github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-17 21:55:43 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #11963] gml_cuda_init: failed to initialize CUDA: system not yet initialized #7943

New Issue
Closed
opened 2026-04-12 20:06:27 -05:00 by GiteaMirror · 5 comments
GiteaMirror commented 2026-04-12 20:06:27 -05:00
Owner
Copy Link

Originally created by @minmie on GitHub (Aug 19, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/11963

What is the issue?

I use the following command to start ollama container:

docker run -d --gpus=all  -p 11434:11434 --name ollama   -v /data01/models:/root/.ollama -d   --restart always  ollama/ollama

I have 8 GPUs, and when I run the model using 'ollama run', I found that ollama always uses CPU. I found the following error in the log:

gml_cuda_init: failed to initialize CUDA: system not yet initialized

how to fix this so that ollama can use GPU?

environment:
ollama images: ollama/ollama latest 029391db139
ollama version: 0.9.6
GPU:

Image Image

Relevant log output

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 '<｜end▁of▁sentence｜>'
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=2025-08-19T07:42:47.630Z level=INFO source=server.go:438 msg="starting llama server" cmd="/usr/bin/ollama runner --model /root/.ollama/models/blobs/sha256-96c415656d377afbff962f6cdb2394ab092ccbcbaab4b82525bc4ca800fe8a49 --ctx-size 8192 --batch-size 512 --threads 96 --no-mmap --parallel 2 --port 42195"
time=2025-08-19T07:42:47.631Z level=INFO source=sched.go:483 msg="loaded runners" count=1
time=2025-08-19T07:42:47.631Z level=INFO source=server.go:598 msg="waiting for llama runner to start responding"
time=2025-08-19T07:42:47.631Z level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server not responding"
time=2025-08-19T07:42:47.646Z level=INFO source=runner.go:815 msg="starting go runner"
ggml_cuda_init: failed to initialize CUDA: system not yet initialized
load_backend: loaded CUDA backend from /usr/lib/ollama/libggml-cuda.so
load_backend: loaded CPU backend from /usr/lib/ollama/libggml-cpu-haswell.so
time=2025-08-19T07:42:47.886Z 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 compiler=cgo(gcc)
time=2025-08-19T07:42:47.887Z level=INFO source=runner.go:874 msg="Server listening on 127.0.0.1:42195"
llama_model_loader: loaded meta data with 26 key-value pairs and 339 tensors from /root/.ollama/models/blobs/sha256-96c415656d377afbff962f6cdb2394ab092ccbcbaab4b82525bc4ca800fe8a49 (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              = DeepSeek R1 Distill Qwen 7B
llama_model_loader: - kv   3:                           general.basename str              = DeepSeek-R1-Distill-Qwen
llama_model_loader: - kv   4:                         general.size_label str              = 7B
llama_model_loader: - kv   5:                          qwen2.block_count u32              = 28
llama_model_loader: - kv   6:                       qwen2.context_length u32              = 131072
llama_model_loader: - kv   7:                     qwen2.embedding_length u32              = 3584
llama_model_loader: - kv   8:                  qwen2.feed_forward_length u32              = 18944
llama_model_loader: - kv   9:                 qwen2.attention.head_count u32              = 28
llama_model_loader: - kv  10:              qwen2.attention.head_count_kv u32              = 4
llama_model_loader: - kv  11:                       qwen2.rope.freq_base f32              = 10000.000000
llama_model_loader: - kv  12:     qwen2.attention.layer_norm_rms_epsilon f32              = 0.000001
llama_model_loader: - kv  13:                          general.file_type u32              = 15
llama_model_loader: - kv  14:                       tokenizer.ggml.model str              = gpt2
llama_model_loader: - kv  15:                         tokenizer.ggml.pre str              = qwen2
llama_model_loader: - kv  16:                      tokenizer.ggml.tokens arr[str,152064]  = ["!", "\"", "#", "$", "%", "&", "'", ...
llama_model_loader: - kv  17:                  tokenizer.ggml.token_type arr[i32,152064]  = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv  18:                      tokenizer.ggml.merges arr[str,151387]  = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
llama_model_loader: - kv  19:                tokenizer.ggml.bos_token_id u32              = 151646
llama_model_loader: - kv  20:                tokenizer.ggml.eos_token_id u32              = 151643
llama_model_loader: - kv  21:            tokenizer.ggml.padding_token_id u32              = 151643
llama_model_loader: - kv  22:               tokenizer.ggml.add_bos_token bool             = true
llama_model_loader: - kv  23:               tokenizer.ggml.add_eos_token bool             = false

OS

Docker

GPU

Nvidia

CPU

Intel

Ollama version

0.9.6

Originally created by @minmie on GitHub (Aug 19, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/11963 ### What is the issue? I use the following command to start ollama container: ``` docker run -d --gpus=all -p 11434:11434 --name ollama -v /data01/models:/root/.ollama -d --restart always ollama/ollama ``` I have 8 GPUs, and when I run the model using 'ollama run', I found that ollama always uses CPU. I found the following error in the log: ``` gml_cuda_init: failed to initialize CUDA: system not yet initialized ``` how to fix this so that ollama can use GPU? environment: ollama images: ollama/ollama latest 029391db139 ollama version: 0.9.6 GPU: <img width="856" height="635" alt="Image" src="https://github.com/user-attachments/assets/df6411f9-0aa0-43bf-90fb-cb08f1e17222" /> <img width="416" height="118" alt="Image" src="https://github.com/user-attachments/assets/b158a611-1422-4486-adc0-aaae3378d192" /> ### Relevant log output ```shell 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 '<｜end▁of▁sentence｜>' 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=2025-08-19T07:42:47.630Z level=INFO source=server.go:438 msg="starting llama server" cmd="/usr/bin/ollama runner --model /root/.ollama/models/blobs/sha256-96c415656d377afbff962f6cdb2394ab092ccbcbaab4b82525bc4ca800fe8a49 --ctx-size 8192 --batch-size 512 --threads 96 --no-mmap --parallel 2 --port 42195" time=2025-08-19T07:42:47.631Z level=INFO source=sched.go:483 msg="loaded runners" count=1 time=2025-08-19T07:42:47.631Z level=INFO source=server.go:598 msg="waiting for llama runner to start responding" time=2025-08-19T07:42:47.631Z level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server not responding" time=2025-08-19T07:42:47.646Z level=INFO source=runner.go:815 msg="starting go runner" ggml_cuda_init: failed to initialize CUDA: system not yet initialized load_backend: loaded CUDA backend from /usr/lib/ollama/libggml-cuda.so load_backend: loaded CPU backend from /usr/lib/ollama/libggml-cpu-haswell.so time=2025-08-19T07:42:47.886Z 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 compiler=cgo(gcc) time=2025-08-19T07:42:47.887Z level=INFO source=runner.go:874 msg="Server listening on 127.0.0.1:42195" llama_model_loader: loaded meta data with 26 key-value pairs and 339 tensors from /root/.ollama/models/blobs/sha256-96c415656d377afbff962f6cdb2394ab092ccbcbaab4b82525bc4ca800fe8a49 (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 = DeepSeek R1 Distill Qwen 7B llama_model_loader: - kv 3: general.basename str = DeepSeek-R1-Distill-Qwen llama_model_loader: - kv 4: general.size_label str = 7B llama_model_loader: - kv 5: qwen2.block_count u32 = 28 llama_model_loader: - kv 6: qwen2.context_length u32 = 131072 llama_model_loader: - kv 7: qwen2.embedding_length u32 = 3584 llama_model_loader: - kv 8: qwen2.feed_forward_length u32 = 18944 llama_model_loader: - kv 9: qwen2.attention.head_count u32 = 28 llama_model_loader: - kv 10: qwen2.attention.head_count_kv u32 = 4 llama_model_loader: - kv 11: qwen2.rope.freq_base f32 = 10000.000000 llama_model_loader: - kv 12: qwen2.attention.layer_norm_rms_epsilon f32 = 0.000001 llama_model_loader: - kv 13: general.file_type u32 = 15 llama_model_loader: - kv 14: tokenizer.ggml.model str = gpt2 llama_model_loader: - kv 15: tokenizer.ggml.pre str = qwen2 llama_model_loader: - kv 16: tokenizer.ggml.tokens arr[str,152064] = ["!", "\"", "#", "$", "%", "&", "'", ... llama_model_loader: - kv 17: tokenizer.ggml.token_type arr[i32,152064] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... llama_model_loader: - kv 18: tokenizer.ggml.merges arr[str,151387] = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",... llama_model_loader: - kv 19: tokenizer.ggml.bos_token_id u32 = 151646 llama_model_loader: - kv 20: tokenizer.ggml.eos_token_id u32 = 151643 llama_model_loader: - kv 21: tokenizer.ggml.padding_token_id u32 = 151643 llama_model_loader: - kv 22: tokenizer.ggml.add_bos_token bool = true llama_model_loader: - kv 23: tokenizer.ggml.add_eos_token bool = false ``` ### OS Docker ### GPU Nvidia ### CPU Intel ### Ollama version 0.9.6
GiteaMirror added the needs more infobug labels 2026-04-12 20:06:27 -05:00
GiteaMirror commented 2026-04-12 20:06:28 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Aug 19, 2025):

Please add the full log.

<!-- gh-comment-id:3199965583 --> @rick-github commented on GitHub (Aug 19, 2025): Please add the full log.
GiteaMirror commented 2026-04-12 20:06:28 -05:00
Author
Owner
Copy Link

@minmie commented on GitHub (Aug 19, 2025):

@rick-github here is the full log.

llama_context: graph nodes  = 1042
llama_context: graph splits = 1
time=2025-08-19T06:41:06.338Z level=INFO source=server.go:637 msg="llama runner started in 1.76 seconds"
[GIN] 2025/08/19 - 06:41:06 | 200 |  2.136573575s |       127.0.0.1 | POST     "/api/generate"
[GIN] 2025/08/19 - 06:41:34 | 200 | 22.729933284s |       127.0.0.1 | POST     "/api/chat"
time=2025-08-19T07:32:37.967Z 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=2025-08-19T07:32:37.967Z level=INFO source=images.go:476 msg="total blobs: 0"
time=2025-08-19T07:32:37.967Z level=INFO source=images.go:483 msg="total unused blobs removed: 0"
time=2025-08-19T07:32:37.968Z level=INFO source=routes.go:1288 msg="Listening on [::]:11434 (version 0.9.6)"
time=2025-08-19T07:32:37.968Z level=INFO source=gpu.go:217 msg="looking for compatible GPUs"
time=2025-08-19T07:32:44.239Z level=INFO source=gpu.go:612 msg="Unable to load cudart library /usr/lib/x86_64-linux-gnu/libcuda.so.550.163.01: cuda driver library init failure: 802"
time=2025-08-19T07:32:44.322Z level=INFO source=gpu.go:377 msg="no compatible GPUs were discovered"
time=2025-08-19T07:32:44.322Z level=INFO source=types.go:130 msg="inference compute" id=0 library=cpu variant="" compute="" driver=0.0 name="" total="1007.2 GiB" available="996.5 GiB"
[GIN] 2025/08/19 - 07:37:33 | 200 |      91.922µs |       127.0.0.1 | HEAD     "/"
[GIN] 2025/08/19 - 07:37:33 | 200 |     325.291µs |       127.0.0.1 | GET      "/api/tags"
[GIN] 2025/08/19 - 07:37:49 | 200 |      32.401µs |       127.0.0.1 | HEAD     "/"
[GIN] 2025/08/19 - 07:37:49 | 200 |     156.413µs |       127.0.0.1 | GET      "/api/tags"
[GIN] 2025/08/19 - 07:41:36 | 200 |      41.708µs |       127.0.0.1 | HEAD     "/"
[GIN] 2025/08/19 - 07:41:36 | 200 |     151.955µs |       127.0.0.1 | GET      "/api/tags"
time=2025-08-19T07:42:02.947Z 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=2025-08-19T07:42:02.949Z level=INFO source=images.go:476 msg="total blobs: 10"
time=2025-08-19T07:42:02.950Z level=INFO source=images.go:483 msg="total unused blobs removed: 0"
time=2025-08-19T07:42:02.951Z level=INFO source=routes.go:1288 msg="Listening on [::]:11434 (version 0.9.6)"
time=2025-08-19T07:42:02.951Z level=INFO source=gpu.go:217 msg="looking for compatible GPUs"
time=2025-08-19T07:42:03.137Z level=INFO source=gpu.go:612 msg="Unable to load cudart library /usr/lib/x86_64-linux-gnu/libcuda.so.550.163.01: cuda driver library init failure: 802"
time=2025-08-19T07:42:03.266Z level=INFO source=gpu.go:377 msg="no compatible GPUs were discovered"
time=2025-08-19T07:42:03.266Z level=INFO source=types.go:130 msg="inference compute" id=0 library=cpu variant="" compute="" driver=0.0 name="" total="1007.2 GiB" available="994.3 GiB"
[GIN] 2025/08/19 - 07:42:16 | 200 |      57.017µs |       127.0.0.1 | HEAD     "/"
[GIN] 2025/08/19 - 07:42:16 | 200 |    1.609709ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2025/08/19 - 07:42:47 | 200 |      45.535µs |       127.0.0.1 | HEAD     "/"
[GIN] 2025/08/19 - 07:42:47 | 200 |   73.415349ms |       127.0.0.1 | POST     "/api/show"
time=2025-08-19T07:42:47.375Z level=INFO source=server.go:135 msg="system memory" total="1007.2 GiB" free="994.6 GiB" free_swap="0 B"
time=2025-08-19T07:42:47.376Z level=INFO source=server.go:175 msg=offload library=cpu layers.requested=-1 layers.model=29 layers.offload=0 layers.split="" memory.available="[994.6 GiB]" memory.gpu_overhead="0 B" memory.required.full="5.1 GiB" memory.required.partial="0 B" memory.required.kv="448.0 MiB" memory.required.allocations="[5.1 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"
llama_model_loader: loaded meta data with 26 key-value pairs and 339 tensors from /root/.ollama/models/blobs/sha256-96c415656d377afbff962f6cdb2394ab092ccbcbaab4b82525bc4ca800fe8a49 (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              = DeepSeek R1 Distill Qwen 7B
llama_model_loader: - kv   3:                           general.basename str              = DeepSeek-R1-Distill-Qwen
llama_model_loader: - kv   4:                         general.size_label str              = 7B
llama_model_loader: - kv   5:                          qwen2.block_count u32              = 28
llama_model_loader: - kv   6:                       qwen2.context_length u32              = 131072
llama_model_loader: - kv   7:                     qwen2.embedding_length u32              = 3584
llama_model_loader: - kv   8:                  qwen2.feed_forward_length u32              = 18944
llama_model_loader: - kv   9:                 qwen2.attention.head_count u32              = 28
llama_model_loader: - kv  10:              qwen2.attention.head_count_kv u32              = 4
llama_model_loader: - kv  11:                       qwen2.rope.freq_base f32              = 10000.000000
llama_model_loader: - kv  12:     qwen2.attention.layer_norm_rms_epsilon f32              = 0.000001
llama_model_loader: - kv  13:                          general.file_type u32              = 15
llama_model_loader: - kv  14:                       tokenizer.ggml.model str              = gpt2
llama_model_loader: - kv  15:                         tokenizer.ggml.pre str              = qwen2
llama_model_loader: - kv  16:                      tokenizer.ggml.tokens arr[str,152064]  = ["!", "\"", "#", "$", "%", "&", "'", ...
llama_model_loader: - kv  17:                  tokenizer.ggml.token_type arr[i32,152064]  = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv  18:                      tokenizer.ggml.merges arr[str,151387]  = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
llama_model_loader: - kv  19:                tokenizer.ggml.bos_token_id u32              = 151646
llama_model_loader: - kv  20:                tokenizer.ggml.eos_token_id u32              = 151643
llama_model_loader: - kv  21:            tokenizer.ggml.padding_token_id u32              = 151643
llama_model_loader: - kv  22:               tokenizer.ggml.add_bos_token bool             = true
llama_model_loader: - kv  23:               tokenizer.ggml.add_eos_token bool             = false
llama_model_loader: - kv  24:                    tokenizer.chat_template str              = {% if not add_generation_prompt is de...
llama_model_loader: - kv  25:               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
print_info: file format = GGUF V3 (latest)
print_info: file type   = Q4_K - Medium
print_info: file size   = 4.36 GiB (4.91 BPW) 
load: special_eos_id is not in special_eog_ids - the tokenizer config may be incorrect
load: special tokens cache size = 22
load: token to piece cache size = 0.9310 MB
print_info: arch             = qwen2
print_info: vocab_only       = 1
print_info: model type       = ?B
print_info: model params     = 7.62 B
print_info: general.name     = DeepSeek R1 Distill Qwen 7B
print_info: vocab type       = BPE
print_info: n_vocab          = 152064
print_info: n_merges         = 151387
print_info: BOS token        = 151646 '<｜begin▁of▁sentence｜>'
print_info: EOS token        = 151643 '<｜end▁of▁sentence｜>'
print_info: EOT token        = 151643 '<｜end▁of▁sentence｜>'
print_info: PAD token        = 151643 '<｜end▁of▁sentence｜>'
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 '<｜end▁of▁sentence｜>'
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=2025-08-19T07:42:47.630Z level=INFO source=server.go:438 msg="starting llama server" cmd="/usr/bin/ollama runner --model /root/.ollama/models/blobs/sha256-96c415656d377afbff962f6cdb2394ab092ccbcbaab4b82525bc4ca800fe8a49 --ctx-size 8192 --batch-size 512 --threads 96 --no-mmap --parallel 2 --port 42195"
time=2025-08-19T07:42:47.631Z level=INFO source=sched.go:483 msg="loaded runners" count=1
time=2025-08-19T07:42:47.631Z level=INFO source=server.go:598 msg="waiting for llama runner to start responding"
time=2025-08-19T07:42:47.631Z level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server not responding"
time=2025-08-19T07:42:47.646Z level=INFO source=runner.go:815 msg="starting go runner"
ggml_cuda_init: failed to initialize CUDA: system not yet initialized
load_backend: loaded CUDA backend from /usr/lib/ollama/libggml-cuda.so
load_backend: loaded CPU backend from /usr/lib/ollama/libggml-cpu-haswell.so
time=2025-08-19T07:42:47.886Z 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 compiler=cgo(gcc)
time=2025-08-19T07:42:47.887Z level=INFO source=runner.go:874 msg="Server listening on 127.0.0.1:42195"
llama_model_loader: loaded meta data with 26 key-value pairs and 339 tensors from /root/.ollama/models/blobs/sha256-96c415656d377afbff962f6cdb2394ab092ccbcbaab4b82525bc4ca800fe8a49 (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              = DeepSeek R1 Distill Qwen 7B
llama_model_loader: - kv   3:                           general.basename str              = DeepSeek-R1-Distill-Qwen
llama_model_loader: - kv   4:                         general.size_label str              = 7B
llama_model_loader: - kv   5:                          qwen2.block_count u32              = 28
llama_model_loader: - kv   6:                       qwen2.context_length u32              = 131072
llama_model_loader: - kv   7:                     qwen2.embedding_length u32              = 3584
llama_model_loader: - kv   8:                  qwen2.feed_forward_length u32              = 18944
llama_model_loader: - kv   9:                 qwen2.attention.head_count u32              = 28
llama_model_loader: - kv  10:              qwen2.attention.head_count_kv u32              = 4
llama_model_loader: - kv  11:                       qwen2.rope.freq_base f32              = 10000.000000
llama_model_loader: - kv  12:     qwen2.attention.layer_norm_rms_epsilon f32              = 0.000001
llama_model_loader: - kv  13:                          general.file_type u32              = 15
llama_model_loader: - kv  14:                       tokenizer.ggml.model str              = gpt2
llama_model_loader: - kv  15:                         tokenizer.ggml.pre str              = qwen2
llama_model_loader: - kv  16:                      tokenizer.ggml.tokens arr[str,152064]  = ["!", "\"", "#", "$", "%", "&", "'", ...
llama_model_loader: - kv  17:                  tokenizer.ggml.token_type arr[i32,152064]  = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv  18:                      tokenizer.ggml.merges arr[str,151387]  = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
llama_model_loader: - kv  19:                tokenizer.ggml.bos_token_id u32              = 151646
llama_model_loader: - kv  20:                tokenizer.ggml.eos_token_id u32              = 151643
llama_model_loader: - kv  21:            tokenizer.ggml.padding_token_id u32              = 151643
llama_model_loader: - kv  22:               tokenizer.ggml.add_bos_token bool             = true
llama_model_loader: - kv  23:               tokenizer.ggml.add_eos_token bool             = false
llama_model_loader: - kv  24:                    tokenizer.chat_template str              = {% if not add_generation_prompt is de...
llama_model_loader: - kv  25:               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
print_info: file format = GGUF V3 (latest)
print_info: file type   = Q4_K - Medium
print_info: file size   = 4.36 GiB (4.91 BPW) 
load: special_eos_id is not in special_eog_ids - the tokenizer config may be incorrect
load: special tokens cache size = 22
time=2025-08-19T07:42:48.133Z level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server loading model"
load: token to piece cache size = 0.9310 MB
print_info: arch             = qwen2
print_info: vocab_only       = 0
print_info: n_ctx_train      = 131072
print_info: n_embd           = 3584
print_info: n_layer          = 28
print_info: n_head           = 28
print_info: n_head_kv        = 4
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            = 7
print_info: n_embd_k_gqa     = 512
print_info: n_embd_v_gqa     = 512
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             = 18944
print_info: n_expert         = 0
print_info: n_expert_used    = 0
print_info: causal attn      = 1
print_info: pooling type     = -1
print_info: rope type        = 2
print_info: rope scaling     = linear
print_info: freq_base_train  = 10000.0
print_info: freq_scale_train = 1
print_info: n_ctx_orig_yarn  = 131072
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     = 7.62 B
print_info: general.name     = DeepSeek R1 Distill Qwen 7B
print_info: vocab type       = BPE
print_info: n_vocab          = 152064
print_info: n_merges         = 151387
print_info: BOS token        = 151646 '<｜begin▁of▁sentence｜>'
print_info: EOS token        = 151643 '<｜end▁of▁sentence｜>'
print_info: EOT token        = 151643 '<｜end▁of▁sentence｜>'
print_info: PAD token        = 151643 '<｜end▁of▁sentence｜>'
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 '<｜end▁of▁sentence｜>'
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:          CPU model buffer size =  4460.45 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     = 10000.0
llama_context: freq_scale    = 1
llama_context: n_ctx_per_seq (4096) < n_ctx_train (131072) -- the full capacity of the model will not be utilized
llama_context:        CPU  output buffer size =     1.19 MiB
llama_kv_cache_unified: kv_size = 8192, type_k = 'f16', type_v = 'f16', n_layer = 28, can_shift = 1, padding = 32
llama_kv_cache_unified:        CPU KV buffer size =   448.00 MiB
llama_kv_cache_unified: KV self size  =  448.00 MiB, K (f16):  224.00 MiB, V (f16):  224.00 MiB
llama_context:        CPU compute buffer size =   492.01 MiB
llama_context: graph nodes  = 1042
llama_context: graph splits = 1
time=2025-08-19T07:42:49.888Z level=INFO source=server.go:637 msg="llama runner started in 2.26 seconds"
[GIN] 2025/08/19 - 07:42:49 | 200 |  2.624595496s |       127.0.0.1 | POST     "/api/generate"
[GIN] 2025/08/19 - 07:43:27 | 200 | 30.757307242s |       127.0.0.1 | POST     "/api/chat"
[GIN] 2025/08/19 - 07:43:45 | 200 |      63.128µs |       127.0.0.1 | HEAD     "/"
[GIN] 2025/08/19 - 07:43:45 | 200 |      94.567µs |       127.0.0.1 | GET      "/api/ps"
[GIN] 2025/08/19 - 08:46:42 | 200 |      95.669µs |       127.0.0.1 | GET      "/api/version"
<!-- gh-comment-id:3200000610 --> @minmie commented on GitHub (Aug 19, 2025): @rick-github here is the full log. ``` llama_context: graph nodes = 1042 llama_context: graph splits = 1 time=2025-08-19T06:41:06.338Z level=INFO source=server.go:637 msg="llama runner started in 1.76 seconds" [GIN] 2025/08/19 - 06:41:06 | 200 | 2.136573575s | 127.0.0.1 | POST "/api/generate" [GIN] 2025/08/19 - 06:41:34 | 200 | 22.729933284s | 127.0.0.1 | POST "/api/chat" time=2025-08-19T07:32:37.967Z 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=2025-08-19T07:32:37.967Z level=INFO source=images.go:476 msg="total blobs: 0" time=2025-08-19T07:32:37.967Z level=INFO source=images.go:483 msg="total unused blobs removed: 0" time=2025-08-19T07:32:37.968Z level=INFO source=routes.go:1288 msg="Listening on [::]:11434 (version 0.9.6)" time=2025-08-19T07:32:37.968Z level=INFO source=gpu.go:217 msg="looking for compatible GPUs" time=2025-08-19T07:32:44.239Z level=INFO source=gpu.go:612 msg="Unable to load cudart library /usr/lib/x86_64-linux-gnu/libcuda.so.550.163.01: cuda driver library init failure: 802" time=2025-08-19T07:32:44.322Z level=INFO source=gpu.go:377 msg="no compatible GPUs were discovered" time=2025-08-19T07:32:44.322Z level=INFO source=types.go:130 msg="inference compute" id=0 library=cpu variant="" compute="" driver=0.0 name="" total="1007.2 GiB" available="996.5 GiB" [GIN] 2025/08/19 - 07:37:33 | 200 | 91.922µs | 127.0.0.1 | HEAD "/" [GIN] 2025/08/19 - 07:37:33 | 200 | 325.291µs | 127.0.0.1 | GET "/api/tags" [GIN] 2025/08/19 - 07:37:49 | 200 | 32.401µs | 127.0.0.1 | HEAD "/" [GIN] 2025/08/19 - 07:37:49 | 200 | 156.413µs | 127.0.0.1 | GET "/api/tags" [GIN] 2025/08/19 - 07:41:36 | 200 | 41.708µs | 127.0.0.1 | HEAD "/" [GIN] 2025/08/19 - 07:41:36 | 200 | 151.955µs | 127.0.0.1 | GET "/api/tags" time=2025-08-19T07:42:02.947Z 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=2025-08-19T07:42:02.949Z level=INFO source=images.go:476 msg="total blobs: 10" time=2025-08-19T07:42:02.950Z level=INFO source=images.go:483 msg="total unused blobs removed: 0" time=2025-08-19T07:42:02.951Z level=INFO source=routes.go:1288 msg="Listening on [::]:11434 (version 0.9.6)" time=2025-08-19T07:42:02.951Z level=INFO source=gpu.go:217 msg="looking for compatible GPUs" time=2025-08-19T07:42:03.137Z level=INFO source=gpu.go:612 msg="Unable to load cudart library /usr/lib/x86_64-linux-gnu/libcuda.so.550.163.01: cuda driver library init failure: 802" time=2025-08-19T07:42:03.266Z level=INFO source=gpu.go:377 msg="no compatible GPUs were discovered" time=2025-08-19T07:42:03.266Z level=INFO source=types.go:130 msg="inference compute" id=0 library=cpu variant="" compute="" driver=0.0 name="" total="1007.2 GiB" available="994.3 GiB" [GIN] 2025/08/19 - 07:42:16 | 200 | 57.017µs | 127.0.0.1 | HEAD "/" [GIN] 2025/08/19 - 07:42:16 | 200 | 1.609709ms | 127.0.0.1 | GET "/api/tags" [GIN] 2025/08/19 - 07:42:47 | 200 | 45.535µs | 127.0.0.1 | HEAD "/" [GIN] 2025/08/19 - 07:42:47 | 200 | 73.415349ms | 127.0.0.1 | POST "/api/show" time=2025-08-19T07:42:47.375Z level=INFO source=server.go:135 msg="system memory" total="1007.2 GiB" free="994.6 GiB" free_swap="0 B" time=2025-08-19T07:42:47.376Z level=INFO source=server.go:175 msg=offload library=cpu layers.requested=-1 layers.model=29 layers.offload=0 layers.split="" memory.available="[994.6 GiB]" memory.gpu_overhead="0 B" memory.required.full="5.1 GiB" memory.required.partial="0 B" memory.required.kv="448.0 MiB" memory.required.allocations="[5.1 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" llama_model_loader: loaded meta data with 26 key-value pairs and 339 tensors from /root/.ollama/models/blobs/sha256-96c415656d377afbff962f6cdb2394ab092ccbcbaab4b82525bc4ca800fe8a49 (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 = DeepSeek R1 Distill Qwen 7B llama_model_loader: - kv 3: general.basename str = DeepSeek-R1-Distill-Qwen llama_model_loader: - kv 4: general.size_label str = 7B llama_model_loader: - kv 5: qwen2.block_count u32 = 28 llama_model_loader: - kv 6: qwen2.context_length u32 = 131072 llama_model_loader: - kv 7: qwen2.embedding_length u32 = 3584 llama_model_loader: - kv 8: qwen2.feed_forward_length u32 = 18944 llama_model_loader: - kv 9: qwen2.attention.head_count u32 = 28 llama_model_loader: - kv 10: qwen2.attention.head_count_kv u32 = 4 llama_model_loader: - kv 11: qwen2.rope.freq_base f32 = 10000.000000 llama_model_loader: - kv 12: qwen2.attention.layer_norm_rms_epsilon f32 = 0.000001 llama_model_loader: - kv 13: general.file_type u32 = 15 llama_model_loader: - kv 14: tokenizer.ggml.model str = gpt2 llama_model_loader: - kv 15: tokenizer.ggml.pre str = qwen2 llama_model_loader: - kv 16: tokenizer.ggml.tokens arr[str,152064] = ["!", "\"", "#", "$", "%", "&", "'", ... llama_model_loader: - kv 17: tokenizer.ggml.token_type arr[i32,152064] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... llama_model_loader: - kv 18: tokenizer.ggml.merges arr[str,151387] = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",... llama_model_loader: - kv 19: tokenizer.ggml.bos_token_id u32 = 151646 llama_model_loader: - kv 20: tokenizer.ggml.eos_token_id u32 = 151643 llama_model_loader: - kv 21: tokenizer.ggml.padding_token_id u32 = 151643 llama_model_loader: - kv 22: tokenizer.ggml.add_bos_token bool = true llama_model_loader: - kv 23: tokenizer.ggml.add_eos_token bool = false llama_model_loader: - kv 24: tokenizer.chat_template str = {% if not add_generation_prompt is de... llama_model_loader: - kv 25: 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 print_info: file format = GGUF V3 (latest) print_info: file type = Q4_K - Medium print_info: file size = 4.36 GiB (4.91 BPW) load: special_eos_id is not in special_eog_ids - the tokenizer config may be incorrect load: special tokens cache size = 22 load: token to piece cache size = 0.9310 MB print_info: arch = qwen2 print_info: vocab_only = 1 print_info: model type = ?B print_info: model params = 7.62 B print_info: general.name = DeepSeek R1 Distill Qwen 7B print_info: vocab type = BPE print_info: n_vocab = 152064 print_info: n_merges = 151387 print_info: BOS token = 151646 '<｜begin▁of▁sentence｜>' print_info: EOS token = 151643 '<｜end▁of▁sentence｜>' print_info: EOT token = 151643 '<｜end▁of▁sentence｜>' print_info: PAD token = 151643 '<｜end▁of▁sentence｜>' 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 '<｜end▁of▁sentence｜>' 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=2025-08-19T07:42:47.630Z level=INFO source=server.go:438 msg="starting llama server" cmd="/usr/bin/ollama runner --model /root/.ollama/models/blobs/sha256-96c415656d377afbff962f6cdb2394ab092ccbcbaab4b82525bc4ca800fe8a49 --ctx-size 8192 --batch-size 512 --threads 96 --no-mmap --parallel 2 --port 42195" time=2025-08-19T07:42:47.631Z level=INFO source=sched.go:483 msg="loaded runners" count=1 time=2025-08-19T07:42:47.631Z level=INFO source=server.go:598 msg="waiting for llama runner to start responding" time=2025-08-19T07:42:47.631Z level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server not responding" time=2025-08-19T07:42:47.646Z level=INFO source=runner.go:815 msg="starting go runner" ggml_cuda_init: failed to initialize CUDA: system not yet initialized load_backend: loaded CUDA backend from /usr/lib/ollama/libggml-cuda.so load_backend: loaded CPU backend from /usr/lib/ollama/libggml-cpu-haswell.so time=2025-08-19T07:42:47.886Z 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 compiler=cgo(gcc) time=2025-08-19T07:42:47.887Z level=INFO source=runner.go:874 msg="Server listening on 127.0.0.1:42195" llama_model_loader: loaded meta data with 26 key-value pairs and 339 tensors from /root/.ollama/models/blobs/sha256-96c415656d377afbff962f6cdb2394ab092ccbcbaab4b82525bc4ca800fe8a49 (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 = DeepSeek R1 Distill Qwen 7B llama_model_loader: - kv 3: general.basename str = DeepSeek-R1-Distill-Qwen llama_model_loader: - kv 4: general.size_label str = 7B llama_model_loader: - kv 5: qwen2.block_count u32 = 28 llama_model_loader: - kv 6: qwen2.context_length u32 = 131072 llama_model_loader: - kv 7: qwen2.embedding_length u32 = 3584 llama_model_loader: - kv 8: qwen2.feed_forward_length u32 = 18944 llama_model_loader: - kv 9: qwen2.attention.head_count u32 = 28 llama_model_loader: - kv 10: qwen2.attention.head_count_kv u32 = 4 llama_model_loader: - kv 11: qwen2.rope.freq_base f32 = 10000.000000 llama_model_loader: - kv 12: qwen2.attention.layer_norm_rms_epsilon f32 = 0.000001 llama_model_loader: - kv 13: general.file_type u32 = 15 llama_model_loader: - kv 14: tokenizer.ggml.model str = gpt2 llama_model_loader: - kv 15: tokenizer.ggml.pre str = qwen2 llama_model_loader: - kv 16: tokenizer.ggml.tokens arr[str,152064] = ["!", "\"", "#", "$", "%", "&", "'", ... llama_model_loader: - kv 17: tokenizer.ggml.token_type arr[i32,152064] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... llama_model_loader: - kv 18: tokenizer.ggml.merges arr[str,151387] = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",... llama_model_loader: - kv 19: tokenizer.ggml.bos_token_id u32 = 151646 llama_model_loader: - kv 20: tokenizer.ggml.eos_token_id u32 = 151643 llama_model_loader: - kv 21: tokenizer.ggml.padding_token_id u32 = 151643 llama_model_loader: - kv 22: tokenizer.ggml.add_bos_token bool = true llama_model_loader: - kv 23: tokenizer.ggml.add_eos_token bool = false llama_model_loader: - kv 24: tokenizer.chat_template str = {% if not add_generation_prompt is de... llama_model_loader: - kv 25: 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 print_info: file format = GGUF V3 (latest) print_info: file type = Q4_K - Medium print_info: file size = 4.36 GiB (4.91 BPW) load: special_eos_id is not in special_eog_ids - the tokenizer config may be incorrect load: special tokens cache size = 22 time=2025-08-19T07:42:48.133Z level=INFO source=server.go:632 msg="waiting for server to become available" status="llm server loading model" load: token to piece cache size = 0.9310 MB print_info: arch = qwen2 print_info: vocab_only = 0 print_info: n_ctx_train = 131072 print_info: n_embd = 3584 print_info: n_layer = 28 print_info: n_head = 28 print_info: n_head_kv = 4 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 = 7 print_info: n_embd_k_gqa = 512 print_info: n_embd_v_gqa = 512 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 = 18944 print_info: n_expert = 0 print_info: n_expert_used = 0 print_info: causal attn = 1 print_info: pooling type = -1 print_info: rope type = 2 print_info: rope scaling = linear print_info: freq_base_train = 10000.0 print_info: freq_scale_train = 1 print_info: n_ctx_orig_yarn = 131072 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 = 7.62 B print_info: general.name = DeepSeek R1 Distill Qwen 7B print_info: vocab type = BPE print_info: n_vocab = 152064 print_info: n_merges = 151387 print_info: BOS token = 151646 '<｜begin▁of▁sentence｜>' print_info: EOS token = 151643 '<｜end▁of▁sentence｜>' print_info: EOT token = 151643 '<｜end▁of▁sentence｜>' print_info: PAD token = 151643 '<｜end▁of▁sentence｜>' 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 '<｜end▁of▁sentence｜>' 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: CPU model buffer size = 4460.45 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 = 10000.0 llama_context: freq_scale = 1 llama_context: n_ctx_per_seq (4096) < n_ctx_train (131072) -- the full capacity of the model will not be utilized llama_context: CPU output buffer size = 1.19 MiB llama_kv_cache_unified: kv_size = 8192, type_k = 'f16', type_v = 'f16', n_layer = 28, can_shift = 1, padding = 32 llama_kv_cache_unified: CPU KV buffer size = 448.00 MiB llama_kv_cache_unified: KV self size = 448.00 MiB, K (f16): 224.00 MiB, V (f16): 224.00 MiB llama_context: CPU compute buffer size = 492.01 MiB llama_context: graph nodes = 1042 llama_context: graph splits = 1 time=2025-08-19T07:42:49.888Z level=INFO source=server.go:637 msg="llama runner started in 2.26 seconds" [GIN] 2025/08/19 - 07:42:49 | 200 | 2.624595496s | 127.0.0.1 | POST "/api/generate" [GIN] 2025/08/19 - 07:43:27 | 200 | 30.757307242s | 127.0.0.1 | POST "/api/chat" [GIN] 2025/08/19 - 07:43:45 | 200 | 63.128µs | 127.0.0.1 | HEAD "/" [GIN] 2025/08/19 - 07:43:45 | 200 | 94.567µs | 127.0.0.1 | GET "/api/ps" [GIN] 2025/08/19 - 08:46:42 | 200 | 95.669µs | 127.0.0.1 | GET "/api/version" ```
GiteaMirror commented 2026-04-12 20:06:29 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Aug 19, 2025):

Unable to load cudart library /usr/lib/x86_64-linux-gnu/libcuda.so.550.163.01:
 cuda driver library init failure: 802

cudaErrorSystemNotReady = 802

  • This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide.

Are there any errors in the system log (dmesg. /var/log/kern.log, /var/log/syslog, etc)? What's the output if you run nvidia-smi inside the container:

docker run --rm --gpus=all --entrypoint nvidia-smi ollama/ollama
<!-- gh-comment-id:3201110574 --> @rick-github commented on GitHub (Aug 19, 2025): ``` Unable to load cudart library /usr/lib/x86_64-linux-gnu/libcuda.so.550.163.01: cuda driver library init failure: 802 ``` [cudaErrorSystemNotReady](https://docs.nvidia.com/cuda/cuda-runtime-api/group__CUDART__TYPES.html#group__CUDART__TYPES_1gg3f51e3575c2178246db0a94a430e0038e942e4cbbd2bef6e92e293253f055613:~:text=cudaErrorSystemNotReady) = 802 - This error indicates that the system is not yet ready to start any CUDA work. To continue using CUDA, verify the system configuration is in a valid state and all required driver daemons are actively running. More information about this error can be found in the system specific user guide. Are there any errors in the system log (dmesg. /var/log/kern.log, /var/log/syslog, etc)? What's the output if you run nvidia-smi inside the container: ``` docker run --rm --gpus=all --entrypoint nvidia-smi ollama/ollama ```
GiteaMirror commented 2026-04-12 20:06:29 -05:00
Author
Owner
Copy Link

@minmie commented on GitHub (Aug 20, 2025):

@rick-github Thank for you help.

  1. I don't find any errors in system log.
  2. The output of the command
docker run --rm --gpus=all --entrypoint nvidia-smi ollama/ollama

is as follow:

Image
  1. I executed the following code in a torch container and obtained the same error code：
Image
<!-- gh-comment-id:3203975284 --> @minmie commented on GitHub (Aug 20, 2025): @rick-github Thank for you help. 1. I don't find any errors in system log. 2. The output of the command ``` docker run --rm --gpus=all --entrypoint nvidia-smi ollama/ollama ``` is as follow: <img width="920" height="746" alt="Image" src="https://github.com/user-attachments/assets/ebb75eef-9ff9-4980-93dc-303821dd9c43" /> 3. I executed the following code in a torch container and obtained the same error code： <img width="1608" height="159" alt="Image" src="https://github.com/user-attachments/assets/0169d236-eb44-4f77-92f9-2eaf93c05b45" />
GiteaMirror commented 2026-04-12 20:06:29 -05:00
Author
Owner
Copy Link

@minmie commented on GitHub (Aug 20, 2025):

@rick-github Thank for your help, I have solved this by install NVIDIA Fabric Manager (FM).

<!-- gh-comment-id:3204479518 --> @minmie commented on GitHub (Aug 20, 2025): @rick-github Thank for your help, I have solved this by install [NVIDIA Fabric Manager (FM)](https://docs.nvidia.com/datacenter/tesla/fabric-manager-user-guide/index.html).
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label bug needs more info
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#7943
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?