github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 16:11:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #9296] GPU VRAM Usage Timeout and Model Loading Failure in Offline Environment #52574

New Issue
Closed
opened 2026-04-28 23:45:18 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-28 23:45:18 -05:00
Owner
Copy Link

Originally created by @DKmiyan on GitHub (Feb 23, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/9296

What is the issue?

Description: I am encountering an issue when running the ollama model (deepseek-r1:671b) in an offline environment. Despite having sufficient GPU resources (NVIDIA A100 80GB GPUs), I am experiencing errors related to GPU VRAM usage and timeouts during model loading.

Steps to Reproduce:

Download the deepseek model weights (~400GB) in an online environment using ollama run deepseek.
Package the environment into a Docker container and transfer it to an offline server.
Start the ollama service on the offline server using the command:

ollama start
Run the model with:
ollama run deepseek-r1:671b

Observe the following error messages:
timed out waiting for llama runner to start
gpu VRAM usage didn't recover within timeout

Expected Behavior: The model should load successfully without encountering VRAM recovery issues or timeouts.

Relevant log output

ollama run deepseek-r1:671b
[GIN] 2025/02/23 - 02:38:24 | 200 |      25.785µs |       127.0.0.1 | HEAD     "/"
[GIN] 2025/02/23 - 02:38:24 | 200 |    21.07066ms |       127.0.0.1 | POST     "/api/show"
⠙ time=2025-02-23T02:38:29.654Z level=INFO source=sched.go:730 msg="new model will fit in available VRAM, loading" model=/slurm-files/LM/ollama/blobs/sha256-9801e7fce27dbf3d0bfb468b7b21f1d132131a546dfc43e50518631b8b1800a9 library=cuda parallel=4 required="445.0 GiB"
⠸ time=2025-02-23T02:38:32.932Z level=INFO source=server.go:100 msg="system memory" total="503.2 GiB" free="452.9 GiB" free_swap="64.0 GiB"
time=2025-02-23T02:38:32.933Z level=INFO source=memory.go:356 msg="offload to cuda" layers.requested=-1 layers.model=62 layers.offload=62 layers.split=9,9,9,9,9,9,8 memory.available="[78.7 GiB 78.7 GiB 78.7 GiB 78.7 GiB 78.7 GiB 78.7 GiB 78.7 GiB]" memory.gpu_overhead="0 B" memory.required.full="445.0 GiB" memory.required.partial="445.0 GiB" memory.required.kv="38.1 GiB" memory.required.allocations="[61.3 GiB 61.3 GiB 62.2 GiB 67.9 GiB 68.9 GiB 62.0 GiB 61.3 GiB]" memory.weights.total="413.6 GiB" memory.weights.repeating="412.9 GiB" memory.weights.nonrepeating="725.0 MiB" memory.graph.full="3.0 GiB" memory.graph.partial="3.0 GiB"
time=2025-02-23T02:38:32.933Z level=INFO source=server.go:380 msg="starting llama server" cmd="/usr/local/bin/ollama runner --model /slurm-files/LM/ollama/blobs/sha256-9801e7fce27dbf3d0bfb468b7b21f1d132131a546dfc43e50518631b8b1800a9 --ctx-size 8192 --batch-size 512 --n-gpu-layers 62 --threads 64 --parallel 4 --tensor-split 9,9,9,9,9,9,8 --port 44005"
time=2025-02-23T02:38:32.934Z level=INFO source=sched.go:449 msg="loaded runners" count=1
time=2025-02-23T02:38:32.934Z level=INFO source=server.go:557 msg="waiting for llama runner to start responding"
time=2025-02-23T02:38:32.934Z level=INFO source=server.go:591 msg="waiting for server to become available" status="llm server error"
time=2025-02-23T02:38:32.948Z level=INFO source=runner.go:936 msg="starting go runner"
time=2025-02-23T02:38:32.948Z level=INFO source=runner.go:937 msg=system info="CPU : LLAMAFILE = 1 | CPU : LLAMAFILE = 1 | cgo(gcc)" threads=64
time=2025-02-23T02:38:32.948Z level=INFO source=runner.go:995 msg="Server listening on 127.0.0.1:44005"
⠴ ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 7 CUDA devices:
  Device 0: NVIDIA A100 80GB PCIe, compute capability 8.0, VMM: yes
  Device 1: NVIDIA A100 80GB PCIe, compute capability 8.0, VMM: yes
  Device 2: NVIDIA A100 80GB PCIe, compute capability 8.0, VMM: yes
  Device 3: NVIDIA A100 80GB PCIe, compute capability 8.0, VMM: yes
  Device 4: NVIDIA A100 80GB PCIe, compute capability 8.0, VMM: yes
  Device 5: NVIDIA A100 80GB PCIe, compute capability 8.0, VMM: yes
  Device 6: NVIDIA A100 80GB PCIe, compute capability 8.0, VMM: yes
⠦ time=2025-02-23T02:38:33.185Z level=INFO source=server.go:591 msg="waiting for server to become available" status="llm server loading model"
⠼ 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-icelake.so
⠼ llama_load_model_from_file: using device CUDA0 (NVIDIA A100 80GB PCIe) - 80623 MiB free
llama_load_model_from_file: using device CUDA1 (NVIDIA A100 80GB PCIe) - 80623 MiB free
llama_load_model_from_file: using device CUDA2 (NVIDIA A100 80GB PCIe) - 80623 MiB free
llama_load_model_from_file: using device CUDA3 (NVIDIA A100 80GB PCIe) - 80623 MiB free
llama_load_model_from_file: using device CUDA4 (NVIDIA A100 80GB PCIe) - 80623 MiB free
llama_load_model_from_file: using device CUDA5 (NVIDIA A100 80GB PCIe) - 80623 MiB free
llama_load_model_from_file: using device CUDA6 (NVIDIA A100 80GB PCIe) - 80623 MiB free
llama_model_loader: loaded meta data with 42 key-value pairs and 1025 tensors from /slurm-files/LM/ollama/blobs/sha256-9801e7fce27dbf3d0bfb468b7b21f1d132131a546dfc43e50518631b8b1800a9 (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              = deepseek2
llama_model_loader: - kv   1:                               general.type str              = model
llama_model_loader: - kv   2:                         general.size_label str              = 256x20B
llama_model_loader: - kv   3:                      deepseek2.block_count u32              = 61
llama_model_loader: - kv   4:                   deepseek2.context_length u32              = 163840
llama_model_loader: - kv   5:                 deepseek2.embedding_length u32              = 7168
llama_model_loader: - kv   6:              deepseek2.feed_forward_length u32              = 18432
llama_model_loader: - kv   7:             deepseek2.attention.head_count u32              = 128
llama_model_loader: - kv   8:          deepseek2.attention.head_count_kv u32              = 128
llama_model_loader: - kv   9:                   deepseek2.rope.freq_base f32              = 10000.000000
llama_model_loader: - kv  10: deepseek2.attention.layer_norm_rms_epsilon f32              = 0.000001
llama_model_loader: - kv  11:                deepseek2.expert_used_count u32              = 8
llama_model_loader: - kv  12:        deepseek2.leading_dense_block_count u32              = 3
llama_model_loader: - kv  13:                       deepseek2.vocab_size u32              = 129280
llama_model_loader: - kv  14:            deepseek2.attention.q_lora_rank u32              = 1536
llama_model_loader: - kv  15:           deepseek2.attention.kv_lora_rank u32              = 512
llama_model_loader: - kv  16:             deepseek2.attention.key_length u32              = 192
llama_model_loader: - kv  17:           deepseek2.attention.value_length u32              = 128
llama_model_loader: - kv  18:       deepseek2.expert_feed_forward_length u32              = 2048
llama_model_loader: - kv  19:                     deepseek2.expert_count u32              = 256
llama_model_loader: - kv  20:              deepseek2.expert_shared_count u32              = 1
llama_model_loader: - kv  21:             deepseek2.expert_weights_scale f32              = 2.500000
llama_model_loader: - kv  22:              deepseek2.expert_weights_norm bool             = true
llama_model_loader: - kv  23:               deepseek2.expert_gating_func u32              = 2
llama_model_loader: - kv  24:             deepseek2.rope.dimension_count u32              = 64
llama_model_loader: - kv  25:                deepseek2.rope.scaling.type str              = yarn
llama_model_loader: - kv  26:              deepseek2.rope.scaling.factor f32              = 40.000000
llama_model_loader: - kv  27: deepseek2.rope.scaling.original_context_length u32              = 4096
llama_model_loader: - kv  28: deepseek2.rope.scaling.yarn_log_multiplier f32              = 0.100000
llama_model_loader: - kv  29:                       tokenizer.ggml.model str              = gpt2
llama_model_loader: - kv  30:                         tokenizer.ggml.pre str              = deepseek-v3
⠴ llama_model_loader: - kv  31:                      tokenizer.ggml.tokens arr[str,129280]  = ["<｜begin▁of▁sentence｜>", "<�...
llama_model_loader: - kv  32:                  tokenizer.ggml.token_type arr[i32,129280]  = [3, 3, 3, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv  33:                      tokenizer.ggml.merges arr[str,127741]  = ["Ġ t", "Ġ a", "i n", "Ġ Ġ", "h e...
llama_model_loader: - kv  34:                tokenizer.ggml.bos_token_id u32              = 0
llama_model_loader: - kv  35:                tokenizer.ggml.eos_token_id u32              = 1
llama_model_loader: - kv  36:            tokenizer.ggml.padding_token_id u32              = 1
llama_model_loader: - kv  37:               tokenizer.ggml.add_bos_token bool             = true
llama_model_loader: - kv  38:               tokenizer.ggml.add_eos_token bool             = false
llama_model_loader: - kv  39:                    tokenizer.chat_template str              = {% if not add_generation_prompt is de...
llama_model_loader: - kv  40:               general.quantization_version u32              = 2
llama_model_loader: - kv  41:                          general.file_type u32              = 15
llama_model_loader: - type  f32:  361 tensors
llama_model_loader: - type q4_K:  606 tensors
llama_model_loader: - type q6_K:   58 tensors
⠧ 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 = 818
⠏ llm_load_vocab: token to piece cache size = 0.8223 MB
llm_load_print_meta: format           = GGUF V3 (latest)
llm_load_print_meta: arch             = deepseek2
llm_load_print_meta: vocab type       = BPE
llm_load_print_meta: n_vocab          = 129280
llm_load_print_meta: n_merges         = 127741
llm_load_print_meta: vocab_only       = 0
llm_load_print_meta: n_ctx_train      = 163840
llm_load_print_meta: n_embd           = 7168
llm_load_print_meta: n_layer          = 61
llm_load_print_meta: n_head           = 128
llm_load_print_meta: n_head_kv        = 128
llm_load_print_meta: n_rot            = 64
llm_load_print_meta: n_swa            = 0
llm_load_print_meta: n_embd_head_k    = 192
llm_load_print_meta: n_embd_head_v    = 128
llm_load_print_meta: n_gqa            = 1
llm_load_print_meta: n_embd_k_gqa     = 24576
llm_load_print_meta: n_embd_v_gqa     = 16384
llm_load_print_meta: f_norm_eps       = 0.0e+00
llm_load_print_meta: f_norm_rms_eps   = 1.0e-06
llm_load_print_meta: f_clamp_kqv      = 0.0e+00
llm_load_print_meta: f_max_alibi_bias = 0.0e+00
llm_load_print_meta: f_logit_scale    = 0.0e+00
llm_load_print_meta: n_ff             = 18432
llm_load_print_meta: n_expert         = 256
llm_load_print_meta: n_expert_used    = 8
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     = yarn
llm_load_print_meta: freq_base_train  = 10000.0
llm_load_print_meta: freq_scale_train = 0.025
llm_load_print_meta: n_ctx_orig_yarn  = 4096
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       = 671B
llm_load_print_meta: model ftype      = Q4_K - Medium
llm_load_print_meta: model params     = 671.03 B
llm_load_print_meta: model size       = 376.65 GiB (4.82 BPW) 
llm_load_print_meta: general.name     = n/a
llm_load_print_meta: BOS token        = 0 '<｜begin▁of▁sentence｜>'
llm_load_print_meta: EOS token        = 1 '<｜end▁of▁sentence｜>'
llm_load_print_meta: EOT token        = 1 '<｜end▁of▁sentence｜>'
llm_load_print_meta: PAD token        = 1 '<｜end▁of▁sentence｜>'
llm_load_print_meta: LF token         = 131 'Ä'
llm_load_print_meta: FIM PRE token    = 128801 '<｜fim▁begin｜>'
llm_load_print_meta: FIM SUF token    = 128800 '<｜fim▁hole｜>'
llm_load_print_meta: FIM MID token    = 128802 '<｜fim▁end｜>'
llm_load_print_meta: EOG token        = 1 '<｜end▁of▁sentence｜>'
llm_load_print_meta: max token length = 256
llm_load_print_meta: n_layer_dense_lead   = 3
llm_load_print_meta: n_lora_q             = 1536
llm_load_print_meta: n_lora_kv            = 512
llm_load_print_meta: n_ff_exp             = 2048
llm_load_print_meta: n_expert_shared      = 1
llm_load_print_meta: expert_weights_scale = 2.5
llm_load_print_meta: expert_weights_norm  = 1
llm_load_print_meta: expert_gating_func   = sigmoid
llm_load_print_meta: rope_yarn_log_mul    = 0.1000
⠹ time=2025-02-23T02:34:26.175Z level=ERROR source=sched.go:455 msg="error loading llama server" error="timed out waiting for llama runner to start - progress 0.00 - "
[GIN] 2025/02/23 - 02:34:26 | 500 |          5m7s |       127.0.0.1 | POST     "/api/generate"
Error: timed out waiting for llama runner to start - progress 0.00 - 
time=2025-02-23T02:34:31.519Z level=WARN source=sched.go:646 msg="gpu VRAM usage didn't recover within timeout" seconds=5.343563291 model=/slurm-files/LM/ollama/blobs/sha256-9801e7fce27dbf3d0bfb468b7b21f1d132131a546dfc43e50518631b8b1800a9
time=2025-02-23T02:34:34.752Z level=WARN source=sched.go:646 msg="gpu VRAM usage didn't recover within timeout" seconds=8.577038533 model=/slurm-files/LM/ollama/blobs/sha256-9801e7fce27dbf3d0bfb468b7b21f1d132131a546dfc43e50518631b8b1800a9
time=2025-02-23T02:34:38.779Z level=WARN source=sched.go:646 msg="gpu VRAM usage didn't recover within timeout" seconds=12.603867038 model=/slurm-files/LM/ollama/blobs/sha256-9801e7fce27dbf3d0bfb468b7b21f1d132131a546dfc43e50518631b8b1800a9
ls

OS

Linux(docker is ubuntu22)

GPU

Nvidia-A100 (80GB) *8

CPU

Intel

Ollama version

0.5.11

Originally created by @DKmiyan on GitHub (Feb 23, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/9296 ### What is the issue? **Description:** I am encountering an issue when running the ollama model (deepseek-r1:671b) in an offline environment. Despite having sufficient GPU resources (NVIDIA A100 80GB GPUs), I am experiencing errors related to GPU VRAM usage and timeouts during model loading. **Steps to Reproduce:** Download the deepseek model weights (~400GB) in an online environment using ollama run deepseek. Package the environment into a Docker container and transfer it to an offline server. Start the ollama service on the offline server using the command: `ollama start` Run the model with: `ollama run deepseek-r1:671b` **Observe the following error messages:** timed out waiting for llama runner to start gpu VRAM usage didn't recover within timeout **Expected Behavior:** The model should load successfully without encountering VRAM recovery issues or timeouts. ### Relevant log output ```shell ollama run deepseek-r1:671b [GIN] 2025/02/23 - 02:38:24 | 200 | 25.785µs | 127.0.0.1 | HEAD "/" [GIN] 2025/02/23 - 02:38:24 | 200 | 21.07066ms | 127.0.0.1 | POST "/api/show" ⠙ time=2025-02-23T02:38:29.654Z level=INFO source=sched.go:730 msg="new model will fit in available VRAM, loading" model=/slurm-files/LM/ollama/blobs/sha256-9801e7fce27dbf3d0bfb468b7b21f1d132131a546dfc43e50518631b8b1800a9 library=cuda parallel=4 required="445.0 GiB" ⠸ time=2025-02-23T02:38:32.932Z level=INFO source=server.go:100 msg="system memory" total="503.2 GiB" free="452.9 GiB" free_swap="64.0 GiB" time=2025-02-23T02:38:32.933Z level=INFO source=memory.go:356 msg="offload to cuda" layers.requested=-1 layers.model=62 layers.offload=62 layers.split=9,9,9,9,9,9,8 memory.available="[78.7 GiB 78.7 GiB 78.7 GiB 78.7 GiB 78.7 GiB 78.7 GiB 78.7 GiB]" memory.gpu_overhead="0 B" memory.required.full="445.0 GiB" memory.required.partial="445.0 GiB" memory.required.kv="38.1 GiB" memory.required.allocations="[61.3 GiB 61.3 GiB 62.2 GiB 67.9 GiB 68.9 GiB 62.0 GiB 61.3 GiB]" memory.weights.total="413.6 GiB" memory.weights.repeating="412.9 GiB" memory.weights.nonrepeating="725.0 MiB" memory.graph.full="3.0 GiB" memory.graph.partial="3.0 GiB" time=2025-02-23T02:38:32.933Z level=INFO source=server.go:380 msg="starting llama server" cmd="/usr/local/bin/ollama runner --model /slurm-files/LM/ollama/blobs/sha256-9801e7fce27dbf3d0bfb468b7b21f1d132131a546dfc43e50518631b8b1800a9 --ctx-size 8192 --batch-size 512 --n-gpu-layers 62 --threads 64 --parallel 4 --tensor-split 9,9,9,9,9,9,8 --port 44005" time=2025-02-23T02:38:32.934Z level=INFO source=sched.go:449 msg="loaded runners" count=1 time=2025-02-23T02:38:32.934Z level=INFO source=server.go:557 msg="waiting for llama runner to start responding" time=2025-02-23T02:38:32.934Z level=INFO source=server.go:591 msg="waiting for server to become available" status="llm server error" time=2025-02-23T02:38:32.948Z level=INFO source=runner.go:936 msg="starting go runner" time=2025-02-23T02:38:32.948Z level=INFO source=runner.go:937 msg=system info="CPU : LLAMAFILE = 1 | CPU : LLAMAFILE = 1 | cgo(gcc)" threads=64 time=2025-02-23T02:38:32.948Z level=INFO source=runner.go:995 msg="Server listening on 127.0.0.1:44005" ⠴ ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no ggml_cuda_init: found 7 CUDA devices: Device 0: NVIDIA A100 80GB PCIe, compute capability 8.0, VMM: yes Device 1: NVIDIA A100 80GB PCIe, compute capability 8.0, VMM: yes Device 2: NVIDIA A100 80GB PCIe, compute capability 8.0, VMM: yes Device 3: NVIDIA A100 80GB PCIe, compute capability 8.0, VMM: yes Device 4: NVIDIA A100 80GB PCIe, compute capability 8.0, VMM: yes Device 5: NVIDIA A100 80GB PCIe, compute capability 8.0, VMM: yes Device 6: NVIDIA A100 80GB PCIe, compute capability 8.0, VMM: yes ⠦ time=2025-02-23T02:38:33.185Z level=INFO source=server.go:591 msg="waiting for server to become available" status="llm server loading model" ⠼ 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-icelake.so ⠼ llama_load_model_from_file: using device CUDA0 (NVIDIA A100 80GB PCIe) - 80623 MiB free llama_load_model_from_file: using device CUDA1 (NVIDIA A100 80GB PCIe) - 80623 MiB free llama_load_model_from_file: using device CUDA2 (NVIDIA A100 80GB PCIe) - 80623 MiB free llama_load_model_from_file: using device CUDA3 (NVIDIA A100 80GB PCIe) - 80623 MiB free llama_load_model_from_file: using device CUDA4 (NVIDIA A100 80GB PCIe) - 80623 MiB free llama_load_model_from_file: using device CUDA5 (NVIDIA A100 80GB PCIe) - 80623 MiB free llama_load_model_from_file: using device CUDA6 (NVIDIA A100 80GB PCIe) - 80623 MiB free llama_model_loader: loaded meta data with 42 key-value pairs and 1025 tensors from /slurm-files/LM/ollama/blobs/sha256-9801e7fce27dbf3d0bfb468b7b21f1d132131a546dfc43e50518631b8b1800a9 (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 = deepseek2 llama_model_loader: - kv 1: general.type str = model llama_model_loader: - kv 2: general.size_label str = 256x20B llama_model_loader: - kv 3: deepseek2.block_count u32 = 61 llama_model_loader: - kv 4: deepseek2.context_length u32 = 163840 llama_model_loader: - kv 5: deepseek2.embedding_length u32 = 7168 llama_model_loader: - kv 6: deepseek2.feed_forward_length u32 = 18432 llama_model_loader: - kv 7: deepseek2.attention.head_count u32 = 128 llama_model_loader: - kv 8: deepseek2.attention.head_count_kv u32 = 128 llama_model_loader: - kv 9: deepseek2.rope.freq_base f32 = 10000.000000 llama_model_loader: - kv 10: deepseek2.attention.layer_norm_rms_epsilon f32 = 0.000001 llama_model_loader: - kv 11: deepseek2.expert_used_count u32 = 8 llama_model_loader: - kv 12: deepseek2.leading_dense_block_count u32 = 3 llama_model_loader: - kv 13: deepseek2.vocab_size u32 = 129280 llama_model_loader: - kv 14: deepseek2.attention.q_lora_rank u32 = 1536 llama_model_loader: - kv 15: deepseek2.attention.kv_lora_rank u32 = 512 llama_model_loader: - kv 16: deepseek2.attention.key_length u32 = 192 llama_model_loader: - kv 17: deepseek2.attention.value_length u32 = 128 llama_model_loader: - kv 18: deepseek2.expert_feed_forward_length u32 = 2048 llama_model_loader: - kv 19: deepseek2.expert_count u32 = 256 llama_model_loader: - kv 20: deepseek2.expert_shared_count u32 = 1 llama_model_loader: - kv 21: deepseek2.expert_weights_scale f32 = 2.500000 llama_model_loader: - kv 22: deepseek2.expert_weights_norm bool = true llama_model_loader: - kv 23: deepseek2.expert_gating_func u32 = 2 llama_model_loader: - kv 24: deepseek2.rope.dimension_count u32 = 64 llama_model_loader: - kv 25: deepseek2.rope.scaling.type str = yarn llama_model_loader: - kv 26: deepseek2.rope.scaling.factor f32 = 40.000000 llama_model_loader: - kv 27: deepseek2.rope.scaling.original_context_length u32 = 4096 llama_model_loader: - kv 28: deepseek2.rope.scaling.yarn_log_multiplier f32 = 0.100000 llama_model_loader: - kv 29: tokenizer.ggml.model str = gpt2 llama_model_loader: - kv 30: tokenizer.ggml.pre str = deepseek-v3 ⠴ llama_model_loader: - kv 31: tokenizer.ggml.tokens arr[str,129280] = ["<｜begin▁of▁sentence｜>", "<�... llama_model_loader: - kv 32: tokenizer.ggml.token_type arr[i32,129280] = [3, 3, 3, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... llama_model_loader: - kv 33: tokenizer.ggml.merges arr[str,127741] = ["Ġ t", "Ġ a", "i n", "Ġ Ġ", "h e... llama_model_loader: - kv 34: tokenizer.ggml.bos_token_id u32 = 0 llama_model_loader: - kv 35: tokenizer.ggml.eos_token_id u32 = 1 llama_model_loader: - kv 36: tokenizer.ggml.padding_token_id u32 = 1 llama_model_loader: - kv 37: tokenizer.ggml.add_bos_token bool = true llama_model_loader: - kv 38: tokenizer.ggml.add_eos_token bool = false llama_model_loader: - kv 39: tokenizer.chat_template str = {% if not add_generation_prompt is de... llama_model_loader: - kv 40: general.quantization_version u32 = 2 llama_model_loader: - kv 41: general.file_type u32 = 15 llama_model_loader: - type f32: 361 tensors llama_model_loader: - type q4_K: 606 tensors llama_model_loader: - type q6_K: 58 tensors ⠧ 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 = 818 ⠏ llm_load_vocab: token to piece cache size = 0.8223 MB llm_load_print_meta: format = GGUF V3 (latest) llm_load_print_meta: arch = deepseek2 llm_load_print_meta: vocab type = BPE llm_load_print_meta: n_vocab = 129280 llm_load_print_meta: n_merges = 127741 llm_load_print_meta: vocab_only = 0 llm_load_print_meta: n_ctx_train = 163840 llm_load_print_meta: n_embd = 7168 llm_load_print_meta: n_layer = 61 llm_load_print_meta: n_head = 128 llm_load_print_meta: n_head_kv = 128 llm_load_print_meta: n_rot = 64 llm_load_print_meta: n_swa = 0 llm_load_print_meta: n_embd_head_k = 192 llm_load_print_meta: n_embd_head_v = 128 llm_load_print_meta: n_gqa = 1 llm_load_print_meta: n_embd_k_gqa = 24576 llm_load_print_meta: n_embd_v_gqa = 16384 llm_load_print_meta: f_norm_eps = 0.0e+00 llm_load_print_meta: f_norm_rms_eps = 1.0e-06 llm_load_print_meta: f_clamp_kqv = 0.0e+00 llm_load_print_meta: f_max_alibi_bias = 0.0e+00 llm_load_print_meta: f_logit_scale = 0.0e+00 llm_load_print_meta: n_ff = 18432 llm_load_print_meta: n_expert = 256 llm_load_print_meta: n_expert_used = 8 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 = yarn llm_load_print_meta: freq_base_train = 10000.0 llm_load_print_meta: freq_scale_train = 0.025 llm_load_print_meta: n_ctx_orig_yarn = 4096 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 = 671B llm_load_print_meta: model ftype = Q4_K - Medium llm_load_print_meta: model params = 671.03 B llm_load_print_meta: model size = 376.65 GiB (4.82 BPW) llm_load_print_meta: general.name = n/a llm_load_print_meta: BOS token = 0 '<｜begin▁of▁sentence｜>' llm_load_print_meta: EOS token = 1 '<｜end▁of▁sentence｜>' llm_load_print_meta: EOT token = 1 '<｜end▁of▁sentence｜>' llm_load_print_meta: PAD token = 1 '<｜end▁of▁sentence｜>' llm_load_print_meta: LF token = 131 'Ä' llm_load_print_meta: FIM PRE token = 128801 '<｜fim▁begin｜>' llm_load_print_meta: FIM SUF token = 128800 '<｜fim▁hole｜>' llm_load_print_meta: FIM MID token = 128802 '<｜fim▁end｜>' llm_load_print_meta: EOG token = 1 '<｜end▁of▁sentence｜>' llm_load_print_meta: max token length = 256 llm_load_print_meta: n_layer_dense_lead = 3 llm_load_print_meta: n_lora_q = 1536 llm_load_print_meta: n_lora_kv = 512 llm_load_print_meta: n_ff_exp = 2048 llm_load_print_meta: n_expert_shared = 1 llm_load_print_meta: expert_weights_scale = 2.5 llm_load_print_meta: expert_weights_norm = 1 llm_load_print_meta: expert_gating_func = sigmoid llm_load_print_meta: rope_yarn_log_mul = 0.1000 ⠹ time=2025-02-23T02:34:26.175Z level=ERROR source=sched.go:455 msg="error loading llama server" error="timed out waiting for llama runner to start - progress 0.00 - " [GIN] 2025/02/23 - 02:34:26 | 500 | 5m7s | 127.0.0.1 | POST "/api/generate" Error: timed out waiting for llama runner to start - progress 0.00 - time=2025-02-23T02:34:31.519Z level=WARN source=sched.go:646 msg="gpu VRAM usage didn't recover within timeout" seconds=5.343563291 model=/slurm-files/LM/ollama/blobs/sha256-9801e7fce27dbf3d0bfb468b7b21f1d132131a546dfc43e50518631b8b1800a9 time=2025-02-23T02:34:34.752Z level=WARN source=sched.go:646 msg="gpu VRAM usage didn't recover within timeout" seconds=8.577038533 model=/slurm-files/LM/ollama/blobs/sha256-9801e7fce27dbf3d0bfb468b7b21f1d132131a546dfc43e50518631b8b1800a9 time=2025-02-23T02:34:38.779Z level=WARN source=sched.go:646 msg="gpu VRAM usage didn't recover within timeout" seconds=12.603867038 model=/slurm-files/LM/ollama/blobs/sha256-9801e7fce27dbf3d0bfb468b7b21f1d132131a546dfc43e50518631b8b1800a9 ls ``` ### OS Linux(docker is ubuntu22) ### GPU Nvidia-A100 (80GB) *8 ### CPU Intel ### Ollama version 0.5.11
GiteaMirror added the bug label 2026-04-28 23:45:18 -05:00
GiteaMirror commented 2026-04-28 23:45:20 -05:00
Author
Owner
Copy Link

@DKmiyan commented on GitHub (Feb 23, 2025):

# nvidia-smi
Sun Feb 23 02:45:29 2025       
+---------------------------------------------------------------------------------------+
| NVIDIA-SMI 535.104.05             Driver Version: 535.104.05   CUDA Version: 12.4     |
|-----------------------------------------+----------------------+----------------------+
| 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  NVIDIA A100 80GB PCIe          On  | 00000000:34:00.0 Off |                    0 |
| N/A   40C    P0              46W / 300W |      7MiB / 81920MiB |      0%      Default |
|                                         |                      |             Disabled |
+-----------------------------------------+----------------------+----------------------+
|   1  NVIDIA A100 80GB PCIe          On  | 00000000:35:00.0 Off |                    0 |
| N/A   38C    P0              65W / 300W |      7MiB / 81920MiB |      0%      Default |
|                                         |                      |             Disabled |
+-----------------------------------------+----------------------+----------------------+
|   2  NVIDIA A100 80GB PCIe          On  | 00000000:36:00.0 Off |                    0 |
| N/A   40C    P0              57W / 300W |      7MiB / 81920MiB |      0%      Default |
|                                         |                      |             Disabled |
+-----------------------------------------+----------------------+----------------------+
|   3  NVIDIA A100 80GB PCIe          On  | 00000000:37:00.0 Off |                    0 |
| N/A   39C    P0              65W / 300W |      7MiB / 81920MiB |      0%      Default |
|                                         |                      |             Disabled |
+-----------------------------------------+----------------------+----------------------+
|   4  NVIDIA A100 80GB PCIe          On  | 00000000:9A:00.0 Off |                    0 |
| N/A   41C    P0              68W / 300W |      7MiB / 81920MiB |      0%      Default |
|                                         |                      |             Disabled |
+-----------------------------------------+----------------------+----------------------+
|   5  NVIDIA A100 80GB PCIe          On  | 00000000:9B:00.0 Off |                    0 |
| N/A   39C    P0              59W / 300W |      7MiB / 81920MiB |      0%      Default |
|                                         |                      |             Disabled |
+-----------------------------------------+----------------------+----------------------+
|   6  NVIDIA A100 80GB PCIe          On  | 00000000:9C:00.0 Off |                    0 |
| N/A   41C    P0              54W / 300W |      7MiB / 81920MiB |      0%      Default |
|                                         |                      |             Disabled |
+-----------------------------------------+----------------------+----------------------+
|   7  NVIDIA A100 80GB PCIe          On  | 00000000:9E:00.0 Off |                    0 |
| N/A   39C    P0              66W / 300W |      7MiB / 81920MiB |      0%      Default |
|                                         |                      |             Disabled |
+-----------------------------------------+----------------------+----------------------+
                                                                                         
+---------------------------------------------------------------------------------------+
| Processes:                                                                            |
|  GPU   GI   CI        PID   Type   Process name                            GPU Memory |
|        ID   ID                                                             Usage      |
|=======================================================================================|
|  No running processes found                                                           |
+---------------------------------------------------------------------------------------+
# ollama --version
[GIN] 2025/02/23 - 02:45:43 | 200 |     528.142µs |       127.0.0.1 | GET      "/api/version"
ollama version is 0.5.11
<!-- gh-comment-id:2676523113 --> @DKmiyan commented on GitHub (Feb 23, 2025): ``` # nvidia-smi Sun Feb 23 02:45:29 2025 +---------------------------------------------------------------------------------------+ | NVIDIA-SMI 535.104.05 Driver Version: 535.104.05 CUDA Version: 12.4 | |-----------------------------------------+----------------------+----------------------+ | 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 NVIDIA A100 80GB PCIe On | 00000000:34:00.0 Off | 0 | | N/A 40C P0 46W / 300W | 7MiB / 81920MiB | 0% Default | | | | Disabled | +-----------------------------------------+----------------------+----------------------+ | 1 NVIDIA A100 80GB PCIe On | 00000000:35:00.0 Off | 0 | | N/A 38C P0 65W / 300W | 7MiB / 81920MiB | 0% Default | | | | Disabled | +-----------------------------------------+----------------------+----------------------+ | 2 NVIDIA A100 80GB PCIe On | 00000000:36:00.0 Off | 0 | | N/A 40C P0 57W / 300W | 7MiB / 81920MiB | 0% Default | | | | Disabled | +-----------------------------------------+----------------------+----------------------+ | 3 NVIDIA A100 80GB PCIe On | 00000000:37:00.0 Off | 0 | | N/A 39C P0 65W / 300W | 7MiB / 81920MiB | 0% Default | | | | Disabled | +-----------------------------------------+----------------------+----------------------+ | 4 NVIDIA A100 80GB PCIe On | 00000000:9A:00.0 Off | 0 | | N/A 41C P0 68W / 300W | 7MiB / 81920MiB | 0% Default | | | | Disabled | +-----------------------------------------+----------------------+----------------------+ | 5 NVIDIA A100 80GB PCIe On | 00000000:9B:00.0 Off | 0 | | N/A 39C P0 59W / 300W | 7MiB / 81920MiB | 0% Default | | | | Disabled | +-----------------------------------------+----------------------+----------------------+ | 6 NVIDIA A100 80GB PCIe On | 00000000:9C:00.0 Off | 0 | | N/A 41C P0 54W / 300W | 7MiB / 81920MiB | 0% Default | | | | Disabled | +-----------------------------------------+----------------------+----------------------+ | 7 NVIDIA A100 80GB PCIe On | 00000000:9E:00.0 Off | 0 | | N/A 39C P0 66W / 300W | 7MiB / 81920MiB | 0% Default | | | | Disabled | +-----------------------------------------+----------------------+----------------------+ +---------------------------------------------------------------------------------------+ | Processes: | | GPU GI CI PID Type Process name GPU Memory | | ID ID Usage | |=======================================================================================| | No running processes found | +---------------------------------------------------------------------------------------+ # ollama --version [GIN] 2025/02/23 - 02:45:43 | 200 | 528.142µs | 127.0.0.1 | GET "/api/version" ollama version is 0.5.11 ```
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#52574
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?