github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-09 01:59:50 -05:00
Code Issues 14.7k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #8990] Calling the model in the podman container through the API takes a long time to load #5838

New Issue
Closed
opened 2026-04-12 17:10:49 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-12 17:10:49 -05:00
Owner
Copy Link

Originally created by @hualong1009 on GitHub (Feb 10, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/8990

What is the issue?

The first call to the model in the podman container through the API takes a long time to load, about 5 minutes, after the model is loaded, the subsequent call will be very fast, before using docker will not have this problem, the call to the model is very fast, I am not sure what the problem is, let's see if it is ollama's reason

time=2025-02-10T11:53:58.598Z level=INFO source=server.go:594 msg="llama runner started in 283.61 seconds"

Relevant log output

time=2025-02-10T11:48:33.469Z level=INFO source=routes.go:1238 msg="Listening on [::]:11434 (version 0.5.7-0-ga420a45-dirty)"
time=2025-02-10T11:48:33.472Z level=INFO source=routes.go:1267 msg="Dynamic LLM libraries" runners="[cpu cpu_avx cpu_avx2 cuda_v11_avx cuda_v12_avx]"
time=2025-02-10T11:48:33.472Z level=INFO source=gpu.go:226 msg="looking for compatible GPUs"
time=2025-02-10T11:48:35.755Z level=INFO source=types.go:131 msg="inference compute" id=GPU-1bea5756-7db4-d13b-f933-13ff87297373 library=cuda variant=v12 compute=8.9 driver=12.6 na
me="NVIDIA GeForce RTX 4060 Laptop GPU" total="8.0 GiB" available="6.9 GiB"
time=2025-02-10T11:49:14.869Z level=INFO source=sched.go:714 msg="new model will fit in available VRAM in single GPU, loading" model=/root/.ollama/models/blobs/sha256-2bada8a745067
7000f678be90653b85d364de7db25eb5ea54136ada5f3933730 gpu=GPU-1bea5756-7db4-d13b-f933-13ff87297373 parallel=4 available=7443841024 required="5.6 GiB"
time=2025-02-10T11:49:14.983Z level=INFO source=server.go:104 msg="system memory" total="15.4 GiB" free="14.6 GiB" free_swap="4.0 GiB"
time=2025-02-10T11:49:14.984Z level=INFO source=memory.go:356 msg="offload to cuda" layers.requested=-1 layers.model=29 layers.offload=29 layers.split="" memory.available="[6.9 GiB
]" memory.gpu_overhead="0 B" memory.required.full="5.6 GiB" memory.required.partial="5.6 GiB" memory.required.kv="448.0 MiB" memory.required.allocations="[5.6 GiB]" memory.weights.
total="4.1 GiB" memory.weights.repeating="3.7 GiB" memory.weights.nonrepeating="426.4 MiB" memory.graph.full="478.0 MiB" memory.graph.partial="730.4 MiB"
time=2025-02-10T11:49:14.985Z level=INFO source=server.go:376 msg="starting llama server" cmd="/usr/lib/ollama/runners/cuda_v12_avx/ollama_llama_server runner --model /root/.ollama
/models/blobs/sha256-2bada8a7450677000f678be90653b85d364de7db25eb5ea54136ada5f3933730 --ctx-size 8192 --batch-size 512 --n-gpu-layers 29 --threads 11 --parallel 4 --port 33959"
time=2025-02-10T11:49:14.986Z level=INFO source=sched.go:449 msg="loaded runners" count=1
time=2025-02-10T11:49:14.986Z level=INFO source=server.go:555 msg="waiting for llama runner to start responding"
time=2025-02-10T11:49:14.987Z level=INFO source=server.go:589 msg="waiting for server to become available" status="llm server error"
time=2025-02-10T11:49:15.054Z level=INFO source=runner.go:936 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 4060 Laptop GPU, compute capability 8.9, VMM: yes
time=2025-02-10T11:49:15.112Z level=INFO source=runner.go:937 msg=system info="CUDA : ARCHS = 600,610,620,700,720,750,800,860,870,890,900 | USE_GRAPHS = 1 | PEER_MAX_BATCH_SIZE = 1
28 | CPU : SSE3 = 1 | SSSE3 = 1 | AVX = 1 | LLAMAFILE = 1 | AARCH64_REPACK = 1 | cgo(gcc)" threads=11
time=2025-02-10T11:49:15.112Z level=INFO source=.:0 msg="Server listening on 127.0.0.1:33959"
llama_load_model_from_file: using device CUDA0 (NVIDIA GeForce RTX 4060 Laptop GPU) - 7099 MiB free
time=2025-02-10T11:49:15.238Z level=INFO source=server.go:589 msg="waiting for server to become available" status="llm server loading model"
llama_model_loader: loaded meta data with 34 key-value pairs and 339 tensors from /root/.ollama/models/blobs/sha256-2bada8a7450677000f678be90653b85d364de7db25eb5ea54136ada5f3933730
 (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 7B 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              = 7B
llama_model_loader: - kv   6:                            general.license str              = apache-2.0
llama_model_loader: - kv   7:                       general.license.link str              = https://huggingface.co/Qwen/Qwen2.5-7...
llama_model_loader: - kv   8:                   general.base_model.count u32              = 1
llama_model_loader: - kv   9:                  general.base_model.0.name str              = Qwen2.5 7B
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/Qwen2.5-7B
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              = 28
llama_model_loader: - kv  15:                       qwen2.context_length u32              = 32768
llama_model_loader: - kv  16:                     qwen2.embedding_length u32              = 3584
llama_model_loader: - kv  17:                  qwen2.feed_forward_length u32              = 18944
llama_model_loader: - kv  18:                 qwen2.attention.head_count u32              = 28
llama_model_loader: - kv  19:              qwen2.attention.head_count_kv u32              = 4
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:  141 tensors
llama_model_loader: - type q4_K:  169 tensors
llama_model_loader: - type q6_K:   29 tensors
llm_load_vocab: special tokens cache size = 22
llm_load_vocab: token to piece cache size = 0.9310 MB
llm_load_print_meta: format           = GGUF V3 (latest)
llm_load_print_meta: arch             = qwen2
llm_load_print_meta: vocab type       = BPE
llm_load_print_meta: n_vocab          = 152064
llm_load_print_meta: n_merges         = 151387
llm_load_print_meta: vocab_only       = 0
llm_load_print_meta: n_ctx_train      = 32768
llm_load_print_meta: n_embd           = 3584
llm_load_print_meta: n_layer          = 28
llm_load_print_meta: n_head           = 28
llm_load_print_meta: n_head_kv        = 4
llm_load_print_meta: n_rot            = 128
llm_load_print_meta: n_swa            = 0
llm_load_print_meta: n_embd_head_k    = 128
llm_load_print_meta: n_embd_head_v    = 128
llm_load_print_meta: n_gqa            = 7
llm_load_print_meta: n_embd_k_gqa     = 512
llm_load_print_meta: n_embd_v_gqa     = 512
llm_load_print_meta: f_norm_eps       = 0.0e+00
llm_load_print_meta: f_norm_rms_eps   = 1.0e-06
llm_load_print_meta: f_clamp_kqv      = 0.0e+00
llm_load_print_meta: f_max_alibi_bias = 0.0e+00
llm_load_print_meta: f_logit_scale    = 0.0e+00
llm_load_print_meta: n_ff             = 18944
llm_load_print_meta: n_expert         = 0
llm_load_print_meta: n_expert_used    = 0
llm_load_print_meta: causal attn      = 1
llm_load_print_meta: pooling type     = 0
llm_load_print_meta: rope type        = 2
llm_load_print_meta: rope scaling     = linear
llm_load_print_meta: freq_base_train  = 1000000.0
llm_load_print_meta: freq_scale_train = 1
llm_load_print_meta: n_ctx_orig_yarn  = 32768
llm_load_print_meta: rope_finetuned   = unknown
llm_load_print_meta: ssm_d_conv       = 0
llm_load_print_meta: ssm_d_inner      = 0
llm_load_print_meta: ssm_d_state      = 0
llm_load_print_meta: ssm_dt_rank      = 0
llm_load_print_meta: ssm_dt_b_c_rms   = 0
llm_load_print_meta: model type       = 7B
llm_load_print_meta: model ftype      = Q4_K - Medium
llm_load_print_meta: model params     = 7.62 B
llm_load_print_meta: model size       = 4.36 GiB (4.91 BPW)
llm_load_print_meta: general.name     = Qwen2.5 7B Instruct
llm_load_print_meta: BOS token        = 151643 '<|endoftext|>'
llm_load_print_meta: EOS token        = 151645 '<|im_end|>'
llm_load_print_meta: EOT token        = 151645 '<|im_end|>'
llm_load_print_meta: PAD token        = 151643 '<|endoftext|>'
llm_load_print_meta: LF token         = 148848 'ÄĬ'
llm_load_print_meta: FIM PRE token    = 151659 '<|fim_prefix|>'
llm_load_print_meta: FIM SUF token    = 151661 '<|fim_suffix|>'
llm_load_print_meta: FIM MID token    = 151660 '<|fim_middle|>'
llm_load_print_meta: FIM PAD token    = 151662 '<|fim_pad|>'
llm_load_print_meta: FIM REP token    = 151663 '<|repo_name|>'
llm_load_print_meta: FIM SEP token    = 151664 '<|file_sep|>'
llm_load_print_meta: EOG token        = 151643 '<|endoftext|>'
llm_load_print_meta: EOG token        = 151645 '<|im_end|>'
llm_load_print_meta: EOG token        = 151662 '<|fim_pad|>'
llm_load_print_meta: EOG token        = 151663 '<|repo_name|>'
llm_load_print_meta: EOG token        = 151664 '<|file_sep|>'
llm_load_print_meta: max token length = 256
llm_load_tensors: offloading 28 repeating layers to GPU
llm_load_tensors: offloading output layer to GPU
llm_load_tensors: offloaded 29/29 layers to GPU
llm_load_tensors:   CPU_Mapped model buffer size =   292.36 MiB
llm_load_tensors:        CUDA0 model buffer size =  4168.09 MiB
llama_new_context_with_model: n_seq_max     = 4
llama_new_context_with_model: n_ctx         = 8192
llama_new_context_with_model: n_ctx_per_seq = 2048
llama_new_context_with_model: n_batch       = 2048
llama_new_context_with_model: n_ubatch      = 512
llama_new_context_with_model: flash_attn    = 0
llama_new_context_with_model: freq_base     = 1000000.0
llama_new_context_with_model: freq_scale    = 1
llama_new_context_with_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 = 28, can_shift = 1
llama_kv_cache_init:      CUDA0 KV buffer size =   448.00 MiB
llama_new_context_with_model: KV self size  =  448.00 MiB, K (f16):  224.00 MiB, V (f16):  224.00 MiB
llama_new_context_with_model:  CUDA_Host  output buffer size =     2.38 MiB
llama_new_context_with_model:      CUDA0 compute buffer size =   492.00 MiB
llama_new_context_with_model:  CUDA_Host compute buffer size =    23.01 MiB
llama_new_context_with_model: graph nodes  = 986
llama_new_context_with_model: graph splits = 2
time=2025-02-10T11:53:58.598Z level=INFO source=server.go:594 msg="llama runner started in 283.61 seconds"
llama_model_loader: loaded meta data with 34 key-value pairs and 339 tensors from /root/.ollama/models/blobs/sha256-2bada8a7450677000f678be90653b85d364de7db25eb5ea54136ada5f3933730
 (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 7B 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              = 7B
llama_model_loader: - kv   6:                            general.license str              = apache-2.0
llama_model_loader: - kv   7:                       general.license.link str              = https://huggingface.co/Qwen/Qwen2.5-7...
llama_model_loader: - kv   8:                   general.base_model.count u32              = 1
llama_model_loader: - kv   9:                  general.base_model.0.name str              = Qwen2.5 7B
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/Qwen2.5-7B
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              = 28
llama_model_loader: - kv  15:                       qwen2.context_length u32              = 32768
llama_model_loader: - kv  16:                     qwen2.embedding_length u32              = 3584
llama_model_loader: - kv  17:                  qwen2.feed_forward_length u32              = 18944
llama_model_loader: - kv  18:                 qwen2.attention.head_count u32              = 28
llama_model_loader: - kv  19:              qwen2.attention.head_count_kv u32              = 4
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:  141 tensors
llama_model_loader: - type q4_K:  169 tensors
llama_model_loader: - type q6_K:   29 tensors
llm_load_vocab: special tokens cache size = 22
llm_load_vocab: token to piece cache size = 0.9310 MB
llm_load_print_meta: format           = GGUF V3 (latest)
llm_load_print_meta: arch             = qwen2
llm_load_print_meta: vocab type       = BPE
llm_load_print_meta: n_vocab          = 152064
llm_load_print_meta: n_merges         = 151387
llm_load_print_meta: vocab_only       = 1
llm_load_print_meta: model type       = ?B
llm_load_print_meta: model ftype      = all F32
llm_load_print_meta: model params     = 7.62 B
llm_load_print_meta: model size       = 4.36 GiB (4.91 BPW)
llm_load_print_meta: general.name     = Qwen2.5 7B Instruct
llm_load_print_meta: BOS token        = 151643 '<|endoftext|>'
llm_load_print_meta: EOS token        = 151645 '<|im_end|>'
llm_load_print_meta: EOT token        = 151645 '<|im_end|>'
llm_load_print_meta: PAD token        = 151643 '<|endoftext|>'
llm_load_print_meta: LF token         = 148848 'ÄĬ'
llm_load_print_meta: FIM PRE token    = 151659 '<|fim_prefix|>'
llm_load_print_meta: FIM SUF token    = 151661 '<|fim_suffix|>'
llm_load_print_meta: FIM MID token    = 151660 '<|fim_middle|>'
llm_load_print_meta: FIM PAD token    = 151662 '<|fim_pad|>'
llm_load_print_meta: FIM REP token    = 151663 '<|repo_name|>'
llm_load_print_meta: FIM SEP token    = 151664 '<|file_sep|>'
llm_load_print_meta: EOG token        = 151643 '<|endoftext|>'
llm_load_print_meta: EOG token        = 151645 '<|im_end|>'
llm_load_print_meta: EOG token        = 151662 '<|fim_pad|>'
llm_load_print_meta: EOG token        = 151663 '<|repo_name|>'
llm_load_print_meta: EOG token        = 151664 '<|file_sep|>'
llm_load_print_meta: max token length = 256
llama_model_load: vocab only - skipping tensors
[GIN] 2025/02/10 - 11:54:01 | 200 |         4m26s |       10.88.0.1 | POST     "/v1/chat/completions"
[GIN] 2025/02/10 - 11:54:21 | 200 |         4m29s |       10.88.0.1 | POST     "/v1/chat/completions"
[GIN] 2025/02/10 - 11:54:22 | 200 |         4m33s |       10.88.0.1 | POST     "/v1/chat/completions"
[GIN] 2025/02/10 - 11:54:23 | 200 |          5m9s |       10.88.0.1 | POST     "/v1/chat/completions"
time=2025-02-10T11:59:29.046Z level=WARN source=sched.go:646 msg="gpu VRAM usage didn't recover within timeout" seconds=5.1281383 model=/root/.ollama/models/blobs/sha256-2bada8a745
0677000f678be90653b85d364de7db25eb5ea54136ada5f3933730
time=2025-02-10T11:59:29.295Z level=WARN source=sched.go:646 msg="gpu VRAM usage didn't recover within timeout" seconds=5.377539302 model=/root/.ollama/models/blobs/sha256-2bada8a7
450677000f678be90653b85d364de7db25eb5ea54136ada5f3933730
time=2025-02-10T11:59:29.546Z level=WARN source=sched.go:646 msg="gpu VRAM usage didn't recover within timeout" seconds=5.628414795 model=/root/.ollama/models/blobs/sha256-2bada8a7
450677000f678be90653b85d364de7db25eb5ea54136ada5f3933730

OS

Windows

GPU

Nvidia

CPU

Intel

Ollama version

ollama version is 0.5.7-0-ga420a45-dirty

Originally created by @hualong1009 on GitHub (Feb 10, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/8990 ### What is the issue? The first call to the model in the podman container through the API takes a long time to load, about 5 minutes, after the model is loaded, the subsequent call will be very fast, before using docker will not have this problem, the call to the model is very fast, I am not sure what the problem is, let's see if it is ollama's reason >time=2025-02-10T11:53:58.598Z level=INFO source=server.go:594 msg="llama runner started in 283.61 seconds" ### Relevant log output ```shell time=2025-02-10T11:48:33.469Z level=INFO source=routes.go:1238 msg="Listening on [::]:11434 (version 0.5.7-0-ga420a45-dirty)" time=2025-02-10T11:48:33.472Z level=INFO source=routes.go:1267 msg="Dynamic LLM libraries" runners="[cpu cpu_avx cpu_avx2 cuda_v11_avx cuda_v12_avx]" time=2025-02-10T11:48:33.472Z level=INFO source=gpu.go:226 msg="looking for compatible GPUs" time=2025-02-10T11:48:35.755Z level=INFO source=types.go:131 msg="inference compute" id=GPU-1bea5756-7db4-d13b-f933-13ff87297373 library=cuda variant=v12 compute=8.9 driver=12.6 na me="NVIDIA GeForce RTX 4060 Laptop GPU" total="8.0 GiB" available="6.9 GiB" time=2025-02-10T11:49:14.869Z level=INFO source=sched.go:714 msg="new model will fit in available VRAM in single GPU, loading" model=/root/.ollama/models/blobs/sha256-2bada8a745067 7000f678be90653b85d364de7db25eb5ea54136ada5f3933730 gpu=GPU-1bea5756-7db4-d13b-f933-13ff87297373 parallel=4 available=7443841024 required="5.6 GiB" time=2025-02-10T11:49:14.983Z level=INFO source=server.go:104 msg="system memory" total="15.4 GiB" free="14.6 GiB" free_swap="4.0 GiB" time=2025-02-10T11:49:14.984Z level=INFO source=memory.go:356 msg="offload to cuda" layers.requested=-1 layers.model=29 layers.offload=29 layers.split="" memory.available="[6.9 GiB ]" memory.gpu_overhead="0 B" memory.required.full="5.6 GiB" memory.required.partial="5.6 GiB" memory.required.kv="448.0 MiB" memory.required.allocations="[5.6 GiB]" memory.weights. total="4.1 GiB" memory.weights.repeating="3.7 GiB" memory.weights.nonrepeating="426.4 MiB" memory.graph.full="478.0 MiB" memory.graph.partial="730.4 MiB" time=2025-02-10T11:49:14.985Z level=INFO source=server.go:376 msg="starting llama server" cmd="/usr/lib/ollama/runners/cuda_v12_avx/ollama_llama_server runner --model /root/.ollama /models/blobs/sha256-2bada8a7450677000f678be90653b85d364de7db25eb5ea54136ada5f3933730 --ctx-size 8192 --batch-size 512 --n-gpu-layers 29 --threads 11 --parallel 4 --port 33959" time=2025-02-10T11:49:14.986Z level=INFO source=sched.go:449 msg="loaded runners" count=1 time=2025-02-10T11:49:14.986Z level=INFO source=server.go:555 msg="waiting for llama runner to start responding" time=2025-02-10T11:49:14.987Z level=INFO source=server.go:589 msg="waiting for server to become available" status="llm server error" time=2025-02-10T11:49:15.054Z level=INFO source=runner.go:936 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 4060 Laptop GPU, compute capability 8.9, VMM: yes time=2025-02-10T11:49:15.112Z level=INFO source=runner.go:937 msg=system info="CUDA : ARCHS = 600,610,620,700,720,750,800,860,870,890,900 | USE_GRAPHS = 1 | PEER_MAX_BATCH_SIZE = 1 28 | CPU : SSE3 = 1 | SSSE3 = 1 | AVX = 1 | LLAMAFILE = 1 | AARCH64_REPACK = 1 | cgo(gcc)" threads=11 time=2025-02-10T11:49:15.112Z level=INFO source=.:0 msg="Server listening on 127.0.0.1:33959" llama_load_model_from_file: using device CUDA0 (NVIDIA GeForce RTX 4060 Laptop GPU) - 7099 MiB free time=2025-02-10T11:49:15.238Z level=INFO source=server.go:589 msg="waiting for server to become available" status="llm server loading model" llama_model_loader: loaded meta data with 34 key-value pairs and 339 tensors from /root/.ollama/models/blobs/sha256-2bada8a7450677000f678be90653b85d364de7db25eb5ea54136ada5f3933730 (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 7B 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 = 7B llama_model_loader: - kv 6: general.license str = apache-2.0 llama_model_loader: - kv 7: general.license.link str = https://huggingface.co/Qwen/Qwen2.5-7... llama_model_loader: - kv 8: general.base_model.count u32 = 1 llama_model_loader: - kv 9: general.base_model.0.name str = Qwen2.5 7B 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/Qwen2.5-7B 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 = 28 llama_model_loader: - kv 15: qwen2.context_length u32 = 32768 llama_model_loader: - kv 16: qwen2.embedding_length u32 = 3584 llama_model_loader: - kv 17: qwen2.feed_forward_length u32 = 18944 llama_model_loader: - kv 18: qwen2.attention.head_count u32 = 28 llama_model_loader: - kv 19: qwen2.attention.head_count_kv u32 = 4 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: 141 tensors llama_model_loader: - type q4_K: 169 tensors llama_model_loader: - type q6_K: 29 tensors llm_load_vocab: special tokens cache size = 22 llm_load_vocab: token to piece cache size = 0.9310 MB llm_load_print_meta: format = GGUF V3 (latest) llm_load_print_meta: arch = qwen2 llm_load_print_meta: vocab type = BPE llm_load_print_meta: n_vocab = 152064 llm_load_print_meta: n_merges = 151387 llm_load_print_meta: vocab_only = 0 llm_load_print_meta: n_ctx_train = 32768 llm_load_print_meta: n_embd = 3584 llm_load_print_meta: n_layer = 28 llm_load_print_meta: n_head = 28 llm_load_print_meta: n_head_kv = 4 llm_load_print_meta: n_rot = 128 llm_load_print_meta: n_swa = 0 llm_load_print_meta: n_embd_head_k = 128 llm_load_print_meta: n_embd_head_v = 128 llm_load_print_meta: n_gqa = 7 llm_load_print_meta: n_embd_k_gqa = 512 llm_load_print_meta: n_embd_v_gqa = 512 llm_load_print_meta: f_norm_eps = 0.0e+00 llm_load_print_meta: f_norm_rms_eps = 1.0e-06 llm_load_print_meta: f_clamp_kqv = 0.0e+00 llm_load_print_meta: f_max_alibi_bias = 0.0e+00 llm_load_print_meta: f_logit_scale = 0.0e+00 llm_load_print_meta: n_ff = 18944 llm_load_print_meta: n_expert = 0 llm_load_print_meta: n_expert_used = 0 llm_load_print_meta: causal attn = 1 llm_load_print_meta: pooling type = 0 llm_load_print_meta: rope type = 2 llm_load_print_meta: rope scaling = linear llm_load_print_meta: freq_base_train = 1000000.0 llm_load_print_meta: freq_scale_train = 1 llm_load_print_meta: n_ctx_orig_yarn = 32768 llm_load_print_meta: rope_finetuned = unknown llm_load_print_meta: ssm_d_conv = 0 llm_load_print_meta: ssm_d_inner = 0 llm_load_print_meta: ssm_d_state = 0 llm_load_print_meta: ssm_dt_rank = 0 llm_load_print_meta: ssm_dt_b_c_rms = 0 llm_load_print_meta: model type = 7B llm_load_print_meta: model ftype = Q4_K - Medium llm_load_print_meta: model params = 7.62 B llm_load_print_meta: model size = 4.36 GiB (4.91 BPW) llm_load_print_meta: general.name = Qwen2.5 7B Instruct llm_load_print_meta: BOS token = 151643 '<|endoftext|>' llm_load_print_meta: EOS token = 151645 '<|im_end|>' llm_load_print_meta: EOT token = 151645 '<|im_end|>' llm_load_print_meta: PAD token = 151643 '<|endoftext|>' llm_load_print_meta: LF token = 148848 'ÄĬ' llm_load_print_meta: FIM PRE token = 151659 '<|fim_prefix|>' llm_load_print_meta: FIM SUF token = 151661 '<|fim_suffix|>' llm_load_print_meta: FIM MID token = 151660 '<|fim_middle|>' llm_load_print_meta: FIM PAD token = 151662 '<|fim_pad|>' llm_load_print_meta: FIM REP token = 151663 '<|repo_name|>' llm_load_print_meta: FIM SEP token = 151664 '<|file_sep|>' llm_load_print_meta: EOG token = 151643 '<|endoftext|>' llm_load_print_meta: EOG token = 151645 '<|im_end|>' llm_load_print_meta: EOG token = 151662 '<|fim_pad|>' llm_load_print_meta: EOG token = 151663 '<|repo_name|>' llm_load_print_meta: EOG token = 151664 '<|file_sep|>' llm_load_print_meta: max token length = 256 llm_load_tensors: offloading 28 repeating layers to GPU llm_load_tensors: offloading output layer to GPU llm_load_tensors: offloaded 29/29 layers to GPU llm_load_tensors: CPU_Mapped model buffer size = 292.36 MiB llm_load_tensors: CUDA0 model buffer size = 4168.09 MiB llama_new_context_with_model: n_seq_max = 4 llama_new_context_with_model: n_ctx = 8192 llama_new_context_with_model: n_ctx_per_seq = 2048 llama_new_context_with_model: n_batch = 2048 llama_new_context_with_model: n_ubatch = 512 llama_new_context_with_model: flash_attn = 0 llama_new_context_with_model: freq_base = 1000000.0 llama_new_context_with_model: freq_scale = 1 llama_new_context_with_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 = 28, can_shift = 1 llama_kv_cache_init: CUDA0 KV buffer size = 448.00 MiB llama_new_context_with_model: KV self size = 448.00 MiB, K (f16): 224.00 MiB, V (f16): 224.00 MiB llama_new_context_with_model: CUDA_Host output buffer size = 2.38 MiB llama_new_context_with_model: CUDA0 compute buffer size = 492.00 MiB llama_new_context_with_model: CUDA_Host compute buffer size = 23.01 MiB llama_new_context_with_model: graph nodes = 986 llama_new_context_with_model: graph splits = 2 time=2025-02-10T11:53:58.598Z level=INFO source=server.go:594 msg="llama runner started in 283.61 seconds" llama_model_loader: loaded meta data with 34 key-value pairs and 339 tensors from /root/.ollama/models/blobs/sha256-2bada8a7450677000f678be90653b85d364de7db25eb5ea54136ada5f3933730 (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 7B 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 = 7B llama_model_loader: - kv 6: general.license str = apache-2.0 llama_model_loader: - kv 7: general.license.link str = https://huggingface.co/Qwen/Qwen2.5-7... llama_model_loader: - kv 8: general.base_model.count u32 = 1 llama_model_loader: - kv 9: general.base_model.0.name str = Qwen2.5 7B 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/Qwen2.5-7B 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 = 28 llama_model_loader: - kv 15: qwen2.context_length u32 = 32768 llama_model_loader: - kv 16: qwen2.embedding_length u32 = 3584 llama_model_loader: - kv 17: qwen2.feed_forward_length u32 = 18944 llama_model_loader: - kv 18: qwen2.attention.head_count u32 = 28 llama_model_loader: - kv 19: qwen2.attention.head_count_kv u32 = 4 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: 141 tensors llama_model_loader: - type q4_K: 169 tensors llama_model_loader: - type q6_K: 29 tensors llm_load_vocab: special tokens cache size = 22 llm_load_vocab: token to piece cache size = 0.9310 MB llm_load_print_meta: format = GGUF V3 (latest) llm_load_print_meta: arch = qwen2 llm_load_print_meta: vocab type = BPE llm_load_print_meta: n_vocab = 152064 llm_load_print_meta: n_merges = 151387 llm_load_print_meta: vocab_only = 1 llm_load_print_meta: model type = ?B llm_load_print_meta: model ftype = all F32 llm_load_print_meta: model params = 7.62 B llm_load_print_meta: model size = 4.36 GiB (4.91 BPW) llm_load_print_meta: general.name = Qwen2.5 7B Instruct llm_load_print_meta: BOS token = 151643 '<|endoftext|>' llm_load_print_meta: EOS token = 151645 '<|im_end|>' llm_load_print_meta: EOT token = 151645 '<|im_end|>' llm_load_print_meta: PAD token = 151643 '<|endoftext|>' llm_load_print_meta: LF token = 148848 'ÄĬ' llm_load_print_meta: FIM PRE token = 151659 '<|fim_prefix|>' llm_load_print_meta: FIM SUF token = 151661 '<|fim_suffix|>' llm_load_print_meta: FIM MID token = 151660 '<|fim_middle|>' llm_load_print_meta: FIM PAD token = 151662 '<|fim_pad|>' llm_load_print_meta: FIM REP token = 151663 '<|repo_name|>' llm_load_print_meta: FIM SEP token = 151664 '<|file_sep|>' llm_load_print_meta: EOG token = 151643 '<|endoftext|>' llm_load_print_meta: EOG token = 151645 '<|im_end|>' llm_load_print_meta: EOG token = 151662 '<|fim_pad|>' llm_load_print_meta: EOG token = 151663 '<|repo_name|>' llm_load_print_meta: EOG token = 151664 '<|file_sep|>' llm_load_print_meta: max token length = 256 llama_model_load: vocab only - skipping tensors [GIN] 2025/02/10 - 11:54:01 | 200 | 4m26s | 10.88.0.1 | POST "/v1/chat/completions" [GIN] 2025/02/10 - 11:54:21 | 200 | 4m29s | 10.88.0.1 | POST "/v1/chat/completions" [GIN] 2025/02/10 - 11:54:22 | 200 | 4m33s | 10.88.0.1 | POST "/v1/chat/completions" [GIN] 2025/02/10 - 11:54:23 | 200 | 5m9s | 10.88.0.1 | POST "/v1/chat/completions" time=2025-02-10T11:59:29.046Z level=WARN source=sched.go:646 msg="gpu VRAM usage didn't recover within timeout" seconds=5.1281383 model=/root/.ollama/models/blobs/sha256-2bada8a745 0677000f678be90653b85d364de7db25eb5ea54136ada5f3933730 time=2025-02-10T11:59:29.295Z level=WARN source=sched.go:646 msg="gpu VRAM usage didn't recover within timeout" seconds=5.377539302 model=/root/.ollama/models/blobs/sha256-2bada8a7 450677000f678be90653b85d364de7db25eb5ea54136ada5f3933730 time=2025-02-10T11:59:29.546Z level=WARN source=sched.go:646 msg="gpu VRAM usage didn't recover within timeout" seconds=5.628414795 model=/root/.ollama/models/blobs/sha256-2bada8a7 450677000f678be90653b85d364de7db25eb5ea54136ada5f3933730 ``` ### OS Windows ### GPU Nvidia ### CPU Intel ### Ollama version ollama version is 0.5.7-0-ga420a45-dirty
GiteaMirror added the bug label 2026-04-12 17:10:49 -05:00
GiteaMirror commented 2026-04-12 17:10:50 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Feb 10, 2025):

https://github.com/ollama/ollama/blob/main/docs/faq.md#how-do-i-keep-a-model-loaded-in-memory-or-make-it-unload-immediately

<!-- gh-comment-id:2647803115 --> @rick-github commented on GitHub (Feb 10, 2025): https://github.com/ollama/ollama/blob/main/docs/faq.md#how-do-i-keep-a-model-loaded-in-memory-or-make-it-unload-immediately
GiteaMirror commented 2026-04-12 17:10:50 -05:00
Author
Owner
Copy Link

@hualong1009 commented on GitHub (Feb 10, 2025):

@rick-github Thanks for your reply. I found the solution at issue #6006, after copy model files to wsl , and mount new volume to podman container, it work for me.

<!-- gh-comment-id:2647855557 --> @hualong1009 commented on GitHub (Feb 10, 2025): @rick-github Thanks for your reply. I found the solution at issue [#6006](https://github.com/ollama/ollama/issues/6006), after copy model files to wsl , and mount new volume to podman container, it work for me.
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#5838
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?