github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-08 08:59:13 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #9129] ollama do not use all my gpus. #67994

New Issue
Closed
opened 2026-05-04 12:13:36 -05:00 by GiteaMirror · 4 comments
GiteaMirror commented 2026-05-04 12:13:36 -05:00
Owner
Copy Link

Originally created by @l00n00l on GitHub (Feb 15, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/9129

What is the issue?

My gpus

+-----------------------------------------------------------------------------------------+
| NVIDIA-SMI 565.57.01              Driver Version: 565.57.01      CUDA Version: 12.7     |
|-----------------------------------------+------------------------+----------------------+
| GPU  Name                 Persistence-M | Bus-Id          Disp.A | Volatile Uncorr. ECC |
| Fan  Temp   Perf          Pwr:Usage/Cap |           Memory-Usage | GPU-Util  Compute M. |
|                                         |                        |               MIG M. |
|=========================================+========================+======================|
|   0  Tesla P40                      Off |   00000000:01:00.0 Off |                  Off |
| N/A   32C    P0             54W /  250W |   23151MiB /  24576MiB |      0%      Default |
|                                         |                        |                  N/A |
+-----------------------------------------+------------------------+----------------------+
|   1  Tesla M40 24GB                 Off |   00000000:04:00.0 Off |                  Off |
| N/A   37C    P8             15W /  250W |       7MiB /  24576MiB |      0%      Default |
|                                         |                        |                  N/A |
+-----------------------------------------+------------------------+----------------------+

My serve commond

OLLAMA_SCHED_SPREAD=1 CUDA_VISIBLE_DEVICES=0,1 ollama serve

My run command

ollama run deepseek-r1:70b

The output log

2025/02/15 16:07:41 routes.go:1186: INFO server config env="map[CUDA_VISIBLE_DEVICES:0,1 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://127.0.0.1:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/media/aaa/data/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:true ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]"
time=2025-02-15T16:07:41.156+08:00 level=INFO source=images.go:432 msg="total blobs: 22"
time=2025-02-15T16:07:41.156+08:00 level=INFO source=images.go:439 msg="total unused blobs removed: 0"
time=2025-02-15T16:07:41.156+08:00 level=INFO source=routes.go:1237 msg="Listening on 127.0.0.1:11434 (version 0.5.10)"
time=2025-02-15T16:07:41.156+08:00 level=INFO source=gpu.go:217 msg="looking for compatible GPUs"
time=2025-02-15T16:07:41.366+08:00 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=2025-02-15T16:07:41.366+08:00 level=INFO source=amd_linux.go:296 msg="unsupported Radeon iGPU detected skipping" id=0 total="512.0 MiB"
time=2025-02-15T16:07:41.366+08:00 level=INFO source=amd_linux.go:402 msg="no compatible amdgpu devices detected"
time=2025-02-15T16:07:41.366+08:00 level=INFO source=types.go:130 msg="inference compute" id=GPU-3bb8d0f1-7fbd-75ee-1589-b2d6866f8fae library=cuda variant=v12 compute=6.1 driver=12.7 name="Tesla P40" total="23.9 GiB" available="23.7 GiB"
time=2025-02-15T16:07:41.366+08:00 level=INFO source=types.go:130 msg="inference compute" id=GPU-01a87dbe-0079-88b7-2a43-5d879a6ef155 library=cuda variant=v11 compute=5.2 driver=12.7 name="Tesla M40 24GB" total="23.9 GiB" available="23.8 GiB"
[GIN] 2025/02/15 - 16:08:33 | 200 |       39.98µs |       127.0.0.1 | HEAD     "/"
[GIN] 2025/02/15 - 16:08:33 | 200 |    14.85932ms |       127.0.0.1 | POST     "/api/show"
time=2025-02-15T16:08:34.221+08:00 level=INFO source=server.go:100 msg="system memory" total="93.6 GiB" free="88.2 GiB" free_swap="15.7 GiB"
time=2025-02-15T16:08:34.222+08:00 level=INFO source=memory.go:356 msg="offload to cuda" layers.requested=-1 layers.model=81 layers.offload=44 layers.split="" memory.available="[23.7 GiB]" memory.gpu_overhead="0 B" memory.required.full="42.7 GiB" memory.required.partial="23.4 GiB" memory.required.kv="640.0 MiB" memory.required.allocations="[23.4 GiB]" memory.weights.total="38.9 GiB" memory.weights.repeating="38.1 GiB" memory.weights.nonrepeating="822.0 MiB" memory.graph.full="324.0 MiB" memory.graph.partial="1.1 GiB"
time=2025-02-15T16:08:34.223+08:00 level=INFO source=server.go:381 msg="starting llama server" cmd="/usr/local/bin/ollama runner --model /media/aaa/data/ollama_models/blobs/sha256-4cd576d9aa16961244012223abf01445567b061f1814b57dfef699e4cf8df339 --ctx-size 2048 --batch-size 512 --n-gpu-layers 44 --threads 8 --parallel 1 --port 45131"
time=2025-02-15T16:08:34.223+08:00 level=INFO source=sched.go:449 msg="loaded runners" count=1
time=2025-02-15T16:08:34.223+08:00 level=INFO source=server.go:558 msg="waiting for llama runner to start responding"
time=2025-02-15T16:08:34.223+08:00 level=INFO source=server.go:592 msg="waiting for server to become available" status="llm server error"
time=2025-02-15T16:08:34.234+08:00 level=INFO source=runner.go:936 msg="starting go runner"
time=2025-02-15T16:08:34.234+08:00 level=INFO source=runner.go:937 msg=system info="CPU : LLAMAFILE = 1 | CPU : LLAMAFILE = 1 | cgo(gcc)" threads=8
time=2025-02-15T16:08:34.234+08:00 level=INFO source=runner.go:995 msg="Server listening on 127.0.0.1:45131"
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: Tesla P40, compute capability 6.1, VMM: yes
load_backend: loaded CUDA backend from /usr/local/lib/ollama/cuda_v12/libggml-cuda.so
load_backend: loaded CPU backend from /usr/local/lib/ollama/libggml-cpu-haswell.so
llama_load_model_from_file: using device CUDA0 (Tesla P40) - 24286 MiB free
llama_model_loader: loaded meta data with 30 key-value pairs and 724 tensors from /media/aaa/data/ollama_models/blobs/sha256-4cd576d9aa16961244012223abf01445567b061f1814b57dfef699e4cf8df339 (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              = DeepSeek R1 Distill Llama 70B
llama_model_loader: - kv   3:                           general.basename str              = DeepSeek-R1-Distill-Llama
llama_model_loader: - kv   4:                         general.size_label str              = 70B
llama_model_loader: - kv   5:                          llama.block_count u32              = 80
llama_model_loader: - kv   6:                       llama.context_length u32              = 131072
llama_model_loader: - kv   7:                     llama.embedding_length u32              = 8192
llama_model_loader: - kv   8:                  llama.feed_forward_length u32              = 28672
llama_model_loader: - kv   9:                 llama.attention.head_count u32              = 64
llama_model_loader: - kv  10:              llama.attention.head_count_kv u32              = 8
llama_model_loader: - kv  11:                       llama.rope.freq_base f32              = 500000.000000
llama_model_loader: - kv  12:     llama.attention.layer_norm_rms_epsilon f32              = 0.000010
llama_model_loader: - kv  13:                 llama.attention.key_length u32              = 128
llama_model_loader: - kv  14:               llama.attention.value_length u32              = 128
llama_model_loader: - kv  15:                          general.file_type u32              = 15
llama_model_loader: - kv  16:                           llama.vocab_size u32              = 128256
llama_model_loader: - kv  17:                 llama.rope.dimension_count u32              = 128
llama_model_loader: - kv  18:                       tokenizer.ggml.model str              = gpt2
llama_model_loader: - kv  19:                         tokenizer.ggml.pre str              = llama-bpe
llama_model_loader: - kv  20:                      tokenizer.ggml.tokens arr[str,128256]  = ["!", "\"", "#", "$", "%", "&", "'", ...
llama_model_loader: - kv  21:                  tokenizer.ggml.token_type arr[i32,128256]  = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv  22:                      tokenizer.ggml.merges arr[str,280147]  = ["Ġ Ġ", "Ġ ĠĠĠ", "ĠĠ ĠĠ", "...
llama_model_loader: - kv  23:                tokenizer.ggml.bos_token_id u32              = 128000
llama_model_loader: - kv  24:                tokenizer.ggml.eos_token_id u32              = 128001
llama_model_loader: - kv  25:            tokenizer.ggml.padding_token_id u32              = 128001
llama_model_loader: - kv  26:               tokenizer.ggml.add_bos_token bool             = true
llama_model_loader: - kv  27:               tokenizer.ggml.add_eos_token bool             = false
llama_model_loader: - kv  28:                    tokenizer.chat_template str              = {% if not add_generation_prompt is de...
llama_model_loader: - kv  29:               general.quantization_version u32              = 2
llama_model_loader: - type  f32:  162 tensors
llama_model_loader: - type q4_K:  441 tensors
llama_model_loader: - type q5_K:   40 tensors
llama_model_loader: - type q6_K:   81 tensors
time=2025-02-15T16:08:34.474+08:00 level=INFO source=server.go:592 msg="waiting for server to become available" status="llm server loading model"
llm_load_vocab: special_eos_id is not in special_eog_ids - the tokenizer config may be incorrect
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           = 8192
llm_load_print_meta: n_layer          = 80
llm_load_print_meta: n_head           = 64
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            = 8
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             = 28672
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       = 70B
llm_load_print_meta: model ftype      = Q4_K - Medium
llm_load_print_meta: model params     = 70.55 B
llm_load_print_meta: model size       = 39.59 GiB (4.82 BPW) 
llm_load_print_meta: general.name     = DeepSeek R1 Distill Llama 70B
llm_load_print_meta: BOS token        = 128000 '<｜begin▁of▁sentence｜>'
llm_load_print_meta: EOS token        = 128001 '<｜end▁of▁sentence｜>'
llm_load_print_meta: EOT token        = 128009 '<|eot_id|>'
llm_load_print_meta: EOM token        = 128008 '<|eom_id|>'
llm_load_print_meta: PAD token        = 128001 '<｜end▁of▁sentence｜>'
llm_load_print_meta: LF token         = 128 'Ä'
llm_load_print_meta: EOG token        = 128001 '<｜end▁of▁sentence｜>'
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
llm_load_tensors: offloading 44 repeating layers to GPU
llm_load_tensors: offloaded 44/81 layers to GPU
llm_load_tensors:        CUDA0 model buffer size = 21536.63 MiB
llm_load_tensors:   CPU_Mapped model buffer size = 19006.48 MiB
llama_new_context_with_model: n_seq_max     = 1
llama_new_context_with_model: n_ctx         = 2048
llama_new_context_with_model: n_ctx_per_seq = 2048
llama_new_context_with_model: n_batch       = 512
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_new_context_with_model: n_ctx_per_seq (2048) < n_ctx_train (131072) -- the full capacity of the model will not be utilized
llama_kv_cache_init: kv_size = 2048, offload = 1, type_k = 'f16', type_v = 'f16', n_layer = 80, can_shift = 1
llama_kv_cache_init:      CUDA0 KV buffer size =   352.00 MiB
llama_kv_cache_init:        CPU KV buffer size =   288.00 MiB
llama_new_context_with_model: KV self size  =  640.00 MiB, K (f16):  320.00 MiB, V (f16):  320.00 MiB
llama_new_context_with_model:        CPU  output buffer size =     0.52 MiB
llama_new_context_with_model:      CUDA0 compute buffer size =  1088.45 MiB
llama_new_context_with_model:  CUDA_Host compute buffer size =    20.01 MiB
llama_new_context_with_model: graph nodes  = 2566
llama_new_context_with_model: graph splits = 401 (with bs=512), 3 (with bs=1)
time=2025-02-15T16:08:41.752+08:00 level=INFO source=server.go:597 msg="llama runner started in 7.53 seconds"
[GIN] 2025/02/15 - 16:08:41 | 200 |   7.89437029s |       127.0.0.1 | POST     "/api/generate"```

### Relevant log output

```shell

OS

Linux

GPU

Nvidia

CPU

AMD

Ollama version

0.5.11

Originally created by @l00n00l on GitHub (Feb 15, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/9129 ### What is the issue? My gpus ``` +-----------------------------------------------------------------------------------------+ | NVIDIA-SMI 565.57.01 Driver Version: 565.57.01 CUDA Version: 12.7 | |-----------------------------------------+------------------------+----------------------+ | GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC | | Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. | | | | MIG M. | |=========================================+========================+======================| | 0 Tesla P40 Off | 00000000:01:00.0 Off | Off | | N/A 32C P0 54W / 250W | 23151MiB / 24576MiB | 0% Default | | | | N/A | +-----------------------------------------+------------------------+----------------------+ | 1 Tesla M40 24GB Off | 00000000:04:00.0 Off | Off | | N/A 37C P8 15W / 250W | 7MiB / 24576MiB | 0% Default | | | | N/A | +-----------------------------------------+------------------------+----------------------+ ``` My serve commond ``` OLLAMA_SCHED_SPREAD=1 CUDA_VISIBLE_DEVICES=0,1 ollama serve ``` My run command ``` ollama run deepseek-r1:70b ``` The output log ``` 2025/02/15 16:07:41 routes.go:1186: INFO server config env="map[CUDA_VISIBLE_DEVICES:0,1 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://127.0.0.1:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:/media/aaa/data/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:true ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]" time=2025-02-15T16:07:41.156+08:00 level=INFO source=images.go:432 msg="total blobs: 22" time=2025-02-15T16:07:41.156+08:00 level=INFO source=images.go:439 msg="total unused blobs removed: 0" time=2025-02-15T16:07:41.156+08:00 level=INFO source=routes.go:1237 msg="Listening on 127.0.0.1:11434 (version 0.5.10)" time=2025-02-15T16:07:41.156+08:00 level=INFO source=gpu.go:217 msg="looking for compatible GPUs" time=2025-02-15T16:07:41.366+08:00 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=2025-02-15T16:07:41.366+08:00 level=INFO source=amd_linux.go:296 msg="unsupported Radeon iGPU detected skipping" id=0 total="512.0 MiB" time=2025-02-15T16:07:41.366+08:00 level=INFO source=amd_linux.go:402 msg="no compatible amdgpu devices detected" time=2025-02-15T16:07:41.366+08:00 level=INFO source=types.go:130 msg="inference compute" id=GPU-3bb8d0f1-7fbd-75ee-1589-b2d6866f8fae library=cuda variant=v12 compute=6.1 driver=12.7 name="Tesla P40" total="23.9 GiB" available="23.7 GiB" time=2025-02-15T16:07:41.366+08:00 level=INFO source=types.go:130 msg="inference compute" id=GPU-01a87dbe-0079-88b7-2a43-5d879a6ef155 library=cuda variant=v11 compute=5.2 driver=12.7 name="Tesla M40 24GB" total="23.9 GiB" available="23.8 GiB" [GIN] 2025/02/15 - 16:08:33 | 200 | 39.98µs | 127.0.0.1 | HEAD "/" [GIN] 2025/02/15 - 16:08:33 | 200 | 14.85932ms | 127.0.0.1 | POST "/api/show" time=2025-02-15T16:08:34.221+08:00 level=INFO source=server.go:100 msg="system memory" total="93.6 GiB" free="88.2 GiB" free_swap="15.7 GiB" time=2025-02-15T16:08:34.222+08:00 level=INFO source=memory.go:356 msg="offload to cuda" layers.requested=-1 layers.model=81 layers.offload=44 layers.split="" memory.available="[23.7 GiB]" memory.gpu_overhead="0 B" memory.required.full="42.7 GiB" memory.required.partial="23.4 GiB" memory.required.kv="640.0 MiB" memory.required.allocations="[23.4 GiB]" memory.weights.total="38.9 GiB" memory.weights.repeating="38.1 GiB" memory.weights.nonrepeating="822.0 MiB" memory.graph.full="324.0 MiB" memory.graph.partial="1.1 GiB" time=2025-02-15T16:08:34.223+08:00 level=INFO source=server.go:381 msg="starting llama server" cmd="/usr/local/bin/ollama runner --model /media/aaa/data/ollama_models/blobs/sha256-4cd576d9aa16961244012223abf01445567b061f1814b57dfef699e4cf8df339 --ctx-size 2048 --batch-size 512 --n-gpu-layers 44 --threads 8 --parallel 1 --port 45131" time=2025-02-15T16:08:34.223+08:00 level=INFO source=sched.go:449 msg="loaded runners" count=1 time=2025-02-15T16:08:34.223+08:00 level=INFO source=server.go:558 msg="waiting for llama runner to start responding" time=2025-02-15T16:08:34.223+08:00 level=INFO source=server.go:592 msg="waiting for server to become available" status="llm server error" time=2025-02-15T16:08:34.234+08:00 level=INFO source=runner.go:936 msg="starting go runner" time=2025-02-15T16:08:34.234+08:00 level=INFO source=runner.go:937 msg=system info="CPU : LLAMAFILE = 1 | CPU : LLAMAFILE = 1 | cgo(gcc)" threads=8 time=2025-02-15T16:08:34.234+08:00 level=INFO source=runner.go:995 msg="Server listening on 127.0.0.1:45131" 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: Tesla P40, compute capability 6.1, VMM: yes load_backend: loaded CUDA backend from /usr/local/lib/ollama/cuda_v12/libggml-cuda.so load_backend: loaded CPU backend from /usr/local/lib/ollama/libggml-cpu-haswell.so llama_load_model_from_file: using device CUDA0 (Tesla P40) - 24286 MiB free llama_model_loader: loaded meta data with 30 key-value pairs and 724 tensors from /media/aaa/data/ollama_models/blobs/sha256-4cd576d9aa16961244012223abf01445567b061f1814b57dfef699e4cf8df339 (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 = DeepSeek R1 Distill Llama 70B llama_model_loader: - kv 3: general.basename str = DeepSeek-R1-Distill-Llama llama_model_loader: - kv 4: general.size_label str = 70B llama_model_loader: - kv 5: llama.block_count u32 = 80 llama_model_loader: - kv 6: llama.context_length u32 = 131072 llama_model_loader: - kv 7: llama.embedding_length u32 = 8192 llama_model_loader: - kv 8: llama.feed_forward_length u32 = 28672 llama_model_loader: - kv 9: llama.attention.head_count u32 = 64 llama_model_loader: - kv 10: llama.attention.head_count_kv u32 = 8 llama_model_loader: - kv 11: llama.rope.freq_base f32 = 500000.000000 llama_model_loader: - kv 12: llama.attention.layer_norm_rms_epsilon f32 = 0.000010 llama_model_loader: - kv 13: llama.attention.key_length u32 = 128 llama_model_loader: - kv 14: llama.attention.value_length u32 = 128 llama_model_loader: - kv 15: general.file_type u32 = 15 llama_model_loader: - kv 16: llama.vocab_size u32 = 128256 llama_model_loader: - kv 17: llama.rope.dimension_count u32 = 128 llama_model_loader: - kv 18: tokenizer.ggml.model str = gpt2 llama_model_loader: - kv 19: tokenizer.ggml.pre str = llama-bpe llama_model_loader: - kv 20: tokenizer.ggml.tokens arr[str,128256] = ["!", "\"", "#", "$", "%", "&", "'", ... llama_model_loader: - kv 21: tokenizer.ggml.token_type arr[i32,128256] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... llama_model_loader: - kv 22: tokenizer.ggml.merges arr[str,280147] = ["Ġ Ġ", "Ġ ĠĠĠ", "ĠĠ ĠĠ", "... llama_model_loader: - kv 23: tokenizer.ggml.bos_token_id u32 = 128000 llama_model_loader: - kv 24: tokenizer.ggml.eos_token_id u32 = 128001 llama_model_loader: - kv 25: tokenizer.ggml.padding_token_id u32 = 128001 llama_model_loader: - kv 26: tokenizer.ggml.add_bos_token bool = true llama_model_loader: - kv 27: tokenizer.ggml.add_eos_token bool = false llama_model_loader: - kv 28: tokenizer.chat_template str = {% if not add_generation_prompt is de... llama_model_loader: - kv 29: general.quantization_version u32 = 2 llama_model_loader: - type f32: 162 tensors llama_model_loader: - type q4_K: 441 tensors llama_model_loader: - type q5_K: 40 tensors llama_model_loader: - type q6_K: 81 tensors time=2025-02-15T16:08:34.474+08:00 level=INFO source=server.go:592 msg="waiting for server to become available" status="llm server loading model" llm_load_vocab: special_eos_id is not in special_eog_ids - the tokenizer config may be incorrect 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 = 8192 llm_load_print_meta: n_layer = 80 llm_load_print_meta: n_head = 64 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 = 8 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 = 28672 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 = 70B llm_load_print_meta: model ftype = Q4_K - Medium llm_load_print_meta: model params = 70.55 B llm_load_print_meta: model size = 39.59 GiB (4.82 BPW) llm_load_print_meta: general.name = DeepSeek R1 Distill Llama 70B llm_load_print_meta: BOS token = 128000 '<｜begin▁of▁sentence｜>' llm_load_print_meta: EOS token = 128001 '<｜end▁of▁sentence｜>' llm_load_print_meta: EOT token = 128009 '<|eot_id|>' llm_load_print_meta: EOM token = 128008 '<|eom_id|>' llm_load_print_meta: PAD token = 128001 '<｜end▁of▁sentence｜>' llm_load_print_meta: LF token = 128 'Ä' llm_load_print_meta: EOG token = 128001 '<｜end▁of▁sentence｜>' 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 llm_load_tensors: offloading 44 repeating layers to GPU llm_load_tensors: offloaded 44/81 layers to GPU llm_load_tensors: CUDA0 model buffer size = 21536.63 MiB llm_load_tensors: CPU_Mapped model buffer size = 19006.48 MiB llama_new_context_with_model: n_seq_max = 1 llama_new_context_with_model: n_ctx = 2048 llama_new_context_with_model: n_ctx_per_seq = 2048 llama_new_context_with_model: n_batch = 512 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_new_context_with_model: n_ctx_per_seq (2048) < n_ctx_train (131072) -- the full capacity of the model will not be utilized llama_kv_cache_init: kv_size = 2048, offload = 1, type_k = 'f16', type_v = 'f16', n_layer = 80, can_shift = 1 llama_kv_cache_init: CUDA0 KV buffer size = 352.00 MiB llama_kv_cache_init: CPU KV buffer size = 288.00 MiB llama_new_context_with_model: KV self size = 640.00 MiB, K (f16): 320.00 MiB, V (f16): 320.00 MiB llama_new_context_with_model: CPU output buffer size = 0.52 MiB llama_new_context_with_model: CUDA0 compute buffer size = 1088.45 MiB llama_new_context_with_model: CUDA_Host compute buffer size = 20.01 MiB llama_new_context_with_model: graph nodes = 2566 llama_new_context_with_model: graph splits = 401 (with bs=512), 3 (with bs=1) time=2025-02-15T16:08:41.752+08:00 level=INFO source=server.go:597 msg="llama runner started in 7.53 seconds" [GIN] 2025/02/15 - 16:08:41 | 200 | 7.89437029s | 127.0.0.1 | POST "/api/generate"``` ### Relevant log output ```shell ``` ### OS Linux ### GPU Nvidia ### CPU AMD ### Ollama version 0.5.11
GiteaMirror added the bug label 2026-05-04 12:13:36 -05:00
GiteaMirror commented 2026-05-04 12:13:39 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Feb 15, 2025):

The M40 has a compute capacity of 5.2 which is currently not supported in cuda_v12 runner, #8567 may fix that. In the meantime you can try setting OLLAMA_LLM_LIBRARY=cuda_v11 in the server environment to see if that will use both cards.

<!-- gh-comment-id:2660892872 --> @rick-github commented on GitHub (Feb 15, 2025): The M40 has a compute capacity of 5.2 which is currently not supported in cuda_v12 runner, #8567 may fix that. In the meantime you can try setting `OLLAMA_LLM_LIBRARY=cuda_v11` in the server environment to see if that will use both cards.
GiteaMirror commented 2026-05-04 12:13:40 -05:00
Author
Owner
Copy Link

@l00n00l commented on GitHub (Feb 16, 2025):

[Unit]
Description=Ollama Service
After=network-online.target

[Service]
ExecStart=/usr/local/bin/ollama serve
User=ollama
Group=ollama
Restart=always
RestartSec=3
Environment="PATH=/media/aaa/data/softs/miniconda3/bin:/media/aaa/data/softs/miniconda3/condabin:/usr/local/bin:/usr/bin:/bin:/usr/local/games:/usr/games:/sbin:/usr/sbin"
Environment="CUDA_VISIBLE_DEVICES=1,0"
Environment="OLLAMA_SCHED_SPREAD=1"
Environment="OLLAMA_LLM_LIBRARY=cuda_v11"
Environment="OLLAMA_MODELS=/media/aaa/data/ollama_models"
[Install]
WantedBy=default.target

I added OLLAMA_llibrary=cuda_v11 to the environment, but it didn't work.

<!-- gh-comment-id:2661185749 --> @l00n00l commented on GitHub (Feb 16, 2025): ``` [Unit] Description=Ollama Service After=network-online.target [Service] ExecStart=/usr/local/bin/ollama serve User=ollama Group=ollama Restart=always RestartSec=3 Environment="PATH=/media/aaa/data/softs/miniconda3/bin:/media/aaa/data/softs/miniconda3/condabin:/usr/local/bin:/usr/bin:/bin:/usr/local/games:/usr/games:/sbin:/usr/sbin" Environment="CUDA_VISIBLE_DEVICES=1,0" Environment="OLLAMA_SCHED_SPREAD=1" Environment="OLLAMA_LLM_LIBRARY=cuda_v11" Environment="OLLAMA_MODELS=/media/aaa/data/ollama_models" [Install] WantedBy=default.target ``` I added `OLLAMA_llibrary=cuda_v11` to the environment, but it didn't work.
GiteaMirror commented 2026-05-04 12:13:40 -05:00
Author
Owner
Copy Link

@AmberHan commented on GitHub (Jul 14, 2025):

have fix it?

<!-- gh-comment-id:3068645531 --> @AmberHan commented on GitHub (Jul 14, 2025): have fix it?
GiteaMirror commented 2026-05-04 12:13:41 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Jul 14, 2025):

#8567 has been merged so presumably yes, fixed.

<!-- gh-comment-id:3068658734 --> @rick-github commented on GitHub (Jul 14, 2025): #8567 has been merged so presumably yes, fixed.
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#67994
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?