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 #11261] the model load success and then it's gone #33182

New Issue
Closed
opened 2026-04-22 15:36:57 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-22 15:36:57 -05:00
Owner
Copy Link

Originally created by @fishfl on GitHub (Jul 2, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/11261

What is the issue?

is ollama has a lazy mode?
We load the llava model use the API, it's success.
we use the ‘ollama ps’ command and can see the model process.
But After a few minutes the model process it's gone.

Image

Relevant log output

time=2025-07-02T02:37:03.946Z level=INFO source=routes.go:1235 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://0.0.0.0:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/root/.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: http_proxy: https_proxy: no_proxy:]"
time=2025-07-02T02:37:03.947Z level=INFO source=images.go:480 msg="total blobs: 0"
time=2025-07-02T02:37:03.947Z level=INFO source=images.go:487 msg="total unused blobs removed: 0"
time=2025-07-02T02:37:03.947Z level=INFO source=routes.go:1288 msg="Listening on [::]:11434 (version 0.9.2)"
time=2025-07-02T02:37:03.947Z level=INFO source=gpu.go:217 msg="looking for compatible GPUs"
time=2025-07-02T02:37:03.956Z level=INFO source=gpu.go:377 msg="no compatible GPUs were discovered"
time=2025-07-02T02:37:03.956Z level=INFO source=types.go:130 msg="inference compute" id=0 library=cpu variant="" compute="" driver=0.0 name="" total="313.9 GiB" available="149.7 GiB"
time=2025-07-02T02:40:18.993Z level=INFO source=server.go:135 msg="system memory" total="313.9 GiB" free="147.6 GiB" free_swap="0 B"
time=2025-07-02T02:40:18.995Z level=INFO source=server.go:168 msg=offload library=cpu layers.requested=-1 layers.model=33 layers.offload=0 layers.split="" memory.available="[147.6 GiB]" memory.gpu_overhead="0 B" memory.required.full="6.0 GiB" memory.required.partial="0 B" memory.required.kv="1.0 GiB" memory.required.allocations="[6.0 GiB]" memory.weights.total="3.8 GiB" memory.weights.repeating="3.7 GiB" memory.weights.nonrepeating="102.6 MiB" memory.graph.full="560.0 MiB" memory.graph.partial="585.0 MiB" projector.weights="595.5 MiB" projector.graph="0 B"
llama_model_loader: loaded meta data with 24 key-value pairs and 291 tensors from /root/.ollama/models/blobs/sha256-170370233dd5c5415250a2ecd5c71586352850729062ccef1496385647293868 (version GGUF V3 (latest))
llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
llama_model_loader: - kv   0:                       general.architecture str              = llama
llama_model_loader: - kv   1:                               general.name str              = liuhaotian
llama_model_loader: - kv   2:                       llama.context_length u32              = 32768
llama_model_loader: - kv   3:                     llama.embedding_length u32              = 4096
llama_model_loader: - kv   4:                          llama.block_count u32              = 32
llama_model_loader: - kv   5:                  llama.feed_forward_length u32              = 14336
llama_model_loader: - kv   6:                 llama.rope.dimension_count u32              = 128
llama_model_loader: - kv   7:                 llama.attention.head_count u32              = 32
llama_model_loader: - kv   8:              llama.attention.head_count_kv u32              = 8
llama_model_loader: - kv   9:     llama.attention.layer_norm_rms_epsilon f32              = 0.000010
llama_model_loader: - kv  10:                       llama.rope.freq_base f32              = 1000000.000000
llama_model_loader: - kv  11:                          general.file_type u32              = 2
llama_model_loader: - kv  12:                       tokenizer.ggml.model str              = llama
llama_model_loader: - kv  13:                      tokenizer.ggml.tokens arr[str,32000]   = ["<unk>", "<s>", "</s>", "<0x00>", "<...
llama_model_loader: - kv  14:                      tokenizer.ggml.scores arr[f32,32000]   = [0.000000, 0.000000, 0.000000, 0.0000...
llama_model_loader: - kv  15:                  tokenizer.ggml.token_type arr[i32,32000]   = [2, 3, 3, 6, 6, 6, 6, 6, 6, 6, 6, 6, ...
llama_model_loader: - kv  16:                tokenizer.ggml.bos_token_id u32              = 1
llama_model_loader: - kv  17:                tokenizer.ggml.eos_token_id u32              = 2
llama_model_loader: - kv  18:            tokenizer.ggml.unknown_token_id u32              = 0
llama_model_loader: - kv  19:            tokenizer.ggml.padding_token_id u32              = 0
llama_model_loader: - kv  20:               tokenizer.ggml.add_bos_token bool             = true
llama_model_loader: - kv  21:               tokenizer.ggml.add_eos_token bool             = false
llama_model_loader: - kv  22:                    tokenizer.chat_template str              = {{ bos_token }}{% for message in mess...
llama_model_loader: - kv  23:               general.quantization_version u32              = 2
llama_model_loader: - type  f32:   65 tensors
llama_model_loader: - type q4_0:  225 tensors
llama_model_loader: - type q6_K:    1 tensors
print_info: file format = GGUF V3 (latest)
print_info: file type   = Q4_0
print_info: file size   = 3.83 GiB (4.54 BPW)
load: special_eos_id is not in special_eog_ids - the tokenizer config may be incorrect
load: special tokens cache size = 3
load: token to piece cache size = 0.1637 MB
print_info: arch             = llama
print_info: vocab_only       = 1
print_info: model type       = ?B
print_info: model params     = 7.24 B
print_info: general.name     = liuhaotian
print_info: vocab type       = SPM
print_info: n_vocab          = 32000
print_info: n_merges         = 0
print_info: BOS token        = 1 '<s>'
print_info: EOS token        = 2 '</s>'
print_info: UNK token        = 0 '<unk>'
print_info: PAD token        = 0 '<unk>'
print_info: LF token         = 13 '<0x0A>'
print_info: EOG token        = 2 '</s>'
print_info: max token length = 48
llama_model_load: vocab only - skipping tensors
time=2025-07-02T02:40:19.097Z level=INFO source=server.go:431 msg="starting llama server" cmd="/usr/bin/ollama runner --model /root/.ollama/models/blobs/sha256-170370233dd5c5415250a2ecd5c71586352850729062ccef1496385647293868 --ctx-size 8192 --batch-size 512 --threads 36 --no-mmap --parallel 2 --mmproj /root/.ollama/models/blobs/sha256-72d6f08a42f656d36b356dbe0920675899a99ce21192fd66266fb7d82ed07539 --port 40903"
time=2025-07-02T02:40:19.097Z level=INFO source=sched.go:483 msg="loaded runners" count=1
time=2025-07-02T02:40:19.097Z level=INFO source=server.go:591 msg="waiting for llama runner to start responding"
time=2025-07-02T02:40:19.098Z level=INFO source=server.go:625 msg="waiting for server to become available" status="llm server not responding"
time=2025-07-02T02:40:19.116Z level=INFO source=runner.go:815 msg="starting go runner"
load_backend: loaded CPU backend from /usr/lib/ollama/libggml-cpu-skylakex.so
time=2025-07-02T02:40:19.126Z 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.AVX512=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 compiler=cgo(gcc)
time=2025-07-02T02:40:19.128Z level=INFO source=runner.go:874 msg="Server listening on 127.0.0.1:40903"
llama_model_loader: loaded meta data with 24 key-value pairs and 291 tensors from /root/.ollama/models/blobs/sha256-170370233dd5c5415250a2ecd5c71586352850729062ccef1496385647293868 (version GGUF V3 (latest))
llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
llama_model_loader: - kv   0:                       general.architecture str              = llama
llama_model_loader: - kv   1:                               general.name str              = liuhaotian
llama_model_loader: - kv   2:                       llama.context_length u32              = 32768
llama_model_loader: - kv   3:                     llama.embedding_length u32              = 4096
llama_model_loader: - kv   4:                          llama.block_count u32              = 32
llama_model_loader: - kv   5:                  llama.feed_forward_length u32              = 14336
llama_model_loader: - kv   6:                 llama.rope.dimension_count u32              = 128
llama_model_loader: - kv   7:                 llama.attention.head_count u32              = 32
llama_model_loader: - kv   8:              llama.attention.head_count_kv u32              = 8
llama_model_loader: - kv   9:     llama.attention.layer_norm_rms_epsilon f32              = 0.000010
llama_model_loader: - kv  10:                       llama.rope.freq_base f32              = 1000000.000000
llama_model_loader: - kv  11:                          general.file_type u32              = 2
llama_model_loader: - kv  12:                       tokenizer.ggml.model str              = llama
llama_model_loader: - kv  13:                      tokenizer.ggml.tokens arr[str,32000]   = ["<unk>", "<s>", "</s>", "<0x00>", "<...
llama_model_loader: - kv  14:                      tokenizer.ggml.scores arr[f32,32000]   = [0.000000, 0.000000, 0.000000, 0.0000...
llama_model_loader: - kv  15:                  tokenizer.ggml.token_type arr[i32,32000]   = [2, 3, 3, 6, 6, 6, 6, 6, 6, 6, 6, 6, ...
llama_model_loader: - kv  16:                tokenizer.ggml.bos_token_id u32              = 1
llama_model_loader: - kv  17:                tokenizer.ggml.eos_token_id u32              = 2
llama_model_loader: - kv  18:            tokenizer.ggml.unknown_token_id u32              = 0
llama_model_loader: - kv  19:            tokenizer.ggml.padding_token_id u32              = 0
llama_model_loader: - kv  20:               tokenizer.ggml.add_bos_token bool             = true
llama_model_loader: - kv  21:               tokenizer.ggml.add_eos_token bool             = false
llama_model_loader: - kv  22:                    tokenizer.chat_template str              = {{ bos_token }}{% for message in mess...
llama_model_loader: - kv  23:               general.quantization_version u32              = 2
llama_model_loader: - type  f32:   65 tensors
llama_model_loader: - type q4_0:  225 tensors
llama_model_loader: - type q6_K:    1 tensors
print_info: file format = GGUF V3 (latest)
print_info: file type   = Q4_0
print_info: file size   = 3.83 GiB (4.54 BPW)
load: special_eos_id is not in special_eog_ids - the tokenizer config may be incorrect
load: special tokens cache size = 3
load: token to piece cache size = 0.1637 MB
print_info: arch             = llama
print_info: vocab_only       = 0
print_info: n_ctx_train      = 32768
print_info: n_embd           = 4096
print_info: n_layer          = 32
print_info: n_head           = 32
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            = 4
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-05
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             = 14336
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        = 0
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       = 7B
print_info: model params     = 7.24 B
print_info: general.name     = liuhaotian
print_info: vocab type       = SPM
print_info: n_vocab          = 32000
print_info: n_merges         = 0
print_info: BOS token        = 1 '<s>'
print_info: EOS token        = 2 '</s>'
print_info: UNK token        = 0 '<unk>'
print_info: PAD token        = 0 '<unk>'
print_info: LF token         = 13 '<0x0A>'
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:          CPU model buffer size =  3917.87 MiB
time=2025-07-02T02:40:19.349Z level=INFO source=server.go:625 msg="waiting for server to become available" status="llm server loading model"
[GIN] 2025/07/02 - 02:40:19 | 200 |      41.398µs |       127.0.0.1 | HEAD     "/"
[GIN] 2025/07/02 - 02:40:19 | 200 |     193.973µs |       127.0.0.1 | GET      "/api/ps"
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 (32768) -- the full capacity of the model will not be utilized
llama_context:        CPU  output buffer size =     0.28 MiB
llama_kv_cache_unified: kv_size = 8192, type_k = 'f16', type_v = 'f16', n_layer = 32, can_shift = 1, padding = 32
llama_kv_cache_unified:        CPU KV buffer size =  1024.00 MiB
llama_kv_cache_unified: KV self size  = 1024.00 MiB, K (f16):  512.00 MiB, V (f16):  512.00 MiB
llama_context:        CPU compute buffer size =   560.01 MiB
llama_context: graph nodes  = 1094
llama_context: graph splits = 1
clip_ctx: CLIP using CPU backend
clip_model_loader: model name:   openai/clip-vit-large-patch14-336
clip_model_loader: description:  image encoder for LLaVA
clip_model_loader: GGUF version: 3
clip_model_loader: alignment:    32
clip_model_loader: n_tensors:    377
clip_model_loader: n_kv:         19

clip_model_loader: tensor[0]: n_dims = 1, name = mm.0.bias, tensor_size=16384, offset=0, shape:[4096, 1, 1, 1], type = f32
clip_model_loader: tensor[1]: n_dims = 2, name = mm.0.weight, tensor_size=8388608, offset=16384, shape:[1024, 4096, 1, 1], type = f16
clip_model_loader: tensor[2]: n_dims = 1, name = mm.2.bias, tensor_size=16384, offset=8404992, shape:[4096, 1, 1, 1], type = f32

...

load_hparams: projector:          mlp
load_hparams: n_embd:             1024
load_hparams: n_head:             16
load_hparams: n_ff:               4096
load_hparams: n_layer:            23
load_hparams: projection_dim:     768
load_hparams: image_size:         336
load_hparams: patch_size:         14

load_hparams: has_llava_proj:     1
load_hparams: minicpmv_version:   0
load_hparams: proj_scale_factor:  0
load_hparams: n_wa_pattern:       0
load_hparams: ffn_op:             gelu_quick
load_hparams: model size:         595.49 MiB
load_hparams: metadata size:      0.13 MiB
load_tensors: loaded 377 tensors from /root/.ollama/models/blobs/sha256-72d6f08a42f656d36b356dbe0920675899a99ce21192fd66266fb7d82ed07539
alloc_compute_meta:        CPU compute buffer size =    32.88 MiB
time=2025-07-02T02:40:23.611Z level=INFO source=server.go:630 msg="llama runner started in 4.51 seconds"
[GIN] 2025/07/02 - 02:40:23 | 200 |   4.64251133s |   10.147.13.186 | POST     "/api/chat"
[GIN] 2025/07/02 - 02:40:35 | 200 |      42.935µs |       127.0.0.1 | HEAD     "/"

OS

Linux

GPU

No response

CPU

Intel

Ollama version

0.9.2

Originally created by @fishfl on GitHub (Jul 2, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/11261 ### What is the issue? is ollama has a lazy mode? We load the llava model use the API, it's success. we use the ‘ollama ps’ command and can see the model process. But After a few minutes the model process it's gone. ![Image](https://github.com/user-attachments/assets/8356b752-5ca6-41d9-9942-abcffbb58956) ### Relevant log output ```shell time=2025-07-02T02:37:03.946Z level=INFO source=routes.go:1235 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://0.0.0.0:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/root/.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: http_proxy: https_proxy: no_proxy:]" time=2025-07-02T02:37:03.947Z level=INFO source=images.go:480 msg="total blobs: 0" time=2025-07-02T02:37:03.947Z level=INFO source=images.go:487 msg="total unused blobs removed: 0" time=2025-07-02T02:37:03.947Z level=INFO source=routes.go:1288 msg="Listening on [::]:11434 (version 0.9.2)" time=2025-07-02T02:37:03.947Z level=INFO source=gpu.go:217 msg="looking for compatible GPUs" time=2025-07-02T02:37:03.956Z level=INFO source=gpu.go:377 msg="no compatible GPUs were discovered" time=2025-07-02T02:37:03.956Z level=INFO source=types.go:130 msg="inference compute" id=0 library=cpu variant="" compute="" driver=0.0 name="" total="313.9 GiB" available="149.7 GiB" time=2025-07-02T02:40:18.993Z level=INFO source=server.go:135 msg="system memory" total="313.9 GiB" free="147.6 GiB" free_swap="0 B" time=2025-07-02T02:40:18.995Z level=INFO source=server.go:168 msg=offload library=cpu layers.requested=-1 layers.model=33 layers.offload=0 layers.split="" memory.available="[147.6 GiB]" memory.gpu_overhead="0 B" memory.required.full="6.0 GiB" memory.required.partial="0 B" memory.required.kv="1.0 GiB" memory.required.allocations="[6.0 GiB]" memory.weights.total="3.8 GiB" memory.weights.repeating="3.7 GiB" memory.weights.nonrepeating="102.6 MiB" memory.graph.full="560.0 MiB" memory.graph.partial="585.0 MiB" projector.weights="595.5 MiB" projector.graph="0 B" llama_model_loader: loaded meta data with 24 key-value pairs and 291 tensors from /root/.ollama/models/blobs/sha256-170370233dd5c5415250a2ecd5c71586352850729062ccef1496385647293868 (version GGUF V3 (latest)) llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output. llama_model_loader: - kv 0: general.architecture str = llama llama_model_loader: - kv 1: general.name str = liuhaotian llama_model_loader: - kv 2: llama.context_length u32 = 32768 llama_model_loader: - kv 3: llama.embedding_length u32 = 4096 llama_model_loader: - kv 4: llama.block_count u32 = 32 llama_model_loader: - kv 5: llama.feed_forward_length u32 = 14336 llama_model_loader: - kv 6: llama.rope.dimension_count u32 = 128 llama_model_loader: - kv 7: llama.attention.head_count u32 = 32 llama_model_loader: - kv 8: llama.attention.head_count_kv u32 = 8 llama_model_loader: - kv 9: llama.attention.layer_norm_rms_epsilon f32 = 0.000010 llama_model_loader: - kv 10: llama.rope.freq_base f32 = 1000000.000000 llama_model_loader: - kv 11: general.file_type u32 = 2 llama_model_loader: - kv 12: tokenizer.ggml.model str = llama llama_model_loader: - kv 13: tokenizer.ggml.tokens arr[str,32000] = ["<unk>", "<s>", "</s>", "<0x00>", "<... llama_model_loader: - kv 14: tokenizer.ggml.scores arr[f32,32000] = [0.000000, 0.000000, 0.000000, 0.0000... llama_model_loader: - kv 15: tokenizer.ggml.token_type arr[i32,32000] = [2, 3, 3, 6, 6, 6, 6, 6, 6, 6, 6, 6, ... llama_model_loader: - kv 16: tokenizer.ggml.bos_token_id u32 = 1 llama_model_loader: - kv 17: tokenizer.ggml.eos_token_id u32 = 2 llama_model_loader: - kv 18: tokenizer.ggml.unknown_token_id u32 = 0 llama_model_loader: - kv 19: tokenizer.ggml.padding_token_id u32 = 0 llama_model_loader: - kv 20: tokenizer.ggml.add_bos_token bool = true llama_model_loader: - kv 21: tokenizer.ggml.add_eos_token bool = false llama_model_loader: - kv 22: tokenizer.chat_template str = {{ bos_token }}{% for message in mess... llama_model_loader: - kv 23: general.quantization_version u32 = 2 llama_model_loader: - type f32: 65 tensors llama_model_loader: - type q4_0: 225 tensors llama_model_loader: - type q6_K: 1 tensors print_info: file format = GGUF V3 (latest) print_info: file type = Q4_0 print_info: file size = 3.83 GiB (4.54 BPW) load: special_eos_id is not in special_eog_ids - the tokenizer config may be incorrect load: special tokens cache size = 3 load: token to piece cache size = 0.1637 MB print_info: arch = llama print_info: vocab_only = 1 print_info: model type = ?B print_info: model params = 7.24 B print_info: general.name = liuhaotian print_info: vocab type = SPM print_info: n_vocab = 32000 print_info: n_merges = 0 print_info: BOS token = 1 '<s>' print_info: EOS token = 2 '</s>' print_info: UNK token = 0 '<unk>' print_info: PAD token = 0 '<unk>' print_info: LF token = 13 '<0x0A>' print_info: EOG token = 2 '</s>' print_info: max token length = 48 llama_model_load: vocab only - skipping tensors time=2025-07-02T02:40:19.097Z level=INFO source=server.go:431 msg="starting llama server" cmd="/usr/bin/ollama runner --model /root/.ollama/models/blobs/sha256-170370233dd5c5415250a2ecd5c71586352850729062ccef1496385647293868 --ctx-size 8192 --batch-size 512 --threads 36 --no-mmap --parallel 2 --mmproj /root/.ollama/models/blobs/sha256-72d6f08a42f656d36b356dbe0920675899a99ce21192fd66266fb7d82ed07539 --port 40903" time=2025-07-02T02:40:19.097Z level=INFO source=sched.go:483 msg="loaded runners" count=1 time=2025-07-02T02:40:19.097Z level=INFO source=server.go:591 msg="waiting for llama runner to start responding" time=2025-07-02T02:40:19.098Z level=INFO source=server.go:625 msg="waiting for server to become available" status="llm server not responding" time=2025-07-02T02:40:19.116Z level=INFO source=runner.go:815 msg="starting go runner" load_backend: loaded CPU backend from /usr/lib/ollama/libggml-cpu-skylakex.so time=2025-07-02T02:40:19.126Z 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.AVX512=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 compiler=cgo(gcc) time=2025-07-02T02:40:19.128Z level=INFO source=runner.go:874 msg="Server listening on 127.0.0.1:40903" llama_model_loader: loaded meta data with 24 key-value pairs and 291 tensors from /root/.ollama/models/blobs/sha256-170370233dd5c5415250a2ecd5c71586352850729062ccef1496385647293868 (version GGUF V3 (latest)) llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output. llama_model_loader: - kv 0: general.architecture str = llama llama_model_loader: - kv 1: general.name str = liuhaotian llama_model_loader: - kv 2: llama.context_length u32 = 32768 llama_model_loader: - kv 3: llama.embedding_length u32 = 4096 llama_model_loader: - kv 4: llama.block_count u32 = 32 llama_model_loader: - kv 5: llama.feed_forward_length u32 = 14336 llama_model_loader: - kv 6: llama.rope.dimension_count u32 = 128 llama_model_loader: - kv 7: llama.attention.head_count u32 = 32 llama_model_loader: - kv 8: llama.attention.head_count_kv u32 = 8 llama_model_loader: - kv 9: llama.attention.layer_norm_rms_epsilon f32 = 0.000010 llama_model_loader: - kv 10: llama.rope.freq_base f32 = 1000000.000000 llama_model_loader: - kv 11: general.file_type u32 = 2 llama_model_loader: - kv 12: tokenizer.ggml.model str = llama llama_model_loader: - kv 13: tokenizer.ggml.tokens arr[str,32000] = ["<unk>", "<s>", "</s>", "<0x00>", "<... llama_model_loader: - kv 14: tokenizer.ggml.scores arr[f32,32000] = [0.000000, 0.000000, 0.000000, 0.0000... llama_model_loader: - kv 15: tokenizer.ggml.token_type arr[i32,32000] = [2, 3, 3, 6, 6, 6, 6, 6, 6, 6, 6, 6, ... llama_model_loader: - kv 16: tokenizer.ggml.bos_token_id u32 = 1 llama_model_loader: - kv 17: tokenizer.ggml.eos_token_id u32 = 2 llama_model_loader: - kv 18: tokenizer.ggml.unknown_token_id u32 = 0 llama_model_loader: - kv 19: tokenizer.ggml.padding_token_id u32 = 0 llama_model_loader: - kv 20: tokenizer.ggml.add_bos_token bool = true llama_model_loader: - kv 21: tokenizer.ggml.add_eos_token bool = false llama_model_loader: - kv 22: tokenizer.chat_template str = {{ bos_token }}{% for message in mess... llama_model_loader: - kv 23: general.quantization_version u32 = 2 llama_model_loader: - type f32: 65 tensors llama_model_loader: - type q4_0: 225 tensors llama_model_loader: - type q6_K: 1 tensors print_info: file format = GGUF V3 (latest) print_info: file type = Q4_0 print_info: file size = 3.83 GiB (4.54 BPW) load: special_eos_id is not in special_eog_ids - the tokenizer config may be incorrect load: special tokens cache size = 3 load: token to piece cache size = 0.1637 MB print_info: arch = llama print_info: vocab_only = 0 print_info: n_ctx_train = 32768 print_info: n_embd = 4096 print_info: n_layer = 32 print_info: n_head = 32 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 = 4 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-05 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 = 14336 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 = 0 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 = 7B print_info: model params = 7.24 B print_info: general.name = liuhaotian print_info: vocab type = SPM print_info: n_vocab = 32000 print_info: n_merges = 0 print_info: BOS token = 1 '<s>' print_info: EOS token = 2 '</s>' print_info: UNK token = 0 '<unk>' print_info: PAD token = 0 '<unk>' print_info: LF token = 13 '<0x0A>' 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: CPU model buffer size = 3917.87 MiB time=2025-07-02T02:40:19.349Z level=INFO source=server.go:625 msg="waiting for server to become available" status="llm server loading model" [GIN] 2025/07/02 - 02:40:19 | 200 | 41.398µs | 127.0.0.1 | HEAD "/" [GIN] 2025/07/02 - 02:40:19 | 200 | 193.973µs | 127.0.0.1 | GET "/api/ps" 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 (32768) -- the full capacity of the model will not be utilized llama_context: CPU output buffer size = 0.28 MiB llama_kv_cache_unified: kv_size = 8192, type_k = 'f16', type_v = 'f16', n_layer = 32, can_shift = 1, padding = 32 llama_kv_cache_unified: CPU KV buffer size = 1024.00 MiB llama_kv_cache_unified: KV self size = 1024.00 MiB, K (f16): 512.00 MiB, V (f16): 512.00 MiB llama_context: CPU compute buffer size = 560.01 MiB llama_context: graph nodes = 1094 llama_context: graph splits = 1 clip_ctx: CLIP using CPU backend clip_model_loader: model name: openai/clip-vit-large-patch14-336 clip_model_loader: description: image encoder for LLaVA clip_model_loader: GGUF version: 3 clip_model_loader: alignment: 32 clip_model_loader: n_tensors: 377 clip_model_loader: n_kv: 19 clip_model_loader: tensor[0]: n_dims = 1, name = mm.0.bias, tensor_size=16384, offset=0, shape:[4096, 1, 1, 1], type = f32 clip_model_loader: tensor[1]: n_dims = 2, name = mm.0.weight, tensor_size=8388608, offset=16384, shape:[1024, 4096, 1, 1], type = f16 clip_model_loader: tensor[2]: n_dims = 1, name = mm.2.bias, tensor_size=16384, offset=8404992, shape:[4096, 1, 1, 1], type = f32 ... load_hparams: projector: mlp load_hparams: n_embd: 1024 load_hparams: n_head: 16 load_hparams: n_ff: 4096 load_hparams: n_layer: 23 load_hparams: projection_dim: 768 load_hparams: image_size: 336 load_hparams: patch_size: 14 load_hparams: has_llava_proj: 1 load_hparams: minicpmv_version: 0 load_hparams: proj_scale_factor: 0 load_hparams: n_wa_pattern: 0 load_hparams: ffn_op: gelu_quick load_hparams: model size: 595.49 MiB load_hparams: metadata size: 0.13 MiB load_tensors: loaded 377 tensors from /root/.ollama/models/blobs/sha256-72d6f08a42f656d36b356dbe0920675899a99ce21192fd66266fb7d82ed07539 alloc_compute_meta: CPU compute buffer size = 32.88 MiB time=2025-07-02T02:40:23.611Z level=INFO source=server.go:630 msg="llama runner started in 4.51 seconds" [GIN] 2025/07/02 - 02:40:23 | 200 | 4.64251133s | 10.147.13.186 | POST "/api/chat" [GIN] 2025/07/02 - 02:40:35 | 200 | 42.935µs | 127.0.0.1 | HEAD "/" ``` ### OS Linux ### GPU _No response_ ### CPU Intel ### Ollama version 0.9.2
GiteaMirror added the bug label 2026-04-22 15:36:57 -05:00
GiteaMirror commented 2026-04-22 15:37:01 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Jul 2, 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:3026181061 --> @rick-github commented on GitHub (Jul 2, 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 2026-04-22 15:37:03 -05:00
Author
Owner
Copy Link

@gee-coder commented on GitHub (Jul 4, 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

@fishfl The log you provided shows that the survival time you set for the model is 5 minutes, so your model will be destroyed from memory after 5 minutes.

Image

This is not a bug. You may need to read the documentation provided by @rick-github first to understand how to set a model to remain in memory forever

<!-- gh-comment-id:3034362530 --> @gee-coder commented on GitHub (Jul 4, 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 @fishfl The log you provided shows that the survival time you set for the model is 5 minutes, so your model will be destroyed from memory after 5 minutes. ![Image](https://github.com/user-attachments/assets/41e4c042-a66d-478f-a891-aba0302cdd72) This is not a bug. You may need to read the documentation provided by @rick-github first to understand how to set a model to remain in memory forever
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#33182
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?