github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 00:22:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #7765] Not using GPU after timeout unload of models with Docker image #67016

New Issue
Closed
opened 2026-05-04 09:14:51 -05:00 by GiteaMirror · 5 comments
GiteaMirror commented 2026-05-04 09:14:51 -05:00
Owner
Copy Link

Originally created by @brauliobo on GitHub (Nov 20, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/7765

What is the issue?

If I run sudo systemctl restart containerd docker then run

 docker exec -it ollama ollama run llama3.2

Then it uses the GPU as can be seen with nvidia-smi, low CPU usage and the speed of prompts.

The container was created with --gpus all and docker configured nvidia-container-toolkit.

But after a little while, the model is unloaded. Then when I run again docker exec -it ollama ollama run llama3.2 it on the CPU

OS

Linux, Docker

GPU

Nvidia

CPU

AMD

Ollama version

0.4.2 from official docker image

Originally created by @brauliobo on GitHub (Nov 20, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/7765 ### What is the issue? If I run `sudo systemctl restart containerd docker` then run ``` docker exec -it ollama ollama run llama3.2 ``` Then it uses the GPU as can be seen with `nvidia-smi`, low CPU usage and the speed of prompts. The container was created with `--gpus all` and docker configured `nvidia-container-toolkit`. But after a little while, the model is unloaded. Then when I run again ` docker exec -it ollama ollama run llama3.2` it on the CPU ### OS Linux, Docker ### GPU Nvidia ### CPU AMD ### Ollama version 0.4.2 from official docker image
GiteaMirror added the bug label 2026-05-04 09:14:51 -05:00
GiteaMirror commented 2026-05-04 09:14:54 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Nov 20, 2024):

Server logs will aid in debugging.

<!-- gh-comment-id:2489308540 --> @rick-github commented on GitHub (Nov 20, 2024): [Server logs](https://github.com/ollama/ollama/blob/main/docs/troubleshooting.md) will aid in debugging.
GiteaMirror commented 2026-05-04 09:14:55 -05:00
Author
Owner
Copy Link

@brauliobo commented on GitHub (Nov 20, 2024):

here it is:

2024/11/20 19:11:44 routes.go:1189: INFO server config env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://0.0.0.0:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:2562047h47m16.854775807s 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_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://*] OLLAMA_SCHED_SPREAD:false OLLAMA_TMPDIR: ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]"
time=2024-11-20T19:11:44.932Z level=INFO source=images.go:755 msg="total blobs: 0"
time=2024-11-20T19:11:44.932Z level=INFO source=images.go:762 msg="total unused blobs removed: 0"
time=2024-11-20T19:11:44.932Z level=INFO source=routes.go:1240 msg="Listening on [::]:11434 (version 0.4.2)"
time=2024-11-20T19:11:44.932Z level=INFO source=common.go:49 msg="Dynamic LLM libraries" runners="[cpu cpu_avx cpu_avx2 cuda_v11 cuda_v12]"
time=2024-11-20T19:11:44.932Z level=INFO source=gpu.go:221 msg="looking for compatible GPUs"
time=2024-11-20T19:11:45.416Z level=WARN source=amd_linux.go:61 msg="ollama recommends running the https://www.amd.com/en/support/linux-drivers" error="amdgpu version file missing: /sys/module/amdgpu/version stat /sys/module/amdgpu/version: no such file or directory"
time=2024-11-20T19:11:45.417Z level=INFO source=amd_linux.go:399 msg="no compatible amdgpu devices detected"
time=2024-11-20T19:11:45.417Z level=INFO source=types.go:123 msg="inference compute" id=GPU-467f0325-4701-7246-da8e-ea5f9e822dbf library=cuda variant=v12 compute=8.6 driver=12.7 name="NVIDIA GeForce RTX 3060" total="11.7 GiB" available="7.1 GiB"
time=2024-11-20T19:16:03.897Z level=INFO source=download.go:175 msg="downloading dde5aa3fc5ff in 16 126 MB part(s)"
time=2024-11-20T19:25:47.063Z level=INFO source=download.go:175 msg="downloading 966de95ca8a6 in 1 1.4 KB part(s)"
time=2024-11-20T19:25:49.406Z level=INFO source=download.go:175 msg="downloading fcc5a6bec9da in 1 7.7 KB part(s)"
time=2024-11-20T19:25:51.786Z level=INFO source=download.go:175 msg="downloading a70ff7e570d9 in 1 6.0 KB part(s)"
time=2024-11-20T19:25:54.015Z level=INFO source=download.go:175 msg="downloading 56bb8bd477a5 in 1 96 B part(s)"
time=2024-11-20T19:25:56.674Z level=INFO source=download.go:175 msg="downloading 34bb5ab01051 in 1 561 B part(s)"
cuda driver library failed to get device context 800time=2024-11-20T19:25:58.956Z level=WARN source=gpu.go:441 msg="error looking up nvidia GPU memory"
time=2024-11-20T19:25:58.979Z level=INFO source=sched.go:714 msg="new model will fit in available VRAM in single GPU, loading" model=/root/.ollama/models/blobs/sha256-dde5aa3fc5ffc17176b5e8bdc82f587b24b2678c6c66101bf7da77af9f7ccdff gpu=GPU-467f0325-4701-7246-da8e-ea5f9e822dbf parallel=4 available=7593525248 required="3.7 GiB"
cuda driver library failed to get device context 800time=2024-11-20T19:25:58.994Z level=WARN source=gpu.go:441 msg="error looking up nvidia GPU memory"
time=2024-11-20T19:25:58.994Z level=INFO source=server.go:105 msg="system memory" total="94.2 GiB" free="70.4 GiB" free_swap="0 B"
time=2024-11-20T19:25:58.994Z level=INFO source=memory.go:343 msg="offload to cuda" layers.requested=-1 layers.model=29 layers.offload=29 layers.split="" memory.available="[7.1 GiB]" memory.gpu_overhead="0 B" memory.required.full="3.7 GiB" memory.required.partial="3.7 GiB" memory.required.kv="896.0 MiB" memory.required.allocations="[3.7 GiB]" memory.weights.total="2.4 GiB" memory.weights.repeating="2.1 GiB" memory.weights.nonrepeating="308.2 MiB" memory.graph.full="424.0 MiB" memory.graph.partial="570.7 MiB"
time=2024-11-20T19:25:58.995Z level=INFO source=server.go:383 msg="starting llama server" cmd="/usr/lib/ollama/runners/cuda_v12/ollama_llama_server --model /root/.ollama/models/blobs/sha256-dde5aa3fc5ffc17176b5e8bdc82f587b24b2678c6c66101bf7da77af9f7ccdff --ctx-size 8192 --batch-size 512 --n-gpu-layers 29 --threads 6 --parallel 4 --port 45637"
time=2024-11-20T19:25:58.998Z level=INFO source=sched.go:449 msg="loaded runners" count=1
time=2024-11-20T19:25:58.998Z level=INFO source=server.go:562 msg="waiting for llama runner to start responding"
time=2024-11-20T19:25:58.999Z level=INFO source=server.go:596 msg="waiting for server to become available" status="llm server error"
time=2024-11-20T19:25:59.083Z level=INFO source=runner.go:883 msg="starting go runner"
time=2024-11-20T19:25:59.083Z level=INFO source=runner.go:884 msg=system info="AVX = 1 | AVX_VNNI = 0 | AVX2 = 0 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | AVX512_BF16 = 0 | FMA = 0 | NEON = 0 | SVE = 0 | ARM_FMA = 0 | F16C = 0 | FP16_VA = 0 | RISCV_VECT = 0 | WASM_SIMD = 0 | BLAS = 1 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | MATMUL_INT8 = 0 | LLAMAFILE = 1 | cgo(gcc)" threads=6
time=2024-11-20T19:25:59.083Z level=INFO source=.:0 msg="Server listening on 127.0.0.1:45637"
llama_model_loader: loaded meta data with 30 key-value pairs and 255 tensors from /root/.ollama/models/blobs/sha256-dde5aa3fc5ffc17176b5e8bdc82f587b24b2678c6c66101bf7da77af9f7ccdff (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.type str              = model
llama_model_loader: - kv   2:                               general.name str              = Llama 3.2 3B Instruct
llama_model_loader: - kv   3:                           general.finetune str              = Instruct
llama_model_loader: - kv   4:                           general.basename str              = Llama-3.2
llama_model_loader: - kv   5:                         general.size_label str              = 3B
llama_model_loader: - kv   6:                               general.tags arr[str,6]       = ["facebook", "meta", "pytorch", "llam...
llama_model_loader: - kv   7:                          general.languages arr[str,8]       = ["en", "de", "fr", "it", "pt", "hi", ...
llama_model_loader: - kv   8:                          llama.block_count u32              = 28
llama_model_loader: - kv   9:                       llama.context_length u32              = 131072
llama_model_loader: - kv  10:                     llama.embedding_length u32              = 3072
llama_model_loader: - kv  11:                  llama.feed_forward_length u32              = 8192
llama_model_loader: - kv  12:                 llama.attention.head_count u32              = 24
llama_model_loader: - kv  13:              llama.attention.head_count_kv u32              = 8
llama_model_loader: - kv  14:                       llama.rope.freq_base f32              = 500000.000000
llama_model_loader: - kv  15:     llama.attention.layer_norm_rms_epsilon f32              = 0.000010
llama_model_loader: - kv  16:                 llama.attention.key_length u32              = 128
llama_model_loader: - kv  17:               llama.attention.value_length u32              = 128
llama_model_loader: - kv  18:                          general.file_type u32              = 15
llama_model_loader: - kv  19:                           llama.vocab_size u32              = 128256
llama_model_loader: - kv  20:                 llama.rope.dimension_count u32              = 128
llama_model_loader: - kv  21:                       tokenizer.ggml.model str              = gpt2
llama_model_loader: - kv  22:                         tokenizer.ggml.pre str              = llama-bpe
llama_model_loader: - kv  23:                      tokenizer.ggml.tokens arr[str,128256]  = ["!", "\"", "#", "$", "%", "&", "'", ...
llama_model_loader: - kv  24:                  tokenizer.ggml.token_type arr[i32,128256]  = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv  25:                      tokenizer.ggml.merges arr[str,280147]  = ["Ġ Ġ", "Ġ ĠĠĠ", "ĠĠ ĠĠ", "...
llama_model_loader: - kv  26:                tokenizer.ggml.bos_token_id u32              = 128000
llama_model_loader: - kv  27:                tokenizer.ggml.eos_token_id u32              = 128009
llama_model_loader: - kv  28:                    tokenizer.chat_template str              = {{- bos_token }}\n{%- if custom_tools ...
llama_model_loader: - kv  29:               general.quantization_version u32              = 2
llama_model_loader: - type  f32:   58 tensors
llama_model_loader: - type q4_K:  168 tensors
llama_model_loader: - type q6_K:   29 tensors
time=2024-11-20T19:25:59.250Z level=INFO source=server.go:596 msg="waiting for server to become available" status="llm server loading model"
llm_load_vocab: special tokens cache size = 256
llm_load_vocab: token to piece cache size = 0.7999 MB
llm_load_print_meta: format           = GGUF V3 (latest)
llm_load_print_meta: arch             = llama
llm_load_print_meta: vocab type       = BPE
llm_load_print_meta: n_vocab          = 128256
llm_load_print_meta: n_merges         = 280147
llm_load_print_meta: vocab_only       = 0
llm_load_print_meta: n_ctx_train      = 131072
llm_load_print_meta: n_embd           = 3072
llm_load_print_meta: n_layer          = 28
llm_load_print_meta: n_head           = 24
llm_load_print_meta: n_head_kv        = 8
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            = 3
llm_load_print_meta: n_embd_k_gqa     = 1024
llm_load_print_meta: n_embd_v_gqa     = 1024
llm_load_print_meta: f_norm_eps       = 0.0e+00
llm_load_print_meta: f_norm_rms_eps   = 1.0e-05
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             = 8192
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        = 0
llm_load_print_meta: rope scaling     = linear
llm_load_print_meta: freq_base_train  = 500000.0
llm_load_print_meta: freq_scale_train = 1
llm_load_print_meta: n_ctx_orig_yarn  = 131072
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       = 3B
llm_load_print_meta: model ftype      = Q4_K - Medium
llm_load_print_meta: model params     = 3.21 B
llm_load_print_meta: model size       = 1.87 GiB (5.01 BPW) 
llm_load_print_meta: general.name     = Llama 3.2 3B Instruct
llm_load_print_meta: BOS token        = 128000 '<|begin_of_text|>'
llm_load_print_meta: EOS token        = 128009 '<|eot_id|>'
llm_load_print_meta: LF token         = 128 'Ä'
llm_load_print_meta: EOT token        = 128009 '<|eot_id|>'
llm_load_print_meta: EOM token        = 128008 '<|eom_id|>'
llm_load_print_meta: EOG token        = 128008 '<|eom_id|>'
llm_load_print_meta: EOG token        = 128009 '<|eot_id|>'
llm_load_print_meta: max token length = 256
ggml_cuda_init: failed to initialize CUDA: no CUDA-capable device is detected
llm_load_tensors: ggml ctx size =    0.12 MiB
llm_load_tensors: offloading 28 repeating layers to GPU
llm_load_tensors: offloading non-repeating layers to GPU
llm_load_tensors: offloaded 29/29 layers to GPU
llm_load_tensors:        CPU buffer size =  1918.35 MiB
llama_new_context_with_model: n_ctx      = 8192
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  = 500000.0
llama_new_context_with_model: freq_scale = 1
ggml_cuda_host_malloc: failed to allocate 896.00 MiB of pinned memory: no CUDA-capable device is detected
llama_kv_cache_init:        CPU KV buffer size =   896.00 MiB
llama_new_context_with_model: KV self size  =  896.00 MiB, K (f16):  448.00 MiB, V (f16):  448.00 MiB
ggml_cuda_host_malloc: failed to allocate 2.00 MiB of pinned memory: no CUDA-capable device is detected
llama_new_context_with_model:        CPU  output buffer size =     2.00 MiB
ggml_cuda_host_malloc: failed to allocate 424.01 MiB of pinned memory: no CUDA-capable device is detected
llama_new_context_with_model:  CUDA_Host compute buffer size =   424.01 MiB
llama_new_context_with_model: graph nodes  = 902
llama_new_context_with_model: graph splits = 1
time=2024-11-20T19:25:59.751Z level=INFO source=server.go:601 msg="llama runner started in 0.75 seconds"

after a stop/start then it works, logs below:

braulio @ bhavapower ➜  ~  docker logs ollama                                                                                                                                                                                                                                                                                                                                                      
Couldn't find '/root/.ollama/id_ed25519'. Generating new private key.                                                                                                                                                                                                                                                                                                                              
Your new public key is:                                                                                                                                                                                                                                                                                                                                                                            
                                                                                                                                                                                                                                                                                                                                                                                                   
ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIK4bI2uih7gjydskG+t/p1JuosWg/1eVsh25Z5D9qH1A                                                                                                                                                                                                                                                                                                                   
                                                                                                                                                                                                                                                                                                                                                                                                   
2024/11/20 19:11:44 routes.go:1189: INFO server config env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://0.0.0.0:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:2562047h47m16.854775807s OLLAMA_LLM_LIBRARY: OLLAMA_LOA
D_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/root/.ollama/models OLLAMA_MULTIUSER_CACHE: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://*] OLLAMA_SCHED_SPREAD:false OLLAMA_TMPDIR: ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]"                                                                                                                                                                                                             
time=2024-11-20T19:11:44.932Z level=INFO source=images.go:755 msg="total blobs: 0"                                                                                                                                                                                                                                                                                                                 
time=2024-11-20T19:11:44.932Z level=INFO source=images.go:762 msg="total unused blobs removed: 0"                                                                                                                                                                                                                                                                                                  
time=2024-11-20T19:11:44.932Z level=INFO source=routes.go:1240 msg="Listening on [::]:11434 (version 0.4.2)"                                                                                                                                                                                                                                                                                       
time=2024-11-20T19:11:44.932Z level=INFO source=common.go:49 msg="Dynamic LLM libraries" runners="[cpu cpu_avx cpu_avx2 cuda_v11 cuda_v12]"                                                                                                                                                                                                                                                        
time=2024-11-20T19:11:44.932Z level=INFO source=gpu.go:221 msg="looking for compatible GPUs"                                                                                                                                                                                                                                                                                                       
time=2024-11-20T19:11:45.416Z level=WARN source=amd_linux.go:61 msg="ollama recommends running the https://www.amd.com/en/support/linux-drivers" error="amdgpu version file missing: /sys/module/amdgpu/version stat /sys/module/amdgpu/version: no such file or directory"                                                                                                                        
time=2024-11-20T19:11:45.417Z level=INFO source=amd_linux.go:399 msg="no compatible amdgpu devices detected"                                                                                                                                                                                                                                                                                       
time=2024-11-20T19:11:45.417Z level=INFO source=types.go:123 msg="inference compute" id=GPU-467f0325-4701-7246-da8e-ea5f9e822dbf library=cuda variant=v12 compute=8.6 driver=12.7 name="NVIDIA GeForce RTX 3060" total="11.7 GiB" available="7.1 GiB"                                                                                                                                              
[GIN] 2024/11/20 - 19:15:59 | 200 |      19.255µs |       127.0.0.1 | HEAD     "/"                                                                                                                                                                                                                                                                                                                 
[GIN] 2024/11/20 - 19:15:59 | 404 |      84.878µs |       127.0.0.1 | POST     "/api/show"                                                                                                                                                                                                                                                                                                         
time=2024-11-20T19:16:03.897Z level=INFO source=download.go:175 msg="downloading dde5aa3fc5ff in 16 126 MB part(s)"                                                                                                                                                                                                                                                                                
time=2024-11-20T19:25:47.063Z level=INFO source=download.go:175 msg="downloading 966de95ca8a6 in 1 1.4 KB part(s)"                                                                                                                                                                                                                                                                                 
time=2024-11-20T19:25:49.406Z level=INFO source=download.go:175 msg="downloading fcc5a6bec9da in 1 7.7 KB part(s)"                                                                                                                                                                                                                                                                                 
time=2024-11-20T19:25:51.786Z level=INFO source=download.go:175 msg="downloading a70ff7e570d9 in 1 6.0 KB part(s)"                                                                                                                                                                                                                                                                                 
time=2024-11-20T19:25:54.015Z level=INFO source=download.go:175 msg="downloading 56bb8bd477a5 in 1 96 B part(s)"                                                                                                                                                                                                                                                                                   
time=2024-11-20T19:25:56.674Z level=INFO source=download.go:175 msg="downloading 34bb5ab01051 in 1 561 B part(s)"                                                                                                                                                                                                                                                                                  
[GIN] 2024/11/20 - 19:25:58 | 200 |         9m59s |       127.0.0.1 | POST     "/api/pull"                                                                                                                                                                                                                                                                                                         
[GIN] 2024/11/20 - 19:25:58 | 200 |   12.366763ms |       127.0.0.1 | POST     "/api/show"                                                                                                                                                                                                                                                                                                         
cuda driver library failed to get device context 800time=2024-11-20T19:25:58.956Z level=WARN source=gpu.go:441 msg="error looking up nvidia GPU memory"                                                                                                                                                                                                                                            
time=2024-11-20T19:25:58.979Z level=INFO source=sched.go:714 msg="new model will fit in available VRAM in single GPU, loading" model=/root/.ollama/models/blobs/sha256-dde5aa3fc5ffc17176b5e8bdc82f587b24b2678c6c66101bf7da77af9f7ccdff gpu=GPU-467f0325-4701-7246-da8e-ea5f9e822dbf parallel=4 available=7593525248 required="3.7 GiB"                                                            
cuda driver library failed to get device context 800time=2024-11-20T19:25:58.994Z level=WARN source=gpu.go:441 msg="error looking up nvidia GPU memory"                                                                                                                                                                                                                                            
time=2024-11-20T19:25:58.994Z level=INFO source=server.go:105 msg="system memory" total="94.2 GiB" free="70.4 GiB" free_swap="0 B"                                                                                                                                                                                                                                                                 
time=2024-11-20T19:25:58.994Z level=INFO source=memory.go:343 msg="offload to cuda" layers.requested=-1 layers.model=29 layers.offload=29 layers.split="" memory.available="[7.1 GiB]" memory.gpu_overhead="0 B" memory.required.full="3.7 GiB" memory.required.partial="3.7 GiB" memory.required.kv="896.0 MiB" memory.required.allocations="[3.7 GiB]" memory.weights.total="2.4 GiB" memory.weig
hts.repeating="2.1 GiB" memory.weights.nonrepeating="308.2 MiB" memory.graph.full="424.0 MiB" memory.graph.partial="570.7 MiB"                                                                                                                                                                                                                                                                     
time=2024-11-20T19:25:58.995Z level=INFO source=server.go:383 msg="starting llama server" cmd="/usr/lib/ollama/runners/cuda_v12/ollama_llama_server --model /root/.ollama/models/blobs/sha256-dde5aa3fc5ffc17176b5e8bdc82f587b24b2678c6c66101bf7da77af9f7ccdff --ctx-size 8192 --batch-size 512 --n-gpu-layers 29 --threads 6 --parallel 4 --port 45637"                                           
time=2024-11-20T19:25:58.998Z level=INFO source=sched.go:449 msg="loaded runners" count=1                                                                                                                                                                                                                                                                                                          
time=2024-11-20T19:25:58.998Z level=INFO source=server.go:562 msg="waiting for llama runner to start responding"                                                                                                                                                                                                                                                                                   
time=2024-11-20T19:25:58.999Z level=INFO source=server.go:596 msg="waiting for server to become available" status="llm server error"                                                                                                                                                                                                                                                               
time=2024-11-20T19:25:59.083Z level=INFO source=runner.go:883 msg="starting go runner"                                                                                                                                                                                                                                                                                                             
time=2024-11-20T19:25:59.083Z level=INFO source=runner.go:884 msg=system info="AVX = 1 | AVX_VNNI = 0 | AVX2 = 0 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | AVX512_BF16 = 0 | FMA = 0 | NEON = 0 | SVE = 0 | ARM_FMA = 0 | F16C = 0 | FP16_VA = 0 | RISCV_VECT = 0 | WASM_SIMD = 0 | BLAS = 1 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | MATMUL_INT8 = 0 | LLAMAFILE = 1 | cgo(gcc)" threads=6     
time=2024-11-20T19:25:59.083Z level=INFO source=.:0 msg="Server listening on 127.0.0.1:45637"                                                                                                                                                                                                                                                                                                      
llama_model_loader: loaded meta data with 30 key-value pairs and 255 tensors from /root/.ollama/models/blobs/sha256-dde5aa3fc5ffc17176b5e8bdc82f587b24b2678c6c66101bf7da77af9f7ccdff (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.type str              = model                                                                                                                                                                                                                                                                                                  
llama_model_loader: - kv   2:                               general.name str              = Llama 3.2 3B Instruct                                                                                                                                                                                                                                                                                  
llama_model_loader: - kv   3:                           general.finetune str              = Instruct                                                                                                                                                                                                                                                                                               
llama_model_loader: - kv   4:                           general.basename str              = Llama-3.2                                                                                                                                                                                                                                                                                              
llama_model_loader: - kv   5:                         general.size_label str              = 3B                                                                                                                                                                                                                                                                                                     
llama_model_loader: - kv   6:                               general.tags arr[str,6]       = ["facebook", "meta", "pytorch", "llam...                                                                                                                                                                                                                                                               
llama_model_loader: - kv   7:                          general.languages arr[str,8]       = ["en", "de", "fr", "it", "pt", "hi", ...                                                                                                                                                                                                                                                               
llama_model_loader: - kv   8:                          llama.block_count u32              = 28                                                                                                                                                                                                                                                                                                     
llama_model_loader: - kv   9:                       llama.context_length u32              = 131072                                                                                                                                                                                                                                                                                                 
llama_model_loader: - kv  10:                     llama.embedding_length u32              = 3072                                                                                                                                                                                                                                                                                                   
llama_model_loader: - kv  11:                  llama.feed_forward_length u32              = 8192                                                                                                                                                                                                                                                                                                   
llama_model_loader: - kv  12:                 llama.attention.head_count u32              = 24                                                                                                                                                                                                                                                                                                     
llama_model_loader: - kv  13:              llama.attention.head_count_kv u32              = 8                                                                                                                                                                                                                                                                                                      
llama_model_loader: - kv  14:                       llama.rope.freq_base f32              = 500000.000000                                                                                                                                                                                                                                                                                          
llama_model_loader: - kv  15:     llama.attention.layer_norm_rms_epsilon f32              = 0.000010                                                                                                                                                                                                                                                                                               
llama_model_loader: - kv  16:                 llama.attention.key_length u32              = 128                                                                                                                                                                                                                                                                                                    
llama_model_loader: - kv  17:               llama.attention.value_length u32              = 128                                                                                                                                                                                                                                                                                                    
llama_model_loader: - kv  18:                          general.file_type u32              = 15                                                                                                                                                                                                                                                                                                     
llama_model_loader: - kv  19:                           llama.vocab_size u32              = 128256                                                                                                                                                                                                                                                                                                 
llama_model_loader: - kv  20:                 llama.rope.dimension_count u32              = 128                                                                                                                                                                                                                                                                                                    
llama_model_loader: - kv  21:                       tokenizer.ggml.model str              = gpt2                                                                                                                                                                                                                                                                                                   
llama_model_loader: - kv  22:                         tokenizer.ggml.pre str              = llama-bpe                                                                                                                                                                                                                                                                                              
llama_model_loader: - kv  23:                      tokenizer.ggml.tokens arr[str,128256]  = ["!", "\"", "#", "$", "%", "&", "'", ...                                                                                                                                                                                                                                                               
llama_model_loader: - kv  24:                  tokenizer.ggml.token_type arr[i32,128256]  = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...                                                                                                                                                                                                                                                               
llama_model_loader: - kv  25:                      tokenizer.ggml.merges arr[str,280147]  = ["Ġ Ġ", "Ġ ĠĠĠ", "ĠĠ ĠĠ", "...                                                                                                                                                                                                                                                                         
llama_model_loader: - kv  26:                tokenizer.ggml.bos_token_id u32              = 128000                                                                                                                                                                                                                                                                                                 
llama_model_loader: - kv  27:                tokenizer.ggml.eos_token_id u32              = 128009                                                                                                                                                                                                                                                                                                 
llama_model_loader: - kv  28:                    tokenizer.chat_template str              = {{- bos_token }}\n{%- if custom_tools ...                                                                                                                                                                                                                                                              
llama_model_loader: - kv  29:               general.quantization_version u32              = 2                                                                                                                                                                                                                                                                                                      
llama_model_loader: - type  f32:   58 tensors                                                                                                                                                                                                                                                                                                                                                      
llama_model_loader: - type q4_K:  168 tensors                                                                                                                                                                                                                                                                                                                                                      
llama_model_loader: - type q6_K:   29 tensors                                                                                                                                                                                                                                                                                                                                                      
time=2024-11-20T19:25:59.250Z level=INFO source=server.go:596 msg="waiting for server to become available" status="llm server loading model"                                                                                                                                                                                                                                                       
llm_load_vocab: special tokens cache size = 256                                                                                                                                                                                                                                                                                                                                                    
llm_load_vocab: token to piece cache size = 0.7999 MB                                                                                                                                                                                                                                                                                                                                              
llm_load_print_meta: format           = GGUF V3 (latest)                                                                                                                                                                                                                                                                                                                                           
llm_load_print_meta: arch             = llama                                                                                                                                                                                                                                                                                                                                                      
llm_load_print_meta: vocab type       = BPE                                                                                                                                                                                                                                                                                                                                                        
llm_load_print_meta: n_vocab          = 128256                                                                                                                                                                                                                                                                                                                                                     
llm_load_print_meta: n_merges         = 280147
llm_load_print_meta: vocab_only       = 0
llm_load_print_meta: n_ctx_train      = 131072
llm_load_print_meta: n_embd           = 3072
llm_load_print_meta: n_layer          = 28
llm_load_print_meta: n_head           = 24
llm_load_print_meta: n_head_kv        = 8
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            = 3
llm_load_print_meta: n_embd_k_gqa     = 1024
llm_load_print_meta: n_embd_v_gqa     = 1024
llm_load_print_meta: f_norm_eps       = 0.0e+00
llm_load_print_meta: f_norm_rms_eps   = 1.0e-05
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             = 8192
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        = 0
llm_load_print_meta: rope scaling     = linear
llm_load_print_meta: freq_base_train  = 500000.0
llm_load_print_meta: freq_scale_train = 1
llm_load_print_meta: n_ctx_orig_yarn  = 131072
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       = 3B
llm_load_print_meta: model ftype      = Q4_K - Medium
llm_load_print_meta: model params     = 3.21 B
llm_load_print_meta: model size       = 1.87 GiB (5.01 BPW) 
llm_load_print_meta: general.name     = Llama 3.2 3B Instruct
llm_load_print_meta: BOS token        = 128000 '<|begin_of_text|>'
llm_load_print_meta: EOS token        = 128009 '<|eot_id|>'
llm_load_print_meta: LF token         = 128 'Ä'
llm_load_print_meta: EOT token        = 128009 '<|eot_id|>'
llm_load_print_meta: EOM token        = 128008 '<|eom_id|>'
llm_load_print_meta: EOG token        = 128008 '<|eom_id|>'
llm_load_print_meta: EOG token        = 128009 '<|eot_id|>'
llm_load_print_meta: max token length = 256
ggml_cuda_init: failed to initialize CUDA: no CUDA-capable device is detected
llm_load_tensors: ggml ctx size =    0.12 MiB
llm_load_tensors: offloading 28 repeating layers to GPU
llm_load_tensors: offloading non-repeating layers to GPU
llm_load_tensors: offloaded 29/29 layers to GPU
llm_load_tensors:        CPU buffer size =  1918.35 MiB
llama_new_context_with_model: n_ctx      = 8192
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  = 500000.0
llama_new_context_with_model: freq_scale = 1
ggml_cuda_host_malloc: failed to allocate 896.00 MiB of pinned memory: no CUDA-capable device is detected
llama_kv_cache_init:        CPU KV buffer size =   896.00 MiB
llama_new_context_with_model: KV self size  =  896.00 MiB, K (f16):  448.00 MiB, V (f16):  448.00 MiB
ggml_cuda_host_malloc: failed to allocate 2.00 MiB of pinned memory: no CUDA-capable device is detected
llama_new_context_with_model:        CPU  output buffer size =     2.00 MiB
ggml_cuda_host_malloc: failed to allocate 424.01 MiB of pinned memory: no CUDA-capable device is detected
llama_new_context_with_model:  CUDA_Host compute buffer size =   424.01 MiB
llama_new_context_with_model: graph nodes  = 902
llama_new_context_with_model: graph splits = 1
time=2024-11-20T19:25:59.751Z level=INFO source=server.go:601 msg="llama runner started in 0.75 seconds"
[GIN] 2024/11/20 - 19:25:59 | 200 |  823.467751ms |       127.0.0.1 | POST     "/api/generate"
2024/11/20 19:28:41 routes.go:1189: INFO server config env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://0.0.0.0:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:2562047h47m16.854775807s 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_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://*] OLLAMA_SCHED_SPREAD:false OLLAMA_TMPDIR: ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]"
time=2024-11-20T19:28:41.527Z level=INFO source=images.go:755 msg="total blobs: 6"
time=2024-11-20T19:28:41.527Z level=INFO source=images.go:762 msg="total unused blobs removed: 0"
time=2024-11-20T19:28:41.527Z level=INFO source=routes.go:1240 msg="Listening on [::]:11434 (version 0.4.2)"
time=2024-11-20T19:28:41.527Z level=INFO source=common.go:49 msg="Dynamic LLM libraries" runners="[cpu_avx2 cuda_v11 cuda_v12 cpu cpu_avx]"
time=2024-11-20T19:28:41.527Z level=INFO source=gpu.go:221 msg="looking for compatible GPUs"
time=2024-11-20T19:28:42.011Z level=WARN source=amd_linux.go:61 msg="ollama recommends running the https://www.amd.com/en/support/linux-drivers" error="amdgpu version file missing: /sys/module/amdgpu/version stat /sys/module/amdgpu/version: no such file or directory"
time=2024-11-20T19:28:42.012Z level=INFO source=amd_linux.go:399 msg="no compatible amdgpu devices detected"
time=2024-11-20T19:28:42.012Z level=INFO source=types.go:123 msg="inference compute" id=GPU-467f0325-4701-7246-da8e-ea5f9e822dbf library=cuda variant=v12 compute=8.6 driver=12.7 name="NVIDIA GeForce RTX 3060" total="11.7 GiB" available="7.1 GiB"
[GIN] 2024/11/20 - 19:28:47 | 200 |      19.856µs |       127.0.0.1 | HEAD     "/"
[GIN] 2024/11/20 - 19:28:47 | 200 |   12.291472ms |       127.0.0.1 | POST     "/api/show"
time=2024-11-20T19:28:47.988Z level=INFO source=sched.go:714 msg="new model will fit in available VRAM in single GPU, loading" model=/root/.ollama/models/blobs/sha256-dde5aa3fc5ffc17176b5e8bdc82f587b24b2678c6c66101bf7da77af9f7ccdff gpu=GPU-467f0325-4701-7246-da8e-ea5f9e822dbf parallel=4 available=7593525248 required="3.7 GiB"
time=2024-11-20T19:28:48.443Z level=INFO source=server.go:105 msg="system memory" total="94.2 GiB" free="69.9 GiB" free_swap="0 B"
time=2024-11-20T19:28:48.443Z level=INFO source=memory.go:343 msg="offload to cuda" layers.requested=-1 layers.model=29 layers.offload=29 layers.split="" memory.available="[7.1 GiB]" memory.gpu_overhead="0 B" memory.required.full="3.7 GiB" memory.required.partial="3.7 GiB" memory.required.kv="896.0 MiB" memory.required.allocations="[3.7 GiB]" memory.weights.total="2.4 GiB" memory.weights.repeating="2.1 GiB" memory.weights.nonrepeating="308.2 MiB" memory.graph.full="424.0 MiB" memory.graph.partial="570.7 MiB"
time=2024-11-20T19:28:48.444Z level=INFO source=server.go:383 msg="starting llama server" cmd="/usr/lib/ollama/runners/cuda_v12/ollama_llama_server --model /root/.ollama/models/blobs/sha256-dde5aa3fc5ffc17176b5e8bdc82f587b24b2678c6c66101bf7da77af9f7ccdff --ctx-size 8192 --batch-size 512 --n-gpu-layers 29 --threads 6 --parallel 4 --port 39057"
time=2024-11-20T19:28:48.444Z level=INFO source=sched.go:449 msg="loaded runners" count=1
time=2024-11-20T19:28:48.444Z level=INFO source=server.go:562 msg="waiting for llama runner to start responding"
time=2024-11-20T19:28:48.444Z level=INFO source=server.go:596 msg="waiting for server to become available" status="llm server error"
time=2024-11-20T19:28:48.457Z level=INFO source=runner.go:883 msg="starting go runner"
time=2024-11-20T19:28:48.457Z level=INFO source=runner.go:884 msg=system info="AVX = 1 | AVX_VNNI = 0 | AVX2 = 0 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | AVX512_BF16 = 0 | FMA = 0 | NEON = 0 | SVE = 0 | ARM_FMA = 0 | F16C = 0 | FP16_VA = 0 | RISCV_VECT = 0 | WASM_SIMD = 0 | BLAS = 1 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | MATMUL_INT8 = 0 | LLAMAFILE = 1 | cgo(gcc)" threads=6
time=2024-11-20T19:28:48.457Z level=INFO source=.:0 msg="Server listening on 127.0.0.1:39057"
llama_model_loader: loaded meta data with 30 key-value pairs and 255 tensors from /root/.ollama/models/blobs/sha256-dde5aa3fc5ffc17176b5e8bdc82f587b24b2678c6c66101bf7da77af9f7ccdff (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.type str              = model
llama_model_loader: - kv   2:                               general.name str              = Llama 3.2 3B Instruct
llama_model_loader: - kv   3:                           general.finetune str              = Instruct
llama_model_loader: - kv   4:                           general.basename str              = Llama-3.2
llama_model_loader: - kv   5:                         general.size_label str              = 3B
llama_model_loader: - kv   6:                               general.tags arr[str,6]       = ["facebook", "meta", "pytorch", "llam...
llama_model_loader: - kv   7:                          general.languages arr[str,8]       = ["en", "de", "fr", "it", "pt", "hi", ...
llama_model_loader: - kv   8:                          llama.block_count u32              = 28
llama_model_loader: - kv   9:                       llama.context_length u32              = 131072
llama_model_loader: - kv  10:                     llama.embedding_length u32              = 3072
llama_model_loader: - kv  11:                  llama.feed_forward_length u32              = 8192
llama_model_loader: - kv  12:                 llama.attention.head_count u32              = 24
llama_model_loader: - kv  13:              llama.attention.head_count_kv u32              = 8
llama_model_loader: - kv  14:                       llama.rope.freq_base f32              = 500000.000000
llama_model_loader: - kv  15:     llama.attention.layer_norm_rms_epsilon f32              = 0.000010
llama_model_loader: - kv  16:                 llama.attention.key_length u32              = 128
llama_model_loader: - kv  17:               llama.attention.value_length u32              = 128
llama_model_loader: - kv  18:                          general.file_type u32              = 15
llama_model_loader: - kv  19:                           llama.vocab_size u32              = 128256
llama_model_loader: - kv  20:                 llama.rope.dimension_count u32              = 128
llama_model_loader: - kv  21:                       tokenizer.ggml.model str              = gpt2
llama_model_loader: - kv  22:                         tokenizer.ggml.pre str              = llama-bpe
llama_model_loader: - kv  23:                      tokenizer.ggml.tokens arr[str,128256]  = ["!", "\"", "#", "$", "%", "&", "'", ...
llama_model_loader: - kv  24:                  tokenizer.ggml.token_type arr[i32,128256]  = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv  25:                      tokenizer.ggml.merges arr[str,280147]  = ["Ġ Ġ", "Ġ ĠĠĠ", "ĠĠ ĠĠ", "...
llama_model_loader: - kv  26:                tokenizer.ggml.bos_token_id u32              = 128000
llama_model_loader: - kv  27:                tokenizer.ggml.eos_token_id u32              = 128009
llama_model_loader: - kv  28:                    tokenizer.chat_template str              = {{- bos_token }}\n{%- if custom_tools ...
llama_model_loader: - kv  29:               general.quantization_version u32              = 2
llama_model_loader: - type  f32:   58 tensors
llama_model_loader: - type q4_K:  168 tensors
llama_model_loader: - type q6_K:   29 tensors
time=2024-11-20T19:28:48.695Z level=INFO source=server.go:596 msg="waiting for server to become available" status="llm server loading model"
llm_load_vocab: special tokens cache size = 256
llm_load_vocab: token to piece cache size = 0.7999 MB
llm_load_print_meta: format           = GGUF V3 (latest)
llm_load_print_meta: arch             = llama
llm_load_print_meta: vocab type       = BPE
llm_load_print_meta: n_vocab          = 128256
llm_load_print_meta: n_merges         = 280147
llm_load_print_meta: vocab_only       = 0
llm_load_print_meta: n_ctx_train      = 131072
llm_load_print_meta: n_embd           = 3072
llm_load_print_meta: n_layer          = 28
llm_load_print_meta: n_head           = 24
llm_load_print_meta: n_head_kv        = 8
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            = 3
llm_load_print_meta: n_embd_k_gqa     = 1024
llm_load_print_meta: n_embd_v_gqa     = 1024
llm_load_print_meta: f_norm_eps       = 0.0e+00
llm_load_print_meta: f_norm_rms_eps   = 1.0e-05
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             = 8192
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        = 0
llm_load_print_meta: rope scaling     = linear
llm_load_print_meta: freq_base_train  = 500000.0
llm_load_print_meta: freq_scale_train = 1
llm_load_print_meta: n_ctx_orig_yarn  = 131072
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       = 3B
llm_load_print_meta: model ftype      = Q4_K - Medium
llm_load_print_meta: model params     = 3.21 B
llm_load_print_meta: model size       = 1.87 GiB (5.01 BPW) 
llm_load_print_meta: general.name     = Llama 3.2 3B Instruct
llm_load_print_meta: BOS token        = 128000 '<|begin_of_text|>'
llm_load_print_meta: EOS token        = 128009 '<|eot_id|>'
llm_load_print_meta: LF token         = 128 'Ä'
llm_load_print_meta: EOT token        = 128009 '<|eot_id|>'
llm_load_print_meta: EOM token        = 128008 '<|eom_id|>'
llm_load_print_meta: EOG token        = 128008 '<|eom_id|>'
llm_load_print_meta: EOG token        = 128009 '<|eot_id|>'
llm_load_print_meta: max token length = 256
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 3060, compute capability 8.6, VMM: yes
llm_load_tensors: ggml ctx size =    0.24 MiB
llm_load_tensors: offloading 28 repeating layers to GPU
llm_load_tensors: offloading non-repeating layers to GPU
llm_load_tensors: offloaded 29/29 layers to GPU
llm_load_tensors:        CPU buffer size =   308.23 MiB
llm_load_tensors:      CUDA0 buffer size =  1918.36 MiB
llama_new_context_with_model: n_ctx      = 8192
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  = 500000.0
llama_new_context_with_model: freq_scale = 1
llama_kv_cache_init:      CUDA0 KV buffer size =   896.00 MiB
llama_new_context_with_model: KV self size  =  896.00 MiB, K (f16):  448.00 MiB, V (f16):  448.00 MiB
llama_new_context_with_model:  CUDA_Host  output buffer size =     2.00 MiB
llama_new_context_with_model:      CUDA0 compute buffer size =   424.00 MiB
llama_new_context_with_model:  CUDA_Host compute buffer size =    22.01 MiB
llama_new_context_with_model: graph nodes  = 902
llama_new_context_with_model: graph splits = 2
time=2024-11-20T19:28:50.201Z level=INFO source=server.go:601 msg="llama runner started in 1.76 seconds"
[GIN] 2024/11/20 - 19:28:50 | 200 |   2.70827177s |       127.0.0.1 | POST     "/api/generate"
[GIN] 2024/11/20 - 19:28:52 | 200 |  1.219114813s |       127.0.0.1 | POST     "/api/chat"
<!-- gh-comment-id:2489389982 --> @brauliobo commented on GitHub (Nov 20, 2024): here it is: ``` 2024/11/20 19:11:44 routes.go:1189: INFO server config env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://0.0.0.0:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:2562047h47m16.854775807s 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_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://*] OLLAMA_SCHED_SPREAD:false OLLAMA_TMPDIR: ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]" time=2024-11-20T19:11:44.932Z level=INFO source=images.go:755 msg="total blobs: 0" time=2024-11-20T19:11:44.932Z level=INFO source=images.go:762 msg="total unused blobs removed: 0" time=2024-11-20T19:11:44.932Z level=INFO source=routes.go:1240 msg="Listening on [::]:11434 (version 0.4.2)" time=2024-11-20T19:11:44.932Z level=INFO source=common.go:49 msg="Dynamic LLM libraries" runners="[cpu cpu_avx cpu_avx2 cuda_v11 cuda_v12]" time=2024-11-20T19:11:44.932Z level=INFO source=gpu.go:221 msg="looking for compatible GPUs" time=2024-11-20T19:11:45.416Z level=WARN source=amd_linux.go:61 msg="ollama recommends running the https://www.amd.com/en/support/linux-drivers" error="amdgpu version file missing: /sys/module/amdgpu/version stat /sys/module/amdgpu/version: no such file or directory" time=2024-11-20T19:11:45.417Z level=INFO source=amd_linux.go:399 msg="no compatible amdgpu devices detected" time=2024-11-20T19:11:45.417Z level=INFO source=types.go:123 msg="inference compute" id=GPU-467f0325-4701-7246-da8e-ea5f9e822dbf library=cuda variant=v12 compute=8.6 driver=12.7 name="NVIDIA GeForce RTX 3060" total="11.7 GiB" available="7.1 GiB" time=2024-11-20T19:16:03.897Z level=INFO source=download.go:175 msg="downloading dde5aa3fc5ff in 16 126 MB part(s)" time=2024-11-20T19:25:47.063Z level=INFO source=download.go:175 msg="downloading 966de95ca8a6 in 1 1.4 KB part(s)" time=2024-11-20T19:25:49.406Z level=INFO source=download.go:175 msg="downloading fcc5a6bec9da in 1 7.7 KB part(s)" time=2024-11-20T19:25:51.786Z level=INFO source=download.go:175 msg="downloading a70ff7e570d9 in 1 6.0 KB part(s)" time=2024-11-20T19:25:54.015Z level=INFO source=download.go:175 msg="downloading 56bb8bd477a5 in 1 96 B part(s)" time=2024-11-20T19:25:56.674Z level=INFO source=download.go:175 msg="downloading 34bb5ab01051 in 1 561 B part(s)" cuda driver library failed to get device context 800time=2024-11-20T19:25:58.956Z level=WARN source=gpu.go:441 msg="error looking up nvidia GPU memory" time=2024-11-20T19:25:58.979Z level=INFO source=sched.go:714 msg="new model will fit in available VRAM in single GPU, loading" model=/root/.ollama/models/blobs/sha256-dde5aa3fc5ffc17176b5e8bdc82f587b24b2678c6c66101bf7da77af9f7ccdff gpu=GPU-467f0325-4701-7246-da8e-ea5f9e822dbf parallel=4 available=7593525248 required="3.7 GiB" cuda driver library failed to get device context 800time=2024-11-20T19:25:58.994Z level=WARN source=gpu.go:441 msg="error looking up nvidia GPU memory" time=2024-11-20T19:25:58.994Z level=INFO source=server.go:105 msg="system memory" total="94.2 GiB" free="70.4 GiB" free_swap="0 B" time=2024-11-20T19:25:58.994Z level=INFO source=memory.go:343 msg="offload to cuda" layers.requested=-1 layers.model=29 layers.offload=29 layers.split="" memory.available="[7.1 GiB]" memory.gpu_overhead="0 B" memory.required.full="3.7 GiB" memory.required.partial="3.7 GiB" memory.required.kv="896.0 MiB" memory.required.allocations="[3.7 GiB]" memory.weights.total="2.4 GiB" memory.weights.repeating="2.1 GiB" memory.weights.nonrepeating="308.2 MiB" memory.graph.full="424.0 MiB" memory.graph.partial="570.7 MiB" time=2024-11-20T19:25:58.995Z level=INFO source=server.go:383 msg="starting llama server" cmd="/usr/lib/ollama/runners/cuda_v12/ollama_llama_server --model /root/.ollama/models/blobs/sha256-dde5aa3fc5ffc17176b5e8bdc82f587b24b2678c6c66101bf7da77af9f7ccdff --ctx-size 8192 --batch-size 512 --n-gpu-layers 29 --threads 6 --parallel 4 --port 45637" time=2024-11-20T19:25:58.998Z level=INFO source=sched.go:449 msg="loaded runners" count=1 time=2024-11-20T19:25:58.998Z level=INFO source=server.go:562 msg="waiting for llama runner to start responding" time=2024-11-20T19:25:58.999Z level=INFO source=server.go:596 msg="waiting for server to become available" status="llm server error" time=2024-11-20T19:25:59.083Z level=INFO source=runner.go:883 msg="starting go runner" time=2024-11-20T19:25:59.083Z level=INFO source=runner.go:884 msg=system info="AVX = 1 | AVX_VNNI = 0 | AVX2 = 0 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | AVX512_BF16 = 0 | FMA = 0 | NEON = 0 | SVE = 0 | ARM_FMA = 0 | F16C = 0 | FP16_VA = 0 | RISCV_VECT = 0 | WASM_SIMD = 0 | BLAS = 1 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | MATMUL_INT8 = 0 | LLAMAFILE = 1 | cgo(gcc)" threads=6 time=2024-11-20T19:25:59.083Z level=INFO source=.:0 msg="Server listening on 127.0.0.1:45637" llama_model_loader: loaded meta data with 30 key-value pairs and 255 tensors from /root/.ollama/models/blobs/sha256-dde5aa3fc5ffc17176b5e8bdc82f587b24b2678c6c66101bf7da77af9f7ccdff (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.type str = model llama_model_loader: - kv 2: general.name str = Llama 3.2 3B Instruct llama_model_loader: - kv 3: general.finetune str = Instruct llama_model_loader: - kv 4: general.basename str = Llama-3.2 llama_model_loader: - kv 5: general.size_label str = 3B llama_model_loader: - kv 6: general.tags arr[str,6] = ["facebook", "meta", "pytorch", "llam... llama_model_loader: - kv 7: general.languages arr[str,8] = ["en", "de", "fr", "it", "pt", "hi", ... llama_model_loader: - kv 8: llama.block_count u32 = 28 llama_model_loader: - kv 9: llama.context_length u32 = 131072 llama_model_loader: - kv 10: llama.embedding_length u32 = 3072 llama_model_loader: - kv 11: llama.feed_forward_length u32 = 8192 llama_model_loader: - kv 12: llama.attention.head_count u32 = 24 llama_model_loader: - kv 13: llama.attention.head_count_kv u32 = 8 llama_model_loader: - kv 14: llama.rope.freq_base f32 = 500000.000000 llama_model_loader: - kv 15: llama.attention.layer_norm_rms_epsilon f32 = 0.000010 llama_model_loader: - kv 16: llama.attention.key_length u32 = 128 llama_model_loader: - kv 17: llama.attention.value_length u32 = 128 llama_model_loader: - kv 18: general.file_type u32 = 15 llama_model_loader: - kv 19: llama.vocab_size u32 = 128256 llama_model_loader: - kv 20: llama.rope.dimension_count u32 = 128 llama_model_loader: - kv 21: tokenizer.ggml.model str = gpt2 llama_model_loader: - kv 22: tokenizer.ggml.pre str = llama-bpe llama_model_loader: - kv 23: tokenizer.ggml.tokens arr[str,128256] = ["!", "\"", "#", "$", "%", "&", "'", ... llama_model_loader: - kv 24: tokenizer.ggml.token_type arr[i32,128256] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... llama_model_loader: - kv 25: tokenizer.ggml.merges arr[str,280147] = ["Ġ Ġ", "Ġ ĠĠĠ", "ĠĠ ĠĠ", "... llama_model_loader: - kv 26: tokenizer.ggml.bos_token_id u32 = 128000 llama_model_loader: - kv 27: tokenizer.ggml.eos_token_id u32 = 128009 llama_model_loader: - kv 28: tokenizer.chat_template str = {{- bos_token }}\n{%- if custom_tools ... llama_model_loader: - kv 29: general.quantization_version u32 = 2 llama_model_loader: - type f32: 58 tensors llama_model_loader: - type q4_K: 168 tensors llama_model_loader: - type q6_K: 29 tensors time=2024-11-20T19:25:59.250Z level=INFO source=server.go:596 msg="waiting for server to become available" status="llm server loading model" llm_load_vocab: special tokens cache size = 256 llm_load_vocab: token to piece cache size = 0.7999 MB llm_load_print_meta: format = GGUF V3 (latest) llm_load_print_meta: arch = llama llm_load_print_meta: vocab type = BPE llm_load_print_meta: n_vocab = 128256 llm_load_print_meta: n_merges = 280147 llm_load_print_meta: vocab_only = 0 llm_load_print_meta: n_ctx_train = 131072 llm_load_print_meta: n_embd = 3072 llm_load_print_meta: n_layer = 28 llm_load_print_meta: n_head = 24 llm_load_print_meta: n_head_kv = 8 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 = 3 llm_load_print_meta: n_embd_k_gqa = 1024 llm_load_print_meta: n_embd_v_gqa = 1024 llm_load_print_meta: f_norm_eps = 0.0e+00 llm_load_print_meta: f_norm_rms_eps = 1.0e-05 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 = 8192 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 = 0 llm_load_print_meta: rope scaling = linear llm_load_print_meta: freq_base_train = 500000.0 llm_load_print_meta: freq_scale_train = 1 llm_load_print_meta: n_ctx_orig_yarn = 131072 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 = 3B llm_load_print_meta: model ftype = Q4_K - Medium llm_load_print_meta: model params = 3.21 B llm_load_print_meta: model size = 1.87 GiB (5.01 BPW) llm_load_print_meta: general.name = Llama 3.2 3B Instruct llm_load_print_meta: BOS token = 128000 '<|begin_of_text|>' llm_load_print_meta: EOS token = 128009 '<|eot_id|>' llm_load_print_meta: LF token = 128 'Ä' llm_load_print_meta: EOT token = 128009 '<|eot_id|>' llm_load_print_meta: EOM token = 128008 '<|eom_id|>' llm_load_print_meta: EOG token = 128008 '<|eom_id|>' llm_load_print_meta: EOG token = 128009 '<|eot_id|>' llm_load_print_meta: max token length = 256 ggml_cuda_init: failed to initialize CUDA: no CUDA-capable device is detected llm_load_tensors: ggml ctx size = 0.12 MiB llm_load_tensors: offloading 28 repeating layers to GPU llm_load_tensors: offloading non-repeating layers to GPU llm_load_tensors: offloaded 29/29 layers to GPU llm_load_tensors: CPU buffer size = 1918.35 MiB llama_new_context_with_model: n_ctx = 8192 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 = 500000.0 llama_new_context_with_model: freq_scale = 1 ggml_cuda_host_malloc: failed to allocate 896.00 MiB of pinned memory: no CUDA-capable device is detected llama_kv_cache_init: CPU KV buffer size = 896.00 MiB llama_new_context_with_model: KV self size = 896.00 MiB, K (f16): 448.00 MiB, V (f16): 448.00 MiB ggml_cuda_host_malloc: failed to allocate 2.00 MiB of pinned memory: no CUDA-capable device is detected llama_new_context_with_model: CPU output buffer size = 2.00 MiB ggml_cuda_host_malloc: failed to allocate 424.01 MiB of pinned memory: no CUDA-capable device is detected llama_new_context_with_model: CUDA_Host compute buffer size = 424.01 MiB llama_new_context_with_model: graph nodes = 902 llama_new_context_with_model: graph splits = 1 time=2024-11-20T19:25:59.751Z level=INFO source=server.go:601 msg="llama runner started in 0.75 seconds" ``` after a stop/start then it works, logs below: ``` braulio @ bhavapower ➜ ~ docker logs ollama Couldn't find '/root/.ollama/id_ed25519'. Generating new private key. Your new public key is: ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAIK4bI2uih7gjydskG+t/p1JuosWg/1eVsh25Z5D9qH1A 2024/11/20 19:11:44 routes.go:1189: INFO server config env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://0.0.0.0:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:2562047h47m16.854775807s OLLAMA_LLM_LIBRARY: OLLAMA_LOA D_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/root/.ollama/models OLLAMA_MULTIUSER_CACHE: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://*] OLLAMA_SCHED_SPREAD:false OLLAMA_TMPDIR: ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]" time=2024-11-20T19:11:44.932Z level=INFO source=images.go:755 msg="total blobs: 0" time=2024-11-20T19:11:44.932Z level=INFO source=images.go:762 msg="total unused blobs removed: 0" time=2024-11-20T19:11:44.932Z level=INFO source=routes.go:1240 msg="Listening on [::]:11434 (version 0.4.2)" time=2024-11-20T19:11:44.932Z level=INFO source=common.go:49 msg="Dynamic LLM libraries" runners="[cpu cpu_avx cpu_avx2 cuda_v11 cuda_v12]" time=2024-11-20T19:11:44.932Z level=INFO source=gpu.go:221 msg="looking for compatible GPUs" time=2024-11-20T19:11:45.416Z level=WARN source=amd_linux.go:61 msg="ollama recommends running the https://www.amd.com/en/support/linux-drivers" error="amdgpu version file missing: /sys/module/amdgpu/version stat /sys/module/amdgpu/version: no such file or directory" time=2024-11-20T19:11:45.417Z level=INFO source=amd_linux.go:399 msg="no compatible amdgpu devices detected" time=2024-11-20T19:11:45.417Z level=INFO source=types.go:123 msg="inference compute" id=GPU-467f0325-4701-7246-da8e-ea5f9e822dbf library=cuda variant=v12 compute=8.6 driver=12.7 name="NVIDIA GeForce RTX 3060" total="11.7 GiB" available="7.1 GiB" [GIN] 2024/11/20 - 19:15:59 | 200 | 19.255µs | 127.0.0.1 | HEAD "/" [GIN] 2024/11/20 - 19:15:59 | 404 | 84.878µs | 127.0.0.1 | POST "/api/show" time=2024-11-20T19:16:03.897Z level=INFO source=download.go:175 msg="downloading dde5aa3fc5ff in 16 126 MB part(s)" time=2024-11-20T19:25:47.063Z level=INFO source=download.go:175 msg="downloading 966de95ca8a6 in 1 1.4 KB part(s)" time=2024-11-20T19:25:49.406Z level=INFO source=download.go:175 msg="downloading fcc5a6bec9da in 1 7.7 KB part(s)" time=2024-11-20T19:25:51.786Z level=INFO source=download.go:175 msg="downloading a70ff7e570d9 in 1 6.0 KB part(s)" time=2024-11-20T19:25:54.015Z level=INFO source=download.go:175 msg="downloading 56bb8bd477a5 in 1 96 B part(s)" time=2024-11-20T19:25:56.674Z level=INFO source=download.go:175 msg="downloading 34bb5ab01051 in 1 561 B part(s)" [GIN] 2024/11/20 - 19:25:58 | 200 | 9m59s | 127.0.0.1 | POST "/api/pull" [GIN] 2024/11/20 - 19:25:58 | 200 | 12.366763ms | 127.0.0.1 | POST "/api/show" cuda driver library failed to get device context 800time=2024-11-20T19:25:58.956Z level=WARN source=gpu.go:441 msg="error looking up nvidia GPU memory" time=2024-11-20T19:25:58.979Z level=INFO source=sched.go:714 msg="new model will fit in available VRAM in single GPU, loading" model=/root/.ollama/models/blobs/sha256-dde5aa3fc5ffc17176b5e8bdc82f587b24b2678c6c66101bf7da77af9f7ccdff gpu=GPU-467f0325-4701-7246-da8e-ea5f9e822dbf parallel=4 available=7593525248 required="3.7 GiB" cuda driver library failed to get device context 800time=2024-11-20T19:25:58.994Z level=WARN source=gpu.go:441 msg="error looking up nvidia GPU memory" time=2024-11-20T19:25:58.994Z level=INFO source=server.go:105 msg="system memory" total="94.2 GiB" free="70.4 GiB" free_swap="0 B" time=2024-11-20T19:25:58.994Z level=INFO source=memory.go:343 msg="offload to cuda" layers.requested=-1 layers.model=29 layers.offload=29 layers.split="" memory.available="[7.1 GiB]" memory.gpu_overhead="0 B" memory.required.full="3.7 GiB" memory.required.partial="3.7 GiB" memory.required.kv="896.0 MiB" memory.required.allocations="[3.7 GiB]" memory.weights.total="2.4 GiB" memory.weig hts.repeating="2.1 GiB" memory.weights.nonrepeating="308.2 MiB" memory.graph.full="424.0 MiB" memory.graph.partial="570.7 MiB" time=2024-11-20T19:25:58.995Z level=INFO source=server.go:383 msg="starting llama server" cmd="/usr/lib/ollama/runners/cuda_v12/ollama_llama_server --model /root/.ollama/models/blobs/sha256-dde5aa3fc5ffc17176b5e8bdc82f587b24b2678c6c66101bf7da77af9f7ccdff --ctx-size 8192 --batch-size 512 --n-gpu-layers 29 --threads 6 --parallel 4 --port 45637" time=2024-11-20T19:25:58.998Z level=INFO source=sched.go:449 msg="loaded runners" count=1 time=2024-11-20T19:25:58.998Z level=INFO source=server.go:562 msg="waiting for llama runner to start responding" time=2024-11-20T19:25:58.999Z level=INFO source=server.go:596 msg="waiting for server to become available" status="llm server error" time=2024-11-20T19:25:59.083Z level=INFO source=runner.go:883 msg="starting go runner" time=2024-11-20T19:25:59.083Z level=INFO source=runner.go:884 msg=system info="AVX = 1 | AVX_VNNI = 0 | AVX2 = 0 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | AVX512_BF16 = 0 | FMA = 0 | NEON = 0 | SVE = 0 | ARM_FMA = 0 | F16C = 0 | FP16_VA = 0 | RISCV_VECT = 0 | WASM_SIMD = 0 | BLAS = 1 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | MATMUL_INT8 = 0 | LLAMAFILE = 1 | cgo(gcc)" threads=6 time=2024-11-20T19:25:59.083Z level=INFO source=.:0 msg="Server listening on 127.0.0.1:45637" llama_model_loader: loaded meta data with 30 key-value pairs and 255 tensors from /root/.ollama/models/blobs/sha256-dde5aa3fc5ffc17176b5e8bdc82f587b24b2678c6c66101bf7da77af9f7ccdff (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.type str = model llama_model_loader: - kv 2: general.name str = Llama 3.2 3B Instruct llama_model_loader: - kv 3: general.finetune str = Instruct llama_model_loader: - kv 4: general.basename str = Llama-3.2 llama_model_loader: - kv 5: general.size_label str = 3B llama_model_loader: - kv 6: general.tags arr[str,6] = ["facebook", "meta", "pytorch", "llam... llama_model_loader: - kv 7: general.languages arr[str,8] = ["en", "de", "fr", "it", "pt", "hi", ... llama_model_loader: - kv 8: llama.block_count u32 = 28 llama_model_loader: - kv 9: llama.context_length u32 = 131072 llama_model_loader: - kv 10: llama.embedding_length u32 = 3072 llama_model_loader: - kv 11: llama.feed_forward_length u32 = 8192 llama_model_loader: - kv 12: llama.attention.head_count u32 = 24 llama_model_loader: - kv 13: llama.attention.head_count_kv u32 = 8 llama_model_loader: - kv 14: llama.rope.freq_base f32 = 500000.000000 llama_model_loader: - kv 15: llama.attention.layer_norm_rms_epsilon f32 = 0.000010 llama_model_loader: - kv 16: llama.attention.key_length u32 = 128 llama_model_loader: - kv 17: llama.attention.value_length u32 = 128 llama_model_loader: - kv 18: general.file_type u32 = 15 llama_model_loader: - kv 19: llama.vocab_size u32 = 128256 llama_model_loader: - kv 20: llama.rope.dimension_count u32 = 128 llama_model_loader: - kv 21: tokenizer.ggml.model str = gpt2 llama_model_loader: - kv 22: tokenizer.ggml.pre str = llama-bpe llama_model_loader: - kv 23: tokenizer.ggml.tokens arr[str,128256] = ["!", "\"", "#", "$", "%", "&", "'", ... llama_model_loader: - kv 24: tokenizer.ggml.token_type arr[i32,128256] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... llama_model_loader: - kv 25: tokenizer.ggml.merges arr[str,280147] = ["Ġ Ġ", "Ġ ĠĠĠ", "ĠĠ ĠĠ", "... llama_model_loader: - kv 26: tokenizer.ggml.bos_token_id u32 = 128000 llama_model_loader: - kv 27: tokenizer.ggml.eos_token_id u32 = 128009 llama_model_loader: - kv 28: tokenizer.chat_template str = {{- bos_token }}\n{%- if custom_tools ... llama_model_loader: - kv 29: general.quantization_version u32 = 2 llama_model_loader: - type f32: 58 tensors llama_model_loader: - type q4_K: 168 tensors llama_model_loader: - type q6_K: 29 tensors time=2024-11-20T19:25:59.250Z level=INFO source=server.go:596 msg="waiting for server to become available" status="llm server loading model" llm_load_vocab: special tokens cache size = 256 llm_load_vocab: token to piece cache size = 0.7999 MB llm_load_print_meta: format = GGUF V3 (latest) llm_load_print_meta: arch = llama llm_load_print_meta: vocab type = BPE llm_load_print_meta: n_vocab = 128256 llm_load_print_meta: n_merges = 280147 llm_load_print_meta: vocab_only = 0 llm_load_print_meta: n_ctx_train = 131072 llm_load_print_meta: n_embd = 3072 llm_load_print_meta: n_layer = 28 llm_load_print_meta: n_head = 24 llm_load_print_meta: n_head_kv = 8 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 = 3 llm_load_print_meta: n_embd_k_gqa = 1024 llm_load_print_meta: n_embd_v_gqa = 1024 llm_load_print_meta: f_norm_eps = 0.0e+00 llm_load_print_meta: f_norm_rms_eps = 1.0e-05 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 = 8192 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 = 0 llm_load_print_meta: rope scaling = linear llm_load_print_meta: freq_base_train = 500000.0 llm_load_print_meta: freq_scale_train = 1 llm_load_print_meta: n_ctx_orig_yarn = 131072 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 = 3B llm_load_print_meta: model ftype = Q4_K - Medium llm_load_print_meta: model params = 3.21 B llm_load_print_meta: model size = 1.87 GiB (5.01 BPW) llm_load_print_meta: general.name = Llama 3.2 3B Instruct llm_load_print_meta: BOS token = 128000 '<|begin_of_text|>' llm_load_print_meta: EOS token = 128009 '<|eot_id|>' llm_load_print_meta: LF token = 128 'Ä' llm_load_print_meta: EOT token = 128009 '<|eot_id|>' llm_load_print_meta: EOM token = 128008 '<|eom_id|>' llm_load_print_meta: EOG token = 128008 '<|eom_id|>' llm_load_print_meta: EOG token = 128009 '<|eot_id|>' llm_load_print_meta: max token length = 256 ggml_cuda_init: failed to initialize CUDA: no CUDA-capable device is detected llm_load_tensors: ggml ctx size = 0.12 MiB llm_load_tensors: offloading 28 repeating layers to GPU llm_load_tensors: offloading non-repeating layers to GPU llm_load_tensors: offloaded 29/29 layers to GPU llm_load_tensors: CPU buffer size = 1918.35 MiB llama_new_context_with_model: n_ctx = 8192 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 = 500000.0 llama_new_context_with_model: freq_scale = 1 ggml_cuda_host_malloc: failed to allocate 896.00 MiB of pinned memory: no CUDA-capable device is detected llama_kv_cache_init: CPU KV buffer size = 896.00 MiB llama_new_context_with_model: KV self size = 896.00 MiB, K (f16): 448.00 MiB, V (f16): 448.00 MiB ggml_cuda_host_malloc: failed to allocate 2.00 MiB of pinned memory: no CUDA-capable device is detected llama_new_context_with_model: CPU output buffer size = 2.00 MiB ggml_cuda_host_malloc: failed to allocate 424.01 MiB of pinned memory: no CUDA-capable device is detected llama_new_context_with_model: CUDA_Host compute buffer size = 424.01 MiB llama_new_context_with_model: graph nodes = 902 llama_new_context_with_model: graph splits = 1 time=2024-11-20T19:25:59.751Z level=INFO source=server.go:601 msg="llama runner started in 0.75 seconds" [GIN] 2024/11/20 - 19:25:59 | 200 | 823.467751ms | 127.0.0.1 | POST "/api/generate" 2024/11/20 19:28:41 routes.go:1189: INFO server config env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://0.0.0.0:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:2562047h47m16.854775807s 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_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://*] OLLAMA_SCHED_SPREAD:false OLLAMA_TMPDIR: ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]" time=2024-11-20T19:28:41.527Z level=INFO source=images.go:755 msg="total blobs: 6" time=2024-11-20T19:28:41.527Z level=INFO source=images.go:762 msg="total unused blobs removed: 0" time=2024-11-20T19:28:41.527Z level=INFO source=routes.go:1240 msg="Listening on [::]:11434 (version 0.4.2)" time=2024-11-20T19:28:41.527Z level=INFO source=common.go:49 msg="Dynamic LLM libraries" runners="[cpu_avx2 cuda_v11 cuda_v12 cpu cpu_avx]" time=2024-11-20T19:28:41.527Z level=INFO source=gpu.go:221 msg="looking for compatible GPUs" time=2024-11-20T19:28:42.011Z level=WARN source=amd_linux.go:61 msg="ollama recommends running the https://www.amd.com/en/support/linux-drivers" error="amdgpu version file missing: /sys/module/amdgpu/version stat /sys/module/amdgpu/version: no such file or directory" time=2024-11-20T19:28:42.012Z level=INFO source=amd_linux.go:399 msg="no compatible amdgpu devices detected" time=2024-11-20T19:28:42.012Z level=INFO source=types.go:123 msg="inference compute" id=GPU-467f0325-4701-7246-da8e-ea5f9e822dbf library=cuda variant=v12 compute=8.6 driver=12.7 name="NVIDIA GeForce RTX 3060" total="11.7 GiB" available="7.1 GiB" [GIN] 2024/11/20 - 19:28:47 | 200 | 19.856µs | 127.0.0.1 | HEAD "/" [GIN] 2024/11/20 - 19:28:47 | 200 | 12.291472ms | 127.0.0.1 | POST "/api/show" time=2024-11-20T19:28:47.988Z level=INFO source=sched.go:714 msg="new model will fit in available VRAM in single GPU, loading" model=/root/.ollama/models/blobs/sha256-dde5aa3fc5ffc17176b5e8bdc82f587b24b2678c6c66101bf7da77af9f7ccdff gpu=GPU-467f0325-4701-7246-da8e-ea5f9e822dbf parallel=4 available=7593525248 required="3.7 GiB" time=2024-11-20T19:28:48.443Z level=INFO source=server.go:105 msg="system memory" total="94.2 GiB" free="69.9 GiB" free_swap="0 B" time=2024-11-20T19:28:48.443Z level=INFO source=memory.go:343 msg="offload to cuda" layers.requested=-1 layers.model=29 layers.offload=29 layers.split="" memory.available="[7.1 GiB]" memory.gpu_overhead="0 B" memory.required.full="3.7 GiB" memory.required.partial="3.7 GiB" memory.required.kv="896.0 MiB" memory.required.allocations="[3.7 GiB]" memory.weights.total="2.4 GiB" memory.weights.repeating="2.1 GiB" memory.weights.nonrepeating="308.2 MiB" memory.graph.full="424.0 MiB" memory.graph.partial="570.7 MiB" time=2024-11-20T19:28:48.444Z level=INFO source=server.go:383 msg="starting llama server" cmd="/usr/lib/ollama/runners/cuda_v12/ollama_llama_server --model /root/.ollama/models/blobs/sha256-dde5aa3fc5ffc17176b5e8bdc82f587b24b2678c6c66101bf7da77af9f7ccdff --ctx-size 8192 --batch-size 512 --n-gpu-layers 29 --threads 6 --parallel 4 --port 39057" time=2024-11-20T19:28:48.444Z level=INFO source=sched.go:449 msg="loaded runners" count=1 time=2024-11-20T19:28:48.444Z level=INFO source=server.go:562 msg="waiting for llama runner to start responding" time=2024-11-20T19:28:48.444Z level=INFO source=server.go:596 msg="waiting for server to become available" status="llm server error" time=2024-11-20T19:28:48.457Z level=INFO source=runner.go:883 msg="starting go runner" time=2024-11-20T19:28:48.457Z level=INFO source=runner.go:884 msg=system info="AVX = 1 | AVX_VNNI = 0 | AVX2 = 0 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | AVX512_BF16 = 0 | FMA = 0 | NEON = 0 | SVE = 0 | ARM_FMA = 0 | F16C = 0 | FP16_VA = 0 | RISCV_VECT = 0 | WASM_SIMD = 0 | BLAS = 1 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | MATMUL_INT8 = 0 | LLAMAFILE = 1 | cgo(gcc)" threads=6 time=2024-11-20T19:28:48.457Z level=INFO source=.:0 msg="Server listening on 127.0.0.1:39057" llama_model_loader: loaded meta data with 30 key-value pairs and 255 tensors from /root/.ollama/models/blobs/sha256-dde5aa3fc5ffc17176b5e8bdc82f587b24b2678c6c66101bf7da77af9f7ccdff (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.type str = model llama_model_loader: - kv 2: general.name str = Llama 3.2 3B Instruct llama_model_loader: - kv 3: general.finetune str = Instruct llama_model_loader: - kv 4: general.basename str = Llama-3.2 llama_model_loader: - kv 5: general.size_label str = 3B llama_model_loader: - kv 6: general.tags arr[str,6] = ["facebook", "meta", "pytorch", "llam... llama_model_loader: - kv 7: general.languages arr[str,8] = ["en", "de", "fr", "it", "pt", "hi", ... llama_model_loader: - kv 8: llama.block_count u32 = 28 llama_model_loader: - kv 9: llama.context_length u32 = 131072 llama_model_loader: - kv 10: llama.embedding_length u32 = 3072 llama_model_loader: - kv 11: llama.feed_forward_length u32 = 8192 llama_model_loader: - kv 12: llama.attention.head_count u32 = 24 llama_model_loader: - kv 13: llama.attention.head_count_kv u32 = 8 llama_model_loader: - kv 14: llama.rope.freq_base f32 = 500000.000000 llama_model_loader: - kv 15: llama.attention.layer_norm_rms_epsilon f32 = 0.000010 llama_model_loader: - kv 16: llama.attention.key_length u32 = 128 llama_model_loader: - kv 17: llama.attention.value_length u32 = 128 llama_model_loader: - kv 18: general.file_type u32 = 15 llama_model_loader: - kv 19: llama.vocab_size u32 = 128256 llama_model_loader: - kv 20: llama.rope.dimension_count u32 = 128 llama_model_loader: - kv 21: tokenizer.ggml.model str = gpt2 llama_model_loader: - kv 22: tokenizer.ggml.pre str = llama-bpe llama_model_loader: - kv 23: tokenizer.ggml.tokens arr[str,128256] = ["!", "\"", "#", "$", "%", "&", "'", ... llama_model_loader: - kv 24: tokenizer.ggml.token_type arr[i32,128256] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... llama_model_loader: - kv 25: tokenizer.ggml.merges arr[str,280147] = ["Ġ Ġ", "Ġ ĠĠĠ", "ĠĠ ĠĠ", "... llama_model_loader: - kv 26: tokenizer.ggml.bos_token_id u32 = 128000 llama_model_loader: - kv 27: tokenizer.ggml.eos_token_id u32 = 128009 llama_model_loader: - kv 28: tokenizer.chat_template str = {{- bos_token }}\n{%- if custom_tools ... llama_model_loader: - kv 29: general.quantization_version u32 = 2 llama_model_loader: - type f32: 58 tensors llama_model_loader: - type q4_K: 168 tensors llama_model_loader: - type q6_K: 29 tensors time=2024-11-20T19:28:48.695Z level=INFO source=server.go:596 msg="waiting for server to become available" status="llm server loading model" llm_load_vocab: special tokens cache size = 256 llm_load_vocab: token to piece cache size = 0.7999 MB llm_load_print_meta: format = GGUF V3 (latest) llm_load_print_meta: arch = llama llm_load_print_meta: vocab type = BPE llm_load_print_meta: n_vocab = 128256 llm_load_print_meta: n_merges = 280147 llm_load_print_meta: vocab_only = 0 llm_load_print_meta: n_ctx_train = 131072 llm_load_print_meta: n_embd = 3072 llm_load_print_meta: n_layer = 28 llm_load_print_meta: n_head = 24 llm_load_print_meta: n_head_kv = 8 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 = 3 llm_load_print_meta: n_embd_k_gqa = 1024 llm_load_print_meta: n_embd_v_gqa = 1024 llm_load_print_meta: f_norm_eps = 0.0e+00 llm_load_print_meta: f_norm_rms_eps = 1.0e-05 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 = 8192 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 = 0 llm_load_print_meta: rope scaling = linear llm_load_print_meta: freq_base_train = 500000.0 llm_load_print_meta: freq_scale_train = 1 llm_load_print_meta: n_ctx_orig_yarn = 131072 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 = 3B llm_load_print_meta: model ftype = Q4_K - Medium llm_load_print_meta: model params = 3.21 B llm_load_print_meta: model size = 1.87 GiB (5.01 BPW) llm_load_print_meta: general.name = Llama 3.2 3B Instruct llm_load_print_meta: BOS token = 128000 '<|begin_of_text|>' llm_load_print_meta: EOS token = 128009 '<|eot_id|>' llm_load_print_meta: LF token = 128 'Ä' llm_load_print_meta: EOT token = 128009 '<|eot_id|>' llm_load_print_meta: EOM token = 128008 '<|eom_id|>' llm_load_print_meta: EOG token = 128008 '<|eom_id|>' llm_load_print_meta: EOG token = 128009 '<|eot_id|>' llm_load_print_meta: max token length = 256 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 3060, compute capability 8.6, VMM: yes llm_load_tensors: ggml ctx size = 0.24 MiB llm_load_tensors: offloading 28 repeating layers to GPU llm_load_tensors: offloading non-repeating layers to GPU llm_load_tensors: offloaded 29/29 layers to GPU llm_load_tensors: CPU buffer size = 308.23 MiB llm_load_tensors: CUDA0 buffer size = 1918.36 MiB llama_new_context_with_model: n_ctx = 8192 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 = 500000.0 llama_new_context_with_model: freq_scale = 1 llama_kv_cache_init: CUDA0 KV buffer size = 896.00 MiB llama_new_context_with_model: KV self size = 896.00 MiB, K (f16): 448.00 MiB, V (f16): 448.00 MiB llama_new_context_with_model: CUDA_Host output buffer size = 2.00 MiB llama_new_context_with_model: CUDA0 compute buffer size = 424.00 MiB llama_new_context_with_model: CUDA_Host compute buffer size = 22.01 MiB llama_new_context_with_model: graph nodes = 902 llama_new_context_with_model: graph splits = 2 time=2024-11-20T19:28:50.201Z level=INFO source=server.go:601 msg="llama runner started in 1.76 seconds" [GIN] 2024/11/20 - 19:28:50 | 200 | 2.70827177s | 127.0.0.1 | POST "/api/generate" [GIN] 2024/11/20 - 19:28:52 | 200 | 1.219114813s | 127.0.0.1 | POST "/api/chat" ```
GiteaMirror commented 2026-05-04 09:14:56 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Nov 20, 2024):

cuda driver library failed to get device context 800
time=2024-11-20T19:25:58.956Z level=WARN source=gpu.go:441 msg="error looking up nvidia GPU memory"

Try the work around in https://github.com/ollama/ollama/pull/7519. It's techically a workaround for AMD GPUs but it sounds a lot like what you are experiencing.

<!-- gh-comment-id:2489406758 --> @rick-github commented on GitHub (Nov 20, 2024): ``` cuda driver library failed to get device context 800 time=2024-11-20T19:25:58.956Z level=WARN source=gpu.go:441 msg="error looking up nvidia GPU memory" ``` Try the work around in https://github.com/ollama/ollama/pull/7519. It's techically a workaround for AMD GPUs but it sounds a lot like what you are experiencing.
GiteaMirror commented 2026-05-04 09:14:57 -05:00
Author
Owner
Copy Link

@brauliobo commented on GitHub (Nov 20, 2024):

Thanks! I've just put "exec-opts": ["native.cgroupdriver=cgroupfs"] in /etc/docker/daemon.json. I've also used -e OLLAMA_KEEP_ALIVE=-1 to avoid restarts. Closing for now

<!-- gh-comment-id:2489428491 --> @brauliobo commented on GitHub (Nov 20, 2024): Thanks! I've just put `"exec-opts": ["native.cgroupdriver=cgroupfs"]` in `/etc/docker/daemon.json`. I've also used `-e OLLAMA_KEEP_ALIVE=-1` to avoid restarts. Closing for now
GiteaMirror commented 2026-05-04 09:14:58 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Nov 20, 2024):

Note that OLLAMA_KEEP_ALIVE=1 means keep the model loaded for 1 second after a completion is finished. If you want the model to be always loaded (which is what I think you mean by "avoid restarts"), you want OLLAMA_KEEP_ALIVE=-1.

<!-- gh-comment-id:2489436767 --> @rick-github commented on GitHub (Nov 20, 2024): Note that `OLLAMA_KEEP_ALIVE=1` means keep the model loaded for 1 second after a completion is finished. If you want the model to be always loaded (which is what I think you mean by "avoid restarts"), you want `OLLAMA_KEEP_ALIVE=-1`.
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#67016
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?