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 #9248] When running DEEPSEEK with Ollama, model crashes occur #52538

New Issue
Closed
opened 2026-04-28 23:37:39 -05:00 by GiteaMirror · 9 comments
GiteaMirror commented 2026-04-28 23:37:39 -05:00
Owner
Copy Link

Originally created by @mjdp168 on GitHub (Feb 20, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/9248

What is the issue?

During the execution of DEEPSEEK, the following error occurred:
Error: An error was encountered while running the model: read tcp 127.0.0.1:55564->127.0.0.1:54784: wsarecv: An existing connection was forcibly closed by the remote host.
Observing that memory usage dropped to 0, which indicates a model crash. Could you suggest possible solutions?
Thank.

Relevant log output

time=2025-02-20T19:36:37.412+08:00 level=INFO source=logging.go:50 msg="ollama app started"
time=2025-02-20T19:36:37.424+08:00 level=INFO source=lifecycle.go:19 msg="app config" env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://0.0.0.0:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:2562047h47m16.854775807s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:C:\\Users\\mj\\.ollama\\models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:0 OLLAMA_ORIGINS:[* http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://*] OLLAMA_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES:]"
time=2025-02-20T19:36:37.455+08:00 level=INFO source=server.go:182 msg="unable to connect to server"
time=2025-02-20T19:36:37.455+08:00 level=INFO source=server.go:141 msg="starting server..."
time=2025-02-20T19:36:37.461+08:00 level=INFO source=server.go:127 msg="started ollama server with pid 16424"
time=2025-02-20T19:36:37.461+08:00 level=INFO source=server.go:129 msg="ollama server logs C:\\Users\\mj\\AppData\\Local\\Ollama\\server.log"

OS

Windows

GPU

AMD

CPU

AMD

Ollama version

0.511

Originally created by @mjdp168 on GitHub (Feb 20, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/9248 ### What is the issue? During the execution of DEEPSEEK, the following error occurred: Error: An error was encountered while running the model: read tcp 127.0.0.1:55564->127.0.0.1:54784: wsarecv: An existing connection was forcibly closed by the remote host. Observing that memory usage dropped to 0, which indicates a model crash. Could you suggest possible solutions? Thank. ### Relevant log output ```shell time=2025-02-20T19:36:37.412+08:00 level=INFO source=logging.go:50 msg="ollama app started" time=2025-02-20T19:36:37.424+08:00 level=INFO source=lifecycle.go:19 msg="app config" env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://0.0.0.0:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:2562047h47m16.854775807s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:C:\\Users\\mj\\.ollama\\models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:0 OLLAMA_ORIGINS:[* http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://*] OLLAMA_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES:]" time=2025-02-20T19:36:37.455+08:00 level=INFO source=server.go:182 msg="unable to connect to server" time=2025-02-20T19:36:37.455+08:00 level=INFO source=server.go:141 msg="starting server..." time=2025-02-20T19:36:37.461+08:00 level=INFO source=server.go:127 msg="started ollama server with pid 16424" time=2025-02-20T19:36:37.461+08:00 level=INFO source=server.go:129 msg="ollama server logs C:\\Users\\mj\\AppData\\Local\\Ollama\\server.log" ``` ### OS Windows ### GPU AMD ### CPU AMD ### Ollama version 0.511
GiteaMirror added the bug label 2026-04-28 23:37:39 -05:00
GiteaMirror commented 2026-04-28 23:37:44 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Feb 20, 2025):

More log will show the problem, but if it's not a distilled deepseek, it's probably https://github.com/ollama/ollama/issues/5975

<!-- gh-comment-id:2671385146 --> @rick-github commented on GitHub (Feb 20, 2025): More log will show the problem, but if it's not a distilled deepseek, it's probably https://github.com/ollama/ollama/issues/5975
GiteaMirror commented 2026-04-28 23:37:44 -05:00
Author
Owner
Copy Link

@mjdp168 commented on GitHub (Feb 20, 2025):

2025/02/20 19:36:37 routes.go:1186: INFO server config env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://0.0.0.0:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:2562047h47m16.854775807s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:C:\Users\mj\.ollama\models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:0 OLLAMA_ORIGINS:[* http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://*] OLLAMA_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES:]"
time=2025-02-20T19:36:37.533+08:00 level=INFO source=images.go:432 msg="total blobs: 7"
time=2025-02-20T19:36:37.534+08:00 level=INFO source=images.go:439 msg="total unused blobs removed: 0"
time=2025-02-20T19:36:37.534+08:00 level=INFO source=routes.go:1237 msg="Listening on [::]:11434 (version 0.5.11)"
time=2025-02-20T19:36:37.534+08:00 level=INFO source=gpu.go:217 msg="looking for compatible GPUs"
time=2025-02-20T19:36:37.535+08:00 level=INFO source=gpu_windows.go:167 msg=packages count=1
time=2025-02-20T19:36:37.535+08:00 level=INFO source=gpu_windows.go:214 msg="" package=0 cores=64 efficiency=0 threads=64
time=2025-02-20T19:36:37.547+08:00 level=INFO source=gpu.go:377 msg="no compatible GPUs were discovered"
time=2025-02-20T19:36:37.547+08:00 level=INFO source=types.go:130 msg="inference compute" id=0 library=cpu variant="" compute="" driver=0.0 name="" total="511.9 GiB" available="496.6 GiB"
[GIN] 2025/02/20 - 19:36:37 | 200 | 724.5µs | 127.0.0.1 | HEAD "/"
[GIN] 2025/02/20 - 19:36:37 | 200 | 19.1974ms | 127.0.0.1 | POST "/api/show"
time=2025-02-20T19:36:37.957+08:00 level=INFO source=server.go:100 msg="system memory" total="511.9 GiB" free="496.6 GiB" free_swap="528.0 GiB"
time=2025-02-20T19:36:37.959+08:00 level=INFO source=memory.go:356 msg="offload to cpu" layers.requested=-1 layers.model=62 layers.offload=0 layers.split="" memory.available="[496.6 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=2025-02-20T19:36:37.967+08:00 level=INFO source=server.go:380 msg="starting llama server" cmd="C:\Users\mj\AppData\Local\Programs\Ollama\ollama.exe runner --model C:\Users\mj\.ollama\models\blobs\sha256-9801e7fce27dbf3d0bfb468b7b21f1d132131a546dfc43e50518631b8b1800a9 --ctx-size 8192 --batch-size 512 --threads 64 --no-mmap --parallel 4 --port 50738"
time=2025-02-20T19:36:37.972+08:00 level=INFO source=sched.go:449 msg="loaded runners" count=1
time=2025-02-20T19:36:37.972+08:00 level=INFO source=server.go:557 msg="waiting for llama runner to start responding"
time=2025-02-20T19:36:37.973+08:00 level=INFO source=server.go:591 msg="waiting for server to become available" status="llm server error"
time=2025-02-20T19:36:38.004+08:00 level=INFO source=runner.go:936 msg="starting go runner"
time=2025-02-20T19:36:38.012+08:00 level=INFO source=runner.go:937 msg=system info="CPU : LLAMAFILE = 1 | CPU : LLAMAFILE = 1 | cgo(clang)" threads=64
time=2025-02-20T19:36:38.013+08:00 level=INFO source=runner.go:995 msg="Server listening on 127.0.0.1:50738"
load_backend: loaded CPU backend from C:\Users\mj\AppData\Local\Programs\Ollama\lib\ollama\ggml-cpu-haswell.dll
llama_model_loader: loaded meta data with 42 key-value pairs and 1025 tensors from C:\Users\mj.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
time=2025-02-20T19:36:38.224+08:00 level=INFO source=server.go:591 msg="waiting for server to become available" status="llm server loading model"
llm_load_vocab: special_eos_id is not in special_eog_ids - the tokenizer config may be incorrect
llm_load_vocab: special tokens cache size = 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
llm_load_tensors: CPU model buffer size = 385689.62 MiB
[GIN] 2025/02/20 - 19:37:21 | 200 | 9.9941ms | 192.168.192.82 | GET "/api/tags"
[GIN] 2025/02/20 - 19:37:23 | 200 | 2.0603ms | 192.168.192.82 | GET "/api/tags"
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 = 0.025
llama_new_context_with_model: n_ctx_per_seq (2048) < n_ctx_train (163840) -- 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 = 61, can_shift = 0
llama_kv_cache_init: CPU KV buffer size = 39040.00 MiB
llama_new_context_with_model: KV self size = 39040.00 MiB, K (f16): 23424.00 MiB, V (f16): 15616.00 MiB
llama_new_context_with_model: CPU output buffer size = 2.08 MiB
llama_new_context_with_model: CPU compute buffer size = 2218.01 MiB
llama_new_context_with_model: graph nodes = 5025
llama_new_context_with_model: graph splits = 1
time=2025-02-20T19:42:05.348+08:00 level=INFO source=server.go:596 msg="llama runner started in 327.38 seconds"
[GIN] 2025/02/20 - 19:42:05 | 200 | 5m27s | 127.0.0.1 | POST "/api/generate"
llama.cpp:11942: The current context does not support K-shift
[GIN] 2025/02/20 - 20:03:44 | 200 | 20m58s | 127.0.0.1 | POST "/api/chat"
[GIN] 2025/02/20 - 20:12:27 | 200 | 536.8µs | 127.0.0.1 | HEAD "/"
[GIN] 2025/02/20 - 20:12:27 | 200 | 19.9133ms | 127.0.0.1 | POST "/api/show"
time=2025-02-20T20:12:27.344+08:00 level=INFO source=server.go:100 msg="system memory" total="511.9 GiB" free="496.6 GiB" free_swap="527.6 GiB"
time=2025-02-20T20:12:27.346+08:00 level=INFO source=memory.go:356 msg="offload to cpu" layers.requested=-1 layers.model=62 layers.offload=0 layers.split="" memory.available="[496.6 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=2025-02-20T20:12:27.351+08:00 level=INFO source=server.go:380 msg="starting llama server" cmd="C:\Users\mj\AppData\Local\Programs\Ollama\ollama.exe runner --model C:\Users\mj\.ollama\models\blobs\sha256-9801e7fce27dbf3d0bfb468b7b21f1d132131a546dfc43e50518631b8b1800a9 --ctx-size 8192 --batch-size 512 --threads 64 --no-mmap --parallel 4 --port 52444"
time=2025-02-20T20:12:27.355+08:00 level=INFO source=sched.go:449 msg="loaded runners" count=1
time=2025-02-20T20:12:27.355+08:00 level=INFO source=server.go:557 msg="waiting for llama runner to start responding"
time=2025-02-20T20:12:27.356+08:00 level=INFO source=server.go:591 msg="waiting for server to become available" status="llm server error"
time=2025-02-20T20:12:27.385+08:00 level=INFO source=runner.go:936 msg="starting go runner"
time=2025-02-20T20:12:27.395+08:00 level=INFO source=runner.go:937 msg=system info="CPU : LLAMAFILE = 1 | CPU : LLAMAFILE = 1 | cgo(clang)" threads=64
time=2025-02-20T20:12:27.396+08:00 level=INFO source=runner.go:995 msg="Server listening on 127.0.0.1:52444"
load_backend: loaded CPU backend from C:\Users\mj\AppData\Local\Programs\Ollama\lib\ollama\ggml-cpu-haswell.dll
llama_model_loader: loaded meta data with 42 key-value pairs and 1025 tensors from C:\Users\mj.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
time=2025-02-20T20:12:27.607+08:00 level=INFO source=server.go:591 msg="waiting for server to become available" status="llm server loading model"
llm_load_vocab: special_eos_id is not in special_eog_ids - the tokenizer config may be incorrect
llm_load_vocab: special tokens cache size = 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
llm_load_tensors: CPU model buffer size = 385689.62 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 = 0.025
llama_new_context_with_model: n_ctx_per_seq (2048) < n_ctx_train (163840) -- 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 = 61, can_shift = 0
llama_kv_cache_init: CPU KV buffer size = 39040.00 MiB
llama_new_context_with_model: KV self size = 39040.00 MiB, K (f16): 23424.00 MiB, V (f16): 15616.00 MiB
llama_new_context_with_model: CPU output buffer size = 2.08 MiB
llama_new_context_with_model: CPU compute buffer size = 2218.01 MiB
llama_new_context_with_model: graph nodes = 5025
llama_new_context_with_model: graph splits = 1
time=2025-02-20T20:17:59.268+08:00 level=INFO source=server.go:596 msg="llama runner started in 331.91 seconds"
[GIN] 2025/02/20 - 20:17:59 | 200 | 5m31s | 127.0.0.1 | POST "/api/generate"
[GIN] 2025/02/20 - 20:19:03 | 200 | 4.2787302s | 127.0.0.1 | POST "/api/chat"
[GIN] 2025/02/20 - 20:28:19 | 200 | 0s | 127.0.0.1 | GET "/api/version"

<!-- gh-comment-id:2671388528 --> @mjdp168 commented on GitHub (Feb 20, 2025): 2025/02/20 19:36:37 routes.go:1186: INFO server config env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://0.0.0.0:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:2562047h47m16.854775807s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:C:\\Users\\mj\\.ollama\\models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:0 OLLAMA_ORIGINS:[* http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://*] OLLAMA_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES:]" time=2025-02-20T19:36:37.533+08:00 level=INFO source=images.go:432 msg="total blobs: 7" time=2025-02-20T19:36:37.534+08:00 level=INFO source=images.go:439 msg="total unused blobs removed: 0" time=2025-02-20T19:36:37.534+08:00 level=INFO source=routes.go:1237 msg="Listening on [::]:11434 (version 0.5.11)" time=2025-02-20T19:36:37.534+08:00 level=INFO source=gpu.go:217 msg="looking for compatible GPUs" time=2025-02-20T19:36:37.535+08:00 level=INFO source=gpu_windows.go:167 msg=packages count=1 time=2025-02-20T19:36:37.535+08:00 level=INFO source=gpu_windows.go:214 msg="" package=0 cores=64 efficiency=0 threads=64 time=2025-02-20T19:36:37.547+08:00 level=INFO source=gpu.go:377 msg="no compatible GPUs were discovered" time=2025-02-20T19:36:37.547+08:00 level=INFO source=types.go:130 msg="inference compute" id=0 library=cpu variant="" compute="" driver=0.0 name="" total="511.9 GiB" available="496.6 GiB" [GIN] 2025/02/20 - 19:36:37 | 200 | 724.5µs | 127.0.0.1 | HEAD "/" [GIN] 2025/02/20 - 19:36:37 | 200 | 19.1974ms | 127.0.0.1 | POST "/api/show" time=2025-02-20T19:36:37.957+08:00 level=INFO source=server.go:100 msg="system memory" total="511.9 GiB" free="496.6 GiB" free_swap="528.0 GiB" time=2025-02-20T19:36:37.959+08:00 level=INFO source=memory.go:356 msg="offload to cpu" layers.requested=-1 layers.model=62 layers.offload=0 layers.split="" memory.available="[496.6 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=2025-02-20T19:36:37.967+08:00 level=INFO source=server.go:380 msg="starting llama server" cmd="C:\\Users\\mj\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --model C:\\Users\\mj\\.ollama\\models\\blobs\\sha256-9801e7fce27dbf3d0bfb468b7b21f1d132131a546dfc43e50518631b8b1800a9 --ctx-size 8192 --batch-size 512 --threads 64 --no-mmap --parallel 4 --port 50738" time=2025-02-20T19:36:37.972+08:00 level=INFO source=sched.go:449 msg="loaded runners" count=1 time=2025-02-20T19:36:37.972+08:00 level=INFO source=server.go:557 msg="waiting for llama runner to start responding" time=2025-02-20T19:36:37.973+08:00 level=INFO source=server.go:591 msg="waiting for server to become available" status="llm server error" time=2025-02-20T19:36:38.004+08:00 level=INFO source=runner.go:936 msg="starting go runner" time=2025-02-20T19:36:38.012+08:00 level=INFO source=runner.go:937 msg=system info="CPU : LLAMAFILE = 1 | CPU : LLAMAFILE = 1 | cgo(clang)" threads=64 time=2025-02-20T19:36:38.013+08:00 level=INFO source=runner.go:995 msg="Server listening on 127.0.0.1:50738" load_backend: loaded CPU backend from C:\Users\mj\AppData\Local\Programs\Ollama\lib\ollama\ggml-cpu-haswell.dll llama_model_loader: loaded meta data with 42 key-value pairs and 1025 tensors from C:\Users\mj\.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 time=2025-02-20T19:36:38.224+08:00 level=INFO source=server.go:591 msg="waiting for server to become available" status="llm server loading model" llm_load_vocab: special_eos_id is not in special_eog_ids - the tokenizer config may be incorrect llm_load_vocab: special tokens cache size = 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 llm_load_tensors: CPU model buffer size = 385689.62 MiB [GIN] 2025/02/20 - 19:37:21 | 200 | 9.9941ms | 192.168.192.82 | GET "/api/tags" [GIN] 2025/02/20 - 19:37:23 | 200 | 2.0603ms | 192.168.192.82 | GET "/api/tags" 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 = 0.025 llama_new_context_with_model: n_ctx_per_seq (2048) < n_ctx_train (163840) -- 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 = 61, can_shift = 0 llama_kv_cache_init: CPU KV buffer size = 39040.00 MiB llama_new_context_with_model: KV self size = 39040.00 MiB, K (f16): 23424.00 MiB, V (f16): 15616.00 MiB llama_new_context_with_model: CPU output buffer size = 2.08 MiB llama_new_context_with_model: CPU compute buffer size = 2218.01 MiB llama_new_context_with_model: graph nodes = 5025 llama_new_context_with_model: graph splits = 1 time=2025-02-20T19:42:05.348+08:00 level=INFO source=server.go:596 msg="llama runner started in 327.38 seconds" [GIN] 2025/02/20 - 19:42:05 | 200 | 5m27s | 127.0.0.1 | POST "/api/generate" llama.cpp:11942: The current context does not support K-shift [GIN] 2025/02/20 - 20:03:44 | 200 | 20m58s | 127.0.0.1 | POST "/api/chat" [GIN] 2025/02/20 - 20:12:27 | 200 | 536.8µs | 127.0.0.1 | HEAD "/" [GIN] 2025/02/20 - 20:12:27 | 200 | 19.9133ms | 127.0.0.1 | POST "/api/show" time=2025-02-20T20:12:27.344+08:00 level=INFO source=server.go:100 msg="system memory" total="511.9 GiB" free="496.6 GiB" free_swap="527.6 GiB" time=2025-02-20T20:12:27.346+08:00 level=INFO source=memory.go:356 msg="offload to cpu" layers.requested=-1 layers.model=62 layers.offload=0 layers.split="" memory.available="[496.6 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=2025-02-20T20:12:27.351+08:00 level=INFO source=server.go:380 msg="starting llama server" cmd="C:\\Users\\mj\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --model C:\\Users\\mj\\.ollama\\models\\blobs\\sha256-9801e7fce27dbf3d0bfb468b7b21f1d132131a546dfc43e50518631b8b1800a9 --ctx-size 8192 --batch-size 512 --threads 64 --no-mmap --parallel 4 --port 52444" time=2025-02-20T20:12:27.355+08:00 level=INFO source=sched.go:449 msg="loaded runners" count=1 time=2025-02-20T20:12:27.355+08:00 level=INFO source=server.go:557 msg="waiting for llama runner to start responding" time=2025-02-20T20:12:27.356+08:00 level=INFO source=server.go:591 msg="waiting for server to become available" status="llm server error" time=2025-02-20T20:12:27.385+08:00 level=INFO source=runner.go:936 msg="starting go runner" time=2025-02-20T20:12:27.395+08:00 level=INFO source=runner.go:937 msg=system info="CPU : LLAMAFILE = 1 | CPU : LLAMAFILE = 1 | cgo(clang)" threads=64 time=2025-02-20T20:12:27.396+08:00 level=INFO source=runner.go:995 msg="Server listening on 127.0.0.1:52444" load_backend: loaded CPU backend from C:\Users\mj\AppData\Local\Programs\Ollama\lib\ollama\ggml-cpu-haswell.dll llama_model_loader: loaded meta data with 42 key-value pairs and 1025 tensors from C:\Users\mj\.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 time=2025-02-20T20:12:27.607+08:00 level=INFO source=server.go:591 msg="waiting for server to become available" status="llm server loading model" llm_load_vocab: special_eos_id is not in special_eog_ids - the tokenizer config may be incorrect llm_load_vocab: special tokens cache size = 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 llm_load_tensors: CPU model buffer size = 385689.62 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 = 0.025 llama_new_context_with_model: n_ctx_per_seq (2048) < n_ctx_train (163840) -- 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 = 61, can_shift = 0 llama_kv_cache_init: CPU KV buffer size = 39040.00 MiB llama_new_context_with_model: KV self size = 39040.00 MiB, K (f16): 23424.00 MiB, V (f16): 15616.00 MiB llama_new_context_with_model: CPU output buffer size = 2.08 MiB llama_new_context_with_model: CPU compute buffer size = 2218.01 MiB llama_new_context_with_model: graph nodes = 5025 llama_new_context_with_model: graph splits = 1 time=2025-02-20T20:17:59.268+08:00 level=INFO source=server.go:596 msg="llama runner started in 331.91 seconds" [GIN] 2025/02/20 - 20:17:59 | 200 | 5m31s | 127.0.0.1 | POST "/api/generate" [GIN] 2025/02/20 - 20:19:03 | 200 | 4.2787302s | 127.0.0.1 | POST "/api/chat" [GIN] 2025/02/20 - 20:28:19 | 200 | 0s | 127.0.0.1 | GET "/api/version"
GiteaMirror commented 2026-04-28 23:37:44 -05:00
Author
Owner
Copy Link

@mjdp168 commented on GitHub (Feb 20, 2025):

更多日志将显示问题，但如果它不是经过提炼的深度搜索，则可能是#5975

Logs have been attached. Could you kindly assist with this issue?
Thank

<!-- gh-comment-id:2671416606 --> @mjdp168 commented on GitHub (Feb 20, 2025): > 更多日志将显示问题，但如果它不是经过提炼的深度搜索，则可能是[#5975](https://github.com/ollama/ollama/issues/5975) Logs have been attached. Could you kindly assist with this issue? Thank
GiteaMirror commented 2026-04-28 23:37:45 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Feb 20, 2025):

The logs don't show a failure, but the model is not a distilled deepseek, so it's probably https://github.com/ollama/ollama/issues/5975

<!-- gh-comment-id:2671424515 --> @rick-github commented on GitHub (Feb 20, 2025): The logs don't show a failure, but the model is not a distilled deepseek, so it's probably https://github.com/ollama/ollama/issues/5975
GiteaMirror commented 2026-04-28 23:37:46 -05:00
Author
Owner
Copy Link

@mjdp168 commented on GitHub (Feb 20, 2025):

thank ，I cry.

<!-- gh-comment-id:2671571495 --> @mjdp168 commented on GitHub (Feb 20, 2025): thank ，I cry.
GiteaMirror commented 2026-04-28 23:37:46 -05:00
Author
Owner
Copy Link

@XIONGPEILIN commented on GitHub (Feb 20, 2025):

Is there any other solution that does not modify the model?

<!-- gh-comment-id:2671580046 --> @XIONGPEILIN commented on GitHub (Feb 20, 2025): Is there any other solution that does not modify the model?
GiteaMirror commented 2026-04-28 23:37:47 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Feb 20, 2025):

Keep (length of input tokens) + (length of output tokens) < (size of context).

<!-- gh-comment-id:2671592265 --> @rick-github commented on GitHub (Feb 20, 2025): Keep (length of input tokens) + (length of output tokens) < (size of context).
GiteaMirror commented 2026-04-28 23:37:47 -05:00
Author
Owner
Copy Link

@XIONGPEILIN commented on GitHub (Feb 21, 2025):

Cry, I want to use deepseek to process documents

<!-- gh-comment-id:2674239919 --> @XIONGPEILIN commented on GitHub (Feb 21, 2025): Cry, I want to use deepseek to process documents
GiteaMirror commented 2026-04-28 23:37:48 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Feb 21, 2025):

I want to use deepseek to process documents

You can, just keep (length of input tokens) + (length of output tokens) < (size of context).

<!-- gh-comment-id:2674246896 --> @rick-github commented on GitHub (Feb 21, 2025): > I want to use deepseek to process documents You can, just keep (length of input tokens) + (length of output tokens) < (size of context).
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#52538
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?