos_token_id u32 = 151643 llama_model_loader: - kv 31: tokenizer.ggml.add_bos_token bool = false llama_model_loader: - kv 32: tokenizer.chat_template str = {%- if tools %}\n {{- '<|im_start|>... llama_model_loader: - kv 33: general.quantization_version u32 = 2 llama_model_loader: - type f32: 241 tensors llama_model_loader: - type q4_K: 289 tensors llama_model_loader: - type q6_K: 49 tensors print_info: file format = GGUF V3 (latest) print_info: file type = Q4_K - Medium print_info: file size = 8.37 GiB (4.87 BPW) load: special tokens cache size = 22 load: token to piece cache size = 0.9310 MB print_info: arch = qwen2 print_info: vocab_only = 0 print_info: n_ctx_train = 32768 print_info: n_embd = 5120 print_info: n_layer = 48 print_info: n_head = 40 print_info: n_head_kv = 8 print_info: n_rot = 128 print_info: n_swa = 0 print_info: n_embd_head_k = 128 print_info: n_embd_head_v = 128 print_info: n_gqa = 5 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-06 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: n_ff = 13824 print_info: n_expert = 0 print_info: n_expert_used = 0 print_info: causal attn = 1 print_info: pooling type = 0 print_info: rope type = 2 print_info: rope scaling = linear print_info: freq_base_train = 1000000.0 print_info: freq_scale_train = 1 print_info: n_ctx_orig_yarn = 32768 print_info: rope_finetuned = unknown print_info: ssm_d_conv = 0 print_info: ssm_d_inner = 0 print_info: ssm_d_state = 0 print_info: ssm_dt_rank = 0 print_info: ssm_dt_b_c_rms = 0 print_info: model type = 14B print_info: model params = 14.77 B print_info: general.name = Qwen2.5 14B Instruct print_info: vocab type = BPE print_info: n_vocab = 152064 print_info: n_merges = 151387 print_info: BOS token = 151643 '<|endoftext|>' print_info: EOS token = 151645 '<|im_end|>' print_info: EOT token = 151645 '<|im_end|>' print_info: PAD token = 151643 '<|endoftext|>' print_info: LF token = 198 'Ċ' print_info: FIM PRE token = 151659 '<|fim_prefix|>' print_info: FIM SUF token = 151661 '<|fim_suffix|>' print_info: FIM MID token = 151660 '<|fim_middle|>' print_info: FIM PAD token = 151662 '<|fim_pad|>' print_info: FIM REP token = 151663 '<|repo_name|>' print_info: FIM SEP token = 151664 '<|file_sep|>' print_info: EOG token = 151643 '<|endoftext|>' print_info: EOG token = 151645 '<|im_end|>' print_info: EOG token = 151662 '<|fim_pad|>' print_info: EOG token = 151663 '<|repo_name|>' print_info: EOG token = 151664 '<|file_sep|>' print_info: max token length = 256 load_tensors: loading model tensors, this can take a while... (mmap = false) load_tensors: offloading 48 repeating layers to GPU load_tensors: offloading output layer to GPU load_tensors: offloaded 49/49 layers to GPU load_tensors: CUDA0 model buffer size = 8148.38 MiB load_tensors: CPU model buffer size = 417.66 MiB llama_init_from_model: n_seq_max = 4 llama_init_from_model: n_ctx = 8192 llama_init_from_model: n_ctx_per_seq = 2048 llama_init_from_model: n_batch = 2048 llama_init_from_model: n_ubatch = 512 llama_init_from_model: flash_attn = 0 llama_init_from_model: freq_base = 1000000.0 llama_init_from_model: freq_scale = 1 llama_init_from_model: n_ctx_per_seq (2048) < n_ctx_train (32768) -- the full capacity of the model will not be utilized llama_kv_cache_init: kv_size = 8192, offload = 1, type_k = 'f16', type_v = 'f16', n_layer = 48, can_shift = 1 llama_kv_cache_init: CUDA0 KV buffer size = 1536.00 MiB llama_init_from_model: KV self size = 1536.00 MiB, K (f16): 768.00 MiB, V (f16): 768.00 MiB llama_init_from_model: CUDA_Host output buffer size = 2.40 MiB llama_init_from_model: CUDA0 compute buffer size = 696.00 MiB llama_init_from_model: CUDA_Host compute buffer size = 26.01 MiB llama_init_from_model: graph nodes = 1686 llama_init_from_model: graph splits = 2 time=2025-03-26T15:10:01.790+08:00 level=INFO source=server.go:624 msg="llama runner started in 4.80 seconds" time=2025-03-26T15:10:01.860+08:00 level=WARN source=runner.go:130 msg="truncating input prompt" limit=2048 prompt=6023 keep=4 new=2048 [GIN] 2025/03/26 - 15:10:08 | 200 | 12.4676306s | ::1 | POST "/v1/chat/completions" time=2025-03-26T15:11:17.787+08:00 level=WARN source=runner.go:130 msg="truncating input prompt" limit=2048 prompt=4652 keep=4 new=2048 [GIN] 2025/03/26 - 15:11:20 | 200 | 2.5896677s | ::1 | POST "/v1/chat/completions" [GIN] 2025/03/26 - 15:22:41 | 200 | 202µs | 127.0.0.1 | HEAD "/" [GIN] 2025/03/26 - 15:22:41 | 200 | 494.2µs | 127.0.0.1 | GET "/api/ps" [GIN] 2025/03/26 - 15:27:18 | 200 | 0s | 127.0.0.1 | HEAD "/" [GIN] 2025/03/26 - 15:27:18 | 200 | 362.6µs | 127.0.0.1 | GET "/api/ps" ``` ### OS _No response_ ### GPU _No response_ ### CPU _No response_ ### Ollama version _No response_
GiteaMirror added the needs more infobug labels 2026-04-22 13:26:35 -05:00
GiteaMirror commented 2026-04-22 13:26:38 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Mar 26, 2025):

What client are you using? What error is returned by the client?

<!-- gh-comment-id:2753660012 --> @rick-github commented on GitHub (Mar 26, 2025): What client are you using? What error is returned by the client?
GiteaMirror commented 2026-04-22 13:26:40 -05:00
Author
Owner
Copy Link

@Liuyuan0803 commented on GitHub (Mar 26, 2025):

cherry studio, nothing information is returned including error, and I use wireshark to monitor port 11434, that shows the information is sending to ollama successfully, but nothing is returned

<!-- gh-comment-id:2753694184 --> @Liuyuan0803 commented on GitHub (Mar 26, 2025): cherry studio, nothing information is returned including error, and I use wireshark to monitor port 11434, that shows the information is sending to ollama successfully, but nothing is returned
GiteaMirror commented 2026-04-22 13:26:43 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Mar 26, 2025):

Does the task monitor show that the GPU is at 100% when it doesn't return a result? It could be that the model has lost coherence and is "rambling", ie just generating tokens without hitting a termination token. This can happen when the context buffer overflows, and your log shows that the input is being truncated. You can try increasing num_ctx to give the model a larger context buffer, or setting num_predict to make the model stop generating tokens after a limit.

<!-- gh-comment-id:2753713038 --> @rick-github commented on GitHub (Mar 26, 2025): Does the task monitor show that the GPU is at 100% when it doesn't return a result? It could be that the model has lost coherence and is "rambling", ie just generating tokens without hitting a termination token. This can happen when the context buffer overflows, and your log shows that the input is being truncated. You can try increasing [`num_ctx`](https://github.com/ollama/ollama/blob/main/docs/modelfile.md#valid-parameters-and-values:~:text=mirostat_tau%205.0-,num_ctx,-Sets%20the%20size) to give the model a larger context buffer, or setting [`num_predict`](https://github.com/ollama/ollama/blob/main/docs/modelfile.md#valid-parameters-and-values:~:text=stop%20%22AI%20assistant%3A%22-,num_predict,-Maximum%20number%20of) to make the model stop generating tokens after a limit.
GiteaMirror commented 2026-04-22 13:26:44 -05:00
Author
Owner
Copy Link

@Liuyuan0803 commented on GitHub (Mar 26, 2025):

Thankyou, but I have another question, when I use "/api/embed" to use embedding model to get vectors, sometimes ollama cannot work too

<!-- gh-comment-id:2753740426 --> @Liuyuan0803 commented on GitHub (Mar 26, 2025): Thankyou, but I have another question, when I use "/api/embed" to use embedding model to get vectors, sometimes ollama cannot work too
GiteaMirror commented 2026-04-22 13:26:44 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Mar 26, 2025):

Do you have ollama logs showing calls to /api/embed when it doesn't work?

<!-- gh-comment-id:2753756316 --> @rick-github commented on GitHub (Mar 26, 2025): Do you have ollama logs showing calls to /api/embed when it doesn't work?
GiteaMirror commented 2026-04-22 13:26:45 -05:00
Author
Owner
Copy Link

@Liuyuan0803 commented on GitHub (Mar 28, 2025):

### 1. logs:
2025/03/28 11:09:44 routes.go:1230: INFO server config env="map[CUDA_VISIBLE_DEVICES:GPU-d8040dfd-0bc8-ad27-6eaf-8a27a2b07beb GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:2048 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:24h0m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:D:\lipuyun\Ollama_Model OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE: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://* vscode-file://*] OLLAMA_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES:]"
time=2025-03-28T11:09:44.566+08:00 level=INFO source=images.go:432 msg="total blobs: 10"
time=2025-03-28T11:09:44.568+08:00 level=INFO source=images.go:439 msg="total unused blobs removed: 0"
time=2025-03-28T11:09:44.569+08:00 level=INFO source=routes.go:1297 msg="Listening on [::]:11434 (version 0.6.1)"
time=2025-03-28T11:09:44.570+08:00 level=INFO source=gpu.go:217 msg="looking for compatible GPUs"
time=2025-03-28T11:09:44.571+08:00 level=INFO source=gpu_windows.go:167 msg=packages count=2
time=2025-03-28T11:09:44.571+08:00 level=INFO source=gpu_windows.go:214 msg="" package=0 cores=48 efficiency=0 threads=96
time=2025-03-28T11:09:44.572+08:00 level=INFO source=gpu_windows.go:214 msg="" package=1 cores=48 efficiency=0 threads=96
time=2025-03-28T11:09:45.061+08:00 level=INFO source=gpu.go:319 msg="detected OS VRAM overhead" id=GPU-d8040dfd-0bc8-ad27-6eaf-8a27a2b07beb library=cuda compute=8.9 driver=12.4 name="NVIDIA GeForce RTX 4090" overhead="2.3 GiB"
time=2025-03-28T11:09:45.065+08:00 level=INFO source=types.go:130 msg="inference compute" id=GPU-d8040dfd-0bc8-ad27-6eaf-8a27a2b07beb library=cuda variant=v12 compute=8.9 driver=12.4 name="NVIDIA GeForce RTX 4090" total="24.0 GiB" available="19.7 GiB"
time=2025-03-28T11:11:38.111+08:00 level=WARN source=ggml.go:149 msg="key not found" key=bert.vision.block_count default=0
time=2025-03-28T11:11:38.112+08:00 level=WARN source=ggml.go:149 msg="key not found" key=bert.attention.head_count_kv default=1
time=2025-03-28T11:11:38.114+08:00 level=WARN source=ggml.go:149 msg="key not found" key=bert.attention.key_length default=64
time=2025-03-28T11:11:38.116+08:00 level=WARN source=ggml.go:149 msg="key not found" key=bert.attention.value_length default=64
time=2025-03-28T11:11:38.117+08:00 level=WARN source=ggml.go:149 msg="key not found" key=bert.attention.head_count_kv default=1
time=2025-03-28T11:11:38.118+08:00 level=INFO source=sched.go:715 msg="new model will fit in available VRAM in single GPU, loading" model=D:\lipuyun\Ollama_Model\blobs\sha256-daec91ffb5dd0c27411bd71f29932917c49cf529a641d0168496c3a501e3062c gpu=GPU-d8040dfd-0bc8-ad27-6eaf-8a27a2b07beb parallel=1 available=21119054643 required="1.6 GiB"
time=2025-03-28T11:11:38.137+08:00 level=INFO source=server.go:105 msg="system memory" total="127.5 GiB" free="73.8 GiB" free_swap="117.4 GiB"
time=2025-03-28T11:11:38.137+08:00 level=WARN source=ggml.go:149 msg="key not found" key=bert.vision.block_count default=0
time=2025-03-28T11:11:38.143+08:00 level=WARN source=ggml.go:149 msg="key not found" key=bert.attention.head_count_kv default=1
time=2025-03-28T11:11:38.144+08:00 level=WARN source=ggml.go:149 msg="key not found" key=bert.attention.key_length default=64
time=2025-03-28T11:11:38.145+08:00 level=WARN source=ggml.go:149 msg="key not found" key=bert.attention.value_length default=64
time=2025-03-28T11:11:38.147+08:00 level=WARN source=ggml.go:149 msg="key not found" key=bert.attention.head_count_kv default=1
time=2025-03-28T11:11:38.148+08:00 level=INFO source=server.go:138 msg=offload library=cuda layers.requested=-1 layers.model=25 layers.offload=25 layers.split="" memory.available="[19.7 GiB]" memory.gpu_overhead="0 B" memory.required.full="1.6 GiB" memory.required.partial="1.6 GiB" memory.required.kv="12.0 MiB" memory.required.allocations="[1.6 GiB]" memory.weights.total="577.2 MiB" memory.weights.repeating="577.2 MiB" memory.weights.nonrepeating="488.3 MiB" memory.graph.full="32.0 MiB" memory.graph.partial="32.0 MiB"
llama_model_loader: loaded meta data with 33 key-value pairs and 389 tensors from D:\lipuyun\Ollama_Model\blobs\sha256-daec91ffb5dd0c27411bd71f29932917c49cf529a641d0168496c3a501e3062c (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 = bert
llama_model_loader: - kv 1: general.type str = model
llama_model_loader: - kv 2: general.size_label str = 567M
llama_model_loader: - kv 3: general.license str = mit
llama_model_loader: - kv 4: general.tags arr[str,4] = ["sentence-transformers", "feature-ex...
llama_model_loader: - kv 5: bert.block_count u32 = 24
llama_model_loader: - kv 6: bert.context_length u32 = 8192
llama_model_loader: - kv 7: bert.embedding_length u32 = 1024
llama_model_loader: - kv 8: bert.feed_forward_length u32 = 4096
llama_model_loader: - kv 9: bert.attention.head_count u32 = 16
llama_model_loader: - kv 10: bert.attention.layer_norm_epsilon f32 = 0.000010
llama_model_loader: - kv 11: general.file_type u32 = 1
llama_model_loader: - kv 12: bert.attention.causal bool = false
llama_model_loader: - kv 13: bert.pooling_type u32 = 2
llama_model_loader: - kv 14: tokenizer.ggml.model str = t5
llama_model_loader: - kv 15: tokenizer.ggml.pre str = default
llama_model_loader: - kv 16: tokenizer.ggml.tokens arr[str,250002] = ["", "", "", "", ","...
llama_model_loader: - kv 17: tokenizer.ggml.scores arr[f32,250002] = [0.000000, 0.000000, 0.000000, 0.0000...
llama_model_loader: - kv 18: tokenizer.ggml.token_type arr[i32,250002] = [3, 3, 3, 2, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv 19: tokenizer.ggml.add_space_prefix bool = true
llama_model_loader: - kv 20: tokenizer.ggml.token_type_count u32 = 1
llama_model_loader: - kv 21: tokenizer.ggml.remove_extra_whitespaces bool = true
llama_model_loader: - kv 22: tokenizer.ggml.precompiled_charsmap arr[u8,237539] = [0, 180, 2, 0, 0, 132, 0, 0, 0, 0, 0,...
llama_model_loader: - kv 23: tokenizer.ggml.bos_token_id u32 = 0
llama_model_loader: - kv 24: tokenizer.ggml.eos_token_id u32 = 2
llama_model_loader: - kv 25: tokenizer.ggml.unknown_token_id u32 = 3
llama_model_loader: - kv 26: tokenizer.ggml.seperator_token_id u32 = 2
llama_model_loader: - kv 27: tokenizer.ggml.padding_token_id u32 = 1
llama_model_loader: - kv 28: tokenizer.ggml.cls_token_id u32 = 0
llama_model_loader: - kv 29: tokenizer.ggml.mask_token_id u32 = 250001
llama_model_loader: - kv 30: tokenizer.ggml.add_bos_token bool = true
llama_model_loader: - kv 31: tokenizer.ggml.add_eos_token bool = true
llama_model_loader: - kv 32: general.quantization_version u32 = 2
llama_model_loader: - type f32: 244 tensors
llama_model_loader: - type f16: 145 tensors
print_info: file format = GGUF V3 (latest)
print_info: file type = F16
print_info: file size = 1.07 GiB (16.25 BPW)
load: model vocab missing newline token, using special_pad_id instead
load: special_eos_id is not in special_eog_ids - the tokenizer config may be incorrect
load: special tokens cache size = 4
load: token to piece cache size = 2.1668 MB
print_info: arch = bert
print_info: vocab_only = 1
print_info: model type = ?B
print_info: model params = 566.70 M
print_info: general.name = n/a
print_info: vocab type = UGM
print_info: n_vocab = 250002
print_info: n_merges = 0
print_info: BOS token = 0 ''
print_info: EOS token = 2 ''
print_info: UNK token = 3 ''
print_info: SEP token = 2 ''
print_info: PAD token = 1 ''
print_info: MASK token = 250001 '[PAD250000]'
print_info: LF token = 0 ''
print_info: EOG token = 2 ''
print_info: max token length = 48
llama_model_load: vocab only - skipping tensors
time=2025-03-28T11:11:38.882+08:00 level=INFO source=server.go:405 msg="starting llama server" cmd="D:\lipuyun\Ollama\ollama.exe runner --model D:\lipuyun\Ollama_Model\blobs\sha256-daec91ffb5dd0c27411bd71f29932917c49cf529a641d0168496c3a501e3062c --ctx-size 2048 --batch-size 512 --n-gpu-layers 25 --threads 96 --no-mmap --parallel 1 --port 60323"
time=2025-03-28T11:11:38.893+08:00 level=INFO source=sched.go:450 msg="loaded runners" count=1
time=2025-03-28T11:11:38.896+08:00 level=INFO source=server.go:585 msg="waiting for llama runner to start responding"
time=2025-03-28T11:11:38.898+08:00 level=INFO source=server.go:619 msg="waiting for server to become available" status="llm server error"
time=2025-03-28T11:11:39.006+08:00 level=INFO source=runner.go:931 msg="starting go runner"
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 CUDA devices:
Device 0: NVIDIA GeForce RTX 4090, compute capability 8.9, VMM: yes
load_backend: loaded CUDA backend from D:\lipuyun\Ollama\lib\ollama\cuda_v12\ggml-cuda.dll
load_backend: loaded CPU backend from D:\lipuyun\Ollama\lib\ollama\ggml-cpu-icelake.dll
time=2025-03-28T11:11:39.200+08:00 level=INFO source=ggml.go:109 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.AVX512=1 CPU.0.AVX512_VBMI=1 CPU.0.AVX512_VNNI=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 CUDA.0.ARCHS=500,600,610,700,750,800,860,870,890,900,1200 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(clang)
time=2025-03-28T11:11:39.226+08:00 level=INFO source=runner.go:991 msg="Server listening on 127.0.0.1:60323"
time=2025-03-28T11:11:39.409+08:00 level=INFO source=server.go:619 msg="waiting for server to become available" status="llm server loading model"
llama_model_load_from_file_impl: using device CUDA0 (NVIDIA GeForce RTX 4090) - 20140 MiB free
llama_model_loader: loaded meta data with 33 key-value pairs and 389 tensors from D:\lipuyun\Ollama_Model\blobs\sha256-daec91ffb5dd0c27411bd71f29932917c49cf529a641d0168496c3a501e3062c (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 = bert
llama_model_loader: - kv 1: general.type str = model
llama_model_loader: - kv 2: general.size_label str = 567M
llama_model_loader: - kv 3: general.license str = mit
llama_model_loader: - kv 4: general.tags arr[str,4] = ["sentence-transformers", "feature-ex...
llama_model_loader: - kv 5: bert.block_count u32 = 24
llama_model_loader: - kv 6: bert.context_length u32 = 8192
llama_model_loader: - kv 7: bert.embedding_length u32 = 1024
llama_model_loader: - kv 8: bert.feed_forward_length u32 = 4096
llama_model_loader: - kv 9: bert.attention.head_count u32 = 16
llama_model_loader: - kv 10: bert.attention.layer_norm_epsilon f32 = 0.000010
llama_model_loader: - kv 11: general.file_type u32 = 1
llama_model_loader: - kv 12: bert.attention.causal bool = false
llama_model_loader: - kv 13: bert.pooling_type u32 = 2
llama_model_loader: - kv 14: tokenizer.ggml.model str = t5
llama_model_loader: - kv 15: tokenizer.ggml.pre str = default
llama_model_loader: - kv 16: tokenizer.ggml.tokens arr[str,250002] = ["", "", "", "", ","...
llama_model_loader: - kv 17: tokenizer.ggml.scores arr[f32,250002] = [0.000000, 0.000000, 0.000000, 0.0000...
llama_model_loader: - kv 18: tokenizer.ggml.token_type arr[i32,250002] = [3, 3, 3, 2, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv 19: tokenizer.ggml.add_space_prefix bool = true
llama_model_loader: - kv 20: tokenizer.ggml.token_type_count u32 = 1
llama_model_loader: - kv 21: tokenizer.ggml.remove_extra_whitespaces bool = true
llama_model_loader: - kv 22: tokenizer.ggml.precompiled_charsmap arr[u8,237539] = [0, 180, 2, 0, 0, 132, 0, 0, 0, 0, 0,...
llama_model_loader: - kv 23: tokenizer.ggml.bos_token_id u32 = 0
llama_model_loader: - kv 24: tokenizer.ggml.eos_token_id u32 = 2
llama_model_loader: - kv 25: tokenizer.ggml.unknown_token_id u32 = 3
llama_model_loader: - kv 26: tokenizer.ggml.seperator_token_id u32 = 2
llama_model_loader: - kv 27: tokenizer.ggml.padding_token_id u32 = 1
llama_model_loader: - kv 28: tokenizer.ggml.cls_token_id u32 = 0
llama_model_loader: - kv 29: tokenizer.ggml.mask_token_id u32 = 250001
llama_model_loader: - kv 30: tokenizer.ggml.add_bos_token bool = true
llama_model_loader: - kv 31: tokenizer.ggml.add_eos_token bool = true
llama_model_loader: - kv 32: general.quantization_version u32 = 2
llama_model_loader: - type f32: 244 tensors
llama_model_loader: - type f16: 145 tensors
print_info: file format = GGUF V3 (latest)
print_info: file type = F16
print_info: file size = 1.07 GiB (16.25 BPW)
load: model vocab missing newline token, using special_pad_id instead
load: special_eos_id is not in special_eog_ids - the tokenizer config may be incorrect
load: special tokens cache size = 4
load: token to piece cache size = 2.1668 MB
print_info: arch = bert
print_info: vocab_only = 0
print_info: n_ctx_train = 8192
print_info: n_embd = 1024
print_info: n_layer = 24
print_info: n_head = 16
print_info: n_head_kv = 16
print_info: n_rot = 64
print_info: n_swa = 0
print_info: n_embd_head_k = 64
print_info: n_embd_head_v = 64
print_info: n_gqa = 1
print_info: n_embd_k_gqa = 1024
print_info: n_embd_v_gqa = 1024
print_info: f_norm_eps = 1.0e-05
print_info: f_norm_rms_eps = 0.0e+00
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: n_ff = 4096
print_info: n_expert = 0
print_info: n_expert_used = 0
print_info: causal attn = 0
print_info: pooling type = 2
print_info: rope type = 2
print_info: rope scaling = linear
print_info: freq_base_train = 10000.0
print_info: freq_scale_train = 1
print_info: n_ctx_orig_yarn = 8192
print_info: rope_finetuned = unknown
print_info: ssm_d_conv = 0
print_info: ssm_d_inner = 0
print_info: ssm_d_state = 0
print_info: ssm_dt_rank = 0
print_info: ssm_dt_b_c_rms = 0
print_info: model type = 335M
print_info: model params = 566.70 M
print_info: general.name = n/a
print_info: vocab type = UGM
print_info: n_vocab = 250002
print_info: n_merges = 0
print_info: BOS token = 0 ''
print_info: EOS token = 2 ''
print_info: UNK token = 3 ''
print_info: SEP token = 2 ''
print_info: PAD token = 1 ''
print_info: MASK token = 250001 '[PAD250000]'
print_info: LF token = 0 ''
print_info: EOG token = 2 ''
print_info: max token length = 48
load_tensors: loading model tensors, this can take a while... (mmap = false)
load_tensors: offloading 24 repeating layers to GPU
load_tensors: offloading output layer to GPU
load_tensors: offloaded 25/25 layers to GPU
load_tensors: CUDA_Host model buffer size = 520.30 MiB
load_tensors: CUDA0 model buffer size = 577.22 MiB
llama_init_from_model: n_seq_max = 1
llama_init_from_model: n_ctx = 2048
llama_init_from_model: n_ctx_per_seq = 2048
llama_init_from_model: n_batch = 512
llama_init_from_model: n_ubatch = 512
llama_init_from_model: flash_attn = 0
llama_init_from_model: freq_base = 10000.0
llama_init_from_model: freq_scale = 1
llama_init_from_model: n_ctx_per_seq (2048) < n_ctx_train (8192) -- the full capacity of the model will not be utilized
llama_kv_cache_init: kv_size = 2048, offload = 1, type_k = 'f16', type_v = 'f16', n_layer = 24, can_shift = 1
llama_kv_cache_init: CUDA0 KV buffer size = 192.00 MiB
llama_init_from_model: KV self size = 192.00 MiB, K (f16): 96.00 MiB, V (f16): 96.00 MiB
llama_init_from_model: CUDA_Host output buffer size = 0.00 MiB
llama_init_from_model: CUDA0 compute buffer size = 25.01 MiB
llama_init_from_model: CUDA_Host compute buffer size = 5.01 MiB
llama_init_from_model: graph nodes = 849
llama_init_from_model: graph splits = 4 (with bs=512), 2 (with bs=1)
time=2025-03-28T11:11:40.921+08:00 level=INFO source=server.go:624 msg="llama runner started in 2.02 seconds"
[GIN] 2025/03/28 - 11:11:41 | 200 | 3.2086079s | 10.29.1.125 | POST "/api/embed"
[GIN] 2025/03/28 - 11:11:41 | 200 | 158.5419ms | 10.29.1.125 | POST "/api/embed"
[GIN] 2025/03/28 - 11:11:41 | 200 | 143.8341ms | 10.29.1.125 | POST "/api/embed"
[GIN] 2025/03/28 - 11:11:41 | 200 | 119.812ms | 10.29.1.125 | POST "/api/embed"
[GIN] 2025/03/28 - 11:11:41 | 200 | 154.2558ms | 10.29.1.125 | POST "/api/embed"
[GIN] 2025/03/28 - 11:11:42 | 200 | 152.3745ms | 10.29.1.125 | POST "/api/embed"
[GIN] 2025/03/28 - 11:11:42 | 200 | 161.5102ms | 10.29.1.125 | POST "/api/embed"
[GIN] 2025/03/28 - 11:11:42 | 200 | 96.7754ms | 10.29.1.125 | POST "/api/embed"
[GIN] 2025/03/28 - 11:11:42 | 200 | 150.9797ms | 10.29.1.125 | POST "/api/embed"
[GIN] 2025/03/28 - 11:11:42 | 200 | 161.3874ms | 10.29.1.125 | POST "/api/embed"
[GIN] 2025/03/28 - 11:11:42 | 200 | 131.177ms | 10.29.1.125 | POST "/api/embed"
[GIN] 2025/03/28 - 11:11:43 | 200 | 121.8086ms | 10.29.1.125 | POST "/api/embed"
[GIN] 2025/03/28 - 11:11:43 | 200 | 111.3074ms | 10.29.1.125 | POST "/api/embed"
[GIN] 2025/03/28 - 11:11:43 | 200 | 110.0062ms | 10.29.1.125 | POST "/api/embed"
[GIN] 2025/03/28 - 11:11:43 | 200 | 101.0394ms | 10.29.1.125 | POST "/api/embed"
[GIN] 2025/03/28 - 11:11:46 | 200 | 2.7701523s | 10.29.1.125 | POST "/api/embed"
[GIN] 2025/03/28 - 11:11:46 | 200 | 132.3933ms | 10.29.1.125 | POST "/api/embed"
[GIN] 2025/03/28 - 11:11:49 | 200 | 2.8192538s | 10.29.1.125 | POST "/api/embed"
[GIN] 2025/03/28 - 11:11:49 | 200 | 174.3936ms | 10.29.1.125 | POST "/api/embed"
[GIN] 2025/03/28 - 11:11:52 | 200 | 2.9610501s | 10.29.1.125 | POST "/api/embed"
[GIN] 2025/03/28 - 11:11:52 | 200 | 180.535ms | 10.29.1.125 | POST "/api/embed"
[GIN] 2025/03/28 - 11:11:55 | 200 | 2.5931473s | 10.29.1.125 | POST "/api/embed"
[GIN] 2025/03/28 - 11:11:55 | 200 | 217.086ms | 10.29.1.125 | POST "/api/embed"
[GIN] 2025/03/28 - 11:11:55 | 200 | 198.8857ms | 10.29.1.125 | POST "/api/embed"
[GIN] 2025/03/28 - 11:11:55 | 200 | 174.0897ms | 10.29.1.125 | POST "/api/embed"
[GIN] 2025/03/28 - 11:11:56 | 200 | 194.5948ms | 10.29.1.125 | POST "/api/embed"
[GIN] 2025/03/28 - 11:11:56 | 200 | 188.8659ms | 10.29.1.125 | POST "/api/embed"
[GIN] 2025/03/28 - 11:11:56 | 200 | 183.4675ms | 10.29.1.125 | POST "/api/embed"
[GIN] 2025/03/28 - 11:11:56 | 200 | 188.5184ms | 10.29.1.125 | POST "/api/embed"
[GIN] 2025/03/28 - 11:11:57 | 200 | 184.6032ms | 10.29.1.125 | POST "/api/embed"
[GIN] 2025/03/28 - 11:11:57 | 200 | 188.0136ms | 10.29.1.125 | POST "/api/embed"
[GIN] 2025/03/28 - 11:11:57 | 200 | 202.4551ms | 10.29.1.125 | POST "/api/embed"
[GIN] 2025/03/28 - 11:11:57 | 200 | 189.0539ms | 10.29.1.125 | POST "/api/embed"
[GIN] 2025/03/28 - 11:11:57 | 200 | 182.562ms | 10.29.1.125 | POST "/api/embed"
[GIN] 2025/03/28 - 11:11:58 | 200 | 176.8825ms | 10.29.1.125 | POST "/api/embed"
[GIN] 2025/03/28 - 11:11:58 | 200 | 163.398ms | 10.29.1.125 | POST "/api/embed"
[GIN] 2025/03/28 - 11:11:58 | 200 | 185.7276ms | 10.29.1.125 | POST "/api/embed"
[GIN] 2025/03/28 - 11:11:58 | 200 | 197.0806ms | 10.29.1.125 | POST "/api/embed"
[GIN] 2025/03/28 - 11:11:59 | 200 | 189.1101ms | 10.29.1.125 | POST "/api/embed"
[GIN] 2025/03/28 - 11:11:59 | 200 | 184.7041ms | 10.29.1.125 | POST "/api/embed"
[GIN] 2025/03/28 - 11:11:59 | 200 | 170.5567ms | 10.29.1.125 | POST "/api/embed"
[GIN] 2025/03/28 - 11:11:59 | 200 | 174.865ms | 10.29.1.125 | POST "/api/embed"
[GIN] 2025/03/28 - 11:12:11 | 200 | 182.0829ms | 10.29.1.125 | POST "/api/embed"
[GIN] 2025/03/28 - 11:12:12 | 200 | 324.4937ms | 10.29.1.125 | POST "/api/embed"
[GIN] 2025/03/28 - 11:12:12 | 200 | 148.9159ms | 10.29.1.125 | POST "/api/embed"
[GIN] 2025/03/28 - 11:12:12 | 200 | 106.9827ms | 10.29.1.125 | POST "/api/embed"
[GIN] 2025/03/28 - 11:12:12 | 200 | 122.7874ms | 10.29.1.125 | POST "/api/embed"
[GIN] 2025/03/28 - 11:12:12 | 200 | 125.8575ms | 10.29.1.125 | POST "/api/embed"
[GIN] 2025/03/28 - 11:12:12 | 200 | 130.3733ms | 10.29.1.125 | POST "/api/embed"
[GIN] 2025/03/28 - 11:12:12 | 200 | 122.163ms | 10.29.1.125 | POST "/api/embed"
[GIN] 2025/03/28 - 11:12:13 | 200 | 116.2861ms | 10.29.1.125 | POST "/api/embed"
[GIN] 2025/03/28 - 11:12:13 | 200 | 122.8919ms | 10.29.1.125 | POST "/api/embed"
[GIN] 2025/03/28 - 11:12:13 | 200 | 136.2746ms | 10.29.1.125 | POST "/api/embed"
[GIN] 2025/03/28 - 11:12:13 | 200 | 128.3028ms | 10.29.1.125 | POST "/api/embed"
[GIN] 2025/03/28 - 11:12:13 | 200 | 110.0891ms | 10.29.1.125 | POST "/api/embed"
[GIN] 2025/03/28 - 11:12:13 | 200 | 122.4463ms | 10.29.1.125 | POST "/api/embed"
[GIN] 2025/03/28 - 11:12:14 | 200 | 124.8436ms | 10.29.1.125 | POST "/api/embed"
[GIN] 2025/03/28 - 11:12:14 | 200 | 119.9132ms | 10.29.1.125 | POST "/api/embed"
[GIN] 2025/03/28 - 11:12:14 | 200 | 128.8288ms | 10.29.1.125 | POST "/api/embed"
[GIN] 2025/03/28 - 11:12:14 | 200 | 125.7882ms | 10.29.1.125 | POST "/api/embed"
[GIN] 2025/03/28 - 11:12:14 | 200 | 123.6601ms | 10.29.1.125 | POST "/api/embed"
[GIN] 2025/03/28 - 11:12:14 | 200 | 111.2645ms | 10.29.1.125 | POST "/api/embed"
[GIN] 2025/03/28 - 11:12:14 | 200 | 129.1993ms | 10.29.1.125 | POST "/api/embed"
[GIN] 2025/03/28 - 11:12:15 | 200 | 123.9483ms | 10.29.1.125 | POST "/api/embed"
[GIN] 2025/03/28 - 11:13:10 | 200 | 3.4333857s | 10.29.1.125 | POST "/api/embed"
[GIN] 2025/03/28 - 11:14:30 | 200 | 3.6304015s | 10.29.1.125 | POST "/api/embed"
[GIN] 2025/03/28 - 11:17:40 | 200 | 0s | 127.0.0.1 | HEAD "/"
[GIN] 2025/03/28 - 11:18:25 | 200 | 522µs | 127.0.0.1 | GET "/api/ps"
2. C:\Users\liuyuan>ollama ps
NAME ID SIZE PROCESSOR UNTIL
bge-m3:latest 790764642607 1.7 GB 100% GPU 24 hours from now

  1. after 11:14:30, I send a sentence to ollama again, it cannot return the result to me. But when I check the running model information, ollama can return me the result successfully
<!-- gh-comment-id:2760089592 --> @Liuyuan0803 commented on GitHub (Mar 28, 2025): **### 1. logs:** 2025/03/28 11:09:44 routes.go:1230: INFO server config env="map[CUDA_VISIBLE_DEVICES:GPU-d8040dfd-0bc8-ad27-6eaf-8a27a2b07beb GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:2048 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:24h0m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:D:\\lipuyun\\Ollama_Model OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE: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://* vscode-file://*] OLLAMA_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES:]" time=2025-03-28T11:09:44.566+08:00 level=INFO source=images.go:432 msg="total blobs: 10" time=2025-03-28T11:09:44.568+08:00 level=INFO source=images.go:439 msg="total unused blobs removed: 0" time=2025-03-28T11:09:44.569+08:00 level=INFO source=routes.go:1297 msg="Listening on [::]:11434 (version 0.6.1)" time=2025-03-28T11:09:44.570+08:00 level=INFO source=gpu.go:217 msg="looking for compatible GPUs" time=2025-03-28T11:09:44.571+08:00 level=INFO source=gpu_windows.go:167 msg=packages count=2 time=2025-03-28T11:09:44.571+08:00 level=INFO source=gpu_windows.go:214 msg="" package=0 cores=48 efficiency=0 threads=96 time=2025-03-28T11:09:44.572+08:00 level=INFO source=gpu_windows.go:214 msg="" package=1 cores=48 efficiency=0 threads=96 time=2025-03-28T11:09:45.061+08:00 level=INFO source=gpu.go:319 msg="detected OS VRAM overhead" id=GPU-d8040dfd-0bc8-ad27-6eaf-8a27a2b07beb library=cuda compute=8.9 driver=12.4 name="NVIDIA GeForce RTX 4090" overhead="2.3 GiB" time=2025-03-28T11:09:45.065+08:00 level=INFO source=types.go:130 msg="inference compute" id=GPU-d8040dfd-0bc8-ad27-6eaf-8a27a2b07beb library=cuda variant=v12 compute=8.9 driver=12.4 name="NVIDIA GeForce RTX 4090" total="24.0 GiB" available="19.7 GiB" time=2025-03-28T11:11:38.111+08:00 level=WARN source=ggml.go:149 msg="key not found" key=bert.vision.block_count default=0 time=2025-03-28T11:11:38.112+08:00 level=WARN source=ggml.go:149 msg="key not found" key=bert.attention.head_count_kv default=1 time=2025-03-28T11:11:38.114+08:00 level=WARN source=ggml.go:149 msg="key not found" key=bert.attention.key_length default=64 time=2025-03-28T11:11:38.116+08:00 level=WARN source=ggml.go:149 msg="key not found" key=bert.attention.value_length default=64 time=2025-03-28T11:11:38.117+08:00 level=WARN source=ggml.go:149 msg="key not found" key=bert.attention.head_count_kv default=1 time=2025-03-28T11:11:38.118+08:00 level=INFO source=sched.go:715 msg="new model will fit in available VRAM in single GPU, loading" model=D:\lipuyun\Ollama_Model\blobs\sha256-daec91ffb5dd0c27411bd71f29932917c49cf529a641d0168496c3a501e3062c gpu=GPU-d8040dfd-0bc8-ad27-6eaf-8a27a2b07beb parallel=1 available=21119054643 required="1.6 GiB" time=2025-03-28T11:11:38.137+08:00 level=INFO source=server.go:105 msg="system memory" total="127.5 GiB" free="73.8 GiB" free_swap="117.4 GiB" time=2025-03-28T11:11:38.137+08:00 level=WARN source=ggml.go:149 msg="key not found" key=bert.vision.block_count default=0 time=2025-03-28T11:11:38.143+08:00 level=WARN source=ggml.go:149 msg="key not found" key=bert.attention.head_count_kv default=1 time=2025-03-28T11:11:38.144+08:00 level=WARN source=ggml.go:149 msg="key not found" key=bert.attention.key_length default=64 time=2025-03-28T11:11:38.145+08:00 level=WARN source=ggml.go:149 msg="key not found" key=bert.attention.value_length default=64 time=2025-03-28T11:11:38.147+08:00 level=WARN source=ggml.go:149 msg="key not found" key=bert.attention.head_count_kv default=1 time=2025-03-28T11:11:38.148+08:00 level=INFO source=server.go:138 msg=offload library=cuda layers.requested=-1 layers.model=25 layers.offload=25 layers.split="" memory.available="[19.7 GiB]" memory.gpu_overhead="0 B" memory.required.full="1.6 GiB" memory.required.partial="1.6 GiB" memory.required.kv="12.0 MiB" memory.required.allocations="[1.6 GiB]" memory.weights.total="577.2 MiB" memory.weights.repeating="577.2 MiB" memory.weights.nonrepeating="488.3 MiB" memory.graph.full="32.0 MiB" memory.graph.partial="32.0 MiB" llama_model_loader: loaded meta data with 33 key-value pairs and 389 tensors from D:\lipuyun\Ollama_Model\blobs\sha256-daec91ffb5dd0c27411bd71f29932917c49cf529a641d0168496c3a501e3062c (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 = bert llama_model_loader: - kv 1: general.type str = model llama_model_loader: - kv 2: general.size_label str = 567M llama_model_loader: - kv 3: general.license str = mit llama_model_loader: - kv 4: general.tags arr[str,4] = ["sentence-transformers", "feature-ex... llama_model_loader: - kv 5: bert.block_count u32 = 24 llama_model_loader: - kv 6: bert.context_length u32 = 8192 llama_model_loader: - kv 7: bert.embedding_length u32 = 1024 llama_model_loader: - kv 8: bert.feed_forward_length u32 = 4096 llama_model_loader: - kv 9: bert.attention.head_count u32 = 16 llama_model_loader: - kv 10: bert.attention.layer_norm_epsilon f32 = 0.000010 llama_model_loader: - kv 11: general.file_type u32 = 1 llama_model_loader: - kv 12: bert.attention.causal bool = false llama_model_loader: - kv 13: bert.pooling_type u32 = 2 llama_model_loader: - kv 14: tokenizer.ggml.model str = t5 llama_model_loader: - kv 15: tokenizer.ggml.pre str = default llama_model_loader: - kv 16: tokenizer.ggml.tokens arr[str,250002] = ["<s>", "<pad>", "</s>", "<unk>", ","... llama_model_loader: - kv 17: tokenizer.ggml.scores arr[f32,250002] = [0.000000, 0.000000, 0.000000, 0.0000... llama_model_loader: - kv 18: tokenizer.ggml.token_type arr[i32,250002] = [3, 3, 3, 2, 1, 1, 1, 1, 1, 1, 1, 1, ... llama_model_loader: - kv 19: tokenizer.ggml.add_space_prefix bool = true llama_model_loader: - kv 20: tokenizer.ggml.token_type_count u32 = 1 llama_model_loader: - kv 21: tokenizer.ggml.remove_extra_whitespaces bool = true llama_model_loader: - kv 22: tokenizer.ggml.precompiled_charsmap arr[u8,237539] = [0, 180, 2, 0, 0, 132, 0, 0, 0, 0, 0,... llama_model_loader: - kv 23: tokenizer.ggml.bos_token_id u32 = 0 llama_model_loader: - kv 24: tokenizer.ggml.eos_token_id u32 = 2 llama_model_loader: - kv 25: tokenizer.ggml.unknown_token_id u32 = 3 llama_model_loader: - kv 26: tokenizer.ggml.seperator_token_id u32 = 2 llama_model_loader: - kv 27: tokenizer.ggml.padding_token_id u32 = 1 llama_model_loader: - kv 28: tokenizer.ggml.cls_token_id u32 = 0 llama_model_loader: - kv 29: tokenizer.ggml.mask_token_id u32 = 250001 llama_model_loader: - kv 30: tokenizer.ggml.add_bos_token bool = true llama_model_loader: - kv 31: tokenizer.ggml.add_eos_token bool = true llama_model_loader: - kv 32: general.quantization_version u32 = 2 llama_model_loader: - type f32: 244 tensors llama_model_loader: - type f16: 145 tensors print_info: file format = GGUF V3 (latest) print_info: file type = F16 print_info: file size = 1.07 GiB (16.25 BPW) load: model vocab missing newline token, using special_pad_id instead load: special_eos_id is not in special_eog_ids - the tokenizer config may be incorrect load: special tokens cache size = 4 load: token to piece cache size = 2.1668 MB print_info: arch = bert print_info: vocab_only = 1 print_info: model type = ?B print_info: model params = 566.70 M print_info: general.name = n/a print_info: vocab type = UGM print_info: n_vocab = 250002 print_info: n_merges = 0 print_info: BOS token = 0 '<s>' print_info: EOS token = 2 '</s>' print_info: UNK token = 3 '<unk>' print_info: SEP token = 2 '</s>' print_info: PAD token = 1 '<pad>' print_info: MASK token = 250001 '[PAD250000]' print_info: LF token = 0 '<s>' print_info: EOG token = 2 '</s>' print_info: max token length = 48 llama_model_load: vocab only - skipping tensors time=2025-03-28T11:11:38.882+08:00 level=INFO source=server.go:405 msg="starting llama server" cmd="D:\\lipuyun\\Ollama\\ollama.exe runner --model D:\\lipuyun\\Ollama_Model\\blobs\\sha256-daec91ffb5dd0c27411bd71f29932917c49cf529a641d0168496c3a501e3062c --ctx-size 2048 --batch-size 512 --n-gpu-layers 25 --threads 96 --no-mmap --parallel 1 --port 60323" time=2025-03-28T11:11:38.893+08:00 level=INFO source=sched.go:450 msg="loaded runners" count=1 time=2025-03-28T11:11:38.896+08:00 level=INFO source=server.go:585 msg="waiting for llama runner to start responding" time=2025-03-28T11:11:38.898+08:00 level=INFO source=server.go:619 msg="waiting for server to become available" status="llm server error" time=2025-03-28T11:11:39.006+08:00 level=INFO source=runner.go:931 msg="starting go runner" ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no ggml_cuda_init: found 1 CUDA devices: Device 0: NVIDIA GeForce RTX 4090, compute capability 8.9, VMM: yes load_backend: loaded CUDA backend from D:\lipuyun\Ollama\lib\ollama\cuda_v12\ggml-cuda.dll load_backend: loaded CPU backend from D:\lipuyun\Ollama\lib\ollama\ggml-cpu-icelake.dll time=2025-03-28T11:11:39.200+08:00 level=INFO source=ggml.go:109 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.AVX512=1 CPU.0.AVX512_VBMI=1 CPU.0.AVX512_VNNI=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 CUDA.0.ARCHS=500,600,610,700,750,800,860,870,890,900,1200 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(clang) time=2025-03-28T11:11:39.226+08:00 level=INFO source=runner.go:991 msg="Server listening on 127.0.0.1:60323" time=2025-03-28T11:11:39.409+08:00 level=INFO source=server.go:619 msg="waiting for server to become available" status="llm server loading model" llama_model_load_from_file_impl: using device CUDA0 (NVIDIA GeForce RTX 4090) - 20140 MiB free llama_model_loader: loaded meta data with 33 key-value pairs and 389 tensors from D:\lipuyun\Ollama_Model\blobs\sha256-daec91ffb5dd0c27411bd71f29932917c49cf529a641d0168496c3a501e3062c (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 = bert llama_model_loader: - kv 1: general.type str = model llama_model_loader: - kv 2: general.size_label str = 567M llama_model_loader: - kv 3: general.license str = mit llama_model_loader: - kv 4: general.tags arr[str,4] = ["sentence-transformers", "feature-ex... llama_model_loader: - kv 5: bert.block_count u32 = 24 llama_model_loader: - kv 6: bert.context_length u32 = 8192 llama_model_loader: - kv 7: bert.embedding_length u32 = 1024 llama_model_loader: - kv 8: bert.feed_forward_length u32 = 4096 llama_model_loader: - kv 9: bert.attention.head_count u32 = 16 llama_model_loader: - kv 10: bert.attention.layer_norm_epsilon f32 = 0.000010 llama_model_loader: - kv 11: general.file_type u32 = 1 llama_model_loader: - kv 12: bert.attention.causal bool = false llama_model_loader: - kv 13: bert.pooling_type u32 = 2 llama_model_loader: - kv 14: tokenizer.ggml.model str = t5 llama_model_loader: - kv 15: tokenizer.ggml.pre str = default llama_model_loader: - kv 16: tokenizer.ggml.tokens arr[str,250002] = ["<s>", "<pad>", "</s>", "<unk>", ","... llama_model_loader: - kv 17: tokenizer.ggml.scores arr[f32,250002] = [0.000000, 0.000000, 0.000000, 0.0000... llama_model_loader: - kv 18: tokenizer.ggml.token_type arr[i32,250002] = [3, 3, 3, 2, 1, 1, 1, 1, 1, 1, 1, 1, ... llama_model_loader: - kv 19: tokenizer.ggml.add_space_prefix bool = true llama_model_loader: - kv 20: tokenizer.ggml.token_type_count u32 = 1 llama_model_loader: - kv 21: tokenizer.ggml.remove_extra_whitespaces bool = true llama_model_loader: - kv 22: tokenizer.ggml.precompiled_charsmap arr[u8,237539] = [0, 180, 2, 0, 0, 132, 0, 0, 0, 0, 0,... llama_model_loader: - kv 23: tokenizer.ggml.bos_token_id u32 = 0 llama_model_loader: - kv 24: tokenizer.ggml.eos_token_id u32 = 2 llama_model_loader: - kv 25: tokenizer.ggml.unknown_token_id u32 = 3 llama_model_loader: - kv 26: tokenizer.ggml.seperator_token_id u32 = 2 llama_model_loader: - kv 27: tokenizer.ggml.padding_token_id u32 = 1 llama_model_loader: - kv 28: tokenizer.ggml.cls_token_id u32 = 0 llama_model_loader: - kv 29: tokenizer.ggml.mask_token_id u32 = 250001 llama_model_loader: - kv 30: tokenizer.ggml.add_bos_token bool = true llama_model_loader: - kv 31: tokenizer.ggml.add_eos_token bool = true llama_model_loader: - kv 32: general.quantization_version u32 = 2 llama_model_loader: - type f32: 244 tensors llama_model_loader: - type f16: 145 tensors print_info: file format = GGUF V3 (latest) print_info: file type = F16 print_info: file size = 1.07 GiB (16.25 BPW) load: model vocab missing newline token, using special_pad_id instead load: special_eos_id is not in special_eog_ids - the tokenizer config may be incorrect load: special tokens cache size = 4 load: token to piece cache size = 2.1668 MB print_info: arch = bert print_info: vocab_only = 0 print_info: n_ctx_train = 8192 print_info: n_embd = 1024 print_info: n_layer = 24 print_info: n_head = 16 print_info: n_head_kv = 16 print_info: n_rot = 64 print_info: n_swa = 0 print_info: n_embd_head_k = 64 print_info: n_embd_head_v = 64 print_info: n_gqa = 1 print_info: n_embd_k_gqa = 1024 print_info: n_embd_v_gqa = 1024 print_info: f_norm_eps = 1.0e-05 print_info: f_norm_rms_eps = 0.0e+00 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: n_ff = 4096 print_info: n_expert = 0 print_info: n_expert_used = 0 print_info: causal attn = 0 print_info: pooling type = 2 print_info: rope type = 2 print_info: rope scaling = linear print_info: freq_base_train = 10000.0 print_info: freq_scale_train = 1 print_info: n_ctx_orig_yarn = 8192 print_info: rope_finetuned = unknown print_info: ssm_d_conv = 0 print_info: ssm_d_inner = 0 print_info: ssm_d_state = 0 print_info: ssm_dt_rank = 0 print_info: ssm_dt_b_c_rms = 0 print_info: model type = 335M print_info: model params = 566.70 M print_info: general.name = n/a print_info: vocab type = UGM print_info: n_vocab = 250002 print_info: n_merges = 0 print_info: BOS token = 0 '<s>' print_info: EOS token = 2 '</s>' print_info: UNK token = 3 '<unk>' print_info: SEP token = 2 '</s>' print_info: PAD token = 1 '<pad>' print_info: MASK token = 250001 '[PAD250000]' print_info: LF token = 0 '<s>' print_info: EOG token = 2 '</s>' print_info: max token length = 48 load_tensors: loading model tensors, this can take a while... (mmap = false) load_tensors: offloading 24 repeating layers to GPU load_tensors: offloading output layer to GPU load_tensors: offloaded 25/25 layers to GPU load_tensors: CUDA_Host model buffer size = 520.30 MiB load_tensors: CUDA0 model buffer size = 577.22 MiB llama_init_from_model: n_seq_max = 1 llama_init_from_model: n_ctx = 2048 llama_init_from_model: n_ctx_per_seq = 2048 llama_init_from_model: n_batch = 512 llama_init_from_model: n_ubatch = 512 llama_init_from_model: flash_attn = 0 llama_init_from_model: freq_base = 10000.0 llama_init_from_model: freq_scale = 1 llama_init_from_model: n_ctx_per_seq (2048) < n_ctx_train (8192) -- the full capacity of the model will not be utilized llama_kv_cache_init: kv_size = 2048, offload = 1, type_k = 'f16', type_v = 'f16', n_layer = 24, can_shift = 1 llama_kv_cache_init: CUDA0 KV buffer size = 192.00 MiB llama_init_from_model: KV self size = 192.00 MiB, K (f16): 96.00 MiB, V (f16): 96.00 MiB llama_init_from_model: CUDA_Host output buffer size = 0.00 MiB llama_init_from_model: CUDA0 compute buffer size = 25.01 MiB llama_init_from_model: CUDA_Host compute buffer size = 5.01 MiB llama_init_from_model: graph nodes = 849 llama_init_from_model: graph splits = 4 (with bs=512), 2 (with bs=1) time=2025-03-28T11:11:40.921+08:00 level=INFO source=server.go:624 msg="llama runner started in 2.02 seconds" [GIN] 2025/03/28 - 11:11:41 | 200 | 3.2086079s | 10.29.1.125 | POST "/api/embed" [GIN] 2025/03/28 - 11:11:41 | 200 | 158.5419ms | 10.29.1.125 | POST "/api/embed" [GIN] 2025/03/28 - 11:11:41 | 200 | 143.8341ms | 10.29.1.125 | POST "/api/embed" [GIN] 2025/03/28 - 11:11:41 | 200 | 119.812ms | 10.29.1.125 | POST "/api/embed" [GIN] 2025/03/28 - 11:11:41 | 200 | 154.2558ms | 10.29.1.125 | POST "/api/embed" [GIN] 2025/03/28 - 11:11:42 | 200 | 152.3745ms | 10.29.1.125 | POST "/api/embed" [GIN] 2025/03/28 - 11:11:42 | 200 | 161.5102ms | 10.29.1.125 | POST "/api/embed" [GIN] 2025/03/28 - 11:11:42 | 200 | 96.7754ms | 10.29.1.125 | POST "/api/embed" [GIN] 2025/03/28 - 11:11:42 | 200 | 150.9797ms | 10.29.1.125 | POST "/api/embed" [GIN] 2025/03/28 - 11:11:42 | 200 | 161.3874ms | 10.29.1.125 | POST "/api/embed" [GIN] 2025/03/28 - 11:11:42 | 200 | 131.177ms | 10.29.1.125 | POST "/api/embed" [GIN] 2025/03/28 - 11:11:43 | 200 | 121.8086ms | 10.29.1.125 | POST "/api/embed" [GIN] 2025/03/28 - 11:11:43 | 200 | 111.3074ms | 10.29.1.125 | POST "/api/embed" [GIN] 2025/03/28 - 11:11:43 | 200 | 110.0062ms | 10.29.1.125 | POST "/api/embed" [GIN] 2025/03/28 - 11:11:43 | 200 | 101.0394ms | 10.29.1.125 | POST "/api/embed" [GIN] 2025/03/28 - 11:11:46 | 200 | 2.7701523s | 10.29.1.125 | POST "/api/embed" [GIN] 2025/03/28 - 11:11:46 | 200 | 132.3933ms | 10.29.1.125 | POST "/api/embed" [GIN] 2025/03/28 - 11:11:49 | 200 | 2.8192538s | 10.29.1.125 | POST "/api/embed" [GIN] 2025/03/28 - 11:11:49 | 200 | 174.3936ms | 10.29.1.125 | POST "/api/embed" [GIN] 2025/03/28 - 11:11:52 | 200 | 2.9610501s | 10.29.1.125 | POST "/api/embed" [GIN] 2025/03/28 - 11:11:52 | 200 | 180.535ms | 10.29.1.125 | POST "/api/embed" [GIN] 2025/03/28 - 11:11:55 | 200 | 2.5931473s | 10.29.1.125 | POST "/api/embed" [GIN] 2025/03/28 - 11:11:55 | 200 | 217.086ms | 10.29.1.125 | POST "/api/embed" [GIN] 2025/03/28 - 11:11:55 | 200 | 198.8857ms | 10.29.1.125 | POST "/api/embed" [GIN] 2025/03/28 - 11:11:55 | 200 | 174.0897ms | 10.29.1.125 | POST "/api/embed" [GIN] 2025/03/28 - 11:11:56 | 200 | 194.5948ms | 10.29.1.125 | POST "/api/embed" [GIN] 2025/03/28 - 11:11:56 | 200 | 188.8659ms | 10.29.1.125 | POST "/api/embed" [GIN] 2025/03/28 - 11:11:56 | 200 | 183.4675ms | 10.29.1.125 | POST "/api/embed" [GIN] 2025/03/28 - 11:11:56 | 200 | 188.5184ms | 10.29.1.125 | POST "/api/embed" [GIN] 2025/03/28 - 11:11:57 | 200 | 184.6032ms | 10.29.1.125 | POST "/api/embed" [GIN] 2025/03/28 - 11:11:57 | 200 | 188.0136ms | 10.29.1.125 | POST "/api/embed" [GIN] 2025/03/28 - 11:11:57 | 200 | 202.4551ms | 10.29.1.125 | POST "/api/embed" [GIN] 2025/03/28 - 11:11:57 | 200 | 189.0539ms | 10.29.1.125 | POST "/api/embed" [GIN] 2025/03/28 - 11:11:57 | 200 | 182.562ms | 10.29.1.125 | POST "/api/embed" [GIN] 2025/03/28 - 11:11:58 | 200 | 176.8825ms | 10.29.1.125 | POST "/api/embed" [GIN] 2025/03/28 - 11:11:58 | 200 | 163.398ms | 10.29.1.125 | POST "/api/embed" [GIN] 2025/03/28 - 11:11:58 | 200 | 185.7276ms | 10.29.1.125 | POST "/api/embed" [GIN] 2025/03/28 - 11:11:58 | 200 | 197.0806ms | 10.29.1.125 | POST "/api/embed" [GIN] 2025/03/28 - 11:11:59 | 200 | 189.1101ms | 10.29.1.125 | POST "/api/embed" [GIN] 2025/03/28 - 11:11:59 | 200 | 184.7041ms | 10.29.1.125 | POST "/api/embed" [GIN] 2025/03/28 - 11:11:59 | 200 | 170.5567ms | 10.29.1.125 | POST "/api/embed" [GIN] 2025/03/28 - 11:11:59 | 200 | 174.865ms | 10.29.1.125 | POST "/api/embed" [GIN] 2025/03/28 - 11:12:11 | 200 | 182.0829ms | 10.29.1.125 | POST "/api/embed" [GIN] 2025/03/28 - 11:12:12 | 200 | 324.4937ms | 10.29.1.125 | POST "/api/embed" [GIN] 2025/03/28 - 11:12:12 | 200 | 148.9159ms | 10.29.1.125 | POST "/api/embed" [GIN] 2025/03/28 - 11:12:12 | 200 | 106.9827ms | 10.29.1.125 | POST "/api/embed" [GIN] 2025/03/28 - 11:12:12 | 200 | 122.7874ms | 10.29.1.125 | POST "/api/embed" [GIN] 2025/03/28 - 11:12:12 | 200 | 125.8575ms | 10.29.1.125 | POST "/api/embed" [GIN] 2025/03/28 - 11:12:12 | 200 | 130.3733ms | 10.29.1.125 | POST "/api/embed" [GIN] 2025/03/28 - 11:12:12 | 200 | 122.163ms | 10.29.1.125 | POST "/api/embed" [GIN] 2025/03/28 - 11:12:13 | 200 | 116.2861ms | 10.29.1.125 | POST "/api/embed" [GIN] 2025/03/28 - 11:12:13 | 200 | 122.8919ms | 10.29.1.125 | POST "/api/embed" [GIN] 2025/03/28 - 11:12:13 | 200 | 136.2746ms | 10.29.1.125 | POST "/api/embed" [GIN] 2025/03/28 - 11:12:13 | 200 | 128.3028ms | 10.29.1.125 | POST "/api/embed" [GIN] 2025/03/28 - 11:12:13 | 200 | 110.0891ms | 10.29.1.125 | POST "/api/embed" [GIN] 2025/03/28 - 11:12:13 | 200 | 122.4463ms | 10.29.1.125 | POST "/api/embed" [GIN] 2025/03/28 - 11:12:14 | 200 | 124.8436ms | 10.29.1.125 | POST "/api/embed" [GIN] 2025/03/28 - 11:12:14 | 200 | 119.9132ms | 10.29.1.125 | POST "/api/embed" [GIN] 2025/03/28 - 11:12:14 | 200 | 128.8288ms | 10.29.1.125 | POST "/api/embed" [GIN] 2025/03/28 - 11:12:14 | 200 | 125.7882ms | 10.29.1.125 | POST "/api/embed" [GIN] 2025/03/28 - 11:12:14 | 200 | 123.6601ms | 10.29.1.125 | POST "/api/embed" [GIN] 2025/03/28 - 11:12:14 | 200 | 111.2645ms | 10.29.1.125 | POST "/api/embed" [GIN] 2025/03/28 - 11:12:14 | 200 | 129.1993ms | 10.29.1.125 | POST "/api/embed" [GIN] 2025/03/28 - 11:12:15 | 200 | 123.9483ms | 10.29.1.125 | POST "/api/embed" [GIN] 2025/03/28 - 11:13:10 | 200 | 3.4333857s | 10.29.1.125 | POST "/api/embed" [GIN] 2025/03/28 - 11:14:30 | 200 | 3.6304015s | 10.29.1.125 | POST "/api/embed" [GIN] 2025/03/28 - 11:17:40 | 200 | 0s | 127.0.0.1 | HEAD "/" [GIN] 2025/03/28 - 11:18:25 | 200 | 522µs | 127.0.0.1 | GET "/api/ps" 2. C:\Users\liuyuan>ollama ps NAME ID SIZE PROCESSOR UNTIL bge-m3:latest 790764642607 1.7 GB 100% GPU 24 hours from now 3. after 11:14:30, I send a sentence to ollama again, it cannot return the result to me. But when I check the running model information, ollama can return me the result successfully
GiteaMirror commented 2026-04-22 13:26:46 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Mar 28, 2025):

[GIN] 2025/03/28 - 11:12:15 | 200 | 123.9483ms | 10.29.1.125 | POST "/api/embed"
[GIN] 2025/03/28 - 11:13:10 | 200 | 3.4333857s | 10.29.1.125 | POST "/api/embed"
[GIN] 2025/03/28 - 11:14:30 | 200 | 3.6304015s | 10.29.1.125 | POST "/api/embed"

The model got slow at the end. Other than that, the log looks normal. Set OLLAMA_DEBUG=1 in the server environment, there might be something relevant in the more detailed log.

<!-- gh-comment-id:2761183392 --> @rick-github commented on GitHub (Mar 28, 2025): ``` [GIN] 2025/03/28 - 11:12:15 | 200 | 123.9483ms | 10.29.1.125 | POST "/api/embed" [GIN] 2025/03/28 - 11:13:10 | 200 | 3.4333857s | 10.29.1.125 | POST "/api/embed" [GIN] 2025/03/28 - 11:14:30 | 200 | 3.6304015s | 10.29.1.125 | POST "/api/embed" ``` The model got slow at the end. Other than that, the log looks normal. Set `OLLAMA_DEBUG=1` in the server environment, there might be something relevant in the more detailed log.
GiteaMirror commented 2026-04-22 13:26:46 -05:00
Author
Owner
Copy Link

@Liuyuan0803 commented on GitHub (Apr 11, 2025):

more logs:

server.log:

time=2025-04-11T15:38:36.581+08:00 level=INFO source=server.go:619 msg="llama runner started in 3.54 seconds"
time=2025-04-11T15:38:36.581+08:00 level=DEBUG source=sched.go:464 msg="finished setting up runner" model=D:\ly\Ollama\Models\blobs\sha256-2bada8a7450677000f678be90653b85d364de7db25eb5ea54136ada5f3933730
time=2025-04-11T15:38:36.582+08:00 level=DEBUG source=sched.go:468 msg="context for request finished"
time=2025-04-11T15:38:36.582+08:00 level=DEBUG source=sched.go:341 msg="runner with non-zero duration has gone idle, adding timer" modelPath=D:\ly\Ollama\Models\blobs\sha256-2bada8a7450677000f678be90653b85d364de7db25eb5ea54136ada5f3933730 duration=24h0m0s
time=2025-04-11T15:38:36.582+08:00 level=DEBUG source=sched.go:359 msg="after processing request finished event" modelPath=D:\ly\Ollama\Models\blobs\sha256-2bada8a7450677000f678be90653b85d364de7db25eb5ea54136ada5f3933730 refCount=0
[GIN] 2025/04/11 - 15:38:36 | 200 | 4.01209s | 127.0.0.1 | POST "/api/generate"
time=2025-04-11T15:39:41.107+08:00 level=DEBUG source=sched.go:577 msg="evaluating already loaded" model=D:\ly\Ollama\Models\blobs\sha256-2bada8a7450677000f678be90653b85d364de7db25eb5ea54136ada5f3933730
time=2025-04-11T15:39:41.114+08:00 level=DEBUG source=routes.go:1522 msg="chat request" images=0 prompt="<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n<|im_start|>user\n用Java写一个费纳波切数列<|im_end|>\n<|im_start|>assistant\n"
time=2025-04-11T15:39:41.120+08:00 level=DEBUG source=cache.go:104 msg="loading cache slot" id=0 cache=0 prompt=39 used=0 remaining=39
[GIN] 2025/04/11 - 15:39:44 | 200 | 3.782699s | 127.0.0.1 | POST "/api/chat"
time=2025-04-11T15:39:44.847+08:00 level=DEBUG source=sched.go:409 msg="context for request finished"
time=2025-04-11T15:39:44.847+08:00 level=DEBUG source=sched.go:341 msg="runner with non-zero duration has gone idle, adding timer" modelPath=D:\ly\Ollama\Models\blobs\sha256-2bada8a7450677000f678be90653b85d364de7db25eb5ea54136ada5f3933730 duration=24h0m0s
time=2025-04-11T15:39:44.847+08:00 level=DEBUG source=sched.go:359 msg="after processing request finished event" modelPath=D:\ly\Ollama\Models\blobs\sha256-2bada8a7450677000f678be90653b85d364de7db25eb5ea54136ada5f3933730 refCount=0
time=2025-04-11T15:41:06.490+08:00 level=DEBUG source=sched.go:577 msg="evaluating already loaded" model=D:\ly\Ollama\Models\blobs\sha256-2bada8a7450677000f678be90653b85d364de7db25eb5ea54136ada5f3933730
time=2025-04-11T15:41:06.510+08:00 level=DEBUG source=routes.go:1522 msg="chat request" images=0 prompt="<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n<|im_start|>user\n用Java写一个费纳波切数列<|im_end|>\n<|im_start|>assistant\n当然可以！斐波那契数列是一个非常经典的序列，其特点是每个数字是前两个数字的和。下面我将提供一个简单的 Java 程序来生成斐波那契数列。这个程序将允许用户输入想要生成的斐波那契数的数量。\n\njava\nimport java.util.Scanner;\n\npublic class FibonacciSequence {\n public static void main(String[] args) {\n Scanner scanner = new Scanner(System.in);\n \n // 获取用户输入，即要输出的斐波那契数列项的数量\n System.out.print(\"请输入您想要生成的斐波那契数列项的数量: \");\n int n = scanner.nextInt();\n \n if (n <= 0) {\n System.out.println(\"请输入一个正整数\");\n } else {\n // 初始化前两个斐波那契数为0和1\n long first = 0;\n long second = 1;\n\n // 输出斐波那契数列的前n项\n for (int i = 0; i < n; i++) {\n System.out.print(first + \" \");\n // 更新两个前驱数\n long next = first + second;\n first = second;\n second = next;\n }\n }\n\n scanner.close();\n }\n}\n\n\n这个程序首先通过 Scanner 类获取用户输入的项数，然后使用一个简单的循环来生成并打印出相应的斐波那契数列。这里我们定义了两个变量 first 和 second 来分别存储当前和下一个斐波那契数值。\n\n希望这段代码对你有所帮助！如果你有任何其他问题或需要进一步的帮助，请随时告诉我。<|im_end|>\n<|im_start|>user\n用python写一段<|im_end|>\n<|im_start|>assistant\n"
time=2025-04-11T15:41:06.521+08:00 level=DEBUG source=cache.go:104 msg="loading cache slot" id=0 cache=387 prompt=401 used=387 remaining=14
[GIN] 2025/04/11 - 15:41:11 | 200 | 4.7855432s | 127.0.0.1 | POST "/api/chat"
time=2025-04-11T15:41:11.236+08:00 level=DEBUG source=sched.go:409 msg="context for request finished"
time=2025-04-11T15:41:11.236+08:00 level=DEBUG source=sched.go:341 msg="runner with non-zero duration has gone idle, adding timer" modelPath=D:\ly\Ollama\Models\blobs\sha256-2bada8a7450677000f678be90653b85d364de7db25eb5ea54136ada5f3933730 duration=24h0m0s
time=2025-04-11T15:41:11.236+08:00 level=DEBUG source=sched.go:359 msg="after processing request finished event" modelPath=D:\ly\Ollama\Models\blobs\sha256-2bada8a7450677000f678be90653b85d364de7db25eb5ea54136ada5f3933730 refCount=0

app.log:

time=2025-04-11T15:36:19.867+08:00 level=INFO source=server.go:141 msg="starting server..."
time=2025-04-11T15:36:19.868+08:00 level=WARN source=logging.go:76 msg="Failed to rotate log" older=C:\Users\liuyuan\AppData\Local\Ollama\server-1.log newer=C:\Users\liuyuan\AppData\Local\Ollama\server.log error="rename C:\Users\liuyuan\AppData\Local\Ollama\server.log C:\Users\liuyuan\AppData\Local\Ollama\server-1.log: The process cannot access the file because it is being used by another process."
time=2025-04-11T15:36:19.869+08:00 level=ERROR source=server.go:145 msg="failed to start server failed to start server context canceled"
time=2025-04-11T15:36:47.659+08:00 level=DEBUG source=eventloop.go:145 msg="unmanaged app message, lParm: 0x204"
time=2025-04-11T15:36:48.497+08:00 level=DEBUG source=lifecycle.go:38 msg="quit called"
time=2025-04-11T15:36:48.590+08:00 level=INFO source=lifecycle.go:89 msg="Waiting for ollama server to shutdown..."
time=2025-04-11T15:36:53.056+08:00 level=INFO source=logging.go:50 msg="ollama app started"
time=2025-04-11T15:36:53.056+08:00 level=INFO source=lifecycle.go:19 msg="app config" env="map[CUDA_VISIBLE_DEVICES:GPU-d8040dfd-0bc8-ad27-6eaf-8a27a2b07beb GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:2048 OLLAMA_DEBUG:true OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://0.0.0.0:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:24h0m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:D:\ly\Ollama\Models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE: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://* vscode-file://*] OLLAMA_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES:]"
time=2025-04-11T15:36:53.112+08:00 level=DEBUG source=store.go:60 msg="loaded existing store C:\Users\liuyuan\AppData\Local\Ollama\config.json - ID: 0224cbd5-1cc6-46b1-9273-38ed3e0917c8"
time=2025-04-11T15:36:53.113+08:00 level=DEBUG source=lifecycle.go:68 msg="Not first time, skipping first run notification"
time=2025-04-11T15:36:53.112+08:00 level=DEBUG source=lifecycle.go:34 msg="starting callback loop"
time=2025-04-11T15:36:53.131+08:00 level=DEBUG source=server.go:181 msg="heartbeat from server: Head "http://0.0.0.0:11434/": EOF"
time=2025-04-11T15:36:53.131+08:00 level=INFO source=server.go:182 msg="unable to connect to server"
time=2025-04-11T15:36:53.131+08:00 level=DEBUG source=eventloop.go:22 msg="starting event handling loop"
time=2025-04-11T15:36:53.131+08:00 level=INFO source=server.go:141 msg="starting server..."
time=2025-04-11T15:36:53.132+08:00 level=WARN source=logging.go:76 msg="Failed to rotate log" older=C:\Users\liuyuan\AppData\Local\Ollama\server-1.log newer=C:\Users\liuyuan\AppData\Local\Ollama\server.log error="rename C:\Users\liuyuan\AppData\Local\Ollama\server.log C:\Users\liuyuan\AppData\Local\Ollama\server-1.log: The process cannot access the file because it is being used by another process."
time=2025-04-11T15:36:53.151+08:00 level=INFO source=server.go:127 msg="started ollama server with pid 20520"
time=2025-04-11T15:36:53.151+08:00 level=INFO source=server.go:129 msg="ollama server logs C:\Users\liuyuan\AppData\Local\Ollama\server.log"
time=2025-04-11T15:36:53.431+08:00 level=INFO source=server.go:158 msg="server shutdown with exit code 0"
time=2025-04-11T15:36:53.431+08:00 level=INFO source=lifecycle.go:93 msg="Ollama app exiting"
time=2025-04-11T15:36:56.138+08:00 level=DEBUG source=updater.go:74 msg="checking for available update" requestURL="https://ollama.com/api/update?arch=amd64&nonce=6c_mgc1SQghAgjwNmP0vOg&os=windows&ts=1744357016&version=0.6.5"
time=2025-04-11T15:36:56.279+08:00 level=DEBUG source=logging_windows.go:12 msg="viewing logs with start C:\Users\liuyuan\AppData\Local\Ollama"
time=2025-04-11T15:36:56.831+08:00 level=DEBUG source=updater.go:83 msg="check update response 204 (current version is up to date)"
time=2025-04-11T15:37:12.194+08:00 level=INFO source=server.go:141 msg="starting server..."
time=2025-04-11T15:37:12.196+08:00 level=WARN source=logging.go:76 msg="Failed to rotate log" older=C:\Users\liuyuan\AppData\Local\Ollama\server-1.log newer=C:\Users\liuyuan\AppData\Local\Ollama\server.log error="rename C:\Users\liuyuan\AppData\Local\Ollama\server.log C:\Users\liuyuan\AppData\Local\Ollama\server-1.log: The process cannot access the file because it is being used by another process."
time=2025-04-11T15:37:12.196+08:00 level=ERROR source=server.go:145 msg="failed to start server failed to start server context canceled"
time=2025-04-11T15:38:43.370+08:00 level=INFO source=server.go:141 msg="starting server..."
time=2025-04-11T15:38:43.372+08:00 level=WARN source=logging.go:76 msg="Failed to rotate log" older=C:\Users\liuyuan\AppData\Local\Ollama\server-1.log newer=C:\Users\liuyuan\AppData\Local\Ollama\server.log error="rename C:\Users\liuyuan\AppData\Local\Ollama\server.log C:\Users\liuyuan\AppData\Local\Ollama\server-1.log: The process cannot access the file because it is being used by another process."
time=2025-04-11T15:38:43.373+08:00 level=ERROR source=server.go:145 msg="failed to start server failed to start server context canceled"
time=2025-04-11T15:39:37.197+08:00 level=INFO source=server.go:141 msg="starting server..."
time=2025-04-11T15:39:37.198+08:00 level=WARN source=logging.go:76 msg="Failed to rotate log" older=C:\Users\liuyuan\AppData\Local\Ollama\server-1.log newer=C:\Users\liuyuan\AppData\Local\Ollama\server.log error="rename C:\Users\liuyuan\AppData\Local\Ollama\server.log C:\Users\liuyuan\AppData\Local\Ollama\server-1.log: The process cannot access the file because it is being used by another process."
time=2025-04-11T15:39:37.200+08:00 level=ERROR source=server.go:145 msg="failed to start server failed to start server context canceled"
time=2025-04-11T15:41:07.374+08:00 level=INFO source=server.go:141 msg="starting server..."
time=2025-04-11T15:41:07.376+08:00 level=WARN source=logging.go:76 msg="Failed to rotate log" older=C:\Users\liuyuan\AppData\Local\Ollama\server-1.log newer=C:\Users\liuyuan\AppData\Local\Ollama\server.log error="rename C:\Users\liuyuan\AppData\Local\Ollama\server.log C:\Users\liuyuan\AppData\Local\Ollama\server-1.log: The process cannot access the file because it is being used by another process."
time=2025-04-11T15:41:07.377+08:00 level=ERROR source=server.go:145 msg="failed to start server failed to start server context canceled"
time=2025-04-11T15:42:02.702+08:00 level=INFO source=server.go:141 msg="starting server..."
time=2025-04-11T15:42:02.703+08:00 level=WARN source=logging.go:76 msg="Failed to rotate log" older=C:\Users\liuyuan\AppData\Local\Ollama\server-1.log newer=C:\Users\liuyuan\AppData\Local\Ollama\server.log error="rename C:\Users\liuyuan\AppData\Local\Ollama\server.log C:\Users\liuyuan\AppData\Local\Ollama\server-1.log: The process cannot access the file because it is being used by another process."
time=2025-04-11T15:42:02.703+08:00 level=ERROR source=server.go:145 msg="failed to start server failed to start server context canceled"
time=2025-04-11T15:43:31.878+08:00 level=INFO source=server.go:141 msg="starting server..."
time=2025-04-11T15:43:31.880+08:00 level=WARN source=logging.go:76 msg="Failed to rotate log" older=C:\Users\liuyuan\AppData\Local\Ollama\server-1.log newer=C:\Users\liuyuan\AppData\Local\Ollama\server.log error="rename C:\Users\liuyuan\AppData\Local\Ollama\server.log C:\Users\liuyuan\AppData\Local\Ollama\server-1.log: The process cannot access the file because it is being used by another process."
time=2025-04-11T15:43:31.880+08:00 level=ERROR source=server.go:145 msg="failed to start server failed to start server context canceled"
time=2025-04-11T15:44:28.704+08:00 level=INFO source=server.go:141 msg="starting server..."
time=2025-04-11T15:44:28.705+08:00 level=WARN source=logging.go:76 msg="Failed to rotate log" older=C:\Users\liuyuan\AppData\Local\Ollama\server-1.log newer=C:\Users\liuyuan\AppData\Local\Ollama\server.log error="rename C:\Users\liuyuan\AppData\Local\Ollama\server.log C:\Users\liuyuan\AppData\Local\Ollama\server-1.log: The process cannot access the file because it is being used by another process."
time=2025-04-11T15:44:28.707+08:00 level=ERROR source=server.go:145 msg="failed to start server failed to start server context canceled"
time=2025-04-11T15:45:56.882+08:00 level=INFO source=server.go:141 msg="starting server..."
time=2025-04-11T15:45:56.884+08:00 level=WARN source=logging.go:76 msg="Failed to rotate log" older=C:\Users\liuyuan\AppData\Local\Ollama\server-1.log newer=C:\Users\liuyuan\AppData\Local\Ollama\server.log error="rename C:\Users\liuyuan\AppData\Local\Ollama\server.log C:\Users\liuyuan\AppData\Local\Ollama\server-1.log: The process cannot access the file because it is being used by another process."
time=2025-04-11T15:45:56.885+08:00 level=ERROR source=server.go:145 msg="failed to start server failed to start server context canceled"

<!-- gh-comment-id:2796121841 --> @Liuyuan0803 commented on GitHub (Apr 11, 2025): # more logs: ## server.log: time=2025-04-11T15:38:36.581+08:00 level=INFO source=server.go:619 msg="llama runner started in 3.54 seconds" time=2025-04-11T15:38:36.581+08:00 level=DEBUG source=sched.go:464 msg="finished setting up runner" model=D:\ly\Ollama\Models\blobs\sha256-2bada8a7450677000f678be90653b85d364de7db25eb5ea54136ada5f3933730 time=2025-04-11T15:38:36.582+08:00 level=DEBUG source=sched.go:468 msg="context for request finished" time=2025-04-11T15:38:36.582+08:00 level=DEBUG source=sched.go:341 msg="runner with non-zero duration has gone idle, adding timer" modelPath=D:\ly\Ollama\Models\blobs\sha256-2bada8a7450677000f678be90653b85d364de7db25eb5ea54136ada5f3933730 duration=24h0m0s time=2025-04-11T15:38:36.582+08:00 level=DEBUG source=sched.go:359 msg="after processing request finished event" modelPath=D:\ly\Ollama\Models\blobs\sha256-2bada8a7450677000f678be90653b85d364de7db25eb5ea54136ada5f3933730 refCount=0 [GIN] 2025/04/11 - 15:38:36 | 200 | 4.01209s | 127.0.0.1 | POST "/api/generate" time=2025-04-11T15:39:41.107+08:00 level=DEBUG source=sched.go:577 msg="evaluating already loaded" model=D:\ly\Ollama\Models\blobs\sha256-2bada8a7450677000f678be90653b85d364de7db25eb5ea54136ada5f3933730 time=2025-04-11T15:39:41.114+08:00 level=DEBUG source=routes.go:1522 msg="chat request" images=0 prompt="<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n<|im_start|>user\n用Java写一个费纳波切数列<|im_end|>\n<|im_start|>assistant\n" time=2025-04-11T15:39:41.120+08:00 level=DEBUG source=cache.go:104 msg="loading cache slot" id=0 cache=0 prompt=39 used=0 remaining=39 [GIN] 2025/04/11 - 15:39:44 | 200 | 3.782699s | 127.0.0.1 | POST "/api/chat" time=2025-04-11T15:39:44.847+08:00 level=DEBUG source=sched.go:409 msg="context for request finished" time=2025-04-11T15:39:44.847+08:00 level=DEBUG source=sched.go:341 msg="runner with non-zero duration has gone idle, adding timer" modelPath=D:\ly\Ollama\Models\blobs\sha256-2bada8a7450677000f678be90653b85d364de7db25eb5ea54136ada5f3933730 duration=24h0m0s time=2025-04-11T15:39:44.847+08:00 level=DEBUG source=sched.go:359 msg="after processing request finished event" modelPath=D:\ly\Ollama\Models\blobs\sha256-2bada8a7450677000f678be90653b85d364de7db25eb5ea54136ada5f3933730 refCount=0 time=2025-04-11T15:41:06.490+08:00 level=DEBUG source=sched.go:577 msg="evaluating already loaded" model=D:\ly\Ollama\Models\blobs\sha256-2bada8a7450677000f678be90653b85d364de7db25eb5ea54136ada5f3933730 time=2025-04-11T15:41:06.510+08:00 level=DEBUG source=routes.go:1522 msg="chat request" images=0 prompt="<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n<|im_start|>user\n用Java写一个费纳波切数列<|im_end|>\n<|im_start|>assistant\n当然可以！斐波那契数列是一个非常经典的序列，其特点是每个数字是前两个数字的和。下面我将提供一个简单的 Java 程序来生成斐波那契数列。这个程序将允许用户输入想要生成的斐波那契数的数量。\n\n```java\nimport java.util.Scanner;\n\npublic class FibonacciSequence {\n public static void main(String[] args) {\n Scanner scanner = new Scanner(System.in);\n \n // 获取用户输入，即要输出的斐波那契数列项的数量\n System.out.print(\"请输入您想要生成的斐波那契数列项的数量: \");\n int n = scanner.nextInt();\n \n if (n <= 0) {\n System.out.println(\"请输入一个正整数\");\n } else {\n // 初始化前两个斐波那契数为0和1\n long first = 0;\n long second = 1;\n\n // 输出斐波那契数列的前n项\n for (int i = 0; i < n; i++) {\n System.out.print(first + \" \");\n // 更新两个前驱数\n long next = first + second;\n first = second;\n second = next;\n }\n }\n\n scanner.close();\n }\n}\n```\n\n这个程序首先通过 `Scanner` 类获取用户输入的项数，然后使用一个简单的循环来生成并打印出相应的斐波那契数列。这里我们定义了两个变量 `first` 和 `second` 来分别存储当前和下一个斐波那契数值。\n\n希望这段代码对你有所帮助！如果你有任何其他问题或需要进一步的帮助，请随时告诉我。<|im_end|>\n<|im_start|>user\n用python写一段<|im_end|>\n<|im_start|>assistant\n" time=2025-04-11T15:41:06.521+08:00 level=DEBUG source=cache.go:104 msg="loading cache slot" id=0 cache=387 prompt=401 used=387 remaining=14 [GIN] 2025/04/11 - 15:41:11 | 200 | 4.7855432s | 127.0.0.1 | POST "/api/chat" time=2025-04-11T15:41:11.236+08:00 level=DEBUG source=sched.go:409 msg="context for request finished" time=2025-04-11T15:41:11.236+08:00 level=DEBUG source=sched.go:341 msg="runner with non-zero duration has gone idle, adding timer" modelPath=D:\ly\Ollama\Models\blobs\sha256-2bada8a7450677000f678be90653b85d364de7db25eb5ea54136ada5f3933730 duration=24h0m0s time=2025-04-11T15:41:11.236+08:00 level=DEBUG source=sched.go:359 msg="after processing request finished event" modelPath=D:\ly\Ollama\Models\blobs\sha256-2bada8a7450677000f678be90653b85d364de7db25eb5ea54136ada5f3933730 refCount=0 ## app.log: time=2025-04-11T15:36:19.867+08:00 level=INFO source=server.go:141 msg="starting server..." time=2025-04-11T15:36:19.868+08:00 level=WARN source=logging.go:76 msg="Failed to rotate log" older=C:\Users\liuyuan\AppData\Local\Ollama\server-1.log newer=C:\Users\liuyuan\AppData\Local\Ollama\server.log error="rename C:\\Users\\liuyuan\\AppData\\Local\\Ollama\\server.log C:\\Users\\liuyuan\\AppData\\Local\\Ollama\\server-1.log: The process cannot access the file because it is being used by another process." time=2025-04-11T15:36:19.869+08:00 level=ERROR source=server.go:145 msg="failed to start server failed to start server context canceled" time=2025-04-11T15:36:47.659+08:00 level=DEBUG source=eventloop.go:145 msg="unmanaged app message, lParm: 0x204" time=2025-04-11T15:36:48.497+08:00 level=DEBUG source=lifecycle.go:38 msg="quit called" time=2025-04-11T15:36:48.590+08:00 level=INFO source=lifecycle.go:89 msg="Waiting for ollama server to shutdown..." time=2025-04-11T15:36:53.056+08:00 level=INFO source=logging.go:50 msg="ollama app started" time=2025-04-11T15:36:53.056+08:00 level=INFO source=lifecycle.go:19 msg="app config" env="map[CUDA_VISIBLE_DEVICES:GPU-d8040dfd-0bc8-ad27-6eaf-8a27a2b07beb GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:2048 OLLAMA_DEBUG:true OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://0.0.0.0:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:24h0m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:D:\\ly\\Ollama\\Models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE: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://* vscode-file://*] OLLAMA_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES:]" time=2025-04-11T15:36:53.112+08:00 level=DEBUG source=store.go:60 msg="loaded existing store C:\\Users\\liuyuan\\AppData\\Local\\Ollama\\config.json - ID: 0224cbd5-1cc6-46b1-9273-38ed3e0917c8" time=2025-04-11T15:36:53.113+08:00 level=DEBUG source=lifecycle.go:68 msg="Not first time, skipping first run notification" time=2025-04-11T15:36:53.112+08:00 level=DEBUG source=lifecycle.go:34 msg="starting callback loop" time=2025-04-11T15:36:53.131+08:00 level=DEBUG source=server.go:181 msg="heartbeat from server: Head \"http://0.0.0.0:11434/\": EOF" time=2025-04-11T15:36:53.131+08:00 level=INFO source=server.go:182 msg="unable to connect to server" time=2025-04-11T15:36:53.131+08:00 level=DEBUG source=eventloop.go:22 msg="starting event handling loop" time=2025-04-11T15:36:53.131+08:00 level=INFO source=server.go:141 msg="starting server..." time=2025-04-11T15:36:53.132+08:00 level=WARN source=logging.go:76 msg="Failed to rotate log" older=C:\Users\liuyuan\AppData\Local\Ollama\server-1.log newer=C:\Users\liuyuan\AppData\Local\Ollama\server.log error="rename C:\\Users\\liuyuan\\AppData\\Local\\Ollama\\server.log C:\\Users\\liuyuan\\AppData\\Local\\Ollama\\server-1.log: The process cannot access the file because it is being used by another process." time=2025-04-11T15:36:53.151+08:00 level=INFO source=server.go:127 msg="started ollama server with pid 20520" time=2025-04-11T15:36:53.151+08:00 level=INFO source=server.go:129 msg="ollama server logs C:\\Users\\liuyuan\\AppData\\Local\\Ollama\\server.log" time=2025-04-11T15:36:53.431+08:00 level=INFO source=server.go:158 msg="server shutdown with exit code 0" time=2025-04-11T15:36:53.431+08:00 level=INFO source=lifecycle.go:93 msg="Ollama app exiting" time=2025-04-11T15:36:56.138+08:00 level=DEBUG source=updater.go:74 msg="checking for available update" requestURL="https://ollama.com/api/update?arch=amd64&nonce=6c_mgc1SQghAgjwNmP0vOg&os=windows&ts=1744357016&version=0.6.5" time=2025-04-11T15:36:56.279+08:00 level=DEBUG source=logging_windows.go:12 msg="viewing logs with start C:\\Users\\liuyuan\\AppData\\Local\\Ollama" time=2025-04-11T15:36:56.831+08:00 level=DEBUG source=updater.go:83 msg="check update response 204 (current version is up to date)" time=2025-04-11T15:37:12.194+08:00 level=INFO source=server.go:141 msg="starting server..." time=2025-04-11T15:37:12.196+08:00 level=WARN source=logging.go:76 msg="Failed to rotate log" older=C:\Users\liuyuan\AppData\Local\Ollama\server-1.log newer=C:\Users\liuyuan\AppData\Local\Ollama\server.log error="rename C:\\Users\\liuyuan\\AppData\\Local\\Ollama\\server.log C:\\Users\\liuyuan\\AppData\\Local\\Ollama\\server-1.log: The process cannot access the file because it is being used by another process." time=2025-04-11T15:37:12.196+08:00 level=ERROR source=server.go:145 msg="failed to start server failed to start server context canceled" time=2025-04-11T15:38:43.370+08:00 level=INFO source=server.go:141 msg="starting server..." time=2025-04-11T15:38:43.372+08:00 level=WARN source=logging.go:76 msg="Failed to rotate log" older=C:\Users\liuyuan\AppData\Local\Ollama\server-1.log newer=C:\Users\liuyuan\AppData\Local\Ollama\server.log error="rename C:\\Users\\liuyuan\\AppData\\Local\\Ollama\\server.log C:\\Users\\liuyuan\\AppData\\Local\\Ollama\\server-1.log: The process cannot access the file because it is being used by another process." time=2025-04-11T15:38:43.373+08:00 level=ERROR source=server.go:145 msg="failed to start server failed to start server context canceled" time=2025-04-11T15:39:37.197+08:00 level=INFO source=server.go:141 msg="starting server..." time=2025-04-11T15:39:37.198+08:00 level=WARN source=logging.go:76 msg="Failed to rotate log" older=C:\Users\liuyuan\AppData\Local\Ollama\server-1.log newer=C:\Users\liuyuan\AppData\Local\Ollama\server.log error="rename C:\\Users\\liuyuan\\AppData\\Local\\Ollama\\server.log C:\\Users\\liuyuan\\AppData\\Local\\Ollama\\server-1.log: The process cannot access the file because it is being used by another process." time=2025-04-11T15:39:37.200+08:00 level=ERROR source=server.go:145 msg="failed to start server failed to start server context canceled" time=2025-04-11T15:41:07.374+08:00 level=INFO source=server.go:141 msg="starting server..." time=2025-04-11T15:41:07.376+08:00 level=WARN source=logging.go:76 msg="Failed to rotate log" older=C:\Users\liuyuan\AppData\Local\Ollama\server-1.log newer=C:\Users\liuyuan\AppData\Local\Ollama\server.log error="rename C:\\Users\\liuyuan\\AppData\\Local\\Ollama\\server.log C:\\Users\\liuyuan\\AppData\\Local\\Ollama\\server-1.log: The process cannot access the file because it is being used by another process." time=2025-04-11T15:41:07.377+08:00 level=ERROR source=server.go:145 msg="failed to start server failed to start server context canceled" time=2025-04-11T15:42:02.702+08:00 level=INFO source=server.go:141 msg="starting server..." time=2025-04-11T15:42:02.703+08:00 level=WARN source=logging.go:76 msg="Failed to rotate log" older=C:\Users\liuyuan\AppData\Local\Ollama\server-1.log newer=C:\Users\liuyuan\AppData\Local\Ollama\server.log error="rename C:\\Users\\liuyuan\\AppData\\Local\\Ollama\\server.log C:\\Users\\liuyuan\\AppData\\Local\\Ollama\\server-1.log: The process cannot access the file because it is being used by another process." time=2025-04-11T15:42:02.703+08:00 level=ERROR source=server.go:145 msg="failed to start server failed to start server context canceled" time=2025-04-11T15:43:31.878+08:00 level=INFO source=server.go:141 msg="starting server..." time=2025-04-11T15:43:31.880+08:00 level=WARN source=logging.go:76 msg="Failed to rotate log" older=C:\Users\liuyuan\AppData\Local\Ollama\server-1.log newer=C:\Users\liuyuan\AppData\Local\Ollama\server.log error="rename C:\\Users\\liuyuan\\AppData\\Local\\Ollama\\server.log C:\\Users\\liuyuan\\AppData\\Local\\Ollama\\server-1.log: The process cannot access the file because it is being used by another process." time=2025-04-11T15:43:31.880+08:00 level=ERROR source=server.go:145 msg="failed to start server failed to start server context canceled" time=2025-04-11T15:44:28.704+08:00 level=INFO source=server.go:141 msg="starting server..." time=2025-04-11T15:44:28.705+08:00 level=WARN source=logging.go:76 msg="Failed to rotate log" older=C:\Users\liuyuan\AppData\Local\Ollama\server-1.log newer=C:\Users\liuyuan\AppData\Local\Ollama\server.log error="rename C:\\Users\\liuyuan\\AppData\\Local\\Ollama\\server.log C:\\Users\\liuyuan\\AppData\\Local\\Ollama\\server-1.log: The process cannot access the file because it is being used by another process." time=2025-04-11T15:44:28.707+08:00 level=ERROR source=server.go:145 msg="failed to start server failed to start server context canceled" time=2025-04-11T15:45:56.882+08:00 level=INFO source=server.go:141 msg="starting server..." time=2025-04-11T15:45:56.884+08:00 level=WARN source=logging.go:76 msg="Failed to rotate log" older=C:\Users\liuyuan\AppData\Local\Ollama\server-1.log newer=C:\Users\liuyuan\AppData\Local\Ollama\server.log error="rename C:\\Users\\liuyuan\\AppData\\Local\\Ollama\\server.log C:\\Users\\liuyuan\\AppData\\Local\\Ollama\\server-1.log: The process cannot access the file because it is being used by another process." time=2025-04-11T15:45:56.885+08:00 level=ERROR source=server.go:145 msg="failed to start server failed to start server context canceled"
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label bug needs more info
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#32309
Delete Branch "%!s()"

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