github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 16:11:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #10927] LLM is stuck in an infinite loop of thinking.大模型陷入了无限循环思考 #7190

New Issue
Closed
opened 2026-04-12 19:11:19 -05:00 by GiteaMirror · 4 comments
GiteaMirror commented 2026-04-12 19:11:19 -05:00
Owner
Copy Link

Originally created by @Djooxx on GitHub (May 31, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/10927

What is the issue?

windows 11 / 5060ti 16g / ollama v0.9 / cuda 12.8 / model: qwen3:14b (bdbd181c33f2)
English:
Even if I just sent a simple "hello", its thought process would still loop infinitely.The probability of this happening is very high (>90%).A few days ago, Ollama's official website updated the Qwen3 model, and then this problem occurred.What has been updated in the official website model? Is there any relevant documentation?
Chinese:
即使我只发送了一个简单问候,它的思考过程依然会无限循环,出现这种情况的概率很高(>90%).前几天ollama官网更新了qwen3的模型,之后就有这个问题了.官网的模型更新了什么东西?这个有相关的文档吗?
Image

Image

Relevant log output

time=2025-05-31T15:13:53.300+08:00 level=INFO source=routes.go:1234 msg="server config" env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:4096 OLLAMA_DEBUG:INFO OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:15m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:E:\\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=2025-05-31T15:13:53.404+08:00 level=INFO source=images.go:479 msg="total blobs: 22"
time=2025-05-31T15:13:53.406+08:00 level=INFO source=images.go:486 msg="total unused blobs removed: 0"
time=2025-05-31T15:13:53.409+08:00 level=INFO source=routes.go:1287 msg="Listening on 127.0.0.1:11434 (version 0.9.0)"
time=2025-05-31T15:13:53.410+08:00 level=INFO source=gpu.go:217 msg="looking for compatible GPUs"
time=2025-05-31T15:13:53.412+08:00 level=INFO source=gpu_windows.go:167 msg=packages count=1
time=2025-05-31T15:13:53.412+08:00 level=INFO source=gpu_windows.go:214 msg="" package=0 cores=6 efficiency=0 threads=12
time=2025-05-31T15:13:53.636+08:00 level=INFO source=gpu.go:319 msg="detected OS VRAM overhead" id=GPU-1daaca27-a481-6f45-04cf-dc0f8e9dd26d library=cuda compute=12.0 driver=12.9 name="NVIDIA GeForce RTX 5060 Ti" overhead="404.4 MiB"
time=2025-05-31T15:13:53.640+08:00 level=INFO source=types.go:130 msg="inference compute" id=GPU-1daaca27-a481-6f45-04cf-dc0f8e9dd26d library=cuda variant=v12 compute=12.0 driver=12.9 name="NVIDIA GeForce RTX 5060 Ti" total="15.9 GiB" available="14.7 GiB"
[GIN] 2025/05/31 - 15:14:10 | 200 |            0s |       127.0.0.1 | HEAD     "/"
[GIN] 2025/05/31 - 15:14:10 | 200 |     154.566ms |       127.0.0.1 | POST     "/api/show"
time=2025-05-31T15:14:10.282+08:00 level=INFO source=sched.go:788 msg="new model will fit in available VRAM in single GPU, loading" model=E:\OLLAMA_models\blobs\sha256-a8cc1361f3145dc01f6d77c6c82c9116b9ffe3c97b34716fe20418455876c40e gpu=GPU-1daaca27-a481-6f45-04cf-dc0f8e9dd26d parallel=2 available=15648612352 required="11.2 GiB"
time=2025-05-31T15:14:10.308+08:00 level=INFO source=server.go:135 msg="system memory" total="55.7 GiB" free="48.0 GiB" free_swap="50.7 GiB"
time=2025-05-31T15:14:10.309+08:00 level=INFO source=server.go:168 msg=offload library=cuda layers.requested=-1 layers.model=41 layers.offload=41 layers.split="" memory.available="[14.6 GiB]" memory.gpu_overhead="0 B" memory.required.full="11.2 GiB" memory.required.partial="11.2 GiB" memory.required.kv="1.2 GiB" memory.required.allocations="[11.2 GiB]" memory.weights.total="8.2 GiB" memory.weights.repeating="7.6 GiB" memory.weights.nonrepeating="608.6 MiB" memory.graph.full="1.0 GiB" memory.graph.partial="1.0 GiB"
llama_model_loader: loaded meta data with 27 key-value pairs and 443 tensors from E:\OLLAMA_models\blobs\sha256-a8cc1361f3145dc01f6d77c6c82c9116b9ffe3c97b34716fe20418455876c40e (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              = qwen3
llama_model_loader: - kv   1:                               general.type str              = model
llama_model_loader: - kv   2:                               general.name str              = Qwen3 14B
llama_model_loader: - kv   3:                           general.basename str              = Qwen3
llama_model_loader: - kv   4:                         general.size_label str              = 14B
llama_model_loader: - kv   5:                          qwen3.block_count u32              = 40
llama_model_loader: - kv   6:                       qwen3.context_length u32              = 40960
llama_model_loader: - kv   7:                     qwen3.embedding_length u32              = 5120
llama_model_loader: - kv   8:                  qwen3.feed_forward_length u32              = 17408
llama_model_loader: - kv   9:                 qwen3.attention.head_count u32              = 40
llama_model_loader: - kv  10:              qwen3.attention.head_count_kv u32              = 8
llama_model_loader: - kv  11:                       qwen3.rope.freq_base f32              = 1000000.000000
llama_model_loader: - kv  12:     qwen3.attention.layer_norm_rms_epsilon f32              = 0.000001
llama_model_loader: - kv  13:                 qwen3.attention.key_length u32              = 128
llama_model_loader: - kv  14:               qwen3.attention.value_length u32              = 128
llama_model_loader: - kv  15:                       tokenizer.ggml.model str              = gpt2
llama_model_loader: - kv  16:                         tokenizer.ggml.pre str              = qwen2
llama_model_loader: - kv  17:                      tokenizer.ggml.tokens arr[str,151936]  = ["!", "\"", "#", "$", "%", "&", "'", ...
llama_model_loader: - kv  18:                  tokenizer.ggml.token_type arr[i32,151936]  = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv  19:                      tokenizer.ggml.merges arr[str,151387]  = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
llama_model_loader: - kv  20:                tokenizer.ggml.eos_token_id u32              = 151645
llama_model_loader: - kv  21:            tokenizer.ggml.padding_token_id u32              = 151643
llama_model_loader: - kv  22:                tokenizer.ggml.bos_token_id u32              = 151643
llama_model_loader: - kv  23:               tokenizer.ggml.add_bos_token bool             = false
llama_model_loader: - kv  24:                    tokenizer.chat_template str              = {%- if tools %}\n    {{- '<|im_start|>...
llama_model_loader: - kv  25:               general.quantization_version u32              = 2
llama_model_loader: - kv  26:                          general.file_type u32              = 15
llama_model_loader: - type  f32:  161 tensors
llama_model_loader: - type  f16:   40 tensors
llama_model_loader: - type q4_K:  221 tensors
llama_model_loader: - type q6_K:   21 tensors
print_info: file format = GGUF V3 (latest)
print_info: file type   = Q4_K - Medium
print_info: file size   = 8.63 GiB (5.02 BPW) 
load: special tokens cache size = 26
load: token to piece cache size = 0.9311 MB
print_info: arch             = qwen3
print_info: vocab_only       = 1
print_info: model type       = ?B
print_info: model params     = 14.77 B
print_info: general.name     = Qwen3 14B
print_info: vocab type       = BPE
print_info: n_vocab          = 151936
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=2025-05-31T15:14:10.602+08:00 level=INFO source=server.go:431 msg="starting llama server" cmd="C:\\Users\\qwerd\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --model E:\\OLLAMA_models\\blobs\\sha256-a8cc1361f3145dc01f6d77c6c82c9116b9ffe3c97b34716fe20418455876c40e --ctx-size 8192 --batch-size 512 --n-gpu-layers 41 --threads 6 --no-mmap --parallel 2 --port 51001"
time=2025-05-31T15:14:10.608+08:00 level=INFO source=sched.go:483 msg="loaded runners" count=1
time=2025-05-31T15:14:10.608+08:00 level=INFO source=server.go:591 msg="waiting for llama runner to start responding"
time=2025-05-31T15:14:10.608+08:00 level=INFO source=server.go:625 msg="waiting for server to become available" status="llm server error"
time=2025-05-31T15:14:10.655+08:00 level=INFO source=runner.go:815 msg="starting go runner"
load_backend: loaded CPU backend from C:\Users\qwerd\AppData\Local\Programs\Ollama\lib\ollama\ggml-cpu-haswell.dll
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 5060 Ti, compute capability 12.0, VMM: yes
load_backend: loaded CUDA backend from C:\Users\qwerd\AppData\Local\Programs\Ollama\lib\ollama\cuda_v12\ggml-cuda.dll
time=2025-05-31T15:14:11.915+08:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.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=2025-05-31T15:14:11.917+08:00 level=INFO source=runner.go:874 msg="Server listening on 127.0.0.1:51001"
llama_model_load_from_file_impl: using device CUDA0 (NVIDIA GeForce RTX 5060 Ti) - 15072 MiB free
llama_model_loader: loaded meta data with 27 key-value pairs and 443 tensors from E:\OLLAMA_models\blobs\sha256-a8cc1361f3145dc01f6d77c6c82c9116b9ffe3c97b34716fe20418455876c40e (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              = qwen3
llama_model_loader: - kv   1:                               general.type str              = model
llama_model_loader: - kv   2:                               general.name str              = Qwen3 14B
llama_model_loader: - kv   3:                           general.basename str              = Qwen3
llama_model_loader: - kv   4:                         general.size_label str              = 14B
llama_model_loader: - kv   5:                          qwen3.block_count u32              = 40
llama_model_loader: - kv   6:                       qwen3.context_length u32              = 40960
llama_model_loader: - kv   7:                     qwen3.embedding_length u32              = 5120
llama_model_loader: - kv   8:                  qwen3.feed_forward_length u32              = 17408
llama_model_loader: - kv   9:                 qwen3.attention.head_count u32              = 40
llama_model_loader: - kv  10:              qwen3.attention.head_count_kv u32              = 8
llama_model_loader: - kv  11:                       qwen3.rope.freq_base f32              = 1000000.000000
llama_model_loader: - kv  12:     qwen3.attention.layer_norm_rms_epsilon f32              = 0.000001
llama_model_loader: - kv  13:                 qwen3.attention.key_length u32              = 128
llama_model_loader: - kv  14:               qwen3.attention.value_length u32              = 128
llama_model_loader: - kv  15:                       tokenizer.ggml.model str              = gpt2
llama_model_loader: - kv  16:                         tokenizer.ggml.pre str              = qwen2
llama_model_loader: - kv  17:                      tokenizer.ggml.tokens arr[str,151936]  = ["!", "\"", "#", "$", "%", "&", "'", ...
llama_model_loader: - kv  18:                  tokenizer.ggml.token_type arr[i32,151936]  = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv  19:                      tokenizer.ggml.merges arr[str,151387]  = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
llama_model_loader: - kv  20:                tokenizer.ggml.eos_token_id u32              = 151645
llama_model_loader: - kv  21:            tokenizer.ggml.padding_token_id u32              = 151643
llama_model_loader: - kv  22:                tokenizer.ggml.bos_token_id u32              = 151643
llama_model_loader: - kv  23:               tokenizer.ggml.add_bos_token bool             = false
llama_model_loader: - kv  24:                    tokenizer.chat_template str              = {%- if tools %}\n    {{- '<|im_start|>...
llama_model_loader: - kv  25:               general.quantization_version u32              = 2
llama_model_loader: - kv  26:                          general.file_type u32              = 15
llama_model_loader: - type  f32:  161 tensors
llama_model_loader: - type  f16:   40 tensors
llama_model_loader: - type q4_K:  221 tensors
llama_model_loader: - type q6_K:   21 tensors
print_info: file format = GGUF V3 (latest)
print_info: file type   = Q4_K - Medium
print_info: file size   = 8.63 GiB (5.02 BPW) 
time=2025-05-31T15:14:12.110+08:00 level=INFO source=server.go:625 msg="waiting for server to become available" status="llm server loading model"
load: special tokens cache size = 26
load: token to piece cache size = 0.9311 MB
print_info: arch             = qwen3
print_info: vocab_only       = 0
print_info: n_ctx_train      = 40960
print_info: n_embd           = 5120
print_info: n_layer          = 40
print_info: n_head           = 40
print_info: n_head_kv        = 8
print_info: n_rot            = 128
print_info: n_swa            = 0
print_info: n_swa_pattern    = 1
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: f_attn_scale     = 0.0e+00
print_info: n_ff             = 17408
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  = 40960
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     = Qwen3 14B
print_info: vocab type       = BPE
print_info: n_vocab          = 151936
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 40 repeating layers to GPU
load_tensors: offloading output layer to GPU
load_tensors: offloaded 41/41 layers to GPU
load_tensors:        CUDA0 model buffer size =  8423.47 MiB
load_tensors:          CPU model buffer size =   417.30 MiB
llama_context: constructing llama_context
llama_context: n_seq_max     = 2
llama_context: n_ctx         = 8192
llama_context: n_ctx_per_seq = 4096
llama_context: n_batch       = 1024
llama_context: n_ubatch      = 512
llama_context: causal_attn   = 1
llama_context: flash_attn    = 0
llama_context: freq_base     = 1000000.0
llama_context: freq_scale    = 1
llama_context: n_ctx_per_seq (4096) < n_ctx_train (40960) -- the full capacity of the model will not be utilized
llama_context:  CUDA_Host  output buffer size =     1.20 MiB
llama_kv_cache_unified: kv_size = 8192, type_k = 'f16', type_v = 'f16', n_layer = 40, can_shift = 1, padding = 32
llama_kv_cache_unified:      CUDA0 KV buffer size =  1280.00 MiB
llama_kv_cache_unified: KV self size  = 1280.00 MiB, K (f16):  640.00 MiB, V (f16):  640.00 MiB
llama_context:      CUDA0 compute buffer size =   696.00 MiB
llama_context:  CUDA_Host compute buffer size =    26.01 MiB
llama_context: graph nodes  = 1526
llama_context: graph splits = 2
time=2025-05-31T15:14:28.134+08:00 level=INFO source=server.go:630 msg="llama runner started in 17.53 seconds"
[GIN] 2025/05/31 - 15:14:28 | 200 |   17.9238859s |       127.0.0.1 | POST     "/api/generate"
[GIN] 2025/05/31 - 15:16:04 | 200 |         1m25s |       127.0.0.1 | POST     "/api/chat"
[GIN] 2025/05/31 - 15:17:14 | 200 |     29.6295ms |       127.0.0.1 | GET      "/api/tags"

OS

Windows

GPU

Nvidia

CPU

Intel

Ollama version

0.9.0

Originally created by @Djooxx on GitHub (May 31, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/10927 ### What is the issue? windows 11 / 5060ti 16g / ollama v0.9 / cuda 12.8 / model: qwen3:14b (bdbd181c33f2) English: Even if I just sent a simple "hello", its thought process would still loop infinitely.The probability of this happening is very high (>90%).A few days ago, Ollama's official website updated the Qwen3 model, and then this problem occurred.What has been updated in the official website model? Is there any relevant documentation? Chinese: 即使我只发送了一个简单问候,它的思考过程依然会无限循环,出现这种情况的概率很高(>90%).前几天ollama官网更新了qwen3的模型,之后就有这个问题了.官网的模型更新了什么东西?这个有相关的文档吗? ![Image](https://github.com/user-attachments/assets/f4a6e470-38d4-4e75-b3ac-1d9ddd292b17) ![Image](https://github.com/user-attachments/assets/ca3f859c-c7a2-4bac-9c82-76d3bb601cc7) ### Relevant log output ```shell time=2025-05-31T15:13:53.300+08:00 level=INFO source=routes.go:1234 msg="server config" env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:4096 OLLAMA_DEBUG:INFO OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:15m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:E:\\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=2025-05-31T15:13:53.404+08:00 level=INFO source=images.go:479 msg="total blobs: 22" time=2025-05-31T15:13:53.406+08:00 level=INFO source=images.go:486 msg="total unused blobs removed: 0" time=2025-05-31T15:13:53.409+08:00 level=INFO source=routes.go:1287 msg="Listening on 127.0.0.1:11434 (version 0.9.0)" time=2025-05-31T15:13:53.410+08:00 level=INFO source=gpu.go:217 msg="looking for compatible GPUs" time=2025-05-31T15:13:53.412+08:00 level=INFO source=gpu_windows.go:167 msg=packages count=1 time=2025-05-31T15:13:53.412+08:00 level=INFO source=gpu_windows.go:214 msg="" package=0 cores=6 efficiency=0 threads=12 time=2025-05-31T15:13:53.636+08:00 level=INFO source=gpu.go:319 msg="detected OS VRAM overhead" id=GPU-1daaca27-a481-6f45-04cf-dc0f8e9dd26d library=cuda compute=12.0 driver=12.9 name="NVIDIA GeForce RTX 5060 Ti" overhead="404.4 MiB" time=2025-05-31T15:13:53.640+08:00 level=INFO source=types.go:130 msg="inference compute" id=GPU-1daaca27-a481-6f45-04cf-dc0f8e9dd26d library=cuda variant=v12 compute=12.0 driver=12.9 name="NVIDIA GeForce RTX 5060 Ti" total="15.9 GiB" available="14.7 GiB" [GIN] 2025/05/31 - 15:14:10 | 200 | 0s | 127.0.0.1 | HEAD "/" [GIN] 2025/05/31 - 15:14:10 | 200 | 154.566ms | 127.0.0.1 | POST "/api/show" time=2025-05-31T15:14:10.282+08:00 level=INFO source=sched.go:788 msg="new model will fit in available VRAM in single GPU, loading" model=E:\OLLAMA_models\blobs\sha256-a8cc1361f3145dc01f6d77c6c82c9116b9ffe3c97b34716fe20418455876c40e gpu=GPU-1daaca27-a481-6f45-04cf-dc0f8e9dd26d parallel=2 available=15648612352 required="11.2 GiB" time=2025-05-31T15:14:10.308+08:00 level=INFO source=server.go:135 msg="system memory" total="55.7 GiB" free="48.0 GiB" free_swap="50.7 GiB" time=2025-05-31T15:14:10.309+08:00 level=INFO source=server.go:168 msg=offload library=cuda layers.requested=-1 layers.model=41 layers.offload=41 layers.split="" memory.available="[14.6 GiB]" memory.gpu_overhead="0 B" memory.required.full="11.2 GiB" memory.required.partial="11.2 GiB" memory.required.kv="1.2 GiB" memory.required.allocations="[11.2 GiB]" memory.weights.total="8.2 GiB" memory.weights.repeating="7.6 GiB" memory.weights.nonrepeating="608.6 MiB" memory.graph.full="1.0 GiB" memory.graph.partial="1.0 GiB" llama_model_loader: loaded meta data with 27 key-value pairs and 443 tensors from E:\OLLAMA_models\blobs\sha256-a8cc1361f3145dc01f6d77c6c82c9116b9ffe3c97b34716fe20418455876c40e (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 = qwen3 llama_model_loader: - kv 1: general.type str = model llama_model_loader: - kv 2: general.name str = Qwen3 14B llama_model_loader: - kv 3: general.basename str = Qwen3 llama_model_loader: - kv 4: general.size_label str = 14B llama_model_loader: - kv 5: qwen3.block_count u32 = 40 llama_model_loader: - kv 6: qwen3.context_length u32 = 40960 llama_model_loader: - kv 7: qwen3.embedding_length u32 = 5120 llama_model_loader: - kv 8: qwen3.feed_forward_length u32 = 17408 llama_model_loader: - kv 9: qwen3.attention.head_count u32 = 40 llama_model_loader: - kv 10: qwen3.attention.head_count_kv u32 = 8 llama_model_loader: - kv 11: qwen3.rope.freq_base f32 = 1000000.000000 llama_model_loader: - kv 12: qwen3.attention.layer_norm_rms_epsilon f32 = 0.000001 llama_model_loader: - kv 13: qwen3.attention.key_length u32 = 128 llama_model_loader: - kv 14: qwen3.attention.value_length u32 = 128 llama_model_loader: - kv 15: tokenizer.ggml.model str = gpt2 llama_model_loader: - kv 16: tokenizer.ggml.pre str = qwen2 llama_model_loader: - kv 17: tokenizer.ggml.tokens arr[str,151936] = ["!", "\"", "#", "$", "%", "&", "'", ... llama_model_loader: - kv 18: tokenizer.ggml.token_type arr[i32,151936] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... llama_model_loader: - kv 19: tokenizer.ggml.merges arr[str,151387] = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",... llama_model_loader: - kv 20: tokenizer.ggml.eos_token_id u32 = 151645 llama_model_loader: - kv 21: tokenizer.ggml.padding_token_id u32 = 151643 llama_model_loader: - kv 22: tokenizer.ggml.bos_token_id u32 = 151643 llama_model_loader: - kv 23: tokenizer.ggml.add_bos_token bool = false llama_model_loader: - kv 24: tokenizer.chat_template str = {%- if tools %}\n {{- '<|im_start|>... llama_model_loader: - kv 25: general.quantization_version u32 = 2 llama_model_loader: - kv 26: general.file_type u32 = 15 llama_model_loader: - type f32: 161 tensors llama_model_loader: - type f16: 40 tensors llama_model_loader: - type q4_K: 221 tensors llama_model_loader: - type q6_K: 21 tensors print_info: file format = GGUF V3 (latest) print_info: file type = Q4_K - Medium print_info: file size = 8.63 GiB (5.02 BPW) load: special tokens cache size = 26 load: token to piece cache size = 0.9311 MB print_info: arch = qwen3 print_info: vocab_only = 1 print_info: model type = ?B print_info: model params = 14.77 B print_info: general.name = Qwen3 14B print_info: vocab type = BPE print_info: n_vocab = 151936 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=2025-05-31T15:14:10.602+08:00 level=INFO source=server.go:431 msg="starting llama server" cmd="C:\\Users\\qwerd\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --model E:\\OLLAMA_models\\blobs\\sha256-a8cc1361f3145dc01f6d77c6c82c9116b9ffe3c97b34716fe20418455876c40e --ctx-size 8192 --batch-size 512 --n-gpu-layers 41 --threads 6 --no-mmap --parallel 2 --port 51001" time=2025-05-31T15:14:10.608+08:00 level=INFO source=sched.go:483 msg="loaded runners" count=1 time=2025-05-31T15:14:10.608+08:00 level=INFO source=server.go:591 msg="waiting for llama runner to start responding" time=2025-05-31T15:14:10.608+08:00 level=INFO source=server.go:625 msg="waiting for server to become available" status="llm server error" time=2025-05-31T15:14:10.655+08:00 level=INFO source=runner.go:815 msg="starting go runner" load_backend: loaded CPU backend from C:\Users\qwerd\AppData\Local\Programs\Ollama\lib\ollama\ggml-cpu-haswell.dll 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 5060 Ti, compute capability 12.0, VMM: yes load_backend: loaded CUDA backend from C:\Users\qwerd\AppData\Local\Programs\Ollama\lib\ollama\cuda_v12\ggml-cuda.dll time=2025-05-31T15:14:11.915+08:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.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=2025-05-31T15:14:11.917+08:00 level=INFO source=runner.go:874 msg="Server listening on 127.0.0.1:51001" llama_model_load_from_file_impl: using device CUDA0 (NVIDIA GeForce RTX 5060 Ti) - 15072 MiB free llama_model_loader: loaded meta data with 27 key-value pairs and 443 tensors from E:\OLLAMA_models\blobs\sha256-a8cc1361f3145dc01f6d77c6c82c9116b9ffe3c97b34716fe20418455876c40e (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 = qwen3 llama_model_loader: - kv 1: general.type str = model llama_model_loader: - kv 2: general.name str = Qwen3 14B llama_model_loader: - kv 3: general.basename str = Qwen3 llama_model_loader: - kv 4: general.size_label str = 14B llama_model_loader: - kv 5: qwen3.block_count u32 = 40 llama_model_loader: - kv 6: qwen3.context_length u32 = 40960 llama_model_loader: - kv 7: qwen3.embedding_length u32 = 5120 llama_model_loader: - kv 8: qwen3.feed_forward_length u32 = 17408 llama_model_loader: - kv 9: qwen3.attention.head_count u32 = 40 llama_model_loader: - kv 10: qwen3.attention.head_count_kv u32 = 8 llama_model_loader: - kv 11: qwen3.rope.freq_base f32 = 1000000.000000 llama_model_loader: - kv 12: qwen3.attention.layer_norm_rms_epsilon f32 = 0.000001 llama_model_loader: - kv 13: qwen3.attention.key_length u32 = 128 llama_model_loader: - kv 14: qwen3.attention.value_length u32 = 128 llama_model_loader: - kv 15: tokenizer.ggml.model str = gpt2 llama_model_loader: - kv 16: tokenizer.ggml.pre str = qwen2 llama_model_loader: - kv 17: tokenizer.ggml.tokens arr[str,151936] = ["!", "\"", "#", "$", "%", "&", "'", ... llama_model_loader: - kv 18: tokenizer.ggml.token_type arr[i32,151936] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... llama_model_loader: - kv 19: tokenizer.ggml.merges arr[str,151387] = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",... llama_model_loader: - kv 20: tokenizer.ggml.eos_token_id u32 = 151645 llama_model_loader: - kv 21: tokenizer.ggml.padding_token_id u32 = 151643 llama_model_loader: - kv 22: tokenizer.ggml.bos_token_id u32 = 151643 llama_model_loader: - kv 23: tokenizer.ggml.add_bos_token bool = false llama_model_loader: - kv 24: tokenizer.chat_template str = {%- if tools %}\n {{- '<|im_start|>... llama_model_loader: - kv 25: general.quantization_version u32 = 2 llama_model_loader: - kv 26: general.file_type u32 = 15 llama_model_loader: - type f32: 161 tensors llama_model_loader: - type f16: 40 tensors llama_model_loader: - type q4_K: 221 tensors llama_model_loader: - type q6_K: 21 tensors print_info: file format = GGUF V3 (latest) print_info: file type = Q4_K - Medium print_info: file size = 8.63 GiB (5.02 BPW) time=2025-05-31T15:14:12.110+08:00 level=INFO source=server.go:625 msg="waiting for server to become available" status="llm server loading model" load: special tokens cache size = 26 load: token to piece cache size = 0.9311 MB print_info: arch = qwen3 print_info: vocab_only = 0 print_info: n_ctx_train = 40960 print_info: n_embd = 5120 print_info: n_layer = 40 print_info: n_head = 40 print_info: n_head_kv = 8 print_info: n_rot = 128 print_info: n_swa = 0 print_info: n_swa_pattern = 1 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: f_attn_scale = 0.0e+00 print_info: n_ff = 17408 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 = 40960 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 = Qwen3 14B print_info: vocab type = BPE print_info: n_vocab = 151936 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 40 repeating layers to GPU load_tensors: offloading output layer to GPU load_tensors: offloaded 41/41 layers to GPU load_tensors: CUDA0 model buffer size = 8423.47 MiB load_tensors: CPU model buffer size = 417.30 MiB llama_context: constructing llama_context llama_context: n_seq_max = 2 llama_context: n_ctx = 8192 llama_context: n_ctx_per_seq = 4096 llama_context: n_batch = 1024 llama_context: n_ubatch = 512 llama_context: causal_attn = 1 llama_context: flash_attn = 0 llama_context: freq_base = 1000000.0 llama_context: freq_scale = 1 llama_context: n_ctx_per_seq (4096) < n_ctx_train (40960) -- the full capacity of the model will not be utilized llama_context: CUDA_Host output buffer size = 1.20 MiB llama_kv_cache_unified: kv_size = 8192, type_k = 'f16', type_v = 'f16', n_layer = 40, can_shift = 1, padding = 32 llama_kv_cache_unified: CUDA0 KV buffer size = 1280.00 MiB llama_kv_cache_unified: KV self size = 1280.00 MiB, K (f16): 640.00 MiB, V (f16): 640.00 MiB llama_context: CUDA0 compute buffer size = 696.00 MiB llama_context: CUDA_Host compute buffer size = 26.01 MiB llama_context: graph nodes = 1526 llama_context: graph splits = 2 time=2025-05-31T15:14:28.134+08:00 level=INFO source=server.go:630 msg="llama runner started in 17.53 seconds" [GIN] 2025/05/31 - 15:14:28 | 200 | 17.9238859s | 127.0.0.1 | POST "/api/generate" [GIN] 2025/05/31 - 15:16:04 | 200 | 1m25s | 127.0.0.1 | POST "/api/chat" [GIN] 2025/05/31 - 15:17:14 | 200 | 29.6295ms | 127.0.0.1 | GET "/api/tags" ``` ### OS Windows ### GPU Nvidia ### CPU Intel ### Ollama version 0.9.0
GiteaMirror added the bug label 2026-04-12 19:11:19 -05:00
GiteaMirror commented 2026-04-12 19:11:21 -05:00
Author
Owner
Copy Link

@JasonHonKL commented on GitHub (Jun 4, 2025):

其他模型有這問題嗎？

<!-- gh-comment-id:2938145655 --> @JasonHonKL commented on GitHub (Jun 4, 2025): 其他模型有這問題嗎？
GiteaMirror commented 2026-04-12 19:11:21 -05:00
Author
Owner
Copy Link

@Djooxx commented on GitHub (Jun 4, 2025):

其他模型有这问题吗？

r1 也是一样的问题

<!-- gh-comment-id:2938296512 --> @Djooxx commented on GitHub (Jun 4, 2025): > 其他模型有这问题吗？ [r1 ](deepseek-r1:8b-0528-qwen3-q4_K_M) 也是一样的问题
GiteaMirror commented 2026-04-12 19:11:21 -05:00
Author
Owner
Copy Link

@dengyunsheng250 commented on GitHub (Jun 4, 2025):

小模型也遇到过这种问题

<!-- gh-comment-id:2938326389 --> @dengyunsheng250 commented on GitHub (Jun 4, 2025): 小模型也遇到过这种问题
GiteaMirror commented 2026-04-12 19:11:22 -05:00
Author
Owner
Copy Link

@JasonHonKL commented on GitHub (Jun 4, 2025):

這應該是model 問題吧

<!-- gh-comment-id:2938546631 --> @JasonHonKL commented on GitHub (Jun 4, 2025): 這應該是model 問題吧
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
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#7190
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?