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 #8699] Set custom timeout with API call. #67694

New Issue
Closed
opened 2026-05-04 11:21:05 -05:00 by GiteaMirror · 17 comments
GiteaMirror commented 2026-05-04 11:21:05 -05:00
Owner
Copy Link

Originally created by @philippstoboy on GitHub (Jan 30, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/8699

What is the issue?

Hello,

I am running ollama inside of a Docker Container on my Unraid Server. The Server has a total of 192GB of normal RAM. Now, I'm trying to run DeepSeekR1 with 4-bit Quantization. According to #8654, I faked my Memory Size to 500GB, because the model won't run if it thinks there aren't at least 446GB(or something similar). Additionally, I enabled mmap in the api-call. Here is my initial command that I used:

curl http://localhost:11434/api/generate -d '{"model":"deepseek-r1:671b","options":{"use_mmap":true}}'

Now, when I run this, for about 4 Minutes it seems like nothing is happening and the logs are filled with a bunch of information about the model, which is being loaded. Then, the process times out.
(time=2025-01-30T16:36:39.209Z level=ERROR source=sched.go:455 msg="error loading llama server" error="timed out waiting for llama runner to start - progress 0.00 - " [GIN] 2025/01/30 - 16:36:39 | 500 | 5m0s | 127.0.0.1 | POST "/api/generate")

As the log says it took 5m until the timeout so my question is how I disable this timeout or maybe increase it by a lot.

I already set Env Vars as of:

  1. OLLAMA_TIMEOUT=120000000
  2. OLLAMA_LOAD_TIMEOUT=120000000

Thanks in advance!

OS

Docker

GPU

No response

CPU

Intel

Ollama version

0.5.7-0-ga420a45-dirty

Originally created by @philippstoboy on GitHub (Jan 30, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/8699 ### What is the issue? Hello, I am running ollama inside of a **Docker Container** on my **Unraid Server**. The Server has a total of 192GB of normal RAM. Now, I'm trying to run **[DeepSeekR1 with 4-bit Quantization](https://ollama.com/library/deepseek-r1:671b)**. According to #8654, I faked my Memory Size to **500GB**, because the model won't run if it thinks there aren't at least **446GB**_(or something similar)_. Additionally, I enabled `mmap` in the api-call. Here is my initial command that I used: `curl http://localhost:11434/api/generate -d '{"model":"deepseek-r1:671b","options":{"use_mmap":true}}'` Now, when I run this, for about **4 Minutes** it seems like nothing is happening and the logs are filled with a bunch of information about the model, which is being loaded. Then, the process times out. `(time=2025-01-30T16:36:39.209Z level=ERROR source=sched.go:455 msg="error loading llama server" error="timed out waiting for llama runner to start - progress 0.00 - " [GIN] 2025/01/30 - 16:36:39 | 500 | 5m0s | 127.0.0.1 | POST "/api/generate")` As the log says it took **5m** until the timeout so my question is how I disable this timeout or maybe increase it by a lot. I already set Env Vars as of: 1. `OLLAMA_TIMEOUT=120000000` 2. `OLLAMA_LOAD_TIMEOUT=120000000` Thanks in advance! ### OS Docker ### GPU _No response_ ### CPU Intel ### Ollama version 0.5.7-0-ga420a45-dirty
GiteaMirror added the bug label 2026-05-04 11:21:05 -05:00
GiteaMirror commented 2026-05-04 11:21:12 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Jan 30, 2025):

OLLAMA_TIMEOUT is not an ollama environment variable.

OLLAMA_LOAD_TIMEOUT=120000000 is 3.8 years so should work. What do the server logs show?

<!-- gh-comment-id:2625062815 --> @rick-github commented on GitHub (Jan 30, 2025): `OLLAMA_TIMEOUT` is not an ollama environment variable. `OLLAMA_LOAD_TIMEOUT=120000000` is 3.8 years so should work. What do the [server logs](https://github.com/ollama/ollama/blob/main/docs/troubleshooting.md#how-to-troubleshoot-issues) show?
GiteaMirror commented 2026-05-04 11:21:15 -05:00
Author
Owner
Copy Link

@philippstoboy commented on GitHub (Jan 30, 2025):

OLLAMA_TIMEOUT is not an ollama environment variable.

OLLAMA_LOAD_TIMEOUT=120000000 is 3.8 years so should work. What do the server logs show?

Should I provide the whole log content after the API-Call?

<!-- gh-comment-id:2625081109 --> @philippstoboy commented on GitHub (Jan 30, 2025): > `OLLAMA_TIMEOUT` is not an ollama environment variable. > > `OLLAMA_LOAD_TIMEOUT=120000000` is 3.8 years so should work. What do the [server logs](https://github.com/ollama/ollama/blob/main/docs/troubleshooting.md#how-to-troubleshoot-issues) show? Should I provide the whole log content after the API-Call?
GiteaMirror commented 2026-05-04 11:21:17 -05:00
Author
Owner
Copy Link

@philippstoboy commented on GitHub (Jan 30, 2025):

Here's what happens after curl command is run:

time=2025-01-30T17:03:33.224Z level=INFO source=server.go:104 msg="system memory" total="188.9 GiB" free="488.3 GiB" free_swap="0 B" time=2025-01-30T17:03:33.227Z level=INFO source=memory.go:356 msg="offload to cpu" layers.requested=-1 layers.model=62 layers.offload=0 layers.split="" memory.available="[488.3 GiB]" memory.gpu_overhead="0 B" memory.required.full="417.4 GiB" memory.required.partial="0 B" memory.required.kv="38.1 GiB" memory.required.allocations="[417.4 GiB]" memory.weights.total="413.6 GiB" memory.weights.repeating="412.9 GiB" memory.weights.nonrepeating="725.0 MiB" memory.graph.full="2.2 GiB" memory.graph.partial="3.0 GiB" time=2025-01-30T17:03:33.228Z level=INFO source=server.go:376 msg="starting llama server" cmd="/usr/lib/ollama/runners/cpu_avx/ollama_llama_server runner --model /root/.ollama/models/blobs/sha256-9801e7fce27dbf3d0bfb468b7b21f1d132131a546dfc43e50518631b8b1800a9 --ctx-size 8192 --batch-size 512 --threads 12 --parallel 4 --port 35387" time=2025-01-30T17:03:33.229Z level=INFO source=sched.go:449 msg="loaded runners" count=1 time=2025-01-30T17:03:33.229Z level=INFO source=server.go:555 msg="waiting for llama runner to start responding" time=2025-01-30T17:03:33.229Z level=INFO source=server.go:589 msg="waiting for server to become available" status="llm server error" time=2025-01-30T17:03:33.294Z level=INFO source=runner.go:936 msg="starting go runner" time=2025-01-30T17:03:33.300Z level=INFO source=runner.go:937 msg=system info="CPU : SSE3 = 1 | SSSE3 = 1 | AVX = 1 | LLAMAFILE = 1 | AARCH64_REPACK = 1 | cgo(gcc)" threads=12 time=2025-01-30T17:03:33.300Z level=INFO source=.:0 msg="Server listening on 127.0.0.1:35387" time=2025-01-30T17:03:33.482Z level=INFO source=server.go:589 msg="waiting for server to become available" status="llm server loading model" llama_model_loader: loaded meta data with 42 key-value pairs and 1025 tensors from /root/.ollama/models/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=2025-01-30T17:08:33.330Z level=ERROR source=sched.go:455 msg="error loading llama server" error="timed out waiting for llama runner to start - progress 0.00 - " [GIN] 2025/01/30 - 17:08:33 | 500 | 5m29s | 127.0.0.1 | POST "/api/generate"

<!-- gh-comment-id:2625090020 --> @philippstoboy commented on GitHub (Jan 30, 2025): Here's what happens after curl command is run: `time=2025-01-30T17:03:33.224Z level=INFO source=server.go:104 msg="system memory" total="188.9 GiB" free="488.3 GiB" free_swap="0 B" time=2025-01-30T17:03:33.227Z level=INFO source=memory.go:356 msg="offload to cpu" layers.requested=-1 layers.model=62 layers.offload=0 layers.split="" memory.available="[488.3 GiB]" memory.gpu_overhead="0 B" memory.required.full="417.4 GiB" memory.required.partial="0 B" memory.required.kv="38.1 GiB" memory.required.allocations="[417.4 GiB]" memory.weights.total="413.6 GiB" memory.weights.repeating="412.9 GiB" memory.weights.nonrepeating="725.0 MiB" memory.graph.full="2.2 GiB" memory.graph.partial="3.0 GiB" time=2025-01-30T17:03:33.228Z level=INFO source=server.go:376 msg="starting llama server" cmd="/usr/lib/ollama/runners/cpu_avx/ollama_llama_server runner --model /root/.ollama/models/blobs/sha256-9801e7fce27dbf3d0bfb468b7b21f1d132131a546dfc43e50518631b8b1800a9 --ctx-size 8192 --batch-size 512 --threads 12 --parallel 4 --port 35387" time=2025-01-30T17:03:33.229Z level=INFO source=sched.go:449 msg="loaded runners" count=1 time=2025-01-30T17:03:33.229Z level=INFO source=server.go:555 msg="waiting for llama runner to start responding" time=2025-01-30T17:03:33.229Z level=INFO source=server.go:589 msg="waiting for server to become available" status="llm server error" time=2025-01-30T17:03:33.294Z level=INFO source=runner.go:936 msg="starting go runner" time=2025-01-30T17:03:33.300Z level=INFO source=runner.go:937 msg=system info="CPU : SSE3 = 1 | SSSE3 = 1 | AVX = 1 | LLAMAFILE = 1 | AARCH64_REPACK = 1 | cgo(gcc)" threads=12 time=2025-01-30T17:03:33.300Z level=INFO source=.:0 msg="Server listening on 127.0.0.1:35387" time=2025-01-30T17:03:33.482Z level=INFO source=server.go:589 msg="waiting for server to become available" status="llm server loading model" llama_model_loader: loaded meta data with 42 key-value pairs and 1025 tensors from /root/.ollama/models/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=2025-01-30T17:08:33.330Z level=ERROR source=sched.go:455 msg="error loading llama server" error="timed out waiting for llama runner to start - progress 0.00 - " [GIN] 2025/01/30 - 17:08:33 | 500 | 5m29s | 127.0.0.1 | POST "/api/generate"`
GiteaMirror commented 2026-05-04 11:21:21 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Jan 30, 2025):

Full log, from the start - that's where it shows the environment variables. And attach as a file, pasting it into the input field makes it unreadable.

<!-- gh-comment-id:2625094633 --> @rick-github commented on GitHub (Jan 30, 2025): Full log, from the start - that's where it shows the environment variables. And attach as a file, pasting it into the input field makes it unreadable.
GiteaMirror commented 2026-05-04 11:21:22 -05:00
Author
Owner
Copy Link

@philippstoboy commented on GitHub (Jan 30, 2025):

This is the whole log file since the start of the container:
output.log

<!-- gh-comment-id:2625135323 --> @philippstoboy commented on GitHub (Jan 30, 2025): This is the whole log file since the start of the container: [output.log](https://github.com/user-attachments/files/18606546/output.log)
GiteaMirror commented 2026-05-04 11:21:23 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Jan 30, 2025):

OLLAMA_LOAD_TIMEOUT:5m0s

However you are setting this, is incorrect. How do you configure the docker container?

<!-- gh-comment-id:2625143700 --> @rick-github commented on GitHub (Jan 30, 2025): ``` OLLAMA_LOAD_TIMEOUT:5m0s ``` However you are setting this, is incorrect. How do you configure the docker container?
GiteaMirror commented 2026-05-04 11:21:24 -05:00
Author
Owner
Copy Link

@philippstoboy commented on GitHub (Jan 30, 2025):

I just did it with export inside of the docker container. As it showed up when using printenv I assumed it set the Variable.

<!-- gh-comment-id:2625160290 --> @philippstoboy commented on GitHub (Jan 30, 2025): I just did it with `export` inside of the docker container. As it showed up when using `printenv` I assumed it set the Variable.
GiteaMirror commented 2026-05-04 11:21:25 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Jan 30, 2025):

So you started the container:

$ docker run --rm -it -d -v ollama-data:/root/.ollama --name ollama ollama/ollama

And then set the variable by running export in the container:

$ docker exec -it ollama bash
# export OLLAMA_LOAD_TIMEOUT=120000000
# printenv | grep OLLAMA_LOAD_TIMEOUT
OLLAMA_LOAD_TIMEOUT=120000000
# exit
$

Is that right?

<!-- gh-comment-id:2625180041 --> @rick-github commented on GitHub (Jan 30, 2025): So you started the container: ```console $ docker run --rm -it -d -v ollama-data:/root/.ollama --name ollama ollama/ollama ``` And then set the variable by running export in the container: ```console $ docker exec -it ollama bash # export OLLAMA_LOAD_TIMEOUT=120000000 # printenv | grep OLLAMA_LOAD_TIMEOUT OLLAMA_LOAD_TIMEOUT=120000000 # exit $ ``` Is that right?
GiteaMirror commented 2026-05-04 11:21:27 -05:00
Author
Owner
Copy Link

@philippstoboy commented on GitHub (Jan 30, 2025):

Yes

<!-- gh-comment-id:2625184167 --> @philippstoboy commented on GitHub (Jan 30, 2025): Yes
GiteaMirror commented 2026-05-04 11:21:27 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Jan 30, 2025):

docker run --rm -it -d -v ollama-data:/root/.ollama --env OLLAMA_LOAD_TIMEOUT=90m --name ollama ollama/ollama
<!-- gh-comment-id:2625188490 --> @rick-github commented on GitHub (Jan 30, 2025): ``` docker run --rm -it -d -v ollama-data:/root/.ollama --env OLLAMA_LOAD_TIMEOUT=90m --name ollama ollama/ollama ```
GiteaMirror commented 2026-05-04 11:21:28 -05:00
Author
Owner
Copy Link

@philippstoboy commented on GitHub (Jan 30, 2025):

And how do I confirm if it worked?

<!-- gh-comment-id:2625195507 --> @philippstoboy commented on GitHub (Jan 30, 2025): And how do I confirm if it worked?
GiteaMirror commented 2026-05-04 11:21:29 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Jan 30, 2025):

Check the server logs.

<!-- gh-comment-id:2625196525 --> @rick-github commented on GitHub (Jan 30, 2025): Check the server logs.
GiteaMirror commented 2026-05-04 11:21:30 -05:00
Author
Owner
Copy Link

@philippstoboy commented on GitHub (Jan 30, 2025):

Okay so I ran the Model Again And it Stopped After 10minuten now. I set variable to 1200000 or something so No idea Why it Ended After 10minutes.

<!-- gh-comment-id:2625266811 --> @philippstoboy commented on GitHub (Jan 30, 2025): Okay so I ran the Model Again And it Stopped After 10minuten now. I set variable to 1200000 or something so No idea Why it Ended After 10minutes.
GiteaMirror commented 2026-05-04 11:21:31 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Jan 30, 2025):

Logs.

<!-- gh-comment-id:2625268905 --> @rick-github commented on GitHub (Jan 30, 2025): Logs.
GiteaMirror commented 2026-05-04 11:21:32 -05:00
Author
Owner
Copy Link

@philippstoboy commented on GitHub (Jan 30, 2025):

output (2).log

<!-- gh-comment-id:2625639754 --> @philippstoboy commented on GitHub (Jan 30, 2025): [output (2).log](https://github.com/user-attachments/files/18608972/output.2.log)
GiteaMirror commented 2026-05-04 11:21:33 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Jan 30, 2025):

OLLAMA_LOAD_TIMEOUT:333h20m0s

Load timeout is now set correctly.

time=2025-01-30T18:11:26.868Z level=INFO source=server.go:594 msg="llama runner started in 954.24 seconds"

Model loaded in 15 minutes and 54 seconds.

[GIN] 2025/01/30 - 18:11:26 | 200 |        16m19s |       127.0.0.1 | POST     "/api/generate"

The generation took an additional 25 seconds.

This all looks fine.

If the client ended after 10 minutes, the client has a ten minute timeout.

<!-- gh-comment-id:2625663132 --> @rick-github commented on GitHub (Jan 30, 2025): ``` OLLAMA_LOAD_TIMEOUT:333h20m0s ``` Load timeout is now set correctly. ``` time=2025-01-30T18:11:26.868Z level=INFO source=server.go:594 msg="llama runner started in 954.24 seconds" ``` Model loaded in 15 minutes and 54 seconds. ``` [GIN] 2025/01/30 - 18:11:26 | 200 | 16m19s | 127.0.0.1 | POST "/api/generate" ``` The generation took an additional 25 seconds. This all looks fine. If the client ended after 10 minutes, the client has a ten minute timeout.
GiteaMirror commented 2026-05-04 11:21:33 -05:00
Author
Owner
Copy Link

@philippstoboy commented on GitHub (Jan 30, 2025):

Oh that's it I just overflew the log and didn't pick it up. Thank you so much for your help @rick-github 👍

<!-- gh-comment-id:2625667250 --> @philippstoboy commented on GitHub (Jan 30, 2025): Oh that's it I just overflew the log and didn't pick it up. Thank you so much for your help @rick-github 👍
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#67694
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?