github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-16 05:05:37 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #8962] Ollama in docker container fails to Initiate gpu after some idle time. #5815

New Issue
Closed
opened 2026-04-12 17:09:33 -05:00 by GiteaMirror · 5 comments
GiteaMirror commented 2026-04-12 17:09:33 -05:00
Owner
Copy Link

Originally created by @awptechnologies on GitHub (Feb 9, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/8962

What is the issue?

For some reason my ollama docker container doesn't Initiate gpu after being idle for sometime. It seems i have to restart the docker container everytime i decide to use any of my models.

Relevant log output

There are no logs for errors i will post some if i see them come up.

OS

Linux, Docker

GPU

Nvidia

CPU

Intel

Ollama version

0.5.7

Originally created by @awptechnologies on GitHub (Feb 9, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/8962 ### What is the issue? For some reason my ollama docker container doesn't Initiate gpu after being idle for sometime. It seems i have to restart the docker container everytime i decide to use any of my models. ### Relevant log output ```shell There are no logs for errors i will post some if i see them come up. ``` ### OS Linux, Docker ### GPU Nvidia ### CPU Intel ### Ollama version 0.5.7
GiteaMirror added the bug label 2026-04-12 17:09:33 -05:00
GiteaMirror commented 2026-04-12 17:09:35 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Feb 9, 2025):

https://github.com/ollama/ollama/blob/main/docs/troubleshooting.md#amd-gpu-discovery:~:text=%22exec%2Dopts%22%3A%20%5B%22native.cgroupdriver%3Dcgroupfs%22%5D

<!-- gh-comment-id:2646154489 --> @rick-github commented on GitHub (Feb 9, 2025): https://github.com/ollama/ollama/blob/main/docs/troubleshooting.md#amd-gpu-discovery:~:text=%22exec%2Dopts%22%3A%20%5B%22native.cgroupdriver%3Dcgroupfs%22%5D
GiteaMirror commented 2026-04-12 17:09:35 -05:00
Author
Owner
Copy Link

@awptechnologies commented on GitHub (Feb 11, 2025):

llama_load_model_from_file: using device CUDA0 (NVIDIA GeForce GTX 1070) - 7836 MiB free

llama_model_loader: loaded meta data with 26 key-value pairs and 339 tensors from /root/.ollama/models/blobs/sha256-96c415656d377afbff962f6cdb2394ab092ccbcbaab4b82525bc4ca800fe8a49 (version GGUF V3 (latest))

llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.

llama_model_loader: - kv 0: general.architecture str = qwen2

llama_model_loader: - kv 1: general.type str = model

llama_model_loader: - kv 2: general.name str = DeepSeek R1 Distill Qwen 7B

llama_model_loader: - kv 3: general.basename str = DeepSeek-R1-Distill-Qwen

llama_model_loader: - kv 4: general.size_label str = 7B

llama_model_loader: - kv 5: qwen2.block_count u32 = 28

llama_model_loader: - kv 6: qwen2.context_length u32 = 131072

llama_model_loader: - kv 7: qwen2.embedding_length u32 = 3584

llama_model_loader: - kv 8: qwen2.feed_forward_length u32 = 18944

llama_model_loader: - kv 9: qwen2.attention.head_count u32 = 28

llama_model_loader: - kv 10: qwen2.attention.head_count_kv u32 = 4

llama_model_loader: - kv 11: qwen2.rope.freq_base f32 = 10000.000000

llama_model_loader: - kv 12: qwen2.attention.layer_norm_rms_epsilon f32 = 0.000001

llama_model_loader: - kv 13: general.file_type u32 = 15

llama_model_loader: - kv 14: tokenizer.ggml.model str = gpt2

llama_model_loader: - kv 15: tokenizer.ggml.pre str = qwen2

llama_model_loader: - kv 16: tokenizer.ggml.tokens arr[str,152064] = ["!", """, "#", "$", "%", "&", "'", ...

llama_model_loader: - kv 17: tokenizer.ggml.token_type arr[i32,152064] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...

llama_model_loader: - kv 18: tokenizer.ggml.merges arr[str,151387] = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...

llama_model_loader: - kv 19: tokenizer.ggml.bos_token_id u32 = 151646

llama_model_loader: - kv 20: tokenizer.ggml.eos_token_id u32 = 151643

llama_model_loader: - kv 21: tokenizer.ggml.padding_token_id u32 = 151643

llama_model_loader: - kv 22: tokenizer.ggml.add_bos_token bool = true

llama_model_loader: - kv 23: tokenizer.ggml.add_eos_token bool = false

llama_model_loader: - kv 24: tokenizer.chat_template str = {% if not add_generation_prompt is de...

llama_model_loader: - kv 25: general.quantization_version u32 = 2

llama_model_loader: - type f32: 141 tensors

llama_model_loader: - type q4_K: 169 tensors

llama_model_loader: - type q6_K: 29 tensors

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 = 22

llm_load_vocab: token to piece cache size = 0.9310 MB

llm_load_print_meta: format = GGUF V3 (latest)

llm_load_print_meta: arch = qwen2

llm_load_print_meta: vocab type = BPE

llm_load_print_meta: n_vocab = 152064

llm_load_print_meta: n_merges = 151387

llm_load_print_meta: vocab_only = 0

llm_load_print_meta: n_ctx_train = 131072

llm_load_print_meta: n_embd = 3584

llm_load_print_meta: n_layer = 28

llm_load_print_meta: n_head = 28

llm_load_print_meta: n_head_kv = 4

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 = 7

llm_load_print_meta: n_embd_k_gqa = 512

llm_load_print_meta: n_embd_v_gqa = 512

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 = 18944

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 = 2

llm_load_print_meta: rope scaling = linear

llm_load_print_meta: freq_base_train = 10000.0

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 = 7B

llm_load_print_meta: model ftype = Q4_K - Medium

llm_load_print_meta: model params = 7.62 B

llm_load_print_meta: model size = 4.36 GiB (4.91 BPW)

llm_load_print_meta: general.name = DeepSeek R1 Distill Qwen 7B

llm_load_print_meta: BOS token = 151646 '<｜begin▁of▁sentence｜>'

llm_load_print_meta: EOS token = 151643 '<｜end▁of▁sentence｜>'

llm_load_print_meta: EOT token = 151643 '<｜end▁of▁sentence｜>'

llm_load_print_meta: PAD token = 151643 '<｜end▁of▁sentence｜>'

llm_load_print_meta: LF token = 148848 'ÄĬ'

llm_load_print_meta: FIM PRE token = 151659 '<|fim_prefix|>'

llm_load_print_meta: FIM SUF token = 151661 '<|fim_suffix|>'

llm_load_print_meta: FIM MID token = 151660 '<|fim_middle|>'

llm_load_print_meta: FIM PAD token = 151662 '<|fim_pad|>'

llm_load_print_meta: FIM REP token = 151663 '<|repo_name|>'

llm_load_print_meta: FIM SEP token = 151664 '<|file_sep|>'

llm_load_print_meta: EOG token = 151643 '<｜end▁of▁sentence｜>'

llm_load_print_meta: EOG token = 151662 '<|fim_pad|>'

llm_load_print_meta: EOG token = 151663 '<|repo_name|>'

llm_load_print_meta: EOG token = 151664 '<|file_sep|>'

llm_load_print_meta: max token length = 256

llm_load_tensors: offloading 28 repeating layers to GPU

llm_load_tensors: offloading output layer to GPU

llm_load_tensors: offloaded 29/29 layers to GPU

llm_load_tensors: CPU_Mapped model buffer size = 292.36 MiB

llm_load_tensors: CUDA0 model buffer size = 4168.09 MiB

llama_new_context_with_model: n_seq_max = 4

llama_new_context_with_model: n_ctx = 8192

llama_new_context_with_model: n_ctx_per_seq = 2048

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 = 10000.0

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 = 8192, offload = 1, type_k = 'f16', type_v = 'f16', n_layer = 28, can_shift = 1

llama_kv_cache_init: CUDA0 KV buffer size = 448.00 MiB

llama_new_context_with_model: KV self size = 448.00 MiB, K (f16): 224.00 MiB, V (f16): 224.00 MiB

llama_new_context_with_model: CUDA_Host output buffer size = 2.38 MiB

llama_new_context_with_model: CUDA0 compute buffer size = 492.00 MiB

llama_new_context_with_model: CUDA_Host compute buffer size = 23.01 MiB

llama_new_context_with_model: graph nodes = 986

llama_new_context_with_model: graph splits = 2

time=2025-02-10T11:03:37.609-05:00 level=INFO source=server.go:594 msg="llama runner started in 3.80 seconds"

[GIN] 2025/02/10 - 11:03:39 | 200 | 6.890111833s | 10.0.0.2 | POST "/api/chat"

[GIN] 2025/02/10 - 11:03:50 | 200 | 17.980985445s | 10.0.0.2 | POST "/api/chat"

[GIN] 2025/02/10 - 11:04:00 | 200 | 20.760358812s | 10.0.0.2 | POST "/api/chat"

[GIN] 2025/02/10 - 11:04:16 | 200 | 15.220715947s | 10.0.0.2 | POST "/api/chat"

[GIN] 2025/02/11 - 04:23:54 | 200 | 206.669747ms | 10.0.0.3 | GET "/api/tags"

[GIN] 2025/02/11 - 10:59:55 | 200 | 111.998572ms | 10.0.0.3 | GET "/api/tags"

cuda driver library failed to get device context 800time=2025-02-11T11:04:14.522-05:00 level=WARN source=gpu.go:449 msg="error looking up nvidia GPU memory"

cuda driver library failed to get device context 800time=2025-02-11T11:04:14.925-05:00 level=WARN source=gpu.go:449 msg="error looking up nvidia GPU memory"

cuda driver library failed to get device context 800time=2025-02-11T11:04:15.170-05:00 level=WARN source=gpu.go:449 msg="error looking up nvidia GPU memory"

cuda driver library failed to get device context 800time=2025-02-11T11:04:15.421-05:00 level=WARN source=gpu.go:449 msg="error looking up nvidia GPU memory"

cuda driver library failed to get device context 800time=2025-02-11T11:04:15.668-05:00 level=WARN source=gpu.go:449 msg="error looking up nvidia GPU memory"

cuda driver library failed to get device context 800time=2025-02-11T11:04:15.911-05:00 level=WARN source=gpu.go:449 msg="error looking up nvidia GPU memory"

cuda driver library failed to get device context 800time=2025-02-11T11:04:16.172-05:00 level=WARN source=gpu.go:449 msg="error looking up nvidia GPU memory"

cuda driver library failed to get device context 800time=2025-02-11T11:04:16.418-05:00 level=WARN source=gpu.go:449 msg="error looking up nvidia GPU memory"

cuda driver library failed to get device context 800time=2025-02-11T11:04:16.663-05:00 level=WARN source=gpu.go:449 msg="error looking up nvidia GPU memory"

cuda driver library failed to get device context 800time=2025-02-11T11:04:16.909-05:00 level=WARN source=gpu.go:449 msg="error looking up nvidia GPU memory"

cuda driver library failed to get device context 800time=2025-02-11T11:04:17.161-05:00 level=WARN source=gpu.go:449 msg="error looking up nvidia GPU memory"

cuda driver library failed to get device context 800time=2025-02-11T11:04:17.416-05:00 level=WARN source=gpu.go:449 msg="error looking up nvidia GPU memory"

cuda driver library failed to get device context 800time=2025-02-11T11:04:17.665-05:00 level=WARN source=gpu.go:449 msg="error looking up nvidia GPU memory"

cuda driver library failed to get device context 800time=2025-02-11T11:04:17.917-05:00 level=WARN source=gpu.go:449 msg="error looking up nvidia GPU memory"

cuda driver library failed to get device context 800time=2025-02-11T11:04:18.162-05:00 level=WARN source=gpu.go:449 msg="error looking up nvidia GPU memory"

cuda driver library failed to get device context 800time=2025-02-11T11:04:18.415-05:00 level=WARN source=gpu.go:449 msg="error looking up nvidia GPU memory"

cuda driver library failed to get device context 800time=2025-02-11T11:04:18.664-05:00 level=WARN source=gpu.go:449 msg="error looking up nvidia GPU memory"

cuda driver library failed to get device context 800time=2025-02-11T11:04:18.917-05:00 level=WARN source=gpu.go:449 msg="error looking up nvidia GPU memory"

cuda driver library failed to get device context 800time=2025-02-11T11:04:19.165-05:00 level=WARN source=gpu.go:449 msg="error looking up nvidia GPU memory"

cuda driver library failed to get device context 800time=2025-02-11T11:04:19.415-05:00 level=WARN source=gpu.go:449 msg="error looking up nvidia GPU memory"

time=2025-02-11T11:04:19.523-05:00 level=WARN source=sched.go:646 msg="gpu VRAM usage didn't recover within timeout" seconds=5.160086726 model=/root/.ollama/models/blobs/sha256-96c415656d377afbff962f6cdb2394ab092ccbcbaab4b82525bc4ca800fe8a49

cuda driver library failed to get device context 800time=2025-02-11T11:04:19.667-05:00 level=WARN source=gpu.go:449 msg="error looking up nvidia GPU memory"

time=2025-02-11T11:04:19.774-05:00 level=WARN source=sched.go:646 msg="gpu VRAM usage didn't recover within timeout" seconds=5.411247994 model=/root/.ollama/models/blobs/sha256-96c415656d377afbff962f6cdb2394ab092ccbcbaab4b82525bc4ca800fe8a49

cuda driver library failed to get device context 800time=2025-02-11T11:04:19.920-05:00 level=WARN source=gpu.go:449 msg="error looking up nvidia GPU memory"

time=2025-02-11T11:04:20.023-05:00 level=WARN source=sched.go:646 msg="gpu VRAM usage didn't recover within timeout" seconds=5.660204722 model=/root/.ollama/models/blobs/sha256-96c415656d377afbff962f6cdb2394ab092ccbcbaab4b82525bc4ca800fe8a49

So you can see it found the 1070 to start with then after some time it starts throwing the errors and i have to restart container for model to load into the gpu again.

<!-- gh-comment-id:2651690998 --> @awptechnologies commented on GitHub (Feb 11, 2025): llama_load_model_from_file: using device CUDA0 (NVIDIA GeForce GTX 1070) - 7836 MiB free llama_model_loader: loaded meta data with 26 key-value pairs and 339 tensors from /root/.ollama/models/blobs/sha256-96c415656d377afbff962f6cdb2394ab092ccbcbaab4b82525bc4ca800fe8a49 (version GGUF V3 (latest)) llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output. llama_model_loader: - kv 0: general.architecture str = qwen2 llama_model_loader: - kv 1: general.type str = model llama_model_loader: - kv 2: general.name str = DeepSeek R1 Distill Qwen 7B llama_model_loader: - kv 3: general.basename str = DeepSeek-R1-Distill-Qwen llama_model_loader: - kv 4: general.size_label str = 7B llama_model_loader: - kv 5: qwen2.block_count u32 = 28 llama_model_loader: - kv 6: qwen2.context_length u32 = 131072 llama_model_loader: - kv 7: qwen2.embedding_length u32 = 3584 llama_model_loader: - kv 8: qwen2.feed_forward_length u32 = 18944 llama_model_loader: - kv 9: qwen2.attention.head_count u32 = 28 llama_model_loader: - kv 10: qwen2.attention.head_count_kv u32 = 4 llama_model_loader: - kv 11: qwen2.rope.freq_base f32 = 10000.000000 llama_model_loader: - kv 12: qwen2.attention.layer_norm_rms_epsilon f32 = 0.000001 llama_model_loader: - kv 13: general.file_type u32 = 15 llama_model_loader: - kv 14: tokenizer.ggml.model str = gpt2 llama_model_loader: - kv 15: tokenizer.ggml.pre str = qwen2 llama_model_loader: - kv 16: tokenizer.ggml.tokens arr[str,152064] = ["!", "\"", "#", "$", "%", "&", "'", ... llama_model_loader: - kv 17: tokenizer.ggml.token_type arr[i32,152064] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... llama_model_loader: - kv 18: tokenizer.ggml.merges arr[str,151387] = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",... llama_model_loader: - kv 19: tokenizer.ggml.bos_token_id u32 = 151646 llama_model_loader: - kv 20: tokenizer.ggml.eos_token_id u32 = 151643 llama_model_loader: - kv 21: tokenizer.ggml.padding_token_id u32 = 151643 llama_model_loader: - kv 22: tokenizer.ggml.add_bos_token bool = true llama_model_loader: - kv 23: tokenizer.ggml.add_eos_token bool = false llama_model_loader: - kv 24: tokenizer.chat_template str = {% if not add_generation_prompt is de... llama_model_loader: - kv 25: general.quantization_version u32 = 2 llama_model_loader: - type f32: 141 tensors llama_model_loader: - type q4_K: 169 tensors llama_model_loader: - type q6_K: 29 tensors 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 = 22 llm_load_vocab: token to piece cache size = 0.9310 MB llm_load_print_meta: format = GGUF V3 (latest) llm_load_print_meta: arch = qwen2 llm_load_print_meta: vocab type = BPE llm_load_print_meta: n_vocab = 152064 llm_load_print_meta: n_merges = 151387 llm_load_print_meta: vocab_only = 0 llm_load_print_meta: n_ctx_train = 131072 llm_load_print_meta: n_embd = 3584 llm_load_print_meta: n_layer = 28 llm_load_print_meta: n_head = 28 llm_load_print_meta: n_head_kv = 4 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 = 7 llm_load_print_meta: n_embd_k_gqa = 512 llm_load_print_meta: n_embd_v_gqa = 512 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 = 18944 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 = 2 llm_load_print_meta: rope scaling = linear llm_load_print_meta: freq_base_train = 10000.0 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 = 7B llm_load_print_meta: model ftype = Q4_K - Medium llm_load_print_meta: model params = 7.62 B llm_load_print_meta: model size = 4.36 GiB (4.91 BPW) llm_load_print_meta: general.name = DeepSeek R1 Distill Qwen 7B llm_load_print_meta: BOS token = 151646 '<｜begin▁of▁sentence｜>' llm_load_print_meta: EOS token = 151643 '<｜end▁of▁sentence｜>' llm_load_print_meta: EOT token = 151643 '<｜end▁of▁sentence｜>' llm_load_print_meta: PAD token = 151643 '<｜end▁of▁sentence｜>' llm_load_print_meta: LF token = 148848 'ÄĬ' llm_load_print_meta: FIM PRE token = 151659 '<|fim_prefix|>' llm_load_print_meta: FIM SUF token = 151661 '<|fim_suffix|>' llm_load_print_meta: FIM MID token = 151660 '<|fim_middle|>' llm_load_print_meta: FIM PAD token = 151662 '<|fim_pad|>' llm_load_print_meta: FIM REP token = 151663 '<|repo_name|>' llm_load_print_meta: FIM SEP token = 151664 '<|file_sep|>' llm_load_print_meta: EOG token = 151643 '<｜end▁of▁sentence｜>' llm_load_print_meta: EOG token = 151662 '<|fim_pad|>' llm_load_print_meta: EOG token = 151663 '<|repo_name|>' llm_load_print_meta: EOG token = 151664 '<|file_sep|>' llm_load_print_meta: max token length = 256 llm_load_tensors: offloading 28 repeating layers to GPU llm_load_tensors: offloading output layer to GPU llm_load_tensors: offloaded 29/29 layers to GPU llm_load_tensors: CPU_Mapped model buffer size = 292.36 MiB llm_load_tensors: CUDA0 model buffer size = 4168.09 MiB llama_new_context_with_model: n_seq_max = 4 llama_new_context_with_model: n_ctx = 8192 llama_new_context_with_model: n_ctx_per_seq = 2048 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 = 10000.0 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 = 8192, offload = 1, type_k = 'f16', type_v = 'f16', n_layer = 28, can_shift = 1 llama_kv_cache_init: CUDA0 KV buffer size = 448.00 MiB llama_new_context_with_model: KV self size = 448.00 MiB, K (f16): 224.00 MiB, V (f16): 224.00 MiB llama_new_context_with_model: CUDA_Host output buffer size = 2.38 MiB llama_new_context_with_model: CUDA0 compute buffer size = 492.00 MiB llama_new_context_with_model: CUDA_Host compute buffer size = 23.01 MiB llama_new_context_with_model: graph nodes = 986 llama_new_context_with_model: graph splits = 2 time=2025-02-10T11:03:37.609-05:00 level=INFO source=server.go:594 msg="llama runner started in 3.80 seconds" [GIN] 2025/02/10 - 11:03:39 | 200 | 6.890111833s | 10.0.0.2 | POST "/api/chat" [GIN] 2025/02/10 - 11:03:50 | 200 | 17.980985445s | 10.0.0.2 | POST "/api/chat" [GIN] 2025/02/10 - 11:04:00 | 200 | 20.760358812s | 10.0.0.2 | POST "/api/chat" [GIN] 2025/02/10 - 11:04:16 | 200 | 15.220715947s | 10.0.0.2 | POST "/api/chat" [GIN] 2025/02/11 - 04:23:54 | 200 | 206.669747ms | 10.0.0.3 | GET "/api/tags" [GIN] 2025/02/11 - 10:59:55 | 200 | 111.998572ms | 10.0.0.3 | GET "/api/tags" cuda driver library failed to get device context 800time=2025-02-11T11:04:14.522-05:00 level=WARN source=gpu.go:449 msg="error looking up nvidia GPU memory" cuda driver library failed to get device context 800time=2025-02-11T11:04:14.925-05:00 level=WARN source=gpu.go:449 msg="error looking up nvidia GPU memory" cuda driver library failed to get device context 800time=2025-02-11T11:04:15.170-05:00 level=WARN source=gpu.go:449 msg="error looking up nvidia GPU memory" cuda driver library failed to get device context 800time=2025-02-11T11:04:15.421-05:00 level=WARN source=gpu.go:449 msg="error looking up nvidia GPU memory" cuda driver library failed to get device context 800time=2025-02-11T11:04:15.668-05:00 level=WARN source=gpu.go:449 msg="error looking up nvidia GPU memory" cuda driver library failed to get device context 800time=2025-02-11T11:04:15.911-05:00 level=WARN source=gpu.go:449 msg="error looking up nvidia GPU memory" cuda driver library failed to get device context 800time=2025-02-11T11:04:16.172-05:00 level=WARN source=gpu.go:449 msg="error looking up nvidia GPU memory" cuda driver library failed to get device context 800time=2025-02-11T11:04:16.418-05:00 level=WARN source=gpu.go:449 msg="error looking up nvidia GPU memory" cuda driver library failed to get device context 800time=2025-02-11T11:04:16.663-05:00 level=WARN source=gpu.go:449 msg="error looking up nvidia GPU memory" cuda driver library failed to get device context 800time=2025-02-11T11:04:16.909-05:00 level=WARN source=gpu.go:449 msg="error looking up nvidia GPU memory" cuda driver library failed to get device context 800time=2025-02-11T11:04:17.161-05:00 level=WARN source=gpu.go:449 msg="error looking up nvidia GPU memory" cuda driver library failed to get device context 800time=2025-02-11T11:04:17.416-05:00 level=WARN source=gpu.go:449 msg="error looking up nvidia GPU memory" cuda driver library failed to get device context 800time=2025-02-11T11:04:17.665-05:00 level=WARN source=gpu.go:449 msg="error looking up nvidia GPU memory" cuda driver library failed to get device context 800time=2025-02-11T11:04:17.917-05:00 level=WARN source=gpu.go:449 msg="error looking up nvidia GPU memory" cuda driver library failed to get device context 800time=2025-02-11T11:04:18.162-05:00 level=WARN source=gpu.go:449 msg="error looking up nvidia GPU memory" cuda driver library failed to get device context 800time=2025-02-11T11:04:18.415-05:00 level=WARN source=gpu.go:449 msg="error looking up nvidia GPU memory" cuda driver library failed to get device context 800time=2025-02-11T11:04:18.664-05:00 level=WARN source=gpu.go:449 msg="error looking up nvidia GPU memory" cuda driver library failed to get device context 800time=2025-02-11T11:04:18.917-05:00 level=WARN source=gpu.go:449 msg="error looking up nvidia GPU memory" cuda driver library failed to get device context 800time=2025-02-11T11:04:19.165-05:00 level=WARN source=gpu.go:449 msg="error looking up nvidia GPU memory" cuda driver library failed to get device context 800time=2025-02-11T11:04:19.415-05:00 level=WARN source=gpu.go:449 msg="error looking up nvidia GPU memory" time=2025-02-11T11:04:19.523-05:00 level=WARN source=sched.go:646 msg="gpu VRAM usage didn't recover within timeout" seconds=5.160086726 model=/root/.ollama/models/blobs/sha256-96c415656d377afbff962f6cdb2394ab092ccbcbaab4b82525bc4ca800fe8a49 cuda driver library failed to get device context 800time=2025-02-11T11:04:19.667-05:00 level=WARN source=gpu.go:449 msg="error looking up nvidia GPU memory" time=2025-02-11T11:04:19.774-05:00 level=WARN source=sched.go:646 msg="gpu VRAM usage didn't recover within timeout" seconds=5.411247994 model=/root/.ollama/models/blobs/sha256-96c415656d377afbff962f6cdb2394ab092ccbcbaab4b82525bc4ca800fe8a49 cuda driver library failed to get device context 800time=2025-02-11T11:04:19.920-05:00 level=WARN source=gpu.go:449 msg="error looking up nvidia GPU memory" time=2025-02-11T11:04:20.023-05:00 level=WARN source=sched.go:646 msg="gpu VRAM usage didn't recover within timeout" seconds=5.660204722 model=/root/.ollama/models/blobs/sha256-96c415656d377afbff962f6cdb2394ab092ccbcbaab4b82525bc4ca800fe8a49 So you can see it found the 1070 to start with then after some time it starts throwing the errors and i have to restart container for model to load into the gpu again.
GiteaMirror commented 2026-04-12 17:09:35 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Feb 11, 2025):

Have you tried setting native.cgroupdriver as in the provided link?

<!-- gh-comment-id:2651851354 --> @rick-github commented on GitHub (Feb 11, 2025): Have you tried setting `native.cgroupdriver` as in the provided link?
GiteaMirror commented 2026-04-12 17:09:36 -05:00
Author
Owner
Copy Link

@awptechnologies commented on GitHub (Feb 12, 2025):

i just saw this i will try now. I would just add

"exec-opts": ["native.cgroupdriver=cgroupfs"]

on a new line at bottom of file correct?

<!-- gh-comment-id:2652490672 --> @awptechnologies commented on GitHub (Feb 12, 2025): i just saw this i will try now. I would just add "exec-opts": ["native.cgroupdriver=cgroupfs"] on a new line at bottom of file correct?
GiteaMirror commented 2026-04-12 17:09:36 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Mar 4, 2025):

$ cat /etc/docker/daemon.json 
{
    "runtimes": {
        "nvidia": {
            "args": [],
            "path": "nvidia-container-runtime"
        }
    },
    "exec-opts": ["native.cgroupdriver=cgroupfs"]
}
<!-- gh-comment-id:2698173810 --> @rick-github commented on GitHub (Mar 4, 2025): ```console $ cat /etc/docker/daemon.json { "runtimes": { "nvidia": { "args": [], "path": "nvidia-container-runtime" } }, "exec-opts": ["native.cgroupdriver=cgroupfs"] } ```
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#5815
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?