github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-24 14:43:39 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #10265] When running the model, this issue arises “CUDA error: an illegal memory access was encountered” #6739

New Issue
Open
opened 2026-04-12 18:29:52 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-12 18:29:52 -05:00
Owner
Copy Link

Originally created by @Garmin969 on GitHub (Apr 14, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/10265

What is the issue?

Hey everyone, I just got a new computer with a 2080ti 22g GPU. I wanted to run the QWQ-32B big model using Ollama, but halfway through running the model, it starts showing random text and black screens with an error: 'An error occurred while running the model: CuDA error'. I wonder if you guys know what might be causing this? (With specific error logs as described)

2025/04/14 20:20:27 routes.go:1231: 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_CONTEXT_LENGTH:2048 OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:C:\Users\Administrator\.ollama\models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE: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://* vscode-file://*] OLLAMA_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES:]"
time=2025-04-14T20:20:27.396+08:00 level=INFO source=images.go:458 msg="total blobs: 14"
time=2025-04-14T20:20:27.397+08:00 level=INFO source=images.go:465 msg="total unused blobs removed: 0"
time=2025-04-14T20:20:27.397+08:00 level=INFO source=routes.go:1298 msg="Listening on 127.0.0.1:11434 (version 0.6.5)"
time=2025-04-14T20:20:27.397+08:00 level=INFO source=gpu.go:217 msg="looking for compatible GPUs"
time=2025-04-14T20:20:27.397+08:00 level=INFO source=gpu_windows.go:167 msg=packages count=1
time=2025-04-14T20:20:27.397+08:00 level=INFO source=gpu_windows.go:183 msg="efficiency cores detected" maxEfficiencyClass=1
time=2025-04-14T20:20:27.397+08:00 level=INFO source=gpu_windows.go:214 msg="" package=0 cores=20 efficiency=12 threads=20
time=2025-04-14T20:20:27.556+08:00 level=INFO source=gpu.go:319 msg="detected OS VRAM overhead" id=GPU-cb1cc77e-8070-d8e2-ed4f-2cb089bb0e0c library=cuda compute=7.5 driver=12.8 name="NVIDIA GeForce RTX 2080 Ti" overhead="216.6 MiB"
time=2025-04-14T20:20:27.561+08:00 level=INFO source=types.go:130 msg="inference compute" id=GPU-cb1cc77e-8070-d8e2-ed4f-2cb089bb0e0c library=cuda variant=v12 compute=7.5 driver=12.8 name="NVIDIA GeForce RTX 2080 Ti" total="22.0 GiB" available="20.8 GiB"
[GIN] 2025/04/14 - 20:20:27 | 200 | 0s | 127.0.0.1 | HEAD "/"
[GIN] 2025/04/14 - 20:20:27 | 200 | 23.1014ms | 127.0.0.1 | POST "/api/show"
time=2025-04-14T20:20:27.862+08:00 level=WARN source=ggml.go:152 msg="key not found" key=qwen2.vision.block_count default=0
time=2025-04-14T20:20:27.862+08:00 level=WARN source=ggml.go:152 msg="key not found" key=qwen2.attention.key_length default=128
time=2025-04-14T20:20:27.862+08:00 level=WARN source=ggml.go:152 msg="key not found" key=qwen2.attention.value_length default=128
time=2025-04-14T20:20:27.863+08:00 level=WARN source=ggml.go:152 msg="key not found" key=qwen2.vision.block_count default=0
time=2025-04-14T20:20:27.863+08:00 level=WARN source=ggml.go:152 msg="key not found" key=qwen2.attention.key_length default=128
time=2025-04-14T20:20:27.863+08:00 level=WARN source=ggml.go:152 msg="key not found" key=qwen2.attention.value_length default=128
time=2025-04-14T20:20:27.863+08:00 level=INFO source=sched.go:716 msg="new model will fit in available VRAM in single GPU, loading" model=C:\Users\Administrator.ollama\models\blobs\sha256-7ccc6415b2c7cb61ff8e01fec069d6f2fd6e213c509824d642c8a15c3d002e73 gpu=GPU-cb1cc77e-8070-d8e2-ed4f-2cb089bb0e0c parallel=1 available=22345154560 required="19.6 GiB"
time=2025-04-14T20:20:27.886+08:00 level=INFO source=server.go:105 msg="system memory" total="63.4 GiB" free="54.9 GiB" free_swap="57.5 GiB"
time=2025-04-14T20:20:27.886+08:00 level=WARN source=ggml.go:152 msg="key not found" key=qwen2.vision.block_count default=0
time=2025-04-14T20:20:27.887+08:00 level=WARN source=ggml.go:152 msg="key not found" key=qwen2.attention.key_length default=128
time=2025-04-14T20:20:27.887+08:00 level=WARN source=ggml.go:152 msg="key not found" key=qwen2.attention.value_length default=128
time=2025-04-14T20:20:27.888+08:00 level=INFO source=server.go:138 msg=offload library=cuda layers.requested=-1 layers.model=65 layers.offload=65 layers.split="" memory.available="[20.8 GiB]" memory.gpu_overhead="0 B" memory.required.full="19.6 GiB" memory.required.partial="19.6 GiB" memory.required.kv="512.0 MiB" memory.required.allocations="[19.6 GiB]" memory.weights.total="18.1 GiB" memory.weights.repeating="17.5 GiB" memory.weights.nonrepeating="609.1 MiB" memory.graph.full="307.0 MiB" memory.graph.partial="916.1 MiB"
llama_model_loader: loaded meta data with 33 key-value pairs and 771 tensors from C:\Users\Administrator.ollama\models\blobs\sha256-7ccc6415b2c7cb61ff8e01fec069d6f2fd6e213c509824d642c8a15c3d002e73 (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 = QwQ 32B
llama_model_loader: - kv 3: general.basename str = QwQ
llama_model_loader: - kv 4: general.size_label str = 32B
llama_model_loader: - kv 5: general.license str = apache-2.0
llama_model_loader: - kv 6: general.license.link str = https://huggingface.co/Qwen/QWQ-32B/b...
llama_model_loader: - kv 7: general.base_model.count u32 = 1
llama_model_loader: - kv 8: general.base_model.0.name str = Qwen2.5 32B
llama_model_loader: - kv 9: general.base_model.0.organization str = Qwen
llama_model_loader: - kv 10: general.base_model.0.repo_url str = https://huggingface.co/Qwen/Qwen2.5-32B
llama_model_loader: - kv 11: general.tags arr[str,2] = ["chat", "text-generation"]
llama_model_loader: - kv 12: general.languages arr[str,1] = ["en"]
llama_model_loader: - kv 13: qwen2.block_count u32 = 64
llama_model_loader: - kv 14: qwen2.context_length u32 = 40960
llama_model_loader: - kv 15: qwen2.embedding_length u32 = 5120
llama_model_loader: - kv 16: qwen2.feed_forward_length u32 = 27648
llama_model_loader: - kv 17: qwen2.attention.head_count u32 = 40
llama_model_loader: - kv 18: qwen2.attention.head_count_kv u32 = 8
llama_model_loader: - kv 19: qwen2.rope.freq_base f32 = 1000000.000000
llama_model_loader: - kv 20: qwen2.attention.layer_norm_rms_epsilon f32 = 0.000010
llama_model_loader: - kv 21: tokenizer.ggml.model str = gpt2
llama_model_loader: - kv 22: tokenizer.ggml.pre str = qwen2
llama_model_loader: - kv 23: tokenizer.ggml.tokens arr[str,152064] = ["!", """, "#", "$", "%", "&", "'", ...
llama_model_loader: - kv 24: tokenizer.ggml.token_type arr[i32,152064] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv 25: tokenizer.ggml.merges arr[str,151387] = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
llama_model_loader: - kv 26: tokenizer.ggml.eos_token_id u32 = 151645
llama_model_loader: - kv 27: tokenizer.ggml.padding_token_id u32 = 151643
llama_model_loader: - kv 28: tokenizer.ggml.bos_token_id u32 = 151643
llama_model_loader: - kv 29: tokenizer.ggml.add_bos_token bool = false
llama_model_loader: - kv 30: tokenizer.chat_template str = {%- if tools %}\n {{- '<|im_start|>...
llama_model_loader: - kv 31: general.quantization_version u32 = 2
llama_model_loader: - kv 32: general.file_type u32 = 15
llama_model_loader: - type f32: 321 tensors
llama_model_loader: - type q4_K: 385 tensors
llama_model_loader: - type q6_K: 65 tensors
print_info: file format = GGUF V3 (latest)
print_info: file type = Q4_K - Medium
print_info: file size = 18.48 GiB (4.85 BPW)
load: special tokens cache size = 26
load: token to piece cache size = 0.9311 MB
print_info: arch = qwen2
print_info: vocab_only = 1
print_info: model type = ?B
print_info: model params = 32.76 B
print_info: general.name = QwQ 32B
print_info: vocab type = BPE
print_info: n_vocab = 152064
print_info: n_merges = 151387
print_info: BOS token = 151643 '<|endoftext|>'
print_info: EOS token = 151645 '<|im_end|>'
print_info: EOT token = 151645 '<|im_end|>'
print_info: PAD token = 151643 '<|endoftext|>'
print_info: LF token = 198 'Ċ'
print_info: FIM PRE token = 151659 '<|fim_prefix|>'
print_info: FIM SUF token = 151661 '<|fim_suffix|>'
print_info: FIM MID token = 151660 '<|fim_middle|>'
print_info: FIM PAD token = 151662 '<|fim_pad|>'
print_info: FIM REP token = 151663 '<|repo_name|>'
print_info: FIM SEP token = 151664 '<|file_sep|>'
print_info: EOG token = 151643 '<|endoftext|>'
print_info: EOG token = 151645 '<|im_end|>'
print_info: EOG token = 151662 '<|fim_pad|>'
print_info: EOG token = 151663 '<|repo_name|>'
print_info: EOG token = 151664 '<|file_sep|>'
print_info: max token length = 256
llama_model_load: vocab only - skipping tensors
time=2025-04-14T20:20:28.027+08:00 level=INFO source=server.go:405 msg="starting llama server" cmd="C:\Users\Administrator\AppData\Local\Programs\Ollama\ollama.exe runner --model C:\Users\Administrator\.ollama\models\blobs\sha256-7ccc6415b2c7cb61ff8e01fec069d6f2fd6e213c509824d642c8a15c3d002e73 --ctx-size 2048 --batch-size 512 --n-gpu-layers 65 --threads 8 --no-mmap --parallel 1 --port 53165"
time=2025-04-14T20:20:28.041+08:00 level=INFO source=sched.go:451 msg="loaded runners" count=1
time=2025-04-14T20:20:28.041+08:00 level=INFO source=server.go:580 msg="waiting for llama runner to start responding"
time=2025-04-14T20:20:28.042+08:00 level=INFO source=server.go:614 msg="waiting for server to become available" status="llm server error"
time=2025-04-14T20:20:28.065+08:00 level=INFO source=runner.go:853 msg="starting go runner"
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 CUDA devices:
Device 0: NVIDIA GeForce RTX 2080 Ti, compute capability 7.5, VMM: yes
load_backend: loaded CUDA backend from C:\Users\Administrator\AppData\Local\Programs\Ollama\lib\ollama\cuda_v12\ggml-cuda.dll
load_backend: loaded CPU backend from C:\Users\Administrator\AppData\Local\Programs\Ollama\lib\ollama\ggml-cpu-alderlake.dll
time=2025-04-14T20:20:28.175+08:00 level=INFO source=ggml.go:109 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX_VNNI=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 CUDA.0.ARCHS=500,600,610,700,750,800,860,870,890,900,1200 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(clang)
time=2025-04-14T20:20:28.177+08:00 level=INFO source=runner.go:913 msg="Server listening on 127.0.0.1:53165"
llama_model_load_from_file_impl: using device CUDA0 (NVIDIA GeForce RTX 2080 Ti) - 21310 MiB free
llama_model_loader: loaded meta data with 33 key-value pairs and 771 tensors from C:\Users\Administrator.ollama\models\blobs\sha256-7ccc6415b2c7cb61ff8e01fec069d6f2fd6e213c509824d642c8a15c3d002e73 (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 = QwQ 32B
llama_model_loader: - kv 3: general.basename str = QwQ
llama_model_loader: - kv 4: general.size_label str = 32B
llama_model_loader: - kv 5: general.license str = apache-2.0
llama_model_loader: - kv 6: general.license.link str = https://huggingface.co/Qwen/QWQ-32B/b...
llama_model_loader: - kv 7: general.base_model.count u32 = 1
llama_model_loader: - kv 8: general.base_model.0.name str = Qwen2.5 32B
llama_model_loader: - kv 9: general.base_model.0.organization str = Qwen
llama_model_loader: - kv 10: general.base_model.0.repo_url str = https://huggingface.co/Qwen/Qwen2.5-32B
llama_model_loader: - kv 11: general.tags arr[str,2] = ["chat", "text-generation"]
llama_model_loader: - kv 12: general.languages arr[str,1] = ["en"]
llama_model_loader: - kv 13: qwen2.block_count u32 = 64
llama_model_loader: - kv 14: qwen2.context_length u32 = 40960
llama_model_loader: - kv 15: qwen2.embedding_length u32 = 5120
llama_model_loader: - kv 16: qwen2.feed_forward_length u32 = 27648
llama_model_loader: - kv 17: qwen2.attention.head_count u32 = 40
llama_model_loader: - kv 18: qwen2.attention.head_count_kv u32 = 8
llama_model_loader: - kv 19: qwen2.rope.freq_base f32 = 1000000.000000
llama_model_loader: - kv 20: qwen2.attention.layer_norm_rms_epsilon f32 = 0.000010
llama_model_loader: - kv 21: tokenizer.ggml.model str = gpt2
llama_model_loader: - kv 22: tokenizer.ggml.pre str = qwen2
time=2025-04-14T20:20:28.293+08:00 level=INFO source=server.go:614 msg="waiting for server to become available" status="llm server loading model"
llama_model_loader: - kv 23: tokenizer.ggml.tokens arr[str,152064] = ["!", """, "#", "$", "%", "&", "'", ...
llama_model_loader: - kv 24: tokenizer.ggml.token_type arr[i32,152064] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv 25: tokenizer.ggml.merges arr[str,151387] = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
llama_model_loader: - kv 26: tokenizer.ggml.eos_token_id u32 = 151645
llama_model_loader: - kv 27: tokenizer.ggml.padding_token_id u32 = 151643
llama_model_loader: - kv 28: tokenizer.ggml.bos_token_id u32 = 151643
llama_model_loader: - kv 29: tokenizer.ggml.add_bos_token bool = false
llama_model_loader: - kv 30: tokenizer.chat_template str = {%- if tools %}\n {{- '<|im_start|>...
llama_model_loader: - kv 31: general.quantization_version u32 = 2
llama_model_loader: - kv 32: general.file_type u32 = 15
llama_model_loader: - type f32: 321 tensors
llama_model_loader: - type q4_K: 385 tensors
llama_model_loader: - type q6_K: 65 tensors
print_info: file format = GGUF V3 (latest)
print_info: file type = Q4_K - Medium
print_info: file size = 18.48 GiB (4.85 BPW)
load: special tokens cache size = 26
load: token to piece cache size = 0.9311 MB
print_info: arch = qwen2
print_info: vocab_only = 0
print_info: n_ctx_train = 40960
print_info: n_embd = 5120
print_info: n_layer = 64
print_info: n_head = 40
print_info: n_head_kv = 8
print_info: n_rot = 128
print_info: n_swa = 0
print_info: n_embd_head_k = 128
print_info: n_embd_head_v = 128
print_info: n_gqa = 5
print_info: n_embd_k_gqa = 1024
print_info: n_embd_v_gqa = 1024
print_info: f_norm_eps = 0.0e+00
print_info: f_norm_rms_eps = 1.0e-05
print_info: f_clamp_kqv = 0.0e+00
print_info: f_max_alibi_bias = 0.0e+00
print_info: f_logit_scale = 0.0e+00
print_info: n_ff = 27648
print_info: n_expert = 0
print_info: n_expert_used = 0
print_info: causal attn = 1
print_info: pooling type = 0
print_info: rope type = 2
print_info: rope scaling = linear
print_info: freq_base_train = 1000000.0
print_info: freq_scale_train = 1
print_info: n_ctx_orig_yarn = 40960
print_info: rope_finetuned = unknown
print_info: ssm_d_conv = 0
print_info: ssm_d_inner = 0
print_info: ssm_d_state = 0
print_info: ssm_dt_rank = 0
print_info: ssm_dt_b_c_rms = 0
print_info: model type = 32B
print_info: model params = 32.76 B
print_info: general.name = QwQ 32B
print_info: vocab type = BPE
print_info: n_vocab = 152064
print_info: n_merges = 151387
print_info: BOS token = 151643 '<|endoftext|>'
print_info: EOS token = 151645 '<|im_end|>'
print_info: EOT token = 151645 '<|im_end|>'
print_info: PAD token = 151643 '<|endoftext|>'
print_info: LF token = 198 'Ċ'
print_info: FIM PRE token = 151659 '<|fim_prefix|>'
print_info: FIM SUF token = 151661 '<|fim_suffix|>'
print_info: FIM MID token = 151660 '<|fim_middle|>'
print_info: FIM PAD token = 151662 '<|fim_pad|>'
print_info: FIM REP token = 151663 '<|repo_name|>'
print_info: FIM SEP token = 151664 '<|file_sep|>'
print_info: EOG token = 151643 '<|endoftext|>'
print_info: EOG token = 151645 '<|im_end|>'
print_info: EOG token = 151662 '<|fim_pad|>'
print_info: EOG token = 151663 '<|repo_name|>'
print_info: EOG token = 151664 '<|file_sep|>'
print_info: max token length = 256
load_tensors: loading model tensors, this can take a while... (mmap = false)
load_tensors: offloading 64 repeating layers to GPU
load_tensors: offloading output layer to GPU
load_tensors: offloaded 65/65 layers to GPU
load_tensors: CUDA0 model buffer size = 18508.35 MiB
load_tensors: CPU model buffer size = 417.66 MiB
llama_init_from_model: n_seq_max = 1
llama_init_from_model: n_ctx = 2048
llama_init_from_model: n_ctx_per_seq = 2048
llama_init_from_model: n_batch = 512
llama_init_from_model: n_ubatch = 512
llama_init_from_model: flash_attn = 0
llama_init_from_model: freq_base = 1000000.0
llama_init_from_model: freq_scale = 1
llama_init_from_model: n_ctx_per_seq (2048) < n_ctx_train (40960) -- the full capacity of the model will not be utilized
llama_kv_cache_init: kv_size = 2048, offload = 1, type_k = 'f16', type_v = 'f16', n_layer = 64, can_shift = 1
llama_kv_cache_init: CUDA0 KV buffer size = 512.00 MiB
llama_init_from_model: KV self size = 512.00 MiB, K (f16): 256.00 MiB, V (f16): 256.00 MiB
llama_init_from_model: CUDA_Host output buffer size = 0.60 MiB
llama_init_from_model: CUDA0 compute buffer size = 307.00 MiB
llama_init_from_model: CUDA_Host compute buffer size = 14.01 MiB
llama_init_from_model: graph nodes = 2246
llama_init_from_model: graph splits = 2
time=2025-04-14T20:20:32.049+08:00 level=INFO source=server.go:619 msg="llama runner started in 4.01 seconds"
[GIN] 2025/04/14 - 20:20:32 | 200 | 4.2413769s | 127.0.0.1 | POST "/api/generate"
CUDA error: an illegal memory access was encountered
current device: 0, in function ggml_cuda_op_mul_mat at C:\a\ollama\ollama\ml\backend\ggml\ggml\src\ggml-cuda\ggml-cuda.cu:1621
cudaGetLastError()
C:\a\ollama\ollama\ml\backend\ggml\ggml\src\ggml-cuda\ggml-cuda.cu:73: CUDA error
[GIN] 2025/04/14 - 20:20:48 | 200 | 3.4721658s | 127.0.0.1 | POST "/api/chat"
time=2025-04-14T20:20:48.993+08:00 level=ERROR source=server.go:449 msg="llama runner terminated" error="exit status 0xc0000409"

Relevant log output

2025/04/14 20:20:27 routes.go:1231: 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_CONTEXT_LENGTH:2048 OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:C:\\Users\\Administrator\\.ollama\\models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE: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://* vscode-file://*] OLLAMA_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES:]"
time=2025-04-14T20:20:27.396+08:00 level=INFO source=images.go:458 msg="total blobs: 14"
time=2025-04-14T20:20:27.397+08:00 level=INFO source=images.go:465 msg="total unused blobs removed: 0"
time=2025-04-14T20:20:27.397+08:00 level=INFO source=routes.go:1298 msg="Listening on 127.0.0.1:11434 (version 0.6.5)"
time=2025-04-14T20:20:27.397+08:00 level=INFO source=gpu.go:217 msg="looking for compatible GPUs"
time=2025-04-14T20:20:27.397+08:00 level=INFO source=gpu_windows.go:167 msg=packages count=1
time=2025-04-14T20:20:27.397+08:00 level=INFO source=gpu_windows.go:183 msg="efficiency cores detected" maxEfficiencyClass=1
time=2025-04-14T20:20:27.397+08:00 level=INFO source=gpu_windows.go:214 msg="" package=0 cores=20 efficiency=12 threads=20
time=2025-04-14T20:20:27.556+08:00 level=INFO source=gpu.go:319 msg="detected OS VRAM overhead" id=GPU-cb1cc77e-8070-d8e2-ed4f-2cb089bb0e0c library=cuda compute=7.5 driver=12.8 name="NVIDIA GeForce RTX 2080 Ti" overhead="216.6 MiB"
time=2025-04-14T20:20:27.561+08:00 level=INFO source=types.go:130 msg="inference compute" id=GPU-cb1cc77e-8070-d8e2-ed4f-2cb089bb0e0c library=cuda variant=v12 compute=7.5 driver=12.8 name="NVIDIA GeForce RTX 2080 Ti" total="22.0 GiB" available="20.8 GiB"
[GIN] 2025/04/14 - 20:20:27 | 200 |            0s |       127.0.0.1 | HEAD     "/"
[GIN] 2025/04/14 - 20:20:27 | 200 |     23.1014ms |       127.0.0.1 | POST     "/api/show"
time=2025-04-14T20:20:27.862+08:00 level=WARN source=ggml.go:152 msg="key not found" key=qwen2.vision.block_count default=0
time=2025-04-14T20:20:27.862+08:00 level=WARN source=ggml.go:152 msg="key not found" key=qwen2.attention.key_length default=128
time=2025-04-14T20:20:27.862+08:00 level=WARN source=ggml.go:152 msg="key not found" key=qwen2.attention.value_length default=128
time=2025-04-14T20:20:27.863+08:00 level=WARN source=ggml.go:152 msg="key not found" key=qwen2.vision.block_count default=0
time=2025-04-14T20:20:27.863+08:00 level=WARN source=ggml.go:152 msg="key not found" key=qwen2.attention.key_length default=128
time=2025-04-14T20:20:27.863+08:00 level=WARN source=ggml.go:152 msg="key not found" key=qwen2.attention.value_length default=128
time=2025-04-14T20:20:27.863+08:00 level=INFO source=sched.go:716 msg="new model will fit in available VRAM in single GPU, loading" model=C:\Users\Administrator\.ollama\models\blobs\sha256-7ccc6415b2c7cb61ff8e01fec069d6f2fd6e213c509824d642c8a15c3d002e73 gpu=GPU-cb1cc77e-8070-d8e2-ed4f-2cb089bb0e0c parallel=1 available=22345154560 required="19.6 GiB"
time=2025-04-14T20:20:27.886+08:00 level=INFO source=server.go:105 msg="system memory" total="63.4 GiB" free="54.9 GiB" free_swap="57.5 GiB"
time=2025-04-14T20:20:27.886+08:00 level=WARN source=ggml.go:152 msg="key not found" key=qwen2.vision.block_count default=0
time=2025-04-14T20:20:27.887+08:00 level=WARN source=ggml.go:152 msg="key not found" key=qwen2.attention.key_length default=128
time=2025-04-14T20:20:27.887+08:00 level=WARN source=ggml.go:152 msg="key not found" key=qwen2.attention.value_length default=128
time=2025-04-14T20:20:27.888+08:00 level=INFO source=server.go:138 msg=offload library=cuda layers.requested=-1 layers.model=65 layers.offload=65 layers.split="" memory.available="[20.8 GiB]" memory.gpu_overhead="0 B" memory.required.full="19.6 GiB" memory.required.partial="19.6 GiB" memory.required.kv="512.0 MiB" memory.required.allocations="[19.6 GiB]" memory.weights.total="18.1 GiB" memory.weights.repeating="17.5 GiB" memory.weights.nonrepeating="609.1 MiB" memory.graph.full="307.0 MiB" memory.graph.partial="916.1 MiB"
llama_model_loader: loaded meta data with 33 key-value pairs and 771 tensors from C:\Users\Administrator\.ollama\models\blobs\sha256-7ccc6415b2c7cb61ff8e01fec069d6f2fd6e213c509824d642c8a15c3d002e73 (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              = QwQ 32B
llama_model_loader: - kv   3:                           general.basename str              = QwQ
llama_model_loader: - kv   4:                         general.size_label str              = 32B
llama_model_loader: - kv   5:                            general.license str              = apache-2.0
llama_model_loader: - kv   6:                       general.license.link str              = https://huggingface.co/Qwen/QWQ-32B/b...
llama_model_loader: - kv   7:                   general.base_model.count u32              = 1
llama_model_loader: - kv   8:                  general.base_model.0.name str              = Qwen2.5 32B
llama_model_loader: - kv   9:          general.base_model.0.organization str              = Qwen
llama_model_loader: - kv  10:              general.base_model.0.repo_url str              = https://huggingface.co/Qwen/Qwen2.5-32B
llama_model_loader: - kv  11:                               general.tags arr[str,2]       = ["chat", "text-generation"]
llama_model_loader: - kv  12:                          general.languages arr[str,1]       = ["en"]
llama_model_loader: - kv  13:                          qwen2.block_count u32              = 64
llama_model_loader: - kv  14:                       qwen2.context_length u32              = 40960
llama_model_loader: - kv  15:                     qwen2.embedding_length u32              = 5120
llama_model_loader: - kv  16:                  qwen2.feed_forward_length u32              = 27648
llama_model_loader: - kv  17:                 qwen2.attention.head_count u32              = 40
llama_model_loader: - kv  18:              qwen2.attention.head_count_kv u32              = 8
llama_model_loader: - kv  19:                       qwen2.rope.freq_base f32              = 1000000.000000
llama_model_loader: - kv  20:     qwen2.attention.layer_norm_rms_epsilon f32              = 0.000010
llama_model_loader: - kv  21:                       tokenizer.ggml.model str              = gpt2
llama_model_loader: - kv  22:                         tokenizer.ggml.pre str              = qwen2
llama_model_loader: - kv  23:                      tokenizer.ggml.tokens arr[str,152064]  = ["!", "\"", "#", "$", "%", "&", "'", ...
llama_model_loader: - kv  24:                  tokenizer.ggml.token_type arr[i32,152064]  = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv  25:                      tokenizer.ggml.merges arr[str,151387]  = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
llama_model_loader: - kv  26:                tokenizer.ggml.eos_token_id u32              = 151645
llama_model_loader: - kv  27:            tokenizer.ggml.padding_token_id u32              = 151643
llama_model_loader: - kv  28:                tokenizer.ggml.bos_token_id u32              = 151643
llama_model_loader: - kv  29:               tokenizer.ggml.add_bos_token bool             = false
llama_model_loader: - kv  30:                    tokenizer.chat_template str              = {%- if tools %}\n    {{- '<|im_start|>...
llama_model_loader: - kv  31:               general.quantization_version u32              = 2
llama_model_loader: - kv  32:                          general.file_type u32              = 15
llama_model_loader: - type  f32:  321 tensors
llama_model_loader: - type q4_K:  385 tensors
llama_model_loader: - type q6_K:   65 tensors
print_info: file format = GGUF V3 (latest)
print_info: file type   = Q4_K - Medium
print_info: file size   = 18.48 GiB (4.85 BPW) 
load: special tokens cache size = 26
load: token to piece cache size = 0.9311 MB
print_info: arch             = qwen2
print_info: vocab_only       = 1
print_info: model type       = ?B
print_info: model params     = 32.76 B
print_info: general.name     = QwQ 32B
print_info: vocab type       = BPE
print_info: n_vocab          = 152064
print_info: n_merges         = 151387
print_info: BOS token        = 151643 '<|endoftext|>'
print_info: EOS token        = 151645 '<|im_end|>'
print_info: EOT token        = 151645 '<|im_end|>'
print_info: PAD token        = 151643 '<|endoftext|>'
print_info: LF token         = 198 'Ċ'
print_info: FIM PRE token    = 151659 '<|fim_prefix|>'
print_info: FIM SUF token    = 151661 '<|fim_suffix|>'
print_info: FIM MID token    = 151660 '<|fim_middle|>'
print_info: FIM PAD token    = 151662 '<|fim_pad|>'
print_info: FIM REP token    = 151663 '<|repo_name|>'
print_info: FIM SEP token    = 151664 '<|file_sep|>'
print_info: EOG token        = 151643 '<|endoftext|>'
print_info: EOG token        = 151645 '<|im_end|>'
print_info: EOG token        = 151662 '<|fim_pad|>'
print_info: EOG token        = 151663 '<|repo_name|>'
print_info: EOG token        = 151664 '<|file_sep|>'
print_info: max token length = 256
llama_model_load: vocab only - skipping tensors
time=2025-04-14T20:20:28.027+08:00 level=INFO source=server.go:405 msg="starting llama server" cmd="C:\\Users\\Administrator\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --model C:\\Users\\Administrator\\.ollama\\models\\blobs\\sha256-7ccc6415b2c7cb61ff8e01fec069d6f2fd6e213c509824d642c8a15c3d002e73 --ctx-size 2048 --batch-size 512 --n-gpu-layers 65 --threads 8 --no-mmap --parallel 1 --port 53165"
time=2025-04-14T20:20:28.041+08:00 level=INFO source=sched.go:451 msg="loaded runners" count=1
time=2025-04-14T20:20:28.041+08:00 level=INFO source=server.go:580 msg="waiting for llama runner to start responding"
time=2025-04-14T20:20:28.042+08:00 level=INFO source=server.go:614 msg="waiting for server to become available" status="llm server error"
time=2025-04-14T20:20:28.065+08:00 level=INFO source=runner.go:853 msg="starting go runner"
ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 CUDA devices:
  Device 0: NVIDIA GeForce RTX 2080 Ti, compute capability 7.5, VMM: yes
load_backend: loaded CUDA backend from C:\Users\Administrator\AppData\Local\Programs\Ollama\lib\ollama\cuda_v12\ggml-cuda.dll
load_backend: loaded CPU backend from C:\Users\Administrator\AppData\Local\Programs\Ollama\lib\ollama\ggml-cpu-alderlake.dll
time=2025-04-14T20:20:28.175+08:00 level=INFO source=ggml.go:109 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX_VNNI=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 CUDA.0.ARCHS=500,600,610,700,750,800,860,870,890,900,1200 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(clang)
time=2025-04-14T20:20:28.177+08:00 level=INFO source=runner.go:913 msg="Server listening on 127.0.0.1:53165"
llama_model_load_from_file_impl: using device CUDA0 (NVIDIA GeForce RTX 2080 Ti) - 21310 MiB free
llama_model_loader: loaded meta data with 33 key-value pairs and 771 tensors from C:\Users\Administrator\.ollama\models\blobs\sha256-7ccc6415b2c7cb61ff8e01fec069d6f2fd6e213c509824d642c8a15c3d002e73 (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              = QwQ 32B
llama_model_loader: - kv   3:                           general.basename str              = QwQ
llama_model_loader: - kv   4:                         general.size_label str              = 32B
llama_model_loader: - kv   5:                            general.license str              = apache-2.0
llama_model_loader: - kv   6:                       general.license.link str              = https://huggingface.co/Qwen/QWQ-32B/b...
llama_model_loader: - kv   7:                   general.base_model.count u32              = 1
llama_model_loader: - kv   8:                  general.base_model.0.name str              = Qwen2.5 32B
llama_model_loader: - kv   9:          general.base_model.0.organization str              = Qwen
llama_model_loader: - kv  10:              general.base_model.0.repo_url str              = https://huggingface.co/Qwen/Qwen2.5-32B
llama_model_loader: - kv  11:                               general.tags arr[str,2]       = ["chat", "text-generation"]
llama_model_loader: - kv  12:                          general.languages arr[str,1]       = ["en"]
llama_model_loader: - kv  13:                          qwen2.block_count u32              = 64
llama_model_loader: - kv  14:                       qwen2.context_length u32              = 40960
llama_model_loader: - kv  15:                     qwen2.embedding_length u32              = 5120
llama_model_loader: - kv  16:                  qwen2.feed_forward_length u32              = 27648
llama_model_loader: - kv  17:                 qwen2.attention.head_count u32              = 40
llama_model_loader: - kv  18:              qwen2.attention.head_count_kv u32              = 8
llama_model_loader: - kv  19:                       qwen2.rope.freq_base f32              = 1000000.000000
llama_model_loader: - kv  20:     qwen2.attention.layer_norm_rms_epsilon f32              = 0.000010
llama_model_loader: - kv  21:                       tokenizer.ggml.model str              = gpt2
llama_model_loader: - kv  22:                         tokenizer.ggml.pre str              = qwen2
time=2025-04-14T20:20:28.293+08:00 level=INFO source=server.go:614 msg="waiting for server to become available" status="llm server loading model"
llama_model_loader: - kv  23:                      tokenizer.ggml.tokens arr[str,152064]  = ["!", "\"", "#", "$", "%", "&", "'", ...
llama_model_loader: - kv  24:                  tokenizer.ggml.token_type arr[i32,152064]  = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv  25:                      tokenizer.ggml.merges arr[str,151387]  = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
llama_model_loader: - kv  26:                tokenizer.ggml.eos_token_id u32              = 151645
llama_model_loader: - kv  27:            tokenizer.ggml.padding_token_id u32              = 151643
llama_model_loader: - kv  28:                tokenizer.ggml.bos_token_id u32              = 151643
llama_model_loader: - kv  29:               tokenizer.ggml.add_bos_token bool             = false
llama_model_loader: - kv  30:                    tokenizer.chat_template str              = {%- if tools %}\n    {{- '<|im_start|>...
llama_model_loader: - kv  31:               general.quantization_version u32              = 2
llama_model_loader: - kv  32:                          general.file_type u32              = 15
llama_model_loader: - type  f32:  321 tensors
llama_model_loader: - type q4_K:  385 tensors
llama_model_loader: - type q6_K:   65 tensors
print_info: file format = GGUF V3 (latest)
print_info: file type   = Q4_K - Medium
print_info: file size   = 18.48 GiB (4.85 BPW) 
load: special tokens cache size = 26
load: token to piece cache size = 0.9311 MB
print_info: arch             = qwen2
print_info: vocab_only       = 0
print_info: n_ctx_train      = 40960
print_info: n_embd           = 5120
print_info: n_layer          = 64
print_info: n_head           = 40
print_info: n_head_kv        = 8
print_info: n_rot            = 128
print_info: n_swa            = 0
print_info: n_embd_head_k    = 128
print_info: n_embd_head_v    = 128
print_info: n_gqa            = 5
print_info: n_embd_k_gqa     = 1024
print_info: n_embd_v_gqa     = 1024
print_info: f_norm_eps       = 0.0e+00
print_info: f_norm_rms_eps   = 1.0e-05
print_info: f_clamp_kqv      = 0.0e+00
print_info: f_max_alibi_bias = 0.0e+00
print_info: f_logit_scale    = 0.0e+00
print_info: n_ff             = 27648
print_info: n_expert         = 0
print_info: n_expert_used    = 0
print_info: causal attn      = 1
print_info: pooling type     = 0
print_info: rope type        = 2
print_info: rope scaling     = linear
print_info: freq_base_train  = 1000000.0
print_info: freq_scale_train = 1
print_info: n_ctx_orig_yarn  = 40960
print_info: rope_finetuned   = unknown
print_info: ssm_d_conv       = 0
print_info: ssm_d_inner      = 0
print_info: ssm_d_state      = 0
print_info: ssm_dt_rank      = 0
print_info: ssm_dt_b_c_rms   = 0
print_info: model type       = 32B
print_info: model params     = 32.76 B
print_info: general.name     = QwQ 32B
print_info: vocab type       = BPE
print_info: n_vocab          = 152064
print_info: n_merges         = 151387
print_info: BOS token        = 151643 '<|endoftext|>'
print_info: EOS token        = 151645 '<|im_end|>'
print_info: EOT token        = 151645 '<|im_end|>'
print_info: PAD token        = 151643 '<|endoftext|>'
print_info: LF token         = 198 'Ċ'
print_info: FIM PRE token    = 151659 '<|fim_prefix|>'
print_info: FIM SUF token    = 151661 '<|fim_suffix|>'
print_info: FIM MID token    = 151660 '<|fim_middle|>'
print_info: FIM PAD token    = 151662 '<|fim_pad|>'
print_info: FIM REP token    = 151663 '<|repo_name|>'
print_info: FIM SEP token    = 151664 '<|file_sep|>'
print_info: EOG token        = 151643 '<|endoftext|>'
print_info: EOG token        = 151645 '<|im_end|>'
print_info: EOG token        = 151662 '<|fim_pad|>'
print_info: EOG token        = 151663 '<|repo_name|>'
print_info: EOG token        = 151664 '<|file_sep|>'
print_info: max token length = 256
load_tensors: loading model tensors, this can take a while... (mmap = false)
load_tensors: offloading 64 repeating layers to GPU
load_tensors: offloading output layer to GPU
load_tensors: offloaded 65/65 layers to GPU
load_tensors:        CUDA0 model buffer size = 18508.35 MiB
load_tensors:          CPU model buffer size =   417.66 MiB
llama_init_from_model: n_seq_max     = 1
llama_init_from_model: n_ctx         = 2048
llama_init_from_model: n_ctx_per_seq = 2048
llama_init_from_model: n_batch       = 512
llama_init_from_model: n_ubatch      = 512
llama_init_from_model: flash_attn    = 0
llama_init_from_model: freq_base     = 1000000.0
llama_init_from_model: freq_scale    = 1
llama_init_from_model: n_ctx_per_seq (2048) < n_ctx_train (40960) -- the full capacity of the model will not be utilized
llama_kv_cache_init: kv_size = 2048, offload = 1, type_k = 'f16', type_v = 'f16', n_layer = 64, can_shift = 1
llama_kv_cache_init:      CUDA0 KV buffer size =   512.00 MiB
llama_init_from_model: KV self size  =  512.00 MiB, K (f16):  256.00 MiB, V (f16):  256.00 MiB
llama_init_from_model:  CUDA_Host  output buffer size =     0.60 MiB
llama_init_from_model:      CUDA0 compute buffer size =   307.00 MiB
llama_init_from_model:  CUDA_Host compute buffer size =    14.01 MiB
llama_init_from_model: graph nodes  = 2246
llama_init_from_model: graph splits = 2
time=2025-04-14T20:20:32.049+08:00 level=INFO source=server.go:619 msg="llama runner started in 4.01 seconds"
[GIN] 2025/04/14 - 20:20:32 | 200 |    4.2413769s |       127.0.0.1 | POST     "/api/generate"
CUDA error: an illegal memory access was encountered
  current device: 0, in function ggml_cuda_op_mul_mat at C:\a\ollama\ollama\ml\backend\ggml\ggml\src\ggml-cuda\ggml-cuda.cu:1621
  cudaGetLastError()
C:\a\ollama\ollama\ml\backend\ggml\ggml\src\ggml-cuda\ggml-cuda.cu:73: CUDA error
[GIN] 2025/04/14 - 20:20:48 | 200 |    3.4721658s |       127.0.0.1 | POST     "/api/chat"
time=2025-04-14T20:20:48.993+08:00 level=ERROR source=server.go:449 msg="llama runner terminated" error="exit status 0xc0000409"

OS

Windows

GPU

Nvidia

CPU

AMD, Intel

Ollama version

0.6.5

Originally created by @Garmin969 on GitHub (Apr 14, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/10265 ### What is the issue? Hey everyone, I just got a new computer with a 2080ti 22g GPU. I wanted to run the QWQ-32B big model using Ollama, but halfway through running the model, it starts showing random text and black screens with an error: 'An error occurred while running the model: CuDA error'. I wonder if you guys know what might be causing this? (With specific error logs as described) 2025/04/14 20:20:27 routes.go:1231: 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_CONTEXT_LENGTH:2048 OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:C:\\Users\\Administrator\\.ollama\\models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE: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://* vscode-file://*] OLLAMA_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES:]" time=2025-04-14T20:20:27.396+08:00 level=INFO source=images.go:458 msg="total blobs: 14" time=2025-04-14T20:20:27.397+08:00 level=INFO source=images.go:465 msg="total unused blobs removed: 0" time=2025-04-14T20:20:27.397+08:00 level=INFO source=routes.go:1298 msg="Listening on 127.0.0.1:11434 (version 0.6.5)" time=2025-04-14T20:20:27.397+08:00 level=INFO source=gpu.go:217 msg="looking for compatible GPUs" time=2025-04-14T20:20:27.397+08:00 level=INFO source=gpu_windows.go:167 msg=packages count=1 time=2025-04-14T20:20:27.397+08:00 level=INFO source=gpu_windows.go:183 msg="efficiency cores detected" maxEfficiencyClass=1 time=2025-04-14T20:20:27.397+08:00 level=INFO source=gpu_windows.go:214 msg="" package=0 cores=20 efficiency=12 threads=20 time=2025-04-14T20:20:27.556+08:00 level=INFO source=gpu.go:319 msg="detected OS VRAM overhead" id=GPU-cb1cc77e-8070-d8e2-ed4f-2cb089bb0e0c library=cuda compute=7.5 driver=12.8 name="NVIDIA GeForce RTX 2080 Ti" overhead="216.6 MiB" time=2025-04-14T20:20:27.561+08:00 level=INFO source=types.go:130 msg="inference compute" id=GPU-cb1cc77e-8070-d8e2-ed4f-2cb089bb0e0c library=cuda variant=v12 compute=7.5 driver=12.8 name="NVIDIA GeForce RTX 2080 Ti" total="22.0 GiB" available="20.8 GiB" [GIN] 2025/04/14 - 20:20:27 | 200 | 0s | 127.0.0.1 | HEAD "/" [GIN] 2025/04/14 - 20:20:27 | 200 | 23.1014ms | 127.0.0.1 | POST "/api/show" time=2025-04-14T20:20:27.862+08:00 level=WARN source=ggml.go:152 msg="key not found" key=qwen2.vision.block_count default=0 time=2025-04-14T20:20:27.862+08:00 level=WARN source=ggml.go:152 msg="key not found" key=qwen2.attention.key_length default=128 time=2025-04-14T20:20:27.862+08:00 level=WARN source=ggml.go:152 msg="key not found" key=qwen2.attention.value_length default=128 time=2025-04-14T20:20:27.863+08:00 level=WARN source=ggml.go:152 msg="key not found" key=qwen2.vision.block_count default=0 time=2025-04-14T20:20:27.863+08:00 level=WARN source=ggml.go:152 msg="key not found" key=qwen2.attention.key_length default=128 time=2025-04-14T20:20:27.863+08:00 level=WARN source=ggml.go:152 msg="key not found" key=qwen2.attention.value_length default=128 time=2025-04-14T20:20:27.863+08:00 level=INFO source=sched.go:716 msg="new model will fit in available VRAM in single GPU, loading" model=C:\Users\Administrator\.ollama\models\blobs\sha256-7ccc6415b2c7cb61ff8e01fec069d6f2fd6e213c509824d642c8a15c3d002e73 gpu=GPU-cb1cc77e-8070-d8e2-ed4f-2cb089bb0e0c parallel=1 available=22345154560 required="19.6 GiB" time=2025-04-14T20:20:27.886+08:00 level=INFO source=server.go:105 msg="system memory" total="63.4 GiB" free="54.9 GiB" free_swap="57.5 GiB" time=2025-04-14T20:20:27.886+08:00 level=WARN source=ggml.go:152 msg="key not found" key=qwen2.vision.block_count default=0 time=2025-04-14T20:20:27.887+08:00 level=WARN source=ggml.go:152 msg="key not found" key=qwen2.attention.key_length default=128 time=2025-04-14T20:20:27.887+08:00 level=WARN source=ggml.go:152 msg="key not found" key=qwen2.attention.value_length default=128 time=2025-04-14T20:20:27.888+08:00 level=INFO source=server.go:138 msg=offload library=cuda layers.requested=-1 layers.model=65 layers.offload=65 layers.split="" memory.available="[20.8 GiB]" memory.gpu_overhead="0 B" memory.required.full="19.6 GiB" memory.required.partial="19.6 GiB" memory.required.kv="512.0 MiB" memory.required.allocations="[19.6 GiB]" memory.weights.total="18.1 GiB" memory.weights.repeating="17.5 GiB" memory.weights.nonrepeating="609.1 MiB" memory.graph.full="307.0 MiB" memory.graph.partial="916.1 MiB" llama_model_loader: loaded meta data with 33 key-value pairs and 771 tensors from C:\Users\Administrator\.ollama\models\blobs\sha256-7ccc6415b2c7cb61ff8e01fec069d6f2fd6e213c509824d642c8a15c3d002e73 (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 = QwQ 32B llama_model_loader: - kv 3: general.basename str = QwQ llama_model_loader: - kv 4: general.size_label str = 32B llama_model_loader: - kv 5: general.license str = apache-2.0 llama_model_loader: - kv 6: general.license.link str = https://huggingface.co/Qwen/QWQ-32B/b... llama_model_loader: - kv 7: general.base_model.count u32 = 1 llama_model_loader: - kv 8: general.base_model.0.name str = Qwen2.5 32B llama_model_loader: - kv 9: general.base_model.0.organization str = Qwen llama_model_loader: - kv 10: general.base_model.0.repo_url str = https://huggingface.co/Qwen/Qwen2.5-32B llama_model_loader: - kv 11: general.tags arr[str,2] = ["chat", "text-generation"] llama_model_loader: - kv 12: general.languages arr[str,1] = ["en"] llama_model_loader: - kv 13: qwen2.block_count u32 = 64 llama_model_loader: - kv 14: qwen2.context_length u32 = 40960 llama_model_loader: - kv 15: qwen2.embedding_length u32 = 5120 llama_model_loader: - kv 16: qwen2.feed_forward_length u32 = 27648 llama_model_loader: - kv 17: qwen2.attention.head_count u32 = 40 llama_model_loader: - kv 18: qwen2.attention.head_count_kv u32 = 8 llama_model_loader: - kv 19: qwen2.rope.freq_base f32 = 1000000.000000 llama_model_loader: - kv 20: qwen2.attention.layer_norm_rms_epsilon f32 = 0.000010 llama_model_loader: - kv 21: tokenizer.ggml.model str = gpt2 llama_model_loader: - kv 22: tokenizer.ggml.pre str = qwen2 llama_model_loader: - kv 23: tokenizer.ggml.tokens arr[str,152064] = ["!", "\"", "#", "$", "%", "&", "'", ... llama_model_loader: - kv 24: tokenizer.ggml.token_type arr[i32,152064] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... llama_model_loader: - kv 25: tokenizer.ggml.merges arr[str,151387] = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",... llama_model_loader: - kv 26: tokenizer.ggml.eos_token_id u32 = 151645 llama_model_loader: - kv 27: tokenizer.ggml.padding_token_id u32 = 151643 llama_model_loader: - kv 28: tokenizer.ggml.bos_token_id u32 = 151643 llama_model_loader: - kv 29: tokenizer.ggml.add_bos_token bool = false llama_model_loader: - kv 30: tokenizer.chat_template str = {%- if tools %}\n {{- '<|im_start|>... llama_model_loader: - kv 31: general.quantization_version u32 = 2 llama_model_loader: - kv 32: general.file_type u32 = 15 llama_model_loader: - type f32: 321 tensors llama_model_loader: - type q4_K: 385 tensors llama_model_loader: - type q6_K: 65 tensors print_info: file format = GGUF V3 (latest) print_info: file type = Q4_K - Medium print_info: file size = 18.48 GiB (4.85 BPW) load: special tokens cache size = 26 load: token to piece cache size = 0.9311 MB print_info: arch = qwen2 print_info: vocab_only = 1 print_info: model type = ?B print_info: model params = 32.76 B print_info: general.name = QwQ 32B print_info: vocab type = BPE print_info: n_vocab = 152064 print_info: n_merges = 151387 print_info: BOS token = 151643 '<|endoftext|>' print_info: EOS token = 151645 '<|im_end|>' print_info: EOT token = 151645 '<|im_end|>' print_info: PAD token = 151643 '<|endoftext|>' print_info: LF token = 198 'Ċ' print_info: FIM PRE token = 151659 '<|fim_prefix|>' print_info: FIM SUF token = 151661 '<|fim_suffix|>' print_info: FIM MID token = 151660 '<|fim_middle|>' print_info: FIM PAD token = 151662 '<|fim_pad|>' print_info: FIM REP token = 151663 '<|repo_name|>' print_info: FIM SEP token = 151664 '<|file_sep|>' print_info: EOG token = 151643 '<|endoftext|>' print_info: EOG token = 151645 '<|im_end|>' print_info: EOG token = 151662 '<|fim_pad|>' print_info: EOG token = 151663 '<|repo_name|>' print_info: EOG token = 151664 '<|file_sep|>' print_info: max token length = 256 llama_model_load: vocab only - skipping tensors time=2025-04-14T20:20:28.027+08:00 level=INFO source=server.go:405 msg="starting llama server" cmd="C:\\Users\\Administrator\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --model C:\\Users\\Administrator\\.ollama\\models\\blobs\\sha256-7ccc6415b2c7cb61ff8e01fec069d6f2fd6e213c509824d642c8a15c3d002e73 --ctx-size 2048 --batch-size 512 --n-gpu-layers 65 --threads 8 --no-mmap --parallel 1 --port 53165" time=2025-04-14T20:20:28.041+08:00 level=INFO source=sched.go:451 msg="loaded runners" count=1 time=2025-04-14T20:20:28.041+08:00 level=INFO source=server.go:580 msg="waiting for llama runner to start responding" time=2025-04-14T20:20:28.042+08:00 level=INFO source=server.go:614 msg="waiting for server to become available" status="llm server error" time=2025-04-14T20:20:28.065+08:00 level=INFO source=runner.go:853 msg="starting go runner" ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no ggml_cuda_init: found 1 CUDA devices: Device 0: NVIDIA GeForce RTX 2080 Ti, compute capability 7.5, VMM: yes load_backend: loaded CUDA backend from C:\Users\Administrator\AppData\Local\Programs\Ollama\lib\ollama\cuda_v12\ggml-cuda.dll load_backend: loaded CPU backend from C:\Users\Administrator\AppData\Local\Programs\Ollama\lib\ollama\ggml-cpu-alderlake.dll time=2025-04-14T20:20:28.175+08:00 level=INFO source=ggml.go:109 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX_VNNI=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 CUDA.0.ARCHS=500,600,610,700,750,800,860,870,890,900,1200 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(clang) time=2025-04-14T20:20:28.177+08:00 level=INFO source=runner.go:913 msg="Server listening on 127.0.0.1:53165" llama_model_load_from_file_impl: using device CUDA0 (NVIDIA GeForce RTX 2080 Ti) - 21310 MiB free llama_model_loader: loaded meta data with 33 key-value pairs and 771 tensors from C:\Users\Administrator\.ollama\models\blobs\sha256-7ccc6415b2c7cb61ff8e01fec069d6f2fd6e213c509824d642c8a15c3d002e73 (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 = QwQ 32B llama_model_loader: - kv 3: general.basename str = QwQ llama_model_loader: - kv 4: general.size_label str = 32B llama_model_loader: - kv 5: general.license str = apache-2.0 llama_model_loader: - kv 6: general.license.link str = https://huggingface.co/Qwen/QWQ-32B/b... llama_model_loader: - kv 7: general.base_model.count u32 = 1 llama_model_loader: - kv 8: general.base_model.0.name str = Qwen2.5 32B llama_model_loader: - kv 9: general.base_model.0.organization str = Qwen llama_model_loader: - kv 10: general.base_model.0.repo_url str = https://huggingface.co/Qwen/Qwen2.5-32B llama_model_loader: - kv 11: general.tags arr[str,2] = ["chat", "text-generation"] llama_model_loader: - kv 12: general.languages arr[str,1] = ["en"] llama_model_loader: - kv 13: qwen2.block_count u32 = 64 llama_model_loader: - kv 14: qwen2.context_length u32 = 40960 llama_model_loader: - kv 15: qwen2.embedding_length u32 = 5120 llama_model_loader: - kv 16: qwen2.feed_forward_length u32 = 27648 llama_model_loader: - kv 17: qwen2.attention.head_count u32 = 40 llama_model_loader: - kv 18: qwen2.attention.head_count_kv u32 = 8 llama_model_loader: - kv 19: qwen2.rope.freq_base f32 = 1000000.000000 llama_model_loader: - kv 20: qwen2.attention.layer_norm_rms_epsilon f32 = 0.000010 llama_model_loader: - kv 21: tokenizer.ggml.model str = gpt2 llama_model_loader: - kv 22: tokenizer.ggml.pre str = qwen2 time=2025-04-14T20:20:28.293+08:00 level=INFO source=server.go:614 msg="waiting for server to become available" status="llm server loading model" llama_model_loader: - kv 23: tokenizer.ggml.tokens arr[str,152064] = ["!", "\"", "#", "$", "%", "&", "'", ... llama_model_loader: - kv 24: tokenizer.ggml.token_type arr[i32,152064] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... llama_model_loader: - kv 25: tokenizer.ggml.merges arr[str,151387] = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",... llama_model_loader: - kv 26: tokenizer.ggml.eos_token_id u32 = 151645 llama_model_loader: - kv 27: tokenizer.ggml.padding_token_id u32 = 151643 llama_model_loader: - kv 28: tokenizer.ggml.bos_token_id u32 = 151643 llama_model_loader: - kv 29: tokenizer.ggml.add_bos_token bool = false llama_model_loader: - kv 30: tokenizer.chat_template str = {%- if tools %}\n {{- '<|im_start|>... llama_model_loader: - kv 31: general.quantization_version u32 = 2 llama_model_loader: - kv 32: general.file_type u32 = 15 llama_model_loader: - type f32: 321 tensors llama_model_loader: - type q4_K: 385 tensors llama_model_loader: - type q6_K: 65 tensors print_info: file format = GGUF V3 (latest) print_info: file type = Q4_K - Medium print_info: file size = 18.48 GiB (4.85 BPW) load: special tokens cache size = 26 load: token to piece cache size = 0.9311 MB print_info: arch = qwen2 print_info: vocab_only = 0 print_info: n_ctx_train = 40960 print_info: n_embd = 5120 print_info: n_layer = 64 print_info: n_head = 40 print_info: n_head_kv = 8 print_info: n_rot = 128 print_info: n_swa = 0 print_info: n_embd_head_k = 128 print_info: n_embd_head_v = 128 print_info: n_gqa = 5 print_info: n_embd_k_gqa = 1024 print_info: n_embd_v_gqa = 1024 print_info: f_norm_eps = 0.0e+00 print_info: f_norm_rms_eps = 1.0e-05 print_info: f_clamp_kqv = 0.0e+00 print_info: f_max_alibi_bias = 0.0e+00 print_info: f_logit_scale = 0.0e+00 print_info: n_ff = 27648 print_info: n_expert = 0 print_info: n_expert_used = 0 print_info: causal attn = 1 print_info: pooling type = 0 print_info: rope type = 2 print_info: rope scaling = linear print_info: freq_base_train = 1000000.0 print_info: freq_scale_train = 1 print_info: n_ctx_orig_yarn = 40960 print_info: rope_finetuned = unknown print_info: ssm_d_conv = 0 print_info: ssm_d_inner = 0 print_info: ssm_d_state = 0 print_info: ssm_dt_rank = 0 print_info: ssm_dt_b_c_rms = 0 print_info: model type = 32B print_info: model params = 32.76 B print_info: general.name = QwQ 32B print_info: vocab type = BPE print_info: n_vocab = 152064 print_info: n_merges = 151387 print_info: BOS token = 151643 '<|endoftext|>' print_info: EOS token = 151645 '<|im_end|>' print_info: EOT token = 151645 '<|im_end|>' print_info: PAD token = 151643 '<|endoftext|>' print_info: LF token = 198 'Ċ' print_info: FIM PRE token = 151659 '<|fim_prefix|>' print_info: FIM SUF token = 151661 '<|fim_suffix|>' print_info: FIM MID token = 151660 '<|fim_middle|>' print_info: FIM PAD token = 151662 '<|fim_pad|>' print_info: FIM REP token = 151663 '<|repo_name|>' print_info: FIM SEP token = 151664 '<|file_sep|>' print_info: EOG token = 151643 '<|endoftext|>' print_info: EOG token = 151645 '<|im_end|>' print_info: EOG token = 151662 '<|fim_pad|>' print_info: EOG token = 151663 '<|repo_name|>' print_info: EOG token = 151664 '<|file_sep|>' print_info: max token length = 256 load_tensors: loading model tensors, this can take a while... (mmap = false) load_tensors: offloading 64 repeating layers to GPU load_tensors: offloading output layer to GPU load_tensors: offloaded 65/65 layers to GPU load_tensors: CUDA0 model buffer size = 18508.35 MiB load_tensors: CPU model buffer size = 417.66 MiB llama_init_from_model: n_seq_max = 1 llama_init_from_model: n_ctx = 2048 llama_init_from_model: n_ctx_per_seq = 2048 llama_init_from_model: n_batch = 512 llama_init_from_model: n_ubatch = 512 llama_init_from_model: flash_attn = 0 llama_init_from_model: freq_base = 1000000.0 llama_init_from_model: freq_scale = 1 llama_init_from_model: n_ctx_per_seq (2048) < n_ctx_train (40960) -- the full capacity of the model will not be utilized llama_kv_cache_init: kv_size = 2048, offload = 1, type_k = 'f16', type_v = 'f16', n_layer = 64, can_shift = 1 llama_kv_cache_init: CUDA0 KV buffer size = 512.00 MiB llama_init_from_model: KV self size = 512.00 MiB, K (f16): 256.00 MiB, V (f16): 256.00 MiB llama_init_from_model: CUDA_Host output buffer size = 0.60 MiB llama_init_from_model: CUDA0 compute buffer size = 307.00 MiB llama_init_from_model: CUDA_Host compute buffer size = 14.01 MiB llama_init_from_model: graph nodes = 2246 llama_init_from_model: graph splits = 2 time=2025-04-14T20:20:32.049+08:00 level=INFO source=server.go:619 msg="llama runner started in 4.01 seconds" [GIN] 2025/04/14 - 20:20:32 | 200 | 4.2413769s | 127.0.0.1 | POST "/api/generate" CUDA error: an illegal memory access was encountered current device: 0, in function ggml_cuda_op_mul_mat at C:\a\ollama\ollama\ml\backend\ggml\ggml\src\ggml-cuda\ggml-cuda.cu:1621 cudaGetLastError() C:\a\ollama\ollama\ml\backend\ggml\ggml\src\ggml-cuda\ggml-cuda.cu:73: CUDA error [GIN] 2025/04/14 - 20:20:48 | 200 | 3.4721658s | 127.0.0.1 | POST "/api/chat" time=2025-04-14T20:20:48.993+08:00 level=ERROR source=server.go:449 msg="llama runner terminated" error="exit status 0xc0000409" ### Relevant log output ```shell 2025/04/14 20:20:27 routes.go:1231: 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_CONTEXT_LENGTH:2048 OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://127.0.0.1:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:5m0s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:C:\\Users\\Administrator\\.ollama\\models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE: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://* vscode-file://*] OLLAMA_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES:]" time=2025-04-14T20:20:27.396+08:00 level=INFO source=images.go:458 msg="total blobs: 14" time=2025-04-14T20:20:27.397+08:00 level=INFO source=images.go:465 msg="total unused blobs removed: 0" time=2025-04-14T20:20:27.397+08:00 level=INFO source=routes.go:1298 msg="Listening on 127.0.0.1:11434 (version 0.6.5)" time=2025-04-14T20:20:27.397+08:00 level=INFO source=gpu.go:217 msg="looking for compatible GPUs" time=2025-04-14T20:20:27.397+08:00 level=INFO source=gpu_windows.go:167 msg=packages count=1 time=2025-04-14T20:20:27.397+08:00 level=INFO source=gpu_windows.go:183 msg="efficiency cores detected" maxEfficiencyClass=1 time=2025-04-14T20:20:27.397+08:00 level=INFO source=gpu_windows.go:214 msg="" package=0 cores=20 efficiency=12 threads=20 time=2025-04-14T20:20:27.556+08:00 level=INFO source=gpu.go:319 msg="detected OS VRAM overhead" id=GPU-cb1cc77e-8070-d8e2-ed4f-2cb089bb0e0c library=cuda compute=7.5 driver=12.8 name="NVIDIA GeForce RTX 2080 Ti" overhead="216.6 MiB" time=2025-04-14T20:20:27.561+08:00 level=INFO source=types.go:130 msg="inference compute" id=GPU-cb1cc77e-8070-d8e2-ed4f-2cb089bb0e0c library=cuda variant=v12 compute=7.5 driver=12.8 name="NVIDIA GeForce RTX 2080 Ti" total="22.0 GiB" available="20.8 GiB" [GIN] 2025/04/14 - 20:20:27 | 200 | 0s | 127.0.0.1 | HEAD "/" [GIN] 2025/04/14 - 20:20:27 | 200 | 23.1014ms | 127.0.0.1 | POST "/api/show" time=2025-04-14T20:20:27.862+08:00 level=WARN source=ggml.go:152 msg="key not found" key=qwen2.vision.block_count default=0 time=2025-04-14T20:20:27.862+08:00 level=WARN source=ggml.go:152 msg="key not found" key=qwen2.attention.key_length default=128 time=2025-04-14T20:20:27.862+08:00 level=WARN source=ggml.go:152 msg="key not found" key=qwen2.attention.value_length default=128 time=2025-04-14T20:20:27.863+08:00 level=WARN source=ggml.go:152 msg="key not found" key=qwen2.vision.block_count default=0 time=2025-04-14T20:20:27.863+08:00 level=WARN source=ggml.go:152 msg="key not found" key=qwen2.attention.key_length default=128 time=2025-04-14T20:20:27.863+08:00 level=WARN source=ggml.go:152 msg="key not found" key=qwen2.attention.value_length default=128 time=2025-04-14T20:20:27.863+08:00 level=INFO source=sched.go:716 msg="new model will fit in available VRAM in single GPU, loading" model=C:\Users\Administrator\.ollama\models\blobs\sha256-7ccc6415b2c7cb61ff8e01fec069d6f2fd6e213c509824d642c8a15c3d002e73 gpu=GPU-cb1cc77e-8070-d8e2-ed4f-2cb089bb0e0c parallel=1 available=22345154560 required="19.6 GiB" time=2025-04-14T20:20:27.886+08:00 level=INFO source=server.go:105 msg="system memory" total="63.4 GiB" free="54.9 GiB" free_swap="57.5 GiB" time=2025-04-14T20:20:27.886+08:00 level=WARN source=ggml.go:152 msg="key not found" key=qwen2.vision.block_count default=0 time=2025-04-14T20:20:27.887+08:00 level=WARN source=ggml.go:152 msg="key not found" key=qwen2.attention.key_length default=128 time=2025-04-14T20:20:27.887+08:00 level=WARN source=ggml.go:152 msg="key not found" key=qwen2.attention.value_length default=128 time=2025-04-14T20:20:27.888+08:00 level=INFO source=server.go:138 msg=offload library=cuda layers.requested=-1 layers.model=65 layers.offload=65 layers.split="" memory.available="[20.8 GiB]" memory.gpu_overhead="0 B" memory.required.full="19.6 GiB" memory.required.partial="19.6 GiB" memory.required.kv="512.0 MiB" memory.required.allocations="[19.6 GiB]" memory.weights.total="18.1 GiB" memory.weights.repeating="17.5 GiB" memory.weights.nonrepeating="609.1 MiB" memory.graph.full="307.0 MiB" memory.graph.partial="916.1 MiB" llama_model_loader: loaded meta data with 33 key-value pairs and 771 tensors from C:\Users\Administrator\.ollama\models\blobs\sha256-7ccc6415b2c7cb61ff8e01fec069d6f2fd6e213c509824d642c8a15c3d002e73 (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 = QwQ 32B llama_model_loader: - kv 3: general.basename str = QwQ llama_model_loader: - kv 4: general.size_label str = 32B llama_model_loader: - kv 5: general.license str = apache-2.0 llama_model_loader: - kv 6: general.license.link str = https://huggingface.co/Qwen/QWQ-32B/b... llama_model_loader: - kv 7: general.base_model.count u32 = 1 llama_model_loader: - kv 8: general.base_model.0.name str = Qwen2.5 32B llama_model_loader: - kv 9: general.base_model.0.organization str = Qwen llama_model_loader: - kv 10: general.base_model.0.repo_url str = https://huggingface.co/Qwen/Qwen2.5-32B llama_model_loader: - kv 11: general.tags arr[str,2] = ["chat", "text-generation"] llama_model_loader: - kv 12: general.languages arr[str,1] = ["en"] llama_model_loader: - kv 13: qwen2.block_count u32 = 64 llama_model_loader: - kv 14: qwen2.context_length u32 = 40960 llama_model_loader: - kv 15: qwen2.embedding_length u32 = 5120 llama_model_loader: - kv 16: qwen2.feed_forward_length u32 = 27648 llama_model_loader: - kv 17: qwen2.attention.head_count u32 = 40 llama_model_loader: - kv 18: qwen2.attention.head_count_kv u32 = 8 llama_model_loader: - kv 19: qwen2.rope.freq_base f32 = 1000000.000000 llama_model_loader: - kv 20: qwen2.attention.layer_norm_rms_epsilon f32 = 0.000010 llama_model_loader: - kv 21: tokenizer.ggml.model str = gpt2 llama_model_loader: - kv 22: tokenizer.ggml.pre str = qwen2 llama_model_loader: - kv 23: tokenizer.ggml.tokens arr[str,152064] = ["!", "\"", "#", "$", "%", "&", "'", ... llama_model_loader: - kv 24: tokenizer.ggml.token_type arr[i32,152064] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... llama_model_loader: - kv 25: tokenizer.ggml.merges arr[str,151387] = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",... llama_model_loader: - kv 26: tokenizer.ggml.eos_token_id u32 = 151645 llama_model_loader: - kv 27: tokenizer.ggml.padding_token_id u32 = 151643 llama_model_loader: - kv 28: tokenizer.ggml.bos_token_id u32 = 151643 llama_model_loader: - kv 29: tokenizer.ggml.add_bos_token bool = false llama_model_loader: - kv 30: tokenizer.chat_template str = {%- if tools %}\n {{- '<|im_start|>... llama_model_loader: - kv 31: general.quantization_version u32 = 2 llama_model_loader: - kv 32: general.file_type u32 = 15 llama_model_loader: - type f32: 321 tensors llama_model_loader: - type q4_K: 385 tensors llama_model_loader: - type q6_K: 65 tensors print_info: file format = GGUF V3 (latest) print_info: file type = Q4_K - Medium print_info: file size = 18.48 GiB (4.85 BPW) load: special tokens cache size = 26 load: token to piece cache size = 0.9311 MB print_info: arch = qwen2 print_info: vocab_only = 1 print_info: model type = ?B print_info: model params = 32.76 B print_info: general.name = QwQ 32B print_info: vocab type = BPE print_info: n_vocab = 152064 print_info: n_merges = 151387 print_info: BOS token = 151643 '<|endoftext|>' print_info: EOS token = 151645 '<|im_end|>' print_info: EOT token = 151645 '<|im_end|>' print_info: PAD token = 151643 '<|endoftext|>' print_info: LF token = 198 'Ċ' print_info: FIM PRE token = 151659 '<|fim_prefix|>' print_info: FIM SUF token = 151661 '<|fim_suffix|>' print_info: FIM MID token = 151660 '<|fim_middle|>' print_info: FIM PAD token = 151662 '<|fim_pad|>' print_info: FIM REP token = 151663 '<|repo_name|>' print_info: FIM SEP token = 151664 '<|file_sep|>' print_info: EOG token = 151643 '<|endoftext|>' print_info: EOG token = 151645 '<|im_end|>' print_info: EOG token = 151662 '<|fim_pad|>' print_info: EOG token = 151663 '<|repo_name|>' print_info: EOG token = 151664 '<|file_sep|>' print_info: max token length = 256 llama_model_load: vocab only - skipping tensors time=2025-04-14T20:20:28.027+08:00 level=INFO source=server.go:405 msg="starting llama server" cmd="C:\\Users\\Administrator\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --model C:\\Users\\Administrator\\.ollama\\models\\blobs\\sha256-7ccc6415b2c7cb61ff8e01fec069d6f2fd6e213c509824d642c8a15c3d002e73 --ctx-size 2048 --batch-size 512 --n-gpu-layers 65 --threads 8 --no-mmap --parallel 1 --port 53165" time=2025-04-14T20:20:28.041+08:00 level=INFO source=sched.go:451 msg="loaded runners" count=1 time=2025-04-14T20:20:28.041+08:00 level=INFO source=server.go:580 msg="waiting for llama runner to start responding" time=2025-04-14T20:20:28.042+08:00 level=INFO source=server.go:614 msg="waiting for server to become available" status="llm server error" time=2025-04-14T20:20:28.065+08:00 level=INFO source=runner.go:853 msg="starting go runner" ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no ggml_cuda_init: found 1 CUDA devices: Device 0: NVIDIA GeForce RTX 2080 Ti, compute capability 7.5, VMM: yes load_backend: loaded CUDA backend from C:\Users\Administrator\AppData\Local\Programs\Ollama\lib\ollama\cuda_v12\ggml-cuda.dll load_backend: loaded CPU backend from C:\Users\Administrator\AppData\Local\Programs\Ollama\lib\ollama\ggml-cpu-alderlake.dll time=2025-04-14T20:20:28.175+08:00 level=INFO source=ggml.go:109 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX_VNNI=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 CUDA.0.ARCHS=500,600,610,700,750,800,860,870,890,900,1200 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(clang) time=2025-04-14T20:20:28.177+08:00 level=INFO source=runner.go:913 msg="Server listening on 127.0.0.1:53165" llama_model_load_from_file_impl: using device CUDA0 (NVIDIA GeForce RTX 2080 Ti) - 21310 MiB free llama_model_loader: loaded meta data with 33 key-value pairs and 771 tensors from C:\Users\Administrator\.ollama\models\blobs\sha256-7ccc6415b2c7cb61ff8e01fec069d6f2fd6e213c509824d642c8a15c3d002e73 (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 = QwQ 32B llama_model_loader: - kv 3: general.basename str = QwQ llama_model_loader: - kv 4: general.size_label str = 32B llama_model_loader: - kv 5: general.license str = apache-2.0 llama_model_loader: - kv 6: general.license.link str = https://huggingface.co/Qwen/QWQ-32B/b... llama_model_loader: - kv 7: general.base_model.count u32 = 1 llama_model_loader: - kv 8: general.base_model.0.name str = Qwen2.5 32B llama_model_loader: - kv 9: general.base_model.0.organization str = Qwen llama_model_loader: - kv 10: general.base_model.0.repo_url str = https://huggingface.co/Qwen/Qwen2.5-32B llama_model_loader: - kv 11: general.tags arr[str,2] = ["chat", "text-generation"] llama_model_loader: - kv 12: general.languages arr[str,1] = ["en"] llama_model_loader: - kv 13: qwen2.block_count u32 = 64 llama_model_loader: - kv 14: qwen2.context_length u32 = 40960 llama_model_loader: - kv 15: qwen2.embedding_length u32 = 5120 llama_model_loader: - kv 16: qwen2.feed_forward_length u32 = 27648 llama_model_loader: - kv 17: qwen2.attention.head_count u32 = 40 llama_model_loader: - kv 18: qwen2.attention.head_count_kv u32 = 8 llama_model_loader: - kv 19: qwen2.rope.freq_base f32 = 1000000.000000 llama_model_loader: - kv 20: qwen2.attention.layer_norm_rms_epsilon f32 = 0.000010 llama_model_loader: - kv 21: tokenizer.ggml.model str = gpt2 llama_model_loader: - kv 22: tokenizer.ggml.pre str = qwen2 time=2025-04-14T20:20:28.293+08:00 level=INFO source=server.go:614 msg="waiting for server to become available" status="llm server loading model" llama_model_loader: - kv 23: tokenizer.ggml.tokens arr[str,152064] = ["!", "\"", "#", "$", "%", "&", "'", ... llama_model_loader: - kv 24: tokenizer.ggml.token_type arr[i32,152064] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... llama_model_loader: - kv 25: tokenizer.ggml.merges arr[str,151387] = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",... llama_model_loader: - kv 26: tokenizer.ggml.eos_token_id u32 = 151645 llama_model_loader: - kv 27: tokenizer.ggml.padding_token_id u32 = 151643 llama_model_loader: - kv 28: tokenizer.ggml.bos_token_id u32 = 151643 llama_model_loader: - kv 29: tokenizer.ggml.add_bos_token bool = false llama_model_loader: - kv 30: tokenizer.chat_template str = {%- if tools %}\n {{- '<|im_start|>... llama_model_loader: - kv 31: general.quantization_version u32 = 2 llama_model_loader: - kv 32: general.file_type u32 = 15 llama_model_loader: - type f32: 321 tensors llama_model_loader: - type q4_K: 385 tensors llama_model_loader: - type q6_K: 65 tensors print_info: file format = GGUF V3 (latest) print_info: file type = Q4_K - Medium print_info: file size = 18.48 GiB (4.85 BPW) load: special tokens cache size = 26 load: token to piece cache size = 0.9311 MB print_info: arch = qwen2 print_info: vocab_only = 0 print_info: n_ctx_train = 40960 print_info: n_embd = 5120 print_info: n_layer = 64 print_info: n_head = 40 print_info: n_head_kv = 8 print_info: n_rot = 128 print_info: n_swa = 0 print_info: n_embd_head_k = 128 print_info: n_embd_head_v = 128 print_info: n_gqa = 5 print_info: n_embd_k_gqa = 1024 print_info: n_embd_v_gqa = 1024 print_info: f_norm_eps = 0.0e+00 print_info: f_norm_rms_eps = 1.0e-05 print_info: f_clamp_kqv = 0.0e+00 print_info: f_max_alibi_bias = 0.0e+00 print_info: f_logit_scale = 0.0e+00 print_info: n_ff = 27648 print_info: n_expert = 0 print_info: n_expert_used = 0 print_info: causal attn = 1 print_info: pooling type = 0 print_info: rope type = 2 print_info: rope scaling = linear print_info: freq_base_train = 1000000.0 print_info: freq_scale_train = 1 print_info: n_ctx_orig_yarn = 40960 print_info: rope_finetuned = unknown print_info: ssm_d_conv = 0 print_info: ssm_d_inner = 0 print_info: ssm_d_state = 0 print_info: ssm_dt_rank = 0 print_info: ssm_dt_b_c_rms = 0 print_info: model type = 32B print_info: model params = 32.76 B print_info: general.name = QwQ 32B print_info: vocab type = BPE print_info: n_vocab = 152064 print_info: n_merges = 151387 print_info: BOS token = 151643 '<|endoftext|>' print_info: EOS token = 151645 '<|im_end|>' print_info: EOT token = 151645 '<|im_end|>' print_info: PAD token = 151643 '<|endoftext|>' print_info: LF token = 198 'Ċ' print_info: FIM PRE token = 151659 '<|fim_prefix|>' print_info: FIM SUF token = 151661 '<|fim_suffix|>' print_info: FIM MID token = 151660 '<|fim_middle|>' print_info: FIM PAD token = 151662 '<|fim_pad|>' print_info: FIM REP token = 151663 '<|repo_name|>' print_info: FIM SEP token = 151664 '<|file_sep|>' print_info: EOG token = 151643 '<|endoftext|>' print_info: EOG token = 151645 '<|im_end|>' print_info: EOG token = 151662 '<|fim_pad|>' print_info: EOG token = 151663 '<|repo_name|>' print_info: EOG token = 151664 '<|file_sep|>' print_info: max token length = 256 load_tensors: loading model tensors, this can take a while... (mmap = false) load_tensors: offloading 64 repeating layers to GPU load_tensors: offloading output layer to GPU load_tensors: offloaded 65/65 layers to GPU load_tensors: CUDA0 model buffer size = 18508.35 MiB load_tensors: CPU model buffer size = 417.66 MiB llama_init_from_model: n_seq_max = 1 llama_init_from_model: n_ctx = 2048 llama_init_from_model: n_ctx_per_seq = 2048 llama_init_from_model: n_batch = 512 llama_init_from_model: n_ubatch = 512 llama_init_from_model: flash_attn = 0 llama_init_from_model: freq_base = 1000000.0 llama_init_from_model: freq_scale = 1 llama_init_from_model: n_ctx_per_seq (2048) < n_ctx_train (40960) -- the full capacity of the model will not be utilized llama_kv_cache_init: kv_size = 2048, offload = 1, type_k = 'f16', type_v = 'f16', n_layer = 64, can_shift = 1 llama_kv_cache_init: CUDA0 KV buffer size = 512.00 MiB llama_init_from_model: KV self size = 512.00 MiB, K (f16): 256.00 MiB, V (f16): 256.00 MiB llama_init_from_model: CUDA_Host output buffer size = 0.60 MiB llama_init_from_model: CUDA0 compute buffer size = 307.00 MiB llama_init_from_model: CUDA_Host compute buffer size = 14.01 MiB llama_init_from_model: graph nodes = 2246 llama_init_from_model: graph splits = 2 time=2025-04-14T20:20:32.049+08:00 level=INFO source=server.go:619 msg="llama runner started in 4.01 seconds" [GIN] 2025/04/14 - 20:20:32 | 200 | 4.2413769s | 127.0.0.1 | POST "/api/generate" CUDA error: an illegal memory access was encountered current device: 0, in function ggml_cuda_op_mul_mat at C:\a\ollama\ollama\ml\backend\ggml\ggml\src\ggml-cuda\ggml-cuda.cu:1621 cudaGetLastError() C:\a\ollama\ollama\ml\backend\ggml\ggml\src\ggml-cuda\ggml-cuda.cu:73: CUDA error [GIN] 2025/04/14 - 20:20:48 | 200 | 3.4721658s | 127.0.0.1 | POST "/api/chat" time=2025-04-14T20:20:48.993+08:00 level=ERROR source=server.go:449 msg="llama runner terminated" error="exit status 0xc0000409" ``` ### OS Windows ### GPU Nvidia ### CPU AMD, Intel ### Ollama version 0.6.5
GiteaMirror added the bug label 2026-04-12 18:29:52 -05:00
GiteaMirror commented 2026-04-12 18:29:53 -05:00
Author
Owner
Copy Link

@kylewintaur commented on GitHub (Apr 27, 2025):

I'm running into this issue as well, depending on the model, and ONLY on version 0.6.6.

❌ 0.6.6 and gemma3:12b ❯ ollama run gemma3:12b "Tell me a random fun fact about the Roman Empire"

Here's a fun fact for you go!

RomansError: an error was encountered while running the model: CUDA error: an illegal memory access was encountered
current device: 0, in function ggml_backend_cuda_synchronize at //ml/backend/ggml/ggml/src/ggml-cuda/ggml-cuda.cu:2473
cudaStreamSynchronize(cuda_ctx->stream())
//ml/backend/ggml/ggml/src/ggml-cuda/ggml-cuda.cu:75: CUDA error

❌ 0.6.6 and phi4:latest

❯ ollama run --verbose phi4:latest "Tell me a random fun fact about the Roman Empire"

Sure! DidError: an error was encountered while running the model: unexpected EOF

❯ ollama run phi4:latest "Tell me a random fun fact about the Roman Empire"

One interesting andError: an error was encountered while running the model: CUDA error

❯ ollama run phi4:latest "Tell me a random fun fact about the Roman Empire"

One fascinating and somewhat lesser-known.isheleng,
the Romans. [the$ ^ not the least the

[ The the the di [ $ clean the the the l{<</less our { the $

we the $ the the the the ^ the hi ^{&</ ^{ {</credentials the minl ^ !

<| !&lkie(1. onekiekiequeishere(lessligickely(que-iglisha{qual{workly presentedique[&lculigl<~[&(properlglicalllual8{( min{(il7{credentials{+ailicisquill^^{ca{cie{l{2li{ the(less{(qual{(
aaelie(italish&[&lh&&g(cd{(1l{&(occe(1((prolPredict(3(2'(&{((the{(s&Schema&l(&-&"li1&l(tie&isha,l&l&aIael&llyl?li,'

{&l&-g(g[&&l-~(ilie&(m(g[&-. net&lh&Error: an error was encountered while running the model: CUDA error: an illegal memory access was encountered
current device: 0, in function ggml_backend_cuda_synchronize at //ml/backend/ggml/ggml/src/ggml-cuda/ggml-cuda.cu:2473
cudaStreamSynchronize(cuda_ctx->stream())
//ml/backend/ggml/ggml/src/ggml-cuda/ggml-cuda.cu:75: CUDA error

✅ 0.6.5 and phi4:latest ❯ ollama run phi4:latest "Tell me a random fun fact about the Roman Empire"

Sure! Did you know that Romans had something called "bread and circuses"? This phrase refers to how the government tried to keep citizens happy by providing free wheat (which they used to make bread) and
organizing massive entertainment events like gladiator games and chariot races. It was a way to distract people from political issues or dissatisfaction with leadership. The term is still used today to describe
policies that try to appease people with distractions instead of addressing real problems!

I'm using an Nvidia RTX 3060

❯ nvidia-smi
Sun Apr 27 23:19:47 2025
+-----------------------------------------------------------------------------+
| NVIDIA-SMI 470.256.02   Driver Version: 470.256.02   CUDA Version: 11.4     |
|-------------------------------+----------------------+----------------------+
| GPU  Name        Persistence-M| Bus-Id        Disp.A | Volatile Uncorr. ECC |
| Fan  Temp  Perf  Pwr:Usage/Cap|         Memory-Usage | GPU-Util  Compute M. |
|                               |                      |               MIG M. |
|===============================+======================+======================|
|   0  NVIDIA GeForce ...  On   | 00000000:05:00.0 Off |                  N/A |
|  0%   38C    P8    17W / 170W |  11164MiB / 12053MiB |      0%      Default |
|                               |                      |                  N/A |
+-------------------------------+----------------------+----------------------+

+-----------------------------------------------------------------------------+
| Processes:                                                                  |
|  GPU   GI   CI        PID   Type   Process name                  GPU Memory |
|        ID   ID                                                   Usage      |
|=============================================================================|
|    0   N/A  N/A   4072643      C   /usr/bin/ollama                 11161MiB |
+-----------------------------------------------------------------------------+
<!-- gh-comment-id:2833456909 --> @kylewintaur commented on GitHub (Apr 27, 2025): I'm running into this issue as well, depending on the model, and ONLY on version 0.6.6. <details> <summary>❌ 0.6.6 and gemma3:12b</summary> ❯ ollama run gemma3:12b "Tell me a random fun fact about the Roman Empire" Here's a fun fact for you go! RomansError: an error was encountered while running the model: CUDA error: an illegal memory access was encountered current device: 0, in function ggml_backend_cuda_synchronize at //ml/backend/ggml/ggml/src/ggml-cuda/ggml-cuda.cu:2473 cudaStreamSynchronize(cuda_ctx->stream()) //ml/backend/ggml/ggml/src/ggml-cuda/ggml-cuda.cu:75: CUDA error </details> <details> <summary>❌ 0.6.6 and phi4:latest</summary> ❯ ollama run --verbose phi4:latest "Tell me a random fun fact about the Roman Empire" Sure! DidError: an error was encountered while running the model: unexpected EOF ❯ ollama run phi4:latest "Tell me a random fun fact about the Roman Empire" One interesting andError: an error was encountered while running the model: CUDA error ❯ ollama run phi4:latest "Tell me a random fun fact about the Roman Empire" One fascinating and somewhat lesser-known.isheleng, the Romans. [the$ ^ not the least the [ The the the di [ $ clean the the the l{<</less our { the $ we the $ the the the the ^ the hi ^{&</ ^{ {</credentials the minl $ ^ $ ! <| !&lkie(1. onekiekiequeishere(lessligickely(que-iglisha{qual{workly presentedique[&lculigl<~[&(properlglicalllual8{( min{(il7{credentials{+ailicisquill^^{ca{cie{l{2li{ the(less{(qual{( aaelie(italish&[&lh&&g(cd{(1l{&(occe(1((prolPredict(3(2'(&{((the{(s&Schema&l(&-&"li1&l(tie&isha,l&l&aIael&llyl?li,' {&l&-g(g[&&l-~(ilie&(m(g[&-. net&lh&Error: an error was encountered while running the model: CUDA error: an illegal memory access was encountered current device: 0, in function ggml_backend_cuda_synchronize at //ml/backend/ggml/ggml/src/ggml-cuda/ggml-cuda.cu:2473 cudaStreamSynchronize(cuda_ctx->stream()) //ml/backend/ggml/ggml/src/ggml-cuda/ggml-cuda.cu:75: CUDA error </details> <details> <summary>✅ 0.6.5 and phi4:latest</summary> ❯ ollama run phi4:latest "Tell me a random fun fact about the Roman Empire" Sure! Did you know that Romans had something called "bread and circuses"? This phrase refers to how the government tried to keep citizens happy by providing free wheat (which they used to make bread) and organizing massive entertainment events like gladiator games and chariot races. It was a way to distract people from political issues or dissatisfaction with leadership. The term is still used today to describe policies that try to appease people with distractions instead of addressing real problems! </details> I'm using an Nvidia RTX 3060 ``` ❯ nvidia-smi Sun Apr 27 23:19:47 2025 +-----------------------------------------------------------------------------+ | NVIDIA-SMI 470.256.02 Driver Version: 470.256.02 CUDA Version: 11.4 | |-------------------------------+----------------------+----------------------+ | GPU Name Persistence-M| Bus-Id Disp.A | Volatile Uncorr. ECC | | Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | GPU-Util Compute M. | | | | MIG M. | |===============================+======================+======================| | 0 NVIDIA GeForce ... On | 00000000:05:00.0 Off | N/A | | 0% 38C P8 17W / 170W | 11164MiB / 12053MiB | 0% Default | | | | N/A | +-------------------------------+----------------------+----------------------+ +-----------------------------------------------------------------------------+ | Processes: | | GPU GI CI PID Type Process name GPU Memory | | ID ID Usage | |=============================================================================| | 0 N/A N/A 4072643 C /usr/bin/ollama 11161MiB | +-----------------------------------------------------------------------------+ ```
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#6739
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?