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

[GH-ISSUE #13013] Ollama not compatible with AMD GPUs when ZLUDA installed #8615

New Issue
Open
opened 2026-04-12 21:21:10 -05:00 by GiteaMirror · 7 comments
GiteaMirror commented 2026-04-12 21:21:10 -05:00
Owner
Copy Link

Originally created by @yihuishou on GitHub (Nov 8, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/13013

Originally assigned to: @dhiltgen on GitHub.

What is the issue?

Access API 500 Error

Relevant log output

print_info: max token length = 1024
load_tensors: loading model tensors, this can take a while... (mmap = false)
load_tensors: offloading 40 repeating layers to GPU
load_tensors: offloading output layer to GPU
load_tensors: offloaded 41/41 layers to GPU
load_tensors:    CUDA_Host model buffer size =   629.00 MiB
load_tensors:        CUDA0 model buffer size =  8897.23 MiB
llama_init_from_model: model default pooling_type is [0], but [-1] was specified
llama_context: constructing llama_context
llama_context: n_seq_max     = 1
llama_context: n_ctx         = 4096
llama_context: n_ctx_per_seq = 4096
llama_context: n_batch       = 512
llama_context: n_ubatch      = 512
llama_context: causal_attn   = 1
llama_context: flash_attn    = disabled
llama_context: kv_unified    = false
llama_context: freq_base     = 5000000.0
llama_context: freq_scale    = 1
llama_context: n_ctx_per_seq (4096) < n_ctx_train (131072) -- the full capacity of the model will not be utilized
llama_context:  CUDA_Host  output buffer size =     0.59 MiB
llama_kv_cache:      CUDA0 KV buffer size =   160.00 MiB
llama_kv_cache: size =  160.00 MiB (  4096 cells,  40 layers,  1/1 seqs), K (f16):   80.00 MiB, V (f16):   80.00 MiB
CUDA error: the resource allocation failed
  current device: 0, in function cublas_handle at C:/a/ollama/ollama/ml/backend/ggml/ggml/src\ggml-cuda/common.cuh:1027
  cublasCreate_v2(&cublas_handles[device])
C:\a\ollama\ollama\ml\backend\ggml\ggml\src\ggml-cuda\ggml-cuda.cu:88: CUDA error
time=2025-11-08T11:33:10.836+08:00 level=INFO source=server.go:1285 msg="waiting for server to become available" status="llm server error"
time=2025-11-08T11:33:10.885+08:00 level=ERROR source=server.go:273 msg="llama runner terminated" error="exit status 0xc0000409"
time=2025-11-08T11:33:11.086+08:00 level=INFO source=sched.go:453 msg="Load failed" model=i:\OllamaModels\.ollama\models\blobs\sha256-8e41022dfc218cd744c56beac04040243fd26f4e9f2026599345a9b348946a85 error="llama runner process has terminated: CUDA error"
[GIN] 2025/11/08 - 11:33:11 | 500 |    7.9300584s |       127.0.0.1 | POST     "/v1/chat/completions"
time=2025-11-08T11:33:11.113+08:00 level=INFO source=server.go:400 msg="starting runner" cmd="C:\\Users\\EvilEnergySeaUrchin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 56786"
time=2025-11-08T11:33:11.652+08:00 level=INFO source=cpu_windows.go:148 msg=packages count=1
time=2025-11-08T11:33:11.652+08:00 level=INFO source=cpu_windows.go:195 msg="" package=0 cores=12 efficiency=0 threads=24
llama_model_loader: loaded meta data with 23 key-value pairs and 283 tensors from i:\OllamaModels\.ollama\models\blobs\sha256-8e41022dfc218cd744c56beac04040243fd26f4e9f2026599345a9b348946a85 (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              = chatglm
llama_model_loader: - kv   1:                               general.name str              = codegeex4-all-9b
llama_model_loader: - kv   2:                     chatglm.context_length u32              = 131072
llama_model_loader: - kv   3:                   chatglm.embedding_length u32              = 4096
llama_model_loader: - kv   4:                chatglm.feed_forward_length u32              = 13696
llama_model_loader: - kv   5:                        chatglm.block_count u32              = 40
llama_model_loader: - kv   6:               chatglm.attention.head_count u32              = 32
llama_model_loader: - kv   7:            chatglm.attention.head_count_kv u32              = 2
llama_model_loader: - kv   8:   chatglm.attention.layer_norm_rms_epsilon f32              = 0.000010
llama_model_loader: - kv   9:                          general.file_type u32              = 7
llama_model_loader: - kv  10:               chatglm.rope.dimension_count u32              = 64
llama_model_loader: - kv  11:               tokenizer.ggml.add_bos_token bool             = false
llama_model_loader: - kv  12:                     chatglm.rope.freq_base f32              = 5000000.000000
llama_model_loader: - kv  13:                       tokenizer.ggml.model str              = gpt2
llama_model_loader: - kv  14:                         tokenizer.ggml.pre str              = chatglm-bpe
llama_model_loader: - kv  15:                      tokenizer.ggml.tokens arr[str,151552]  = ["!", "\"", "#", "$", "%", "&", "'", ...
llama_model_loader: - kv  16:                  tokenizer.ggml.token_type arr[i32,151552]  = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv  17:                      tokenizer.ggml.merges arr[str,151073]  = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
llama_model_loader: - kv  18:            tokenizer.ggml.padding_token_id u32              = 151329
llama_model_loader: - kv  19:                tokenizer.ggml.eos_token_id u32              = 151329
llama_model_loader: - kv  20:                tokenizer.ggml.eot_token_id u32              = 151336
llama_model_loader: - kv  21:            tokenizer.ggml.unknown_token_id u32              = 151329
llama_model_loader: - kv  22:               general.quantization_version u32              = 2
llama_model_loader: - type  f32:  121 tensors
llama_model_loader: - type q8_0:  162 tensors



print_info: max token length = 1024
load_tensors: loading model tensors, this can take a while... (mmap = false)
load_tensors: offloading 40 repeating layers to GPU
load_tensors: offloading output layer to GPU
load_tensors: offloaded 41/41 layers to GPU
load_tensors:    CUDA_Host model buffer size =   629.00 MiB
load_tensors:        CUDA0 model buffer size =  8897.23 MiB
llama_init_from_model: model default pooling_type is [0], but [-1] was specified
llama_context: constructing llama_context
llama_context: n_seq_max     = 1
llama_context: n_ctx         = 4096
llama_context: n_ctx_per_seq = 4096
llama_context: n_batch       = 512
llama_context: n_ubatch      = 512
llama_context: causal_attn   = 1
llama_context: flash_attn    = disabled
llama_context: kv_unified    = false
llama_context: freq_base     = 5000000.0
llama_context: freq_scale    = 1
llama_context: n_ctx_per_seq (4096) < n_ctx_train (131072) -- the full capacity of the model will not be utilized
llama_context:  CUDA_Host  output buffer size =     0.59 MiB
llama_kv_cache:      CUDA0 KV buffer size =   160.00 MiB
llama_kv_cache: size =  160.00 MiB (  4096 cells,  40 layers,  1/1 seqs), K (f16):   80.00 MiB, V (f16):   80.00 MiB
CUDA error: the resource allocation failed
  current device: 0, in function cublas_handle at C:/a/ollama/ollama/ml/backend/ggml/ggml/src\ggml-cuda/common.cuh:1027
  cublasCreate_v2(&cublas_handles[device])
C:\a\ollama\ollama\ml\backend\ggml\ggml\src\ggml-cuda\ggml-cuda.cu:88: CUDA error
time=2025-11-08T11:33:30.373+08:00 level=INFO source=server.go:1285 msg="waiting for server to become available" status="llm server error"
time=2025-11-08T11:33:30.417+08:00 level=ERROR source=server.go:273 msg="llama runner terminated" error="exit status 0xc0000409"
time=2025-11-08T11:33:30.623+08:00 level=INFO source=sched.go:453 msg="Load failed" model=i:\OllamaModels\.ollama\models\blobs\sha256-8e41022dfc218cd744c56beac04040243fd26f4e9f2026599345a9b348946a85 error="llama runner process has terminated: CUDA error"
[GIN] 2025/11/08 - 11:33:30 | 500 |    2.9328621s |       127.0.0.1 | POST     "/v1/chat/completions"
[GIN] 2025/11/08 - 11:33:50 | 204 |            0s |             ::1 | OPTIONS  "/v1/chat/completions"
time=2025-11-08T11:33:50.856+08:00 level=INFO source=server.go:400 msg="starting runner" cmd="C:\\Users\\EvilEnergySeaUrchin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 56859"
time=2025-11-08T11:33:51.372+08:00 level=INFO source=cpu_windows.go:148 msg=packages count=1
time=2025-11-08T11:33:51.373+08:00 level=INFO source=cpu_windows.go:195 msg="" package=0 cores=12 efficiency=0 threads=24
llama_model_loader: loaded meta data with 23 key-value pairs and 283 tensors from i:\OllamaModels\.ollama\models\blobs\sha256-8e41022dfc218cd744c56beac04040243fd26f4e9f2026599345a9b348946a85 (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              = chatglm
llama_model_loader: - kv   1:                               general.name str              = codegeex4-all-9b
llama_model_loader: - kv   2:                     chatglm.context_length u32              = 131072
llama_model_loader: - kv   3:                   chatglm.embedding_length u32              = 4096
llama_model_loader: - kv   4:                chatglm.feed_forward_length u32              = 13696
llama_model_loader: - kv   5:                        chatglm.block_count u32              = 40
llama_model_loader: - kv   6:               chatglm.attention.head_count u32              = 32
llama_model_loader: - kv   7:            chatglm.attention.head_count_kv u32              = 2
llama_model_loader: - kv   8:   chatglm.attention.layer_norm_rms_epsilon f32              = 0.000010
llama_model_loader: - kv   9:                          general.file_type u32              = 7
llama_model_loader: - kv  10:               chatglm.rope.dimension_count u32              = 64
llama_model_loader: - kv  11:               tokenizer.ggml.add_bos_token bool             = false
llama_model_loader: - kv  12:                     chatglm.rope.freq_base f32              = 5000000.000000
llama_model_loader: - kv  13:                       tokenizer.ggml.model str              = gpt2
llama_model_loader: - kv  14:                         tokenizer.ggml.pre str              = chatglm-bpe
llama_model_loader: - kv  15:                      tokenizer.ggml.tokens arr[str,151552]  = ["!", "\"", "#", "$", "%", "&", "'", ...
llama_model_loader: - kv  16:                  tokenizer.ggml.token_type arr[i32,151552]  = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
llama_model_loader: - kv  17:                      tokenizer.ggml.merges arr[str,151073]  = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
llama_model_loader: - kv  18:            tokenizer.ggml.padding_token_id u32              = 151329
llama_model_loader: - kv  19:                tokenizer.ggml.eos_token_id u32              = 151329
llama_model_loader: - kv  20:                tokenizer.ggml.eot_token_id u32              = 151336
llama_model_loader: - kv  21:            tokenizer.ggml.unknown_token_id u32              = 151329
llama_model_loader: - kv  22:               general.quantization_version u32              = 2
llama_model_loader: - type  f32:  121 tensors
llama_model_loader: - type q8_0:  162 tensors
print_info: file format = GGUF V3 (latest)
print_info: file type   = Q8_0
print_info: file size   = 9.30 GiB (8.50 BPW)

OS

Windows

GPU

AMD

CPU

AMD

Ollama version

0.12.10

Originally created by @yihuishou on GitHub (Nov 8, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/13013 Originally assigned to: @dhiltgen on GitHub. ### What is the issue? Access API 500 Error ### Relevant log output ```shell print_info: max token length = 1024 load_tensors: loading model tensors, this can take a while... (mmap = false) load_tensors: offloading 40 repeating layers to GPU load_tensors: offloading output layer to GPU load_tensors: offloaded 41/41 layers to GPU load_tensors: CUDA_Host model buffer size = 629.00 MiB load_tensors: CUDA0 model buffer size = 8897.23 MiB llama_init_from_model: model default pooling_type is [0], but [-1] was specified llama_context: constructing llama_context llama_context: n_seq_max = 1 llama_context: n_ctx = 4096 llama_context: n_ctx_per_seq = 4096 llama_context: n_batch = 512 llama_context: n_ubatch = 512 llama_context: causal_attn = 1 llama_context: flash_attn = disabled llama_context: kv_unified = false llama_context: freq_base = 5000000.0 llama_context: freq_scale = 1 llama_context: n_ctx_per_seq (4096) < n_ctx_train (131072) -- the full capacity of the model will not be utilized llama_context: CUDA_Host output buffer size = 0.59 MiB llama_kv_cache: CUDA0 KV buffer size = 160.00 MiB llama_kv_cache: size = 160.00 MiB ( 4096 cells, 40 layers, 1/1 seqs), K (f16): 80.00 MiB, V (f16): 80.00 MiB CUDA error: the resource allocation failed current device: 0, in function cublas_handle at C:/a/ollama/ollama/ml/backend/ggml/ggml/src\ggml-cuda/common.cuh:1027 cublasCreate_v2(&cublas_handles[device]) C:\a\ollama\ollama\ml\backend\ggml\ggml\src\ggml-cuda\ggml-cuda.cu:88: CUDA error time=2025-11-08T11:33:10.836+08:00 level=INFO source=server.go:1285 msg="waiting for server to become available" status="llm server error" time=2025-11-08T11:33:10.885+08:00 level=ERROR source=server.go:273 msg="llama runner terminated" error="exit status 0xc0000409" time=2025-11-08T11:33:11.086+08:00 level=INFO source=sched.go:453 msg="Load failed" model=i:\OllamaModels\.ollama\models\blobs\sha256-8e41022dfc218cd744c56beac04040243fd26f4e9f2026599345a9b348946a85 error="llama runner process has terminated: CUDA error" [GIN] 2025/11/08 - 11:33:11 | 500 | 7.9300584s | 127.0.0.1 | POST "/v1/chat/completions" time=2025-11-08T11:33:11.113+08:00 level=INFO source=server.go:400 msg="starting runner" cmd="C:\\Users\\EvilEnergySeaUrchin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 56786" time=2025-11-08T11:33:11.652+08:00 level=INFO source=cpu_windows.go:148 msg=packages count=1 time=2025-11-08T11:33:11.652+08:00 level=INFO source=cpu_windows.go:195 msg="" package=0 cores=12 efficiency=0 threads=24 llama_model_loader: loaded meta data with 23 key-value pairs and 283 tensors from i:\OllamaModels\.ollama\models\blobs\sha256-8e41022dfc218cd744c56beac04040243fd26f4e9f2026599345a9b348946a85 (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 = chatglm llama_model_loader: - kv 1: general.name str = codegeex4-all-9b llama_model_loader: - kv 2: chatglm.context_length u32 = 131072 llama_model_loader: - kv 3: chatglm.embedding_length u32 = 4096 llama_model_loader: - kv 4: chatglm.feed_forward_length u32 = 13696 llama_model_loader: - kv 5: chatglm.block_count u32 = 40 llama_model_loader: - kv 6: chatglm.attention.head_count u32 = 32 llama_model_loader: - kv 7: chatglm.attention.head_count_kv u32 = 2 llama_model_loader: - kv 8: chatglm.attention.layer_norm_rms_epsilon f32 = 0.000010 llama_model_loader: - kv 9: general.file_type u32 = 7 llama_model_loader: - kv 10: chatglm.rope.dimension_count u32 = 64 llama_model_loader: - kv 11: tokenizer.ggml.add_bos_token bool = false llama_model_loader: - kv 12: chatglm.rope.freq_base f32 = 5000000.000000 llama_model_loader: - kv 13: tokenizer.ggml.model str = gpt2 llama_model_loader: - kv 14: tokenizer.ggml.pre str = chatglm-bpe llama_model_loader: - kv 15: tokenizer.ggml.tokens arr[str,151552] = ["!", "\"", "#", "$", "%", "&", "'", ... llama_model_loader: - kv 16: tokenizer.ggml.token_type arr[i32,151552] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... llama_model_loader: - kv 17: tokenizer.ggml.merges arr[str,151073] = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",... llama_model_loader: - kv 18: tokenizer.ggml.padding_token_id u32 = 151329 llama_model_loader: - kv 19: tokenizer.ggml.eos_token_id u32 = 151329 llama_model_loader: - kv 20: tokenizer.ggml.eot_token_id u32 = 151336 llama_model_loader: - kv 21: tokenizer.ggml.unknown_token_id u32 = 151329 llama_model_loader: - kv 22: general.quantization_version u32 = 2 llama_model_loader: - type f32: 121 tensors llama_model_loader: - type q8_0: 162 tensors print_info: max token length = 1024 load_tensors: loading model tensors, this can take a while... (mmap = false) load_tensors: offloading 40 repeating layers to GPU load_tensors: offloading output layer to GPU load_tensors: offloaded 41/41 layers to GPU load_tensors: CUDA_Host model buffer size = 629.00 MiB load_tensors: CUDA0 model buffer size = 8897.23 MiB llama_init_from_model: model default pooling_type is [0], but [-1] was specified llama_context: constructing llama_context llama_context: n_seq_max = 1 llama_context: n_ctx = 4096 llama_context: n_ctx_per_seq = 4096 llama_context: n_batch = 512 llama_context: n_ubatch = 512 llama_context: causal_attn = 1 llama_context: flash_attn = disabled llama_context: kv_unified = false llama_context: freq_base = 5000000.0 llama_context: freq_scale = 1 llama_context: n_ctx_per_seq (4096) < n_ctx_train (131072) -- the full capacity of the model will not be utilized llama_context: CUDA_Host output buffer size = 0.59 MiB llama_kv_cache: CUDA0 KV buffer size = 160.00 MiB llama_kv_cache: size = 160.00 MiB ( 4096 cells, 40 layers, 1/1 seqs), K (f16): 80.00 MiB, V (f16): 80.00 MiB CUDA error: the resource allocation failed current device: 0, in function cublas_handle at C:/a/ollama/ollama/ml/backend/ggml/ggml/src\ggml-cuda/common.cuh:1027 cublasCreate_v2(&cublas_handles[device]) C:\a\ollama\ollama\ml\backend\ggml\ggml\src\ggml-cuda\ggml-cuda.cu:88: CUDA error time=2025-11-08T11:33:30.373+08:00 level=INFO source=server.go:1285 msg="waiting for server to become available" status="llm server error" time=2025-11-08T11:33:30.417+08:00 level=ERROR source=server.go:273 msg="llama runner terminated" error="exit status 0xc0000409" time=2025-11-08T11:33:30.623+08:00 level=INFO source=sched.go:453 msg="Load failed" model=i:\OllamaModels\.ollama\models\blobs\sha256-8e41022dfc218cd744c56beac04040243fd26f4e9f2026599345a9b348946a85 error="llama runner process has terminated: CUDA error" [GIN] 2025/11/08 - 11:33:30 | 500 | 2.9328621s | 127.0.0.1 | POST "/v1/chat/completions" [GIN] 2025/11/08 - 11:33:50 | 204 | 0s | ::1 | OPTIONS "/v1/chat/completions" time=2025-11-08T11:33:50.856+08:00 level=INFO source=server.go:400 msg="starting runner" cmd="C:\\Users\\EvilEnergySeaUrchin\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 56859" time=2025-11-08T11:33:51.372+08:00 level=INFO source=cpu_windows.go:148 msg=packages count=1 time=2025-11-08T11:33:51.373+08:00 level=INFO source=cpu_windows.go:195 msg="" package=0 cores=12 efficiency=0 threads=24 llama_model_loader: loaded meta data with 23 key-value pairs and 283 tensors from i:\OllamaModels\.ollama\models\blobs\sha256-8e41022dfc218cd744c56beac04040243fd26f4e9f2026599345a9b348946a85 (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 = chatglm llama_model_loader: - kv 1: general.name str = codegeex4-all-9b llama_model_loader: - kv 2: chatglm.context_length u32 = 131072 llama_model_loader: - kv 3: chatglm.embedding_length u32 = 4096 llama_model_loader: - kv 4: chatglm.feed_forward_length u32 = 13696 llama_model_loader: - kv 5: chatglm.block_count u32 = 40 llama_model_loader: - kv 6: chatglm.attention.head_count u32 = 32 llama_model_loader: - kv 7: chatglm.attention.head_count_kv u32 = 2 llama_model_loader: - kv 8: chatglm.attention.layer_norm_rms_epsilon f32 = 0.000010 llama_model_loader: - kv 9: general.file_type u32 = 7 llama_model_loader: - kv 10: chatglm.rope.dimension_count u32 = 64 llama_model_loader: - kv 11: tokenizer.ggml.add_bos_token bool = false llama_model_loader: - kv 12: chatglm.rope.freq_base f32 = 5000000.000000 llama_model_loader: - kv 13: tokenizer.ggml.model str = gpt2 llama_model_loader: - kv 14: tokenizer.ggml.pre str = chatglm-bpe llama_model_loader: - kv 15: tokenizer.ggml.tokens arr[str,151552] = ["!", "\"", "#", "$", "%", "&", "'", ... llama_model_loader: - kv 16: tokenizer.ggml.token_type arr[i32,151552] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... llama_model_loader: - kv 17: tokenizer.ggml.merges arr[str,151073] = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",... llama_model_loader: - kv 18: tokenizer.ggml.padding_token_id u32 = 151329 llama_model_loader: - kv 19: tokenizer.ggml.eos_token_id u32 = 151329 llama_model_loader: - kv 20: tokenizer.ggml.eot_token_id u32 = 151336 llama_model_loader: - kv 21: tokenizer.ggml.unknown_token_id u32 = 151329 llama_model_loader: - kv 22: general.quantization_version u32 = 2 llama_model_loader: - type f32: 121 tensors llama_model_loader: - type q8_0: 162 tensors print_info: file format = GGUF V3 (latest) print_info: file type = Q8_0 print_info: file size = 9.30 GiB (8.50 BPW) ``` ### OS Windows ### GPU AMD ### CPU AMD ### Ollama version 0.12.10
GiteaMirror added the feature requestamdwindows labels 2026-04-12 21:21:10 -05:00
GiteaMirror commented 2026-04-12 21:21:14 -05:00
Author
Owner
Copy Link

@jessegross commented on GitHub (Nov 14, 2025):

Can you please post the full log? The error message isn't very good but usually this indicates a mismatch between the CUDA library and the hardware.

<!-- gh-comment-id:3534826712 --> @jessegross commented on GitHub (Nov 14, 2025): Can you please post the full log? The error message isn't very good but usually this indicates a mismatch between the CUDA library and the hardware.
GiteaMirror commented 2026-04-12 21:21:15 -05:00
Author
Owner
Copy Link

@Oliver-Strange commented on GitHub (Nov 19, 2025):

Not op but this started happening to me after the most recent update. It seems it sees my GPU but does not respect the OLLAMA_VULKAN=1 environment variable I have created. I also tried with multiple sized models that had worked previously, even pulled updates for them but they all return a similar error.

Server log below:

time=2025-11-19T11:09:04.175-08:00 level=INFO source=routes.go:1544 msg="server config" env="map[CUDA_VISIBLE_DEVICES: GGML_VK_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:4096 OLLAMA_DEBUG:INFO OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://0.0.0.0:11434 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\\Mr Cat\\.ollama\\models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:1 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_REMOTES:[ollama.com] OLLAMA_SCHED_SPREAD:false OLLAMA_VULKAN:false ROCR_VISIBLE_DEVICES:]"
time=2025-11-19T11:09:04.190-08:00 level=INFO source=images.go:522 msg="total blobs: 70"
time=2025-11-19T11:09:04.193-08:00 level=INFO source=images.go:529 msg="total unused blobs removed: 0"
time=2025-11-19T11:09:04.196-08:00 level=INFO source=routes.go:1597 msg="Listening on [::]:11434 (version 0.12.11)"
time=2025-11-19T11:09:04.196-08:00 level=INFO source=runner.go:67 msg="discovering available GPUs..."
time=2025-11-19T11:09:04.206-08:00 level=INFO source=server.go:392 msg="starting runner" cmd="C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 52456"
time=2025-11-19T11:09:04.915-08:00 level=INFO source=server.go:392 msg="starting runner" cmd="C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 52461"
time=2025-11-19T11:09:05.063-08:00 level=INFO source=server.go:392 msg="starting runner" cmd="C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 52466"
time=2025-11-19T11:09:05.455-08:00 level=INFO source=runner.go:98 msg="experimental Vulkan support disabled.  To enable, set OLLAMA_VULKAN=1"
time=2025-11-19T11:09:05.457-08:00 level=INFO source=server.go:392 msg="starting runner" cmd="C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 52471"
time=2025-11-19T11:09:07.521-08:00 level=INFO source=types.go:42 msg="inference compute" id=GPU-00000000-0000-0000-0000-000000000000 filter_id="" library=CUDA compute=8.8 name=CUDA0 description="AMD Radeon RX 7800 XT [ZLUDA]" libdirs=ollama,cuda_v12 driver=12.2 pci_id=0000:2d:00.0 type=discrete total="16.0 GiB" available="15.8 GiB"
time=2025-11-19T11:09:07.521-08:00 level=INFO source=routes.go:1638 msg="entering low vram mode" "total vram"="16.0 GiB" threshold="20.0 GiB"
[GIN] 2025/11/19 - 11:09:07 | 200 |            0s |       127.0.0.1 | GET      "/api/version"
[GIN] 2025/11/19 - 11:09:07 | 200 |      4.7104ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2025/11/19 - 11:09:10 | 200 |      4.8953ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2025/11/19 - 11:09:18 | 200 |     14.0034ms |       127.0.0.1 | POST     "/api/show"
[GIN] 2025/11/19 - 11:09:18 | 200 |     13.6765ms |       127.0.0.1 | POST     "/api/show"
time=2025-11-19T11:09:18.690-08:00 level=INFO source=server.go:392 msg="starting runner" cmd="C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 54898"
time=2025-11-19T11:09:19.342-08:00 level=INFO source=cpu_windows.go:148 msg=packages count=1
time=2025-11-19T11:09:19.342-08:00 level=INFO source=cpu_windows.go:195 msg="" package=0 cores=8 efficiency=0 threads=16
llama_model_loader: loaded meta data with 36 key-value pairs and 197 tensors from C:\Users\Mr Cat\.ollama\models\blobs\sha256-b5374915da534cb93df39f03bd4f2cd5a0c533df0d5e21957dc9556c260be9eb (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              = phi3
llama_model_loader: - kv   1:                               general.type str              = model
llama_model_loader: - kv   2:                               general.name str              = Phi 3.5 Mini Instruct
llama_model_loader: - kv   3:                           general.finetune str              = instruct
llama_model_loader: - kv   4:                           general.basename str              = Phi-3.5
llama_model_loader: - kv   5:                         general.size_label str              = mini
llama_model_loader: - kv   6:                            general.license str              = mit
llama_model_loader: - kv   7:                       general.license.link str              = https://huggingface.co/microsoft/Phi-...
llama_model_loader: - kv   8:                               general.tags arr[str,3]       = ["nlp", "code", "text-generation"]
llama_model_loader: - kv   9:                          general.languages arr[str,1]       = ["multilingual"]
llama_model_loader: - kv  10:                        phi3.context_length u32              = 131072
llama_model_loader: - kv  11:  phi3.rope.scaling.original_context_length u32              = 4096
llama_model_loader: - kv  12:                      phi3.embedding_length u32              = 3072
llama_model_loader: - kv  13:                   phi3.feed_forward_length u32              = 8192
llama_model_loader: - kv  14:                           phi3.block_count u32              = 32
llama_model_loader: - kv  15:                  phi3.attention.head_count u32              = 32
llama_model_loader: - kv  16:               phi3.attention.head_count_kv u32              = 32
llama_model_loader: - kv  17:      phi3.attention.layer_norm_rms_epsilon f32              = 0.000010
llama_model_loader: - kv  18:                  phi3.rope.dimension_count u32              = 96
llama_model_loader: - kv  19:                        phi3.rope.freq_base f32              = 10000.000000
llama_model_loader: - kv  20:                          general.file_type u32              = 2
llama_model_loader: - kv  21:              phi3.attention.sliding_window u32              = 262144
llama_model_loader: - kv  22:              phi3.rope.scaling.attn_factor f32              = 1.190238
llama_model_loader: - kv  23:                       tokenizer.ggml.model str              = llama
llama_model_loader: - kv  24:                         tokenizer.ggml.pre str              = default
llama_model_loader: - kv  25:                      tokenizer.ggml.tokens arr[str,32064]   = ["<unk>", "<s>", "</s>", "<0x00>", "<...
llama_model_loader: - kv  26:                      tokenizer.ggml.scores arr[f32,32064]   = [-1000.000000, -1000.000000, -1000.00...
llama_model_loader: - kv  27:                  tokenizer.ggml.token_type arr[i32,32064]   = [3, 3, 4, 6, 6, 6, 6, 6, 6, 6, 6, 6, ...
llama_model_loader: - kv  28:                tokenizer.ggml.bos_token_id u32              = 1
llama_model_loader: - kv  29:                tokenizer.ggml.eos_token_id u32              = 32000
llama_model_loader: - kv  30:            tokenizer.ggml.unknown_token_id u32              = 0
llama_model_loader: - kv  31:            tokenizer.ggml.padding_token_id u32              = 32000
llama_model_loader: - kv  32:               tokenizer.ggml.add_bos_token bool             = false
llama_model_loader: - kv  33:               tokenizer.ggml.add_eos_token bool             = false
llama_model_loader: - kv  34:                    tokenizer.chat_template str              = {% for message in messages %}{% if me...
llama_model_loader: - kv  35:               general.quantization_version u32              = 2
llama_model_loader: - type  f32:   67 tensors
llama_model_loader: - type q4_0:  129 tensors
llama_model_loader: - type q6_K:    1 tensors
print_info: file format = GGUF V3 (latest)
print_info: file type   = Q4_0
print_info: file size   = 2.03 GiB (4.55 BPW) 
load: printing all EOG tokens:
load:   - 32000 ('<|endoftext|>')
load:   - 32007 ('<|end|>')
load: special tokens cache size = 14
load: token to piece cache size = 0.1685 MB
print_info: arch             = phi3
print_info: vocab_only       = 1
print_info: model type       = ?B
print_info: model params     = 3.82 B
print_info: general.name     = Phi 3.5 Mini Instruct
print_info: vocab type       = SPM
print_info: n_vocab          = 32064
print_info: n_merges         = 0
print_info: BOS token        = 1 '<s>'
print_info: EOS token        = 32000 '<|endoftext|>'
print_info: EOT token        = 32007 '<|end|>'
print_info: UNK token        = 0 '<unk>'
print_info: PAD token        = 32000 '<|endoftext|>'
print_info: LF token         = 13 '<0x0A>'
print_info: EOG token        = 32000 '<|endoftext|>'
print_info: EOG token        = 32007 '<|end|>'
print_info: max token length = 48
llama_model_load: vocab only - skipping tensors
time=2025-11-19T11:09:19.385-08:00 level=INFO source=server.go:392 msg="starting runner" cmd="C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --model C:\\Users\\Mr Cat\\.ollama\\models\\blobs\\sha256-b5374915da534cb93df39f03bd4f2cd5a0c533df0d5e21957dc9556c260be9eb --port 54903"
time=2025-11-19T11:09:19.388-08:00 level=INFO source=sched.go:443 msg="system memory" total="31.9 GiB" free="22.5 GiB" free_swap="20.6 GiB"
time=2025-11-19T11:09:19.388-08:00 level=INFO source=sched.go:450 msg="gpu memory" id=GPU-00000000-0000-0000-0000-000000000000 library=CUDA available="15.4 GiB" free="15.8 GiB" minimum="457.0 MiB" overhead="0 B"
time=2025-11-19T11:09:19.388-08:00 level=INFO source=server.go:459 msg="loading model" "model layers"=33 requested=-1
time=2025-11-19T11:09:19.389-08:00 level=INFO source=device.go:240 msg="model weights" device=CUDA0 size="2.0 GiB"
time=2025-11-19T11:09:19.389-08:00 level=INFO source=device.go:251 msg="kv cache" device=CUDA0 size="1.5 GiB"
time=2025-11-19T11:09:19.389-08:00 level=INFO source=device.go:262 msg="compute graph" device=CUDA0 size="256.0 MiB"
time=2025-11-19T11:09:19.389-08:00 level=INFO source=device.go:272 msg="total memory" size="3.7 GiB"
time=2025-11-19T11:09:19.420-08:00 level=INFO source=runner.go:963 msg="starting go runner"
load_backend: loaded CPU backend from C:\Users\Mr Cat\AppData\Local\Programs\Ollama\lib\ollama\ggml-cpu-haswell.dll
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: AMD Radeon RX 7800 XT [ZLUDA], compute capability 8.8, VMM: no, ID: GPU-00000000-0000-0000-0000-000000000000
load_backend: loaded CUDA backend from C:\Users\Mr Cat\AppData\Local\Programs\Ollama\lib\ollama\cuda_v12\ggml-cuda.dll
time=2025-11-19T11:09:19.566-08:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 CUDA.0.ARCHS=500,520,600,610,700,750,800,860,890,900,1200 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(clang)
time=2025-11-19T11:09:19.567-08:00 level=INFO source=runner.go:999 msg="Server listening on 127.0.0.1:54903"
time=2025-11-19T11:09:19.571-08:00 level=INFO source=runner.go:893 msg=load request="{Operation:commit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:false KvSize:4096 KvCacheType: NumThreads:8 GPULayers:33[ID:GPU-00000000-0000-0000-0000-000000000000 Layers:33(0..32)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
time=2025-11-19T11:09:19.571-08:00 level=INFO source=server.go:1294 msg="waiting for llama runner to start responding"
time=2025-11-19T11:09:19.572-08:00 level=INFO source=server.go:1328 msg="waiting for server to become available" status="llm server loading model"
llama_model_load_from_file_impl: using device CUDA0 (AMD Radeon RX 7800 XT [ZLUDA]) (0000:2d:00.0) - 16223 MiB free
llama_model_loader: loaded meta data with 36 key-value pairs and 197 tensors from C:\Users\Mr Cat\.ollama\models\blobs\sha256-b5374915da534cb93df39f03bd4f2cd5a0c533df0d5e21957dc9556c260be9eb (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              = phi3
llama_model_loader: - kv   1:                               general.type str              = model
llama_model_loader: - kv   2:                               general.name str              = Phi 3.5 Mini Instruct
llama_model_loader: - kv   3:                           general.finetune str              = instruct
llama_model_loader: - kv   4:                           general.basename str              = Phi-3.5
llama_model_loader: - kv   5:                         general.size_label str              = mini
llama_model_loader: - kv   6:                            general.license str              = mit
llama_model_loader: - kv   7:                       general.license.link str              = https://huggingface.co/microsoft/Phi-...
llama_model_loader: - kv   8:                               general.tags arr[str,3]       = ["nlp", "code", "text-generation"]
llama_model_loader: - kv   9:                          general.languages arr[str,1]       = ["multilingual"]
llama_model_loader: - kv  10:                        phi3.context_length u32              = 131072
llama_model_loader: - kv  11:  phi3.rope.scaling.original_context_length u32              = 4096
llama_model_loader: - kv  12:                      phi3.embedding_length u32              = 3072
llama_model_loader: - kv  13:                   phi3.feed_forward_length u32              = 8192
llama_model_loader: - kv  14:                           phi3.block_count u32              = 32
llama_model_loader: - kv  15:                  phi3.attention.head_count u32              = 32
llama_model_loader: - kv  16:               phi3.attention.head_count_kv u32              = 32
llama_model_loader: - kv  17:      phi3.attention.layer_norm_rms_epsilon f32              = 0.000010
llama_model_loader: - kv  18:                  phi3.rope.dimension_count u32              = 96
llama_model_loader: - kv  19:                        phi3.rope.freq_base f32              = 10000.000000
llama_model_loader: - kv  20:                          general.file_type u32              = 2
llama_model_loader: - kv  21:              phi3.attention.sliding_window u32              = 262144
llama_model_loader: - kv  22:              phi3.rope.scaling.attn_factor f32              = 1.190238
llama_model_loader: - kv  23:                       tokenizer.ggml.model str              = llama
llama_model_loader: - kv  24:                         tokenizer.ggml.pre str              = default
llama_model_loader: - kv  25:                      tokenizer.ggml.tokens arr[str,32064]   = ["<unk>", "<s>", "</s>", "<0x00>", "<...
llama_model_loader: - kv  26:                      tokenizer.ggml.scores arr[f32,32064]   = [-1000.000000, -1000.000000, -1000.00...
llama_model_loader: - kv  27:                  tokenizer.ggml.token_type arr[i32,32064]   = [3, 3, 4, 6, 6, 6, 6, 6, 6, 6, 6, 6, ...
llama_model_loader: - kv  28:                tokenizer.ggml.bos_token_id u32              = 1
llama_model_loader: - kv  29:                tokenizer.ggml.eos_token_id u32              = 32000
llama_model_loader: - kv  30:            tokenizer.ggml.unknown_token_id u32              = 0
llama_model_loader: - kv  31:            tokenizer.ggml.padding_token_id u32              = 32000
llama_model_loader: - kv  32:               tokenizer.ggml.add_bos_token bool             = false
llama_model_loader: - kv  33:               tokenizer.ggml.add_eos_token bool             = false
llama_model_loader: - kv  34:                    tokenizer.chat_template str              = {% for message in messages %}{% if me...
llama_model_loader: - kv  35:               general.quantization_version u32              = 2
llama_model_loader: - type  f32:   67 tensors
llama_model_loader: - type q4_0:  129 tensors
llama_model_loader: - type q6_K:    1 tensors
print_info: file format = GGUF V3 (latest)
print_info: file type   = Q4_0
print_info: file size   = 2.03 GiB (4.55 BPW) 
load_hparams: Phi SWA is currently disabled - results might be suboptimal for some models (see https://github.com/ggml-org/llama.cpp/pull/13676)
load: printing all EOG tokens:
load:   - 32000 ('<|endoftext|>')
load:   - 32007 ('<|end|>')
load: special tokens cache size = 14
load: token to piece cache size = 0.1685 MB
print_info: arch             = phi3
print_info: vocab_only       = 0
print_info: n_ctx_train      = 131072
print_info: n_embd           = 3072
print_info: n_layer          = 32
print_info: n_head           = 32
print_info: n_head_kv        = 32
print_info: n_rot            = 96
print_info: n_swa            = 0
print_info: is_swa_any       = 0
print_info: n_embd_head_k    = 96
print_info: n_embd_head_v    = 96
print_info: n_gqa            = 1
print_info: n_embd_k_gqa     = 3072
print_info: n_embd_v_gqa     = 3072
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: f_attn_scale     = 0.0e+00
print_info: n_ff             = 8192
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  = 10000.0
print_info: freq_scale_train = 1
print_info: n_ctx_orig_yarn  = 4096
print_info: rope_finetuned   = unknown
print_info: model type       = 3B
print_info: model params     = 3.82 B
print_info: general.name     = Phi 3.5 Mini Instruct
print_info: vocab type       = SPM
print_info: n_vocab          = 32064
print_info: n_merges         = 0
print_info: BOS token        = 1 '<s>'
print_info: EOS token        = 32000 '<|endoftext|>'
print_info: EOT token        = 32007 '<|end|>'
print_info: UNK token        = 0 '<unk>'
print_info: PAD token        = 32000 '<|endoftext|>'
print_info: LF token         = 13 '<0x0A>'
print_info: EOG token        = 32000 '<|endoftext|>'
print_info: EOG token        = 32007 '<|end|>'
print_info: max token length = 48
load_tensors: loading model tensors, this can take a while... (mmap = false)
load_tensors: offloading 32 repeating layers to GPU
load_tensors: offloading output layer to GPU
load_tensors: offloaded 33/33 layers to GPU
load_tensors:        CUDA0 model buffer size =  2021.82 MiB
load_tensors:    CUDA_Host model buffer size =    52.84 MiB
llama_context: constructing llama_context
llama_context: n_seq_max     = 1
llama_context: n_ctx         = 4096
llama_context: n_ctx_per_seq = 4096
llama_context: n_batch       = 512
llama_context: n_ubatch      = 512
llama_context: causal_attn   = 1
llama_context: flash_attn    = disabled
llama_context: kv_unified    = false
llama_context: freq_base     = 10000.0
llama_context: freq_scale    = 1
llama_context: n_ctx_per_seq (4096) < n_ctx_train (131072) -- the full capacity of the model will not be utilized
llama_context:  CUDA_Host  output buffer size =     0.13 MiB
llama_kv_cache:      CUDA0 KV buffer size =  1536.00 MiB
llama_kv_cache: size = 1536.00 MiB (  4096 cells,  32 layers,  1/1 seqs), K (f16):  768.00 MiB, V (f16):  768.00 MiB
CUDA error: the resource allocation failed
  current device: 0, in function cublas_handle at C:/a/ollama/ollama/ml/backend/ggml/ggml/src\ggml-cuda/common.cuh:1020
  cublasCreate_v2(&cublas_handles[device])
C:\a\ollama\ollama\ml\backend\ggml\ggml\src\ggml-cuda\ggml-cuda.cu:88: CUDA error
time=2025-11-19T11:09:20.824-08:00 level=INFO source=server.go:1328 msg="waiting for server to become available" status="llm server error"
time=2025-11-19T11:09:20.854-08:00 level=ERROR source=server.go:265 msg="llama runner terminated" error="exit status 0xc0000409"
time=2025-11-19T11:09:21.075-08:00 level=INFO source=sched.go:470 msg="Load failed" model="C:\\Users\\Mr Cat\\.ollama\\models\\blobs\\sha256-b5374915da534cb93df39f03bd4f2cd5a0c533df0d5e21957dc9556c260be9eb" error="llama runner process has terminated: CUDA error"
[GIN] 2025/11/19 - 11:09:21 | 500 |    2.4110663s |       127.0.0.1 | POST     "/api/chat"
[GIN] 2025/11/19 - 11:09:34 | 200 |      4.3007ms |  192.168.50.247 | GET      "/api/tags"
[GIN] 2025/11/19 - 11:09:34 | 200 |            0s |  192.168.50.247 | GET      "/api/ps"
[GIN] 2025/11/19 - 11:09:40 | 200 |      4.8104ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2025/11/19 - 11:10:10 | 200 |      4.3141ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2025/11/19 - 11:10:40 | 200 |      5.7495ms |       127.0.0.1 | GET      "/api/tags"
<!-- gh-comment-id:3554251033 --> @Oliver-Strange commented on GitHub (Nov 19, 2025): Not op but this started happening to me after the most recent update. It seems it sees my GPU but does not respect the OLLAMA_VULKAN=1 environment variable I have created. I also tried with multiple sized models that had worked previously, even pulled updates for them but they all return a similar error. Server log below: ``` time=2025-11-19T11:09:04.175-08:00 level=INFO source=routes.go:1544 msg="server config" env="map[CUDA_VISIBLE_DEVICES: GGML_VK_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:4096 OLLAMA_DEBUG:INFO OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://0.0.0.0:11434 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\\Mr Cat\\.ollama\\models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:1 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_REMOTES:[ollama.com] OLLAMA_SCHED_SPREAD:false OLLAMA_VULKAN:false ROCR_VISIBLE_DEVICES:]" time=2025-11-19T11:09:04.190-08:00 level=INFO source=images.go:522 msg="total blobs: 70" time=2025-11-19T11:09:04.193-08:00 level=INFO source=images.go:529 msg="total unused blobs removed: 0" time=2025-11-19T11:09:04.196-08:00 level=INFO source=routes.go:1597 msg="Listening on [::]:11434 (version 0.12.11)" time=2025-11-19T11:09:04.196-08:00 level=INFO source=runner.go:67 msg="discovering available GPUs..." time=2025-11-19T11:09:04.206-08:00 level=INFO source=server.go:392 msg="starting runner" cmd="C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 52456" time=2025-11-19T11:09:04.915-08:00 level=INFO source=server.go:392 msg="starting runner" cmd="C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 52461" time=2025-11-19T11:09:05.063-08:00 level=INFO source=server.go:392 msg="starting runner" cmd="C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 52466" time=2025-11-19T11:09:05.455-08:00 level=INFO source=runner.go:98 msg="experimental Vulkan support disabled. To enable, set OLLAMA_VULKAN=1" time=2025-11-19T11:09:05.457-08:00 level=INFO source=server.go:392 msg="starting runner" cmd="C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 52471" time=2025-11-19T11:09:07.521-08:00 level=INFO source=types.go:42 msg="inference compute" id=GPU-00000000-0000-0000-0000-000000000000 filter_id="" library=CUDA compute=8.8 name=CUDA0 description="AMD Radeon RX 7800 XT [ZLUDA]" libdirs=ollama,cuda_v12 driver=12.2 pci_id=0000:2d:00.0 type=discrete total="16.0 GiB" available="15.8 GiB" time=2025-11-19T11:09:07.521-08:00 level=INFO source=routes.go:1638 msg="entering low vram mode" "total vram"="16.0 GiB" threshold="20.0 GiB" [GIN] 2025/11/19 - 11:09:07 | 200 | 0s | 127.0.0.1 | GET "/api/version" [GIN] 2025/11/19 - 11:09:07 | 200 | 4.7104ms | 127.0.0.1 | GET "/api/tags" [GIN] 2025/11/19 - 11:09:10 | 200 | 4.8953ms | 127.0.0.1 | GET "/api/tags" [GIN] 2025/11/19 - 11:09:18 | 200 | 14.0034ms | 127.0.0.1 | POST "/api/show" [GIN] 2025/11/19 - 11:09:18 | 200 | 13.6765ms | 127.0.0.1 | POST "/api/show" time=2025-11-19T11:09:18.690-08:00 level=INFO source=server.go:392 msg="starting runner" cmd="C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 54898" time=2025-11-19T11:09:19.342-08:00 level=INFO source=cpu_windows.go:148 msg=packages count=1 time=2025-11-19T11:09:19.342-08:00 level=INFO source=cpu_windows.go:195 msg="" package=0 cores=8 efficiency=0 threads=16 llama_model_loader: loaded meta data with 36 key-value pairs and 197 tensors from C:\Users\Mr Cat\.ollama\models\blobs\sha256-b5374915da534cb93df39f03bd4f2cd5a0c533df0d5e21957dc9556c260be9eb (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 = phi3 llama_model_loader: - kv 1: general.type str = model llama_model_loader: - kv 2: general.name str = Phi 3.5 Mini Instruct llama_model_loader: - kv 3: general.finetune str = instruct llama_model_loader: - kv 4: general.basename str = Phi-3.5 llama_model_loader: - kv 5: general.size_label str = mini llama_model_loader: - kv 6: general.license str = mit llama_model_loader: - kv 7: general.license.link str = https://huggingface.co/microsoft/Phi-... llama_model_loader: - kv 8: general.tags arr[str,3] = ["nlp", "code", "text-generation"] llama_model_loader: - kv 9: general.languages arr[str,1] = ["multilingual"] llama_model_loader: - kv 10: phi3.context_length u32 = 131072 llama_model_loader: - kv 11: phi3.rope.scaling.original_context_length u32 = 4096 llama_model_loader: - kv 12: phi3.embedding_length u32 = 3072 llama_model_loader: - kv 13: phi3.feed_forward_length u32 = 8192 llama_model_loader: - kv 14: phi3.block_count u32 = 32 llama_model_loader: - kv 15: phi3.attention.head_count u32 = 32 llama_model_loader: - kv 16: phi3.attention.head_count_kv u32 = 32 llama_model_loader: - kv 17: phi3.attention.layer_norm_rms_epsilon f32 = 0.000010 llama_model_loader: - kv 18: phi3.rope.dimension_count u32 = 96 llama_model_loader: - kv 19: phi3.rope.freq_base f32 = 10000.000000 llama_model_loader: - kv 20: general.file_type u32 = 2 llama_model_loader: - kv 21: phi3.attention.sliding_window u32 = 262144 llama_model_loader: - kv 22: phi3.rope.scaling.attn_factor f32 = 1.190238 llama_model_loader: - kv 23: tokenizer.ggml.model str = llama llama_model_loader: - kv 24: tokenizer.ggml.pre str = default llama_model_loader: - kv 25: tokenizer.ggml.tokens arr[str,32064] = ["<unk>", "<s>", "</s>", "<0x00>", "<... llama_model_loader: - kv 26: tokenizer.ggml.scores arr[f32,32064] = [-1000.000000, -1000.000000, -1000.00... llama_model_loader: - kv 27: tokenizer.ggml.token_type arr[i32,32064] = [3, 3, 4, 6, 6, 6, 6, 6, 6, 6, 6, 6, ... llama_model_loader: - kv 28: tokenizer.ggml.bos_token_id u32 = 1 llama_model_loader: - kv 29: tokenizer.ggml.eos_token_id u32 = 32000 llama_model_loader: - kv 30: tokenizer.ggml.unknown_token_id u32 = 0 llama_model_loader: - kv 31: tokenizer.ggml.padding_token_id u32 = 32000 llama_model_loader: - kv 32: tokenizer.ggml.add_bos_token bool = false llama_model_loader: - kv 33: tokenizer.ggml.add_eos_token bool = false llama_model_loader: - kv 34: tokenizer.chat_template str = {% for message in messages %}{% if me... llama_model_loader: - kv 35: general.quantization_version u32 = 2 llama_model_loader: - type f32: 67 tensors llama_model_loader: - type q4_0: 129 tensors llama_model_loader: - type q6_K: 1 tensors print_info: file format = GGUF V3 (latest) print_info: file type = Q4_0 print_info: file size = 2.03 GiB (4.55 BPW) load: printing all EOG tokens: load: - 32000 ('<|endoftext|>') load: - 32007 ('<|end|>') load: special tokens cache size = 14 load: token to piece cache size = 0.1685 MB print_info: arch = phi3 print_info: vocab_only = 1 print_info: model type = ?B print_info: model params = 3.82 B print_info: general.name = Phi 3.5 Mini Instruct print_info: vocab type = SPM print_info: n_vocab = 32064 print_info: n_merges = 0 print_info: BOS token = 1 '<s>' print_info: EOS token = 32000 '<|endoftext|>' print_info: EOT token = 32007 '<|end|>' print_info: UNK token = 0 '<unk>' print_info: PAD token = 32000 '<|endoftext|>' print_info: LF token = 13 '<0x0A>' print_info: EOG token = 32000 '<|endoftext|>' print_info: EOG token = 32007 '<|end|>' print_info: max token length = 48 llama_model_load: vocab only - skipping tensors time=2025-11-19T11:09:19.385-08:00 level=INFO source=server.go:392 msg="starting runner" cmd="C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --model C:\\Users\\Mr Cat\\.ollama\\models\\blobs\\sha256-b5374915da534cb93df39f03bd4f2cd5a0c533df0d5e21957dc9556c260be9eb --port 54903" time=2025-11-19T11:09:19.388-08:00 level=INFO source=sched.go:443 msg="system memory" total="31.9 GiB" free="22.5 GiB" free_swap="20.6 GiB" time=2025-11-19T11:09:19.388-08:00 level=INFO source=sched.go:450 msg="gpu memory" id=GPU-00000000-0000-0000-0000-000000000000 library=CUDA available="15.4 GiB" free="15.8 GiB" minimum="457.0 MiB" overhead="0 B" time=2025-11-19T11:09:19.388-08:00 level=INFO source=server.go:459 msg="loading model" "model layers"=33 requested=-1 time=2025-11-19T11:09:19.389-08:00 level=INFO source=device.go:240 msg="model weights" device=CUDA0 size="2.0 GiB" time=2025-11-19T11:09:19.389-08:00 level=INFO source=device.go:251 msg="kv cache" device=CUDA0 size="1.5 GiB" time=2025-11-19T11:09:19.389-08:00 level=INFO source=device.go:262 msg="compute graph" device=CUDA0 size="256.0 MiB" time=2025-11-19T11:09:19.389-08:00 level=INFO source=device.go:272 msg="total memory" size="3.7 GiB" time=2025-11-19T11:09:19.420-08:00 level=INFO source=runner.go:963 msg="starting go runner" load_backend: loaded CPU backend from C:\Users\Mr Cat\AppData\Local\Programs\Ollama\lib\ollama\ggml-cpu-haswell.dll 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: AMD Radeon RX 7800 XT [ZLUDA], compute capability 8.8, VMM: no, ID: GPU-00000000-0000-0000-0000-000000000000 load_backend: loaded CUDA backend from C:\Users\Mr Cat\AppData\Local\Programs\Ollama\lib\ollama\cuda_v12\ggml-cuda.dll time=2025-11-19T11:09:19.566-08:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 CUDA.0.ARCHS=500,520,600,610,700,750,800,860,890,900,1200 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(clang) time=2025-11-19T11:09:19.567-08:00 level=INFO source=runner.go:999 msg="Server listening on 127.0.0.1:54903" time=2025-11-19T11:09:19.571-08:00 level=INFO source=runner.go:893 msg=load request="{Operation:commit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:false KvSize:4096 KvCacheType: NumThreads:8 GPULayers:33[ID:GPU-00000000-0000-0000-0000-000000000000 Layers:33(0..32)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" time=2025-11-19T11:09:19.571-08:00 level=INFO source=server.go:1294 msg="waiting for llama runner to start responding" time=2025-11-19T11:09:19.572-08:00 level=INFO source=server.go:1328 msg="waiting for server to become available" status="llm server loading model" llama_model_load_from_file_impl: using device CUDA0 (AMD Radeon RX 7800 XT [ZLUDA]) (0000:2d:00.0) - 16223 MiB free llama_model_loader: loaded meta data with 36 key-value pairs and 197 tensors from C:\Users\Mr Cat\.ollama\models\blobs\sha256-b5374915da534cb93df39f03bd4f2cd5a0c533df0d5e21957dc9556c260be9eb (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 = phi3 llama_model_loader: - kv 1: general.type str = model llama_model_loader: - kv 2: general.name str = Phi 3.5 Mini Instruct llama_model_loader: - kv 3: general.finetune str = instruct llama_model_loader: - kv 4: general.basename str = Phi-3.5 llama_model_loader: - kv 5: general.size_label str = mini llama_model_loader: - kv 6: general.license str = mit llama_model_loader: - kv 7: general.license.link str = https://huggingface.co/microsoft/Phi-... llama_model_loader: - kv 8: general.tags arr[str,3] = ["nlp", "code", "text-generation"] llama_model_loader: - kv 9: general.languages arr[str,1] = ["multilingual"] llama_model_loader: - kv 10: phi3.context_length u32 = 131072 llama_model_loader: - kv 11: phi3.rope.scaling.original_context_length u32 = 4096 llama_model_loader: - kv 12: phi3.embedding_length u32 = 3072 llama_model_loader: - kv 13: phi3.feed_forward_length u32 = 8192 llama_model_loader: - kv 14: phi3.block_count u32 = 32 llama_model_loader: - kv 15: phi3.attention.head_count u32 = 32 llama_model_loader: - kv 16: phi3.attention.head_count_kv u32 = 32 llama_model_loader: - kv 17: phi3.attention.layer_norm_rms_epsilon f32 = 0.000010 llama_model_loader: - kv 18: phi3.rope.dimension_count u32 = 96 llama_model_loader: - kv 19: phi3.rope.freq_base f32 = 10000.000000 llama_model_loader: - kv 20: general.file_type u32 = 2 llama_model_loader: - kv 21: phi3.attention.sliding_window u32 = 262144 llama_model_loader: - kv 22: phi3.rope.scaling.attn_factor f32 = 1.190238 llama_model_loader: - kv 23: tokenizer.ggml.model str = llama llama_model_loader: - kv 24: tokenizer.ggml.pre str = default llama_model_loader: - kv 25: tokenizer.ggml.tokens arr[str,32064] = ["<unk>", "<s>", "</s>", "<0x00>", "<... llama_model_loader: - kv 26: tokenizer.ggml.scores arr[f32,32064] = [-1000.000000, -1000.000000, -1000.00... llama_model_loader: - kv 27: tokenizer.ggml.token_type arr[i32,32064] = [3, 3, 4, 6, 6, 6, 6, 6, 6, 6, 6, 6, ... llama_model_loader: - kv 28: tokenizer.ggml.bos_token_id u32 = 1 llama_model_loader: - kv 29: tokenizer.ggml.eos_token_id u32 = 32000 llama_model_loader: - kv 30: tokenizer.ggml.unknown_token_id u32 = 0 llama_model_loader: - kv 31: tokenizer.ggml.padding_token_id u32 = 32000 llama_model_loader: - kv 32: tokenizer.ggml.add_bos_token bool = false llama_model_loader: - kv 33: tokenizer.ggml.add_eos_token bool = false llama_model_loader: - kv 34: tokenizer.chat_template str = {% for message in messages %}{% if me... llama_model_loader: - kv 35: general.quantization_version u32 = 2 llama_model_loader: - type f32: 67 tensors llama_model_loader: - type q4_0: 129 tensors llama_model_loader: - type q6_K: 1 tensors print_info: file format = GGUF V3 (latest) print_info: file type = Q4_0 print_info: file size = 2.03 GiB (4.55 BPW) load_hparams: Phi SWA is currently disabled - results might be suboptimal for some models (see https://github.com/ggml-org/llama.cpp/pull/13676) load: printing all EOG tokens: load: - 32000 ('<|endoftext|>') load: - 32007 ('<|end|>') load: special tokens cache size = 14 load: token to piece cache size = 0.1685 MB print_info: arch = phi3 print_info: vocab_only = 0 print_info: n_ctx_train = 131072 print_info: n_embd = 3072 print_info: n_layer = 32 print_info: n_head = 32 print_info: n_head_kv = 32 print_info: n_rot = 96 print_info: n_swa = 0 print_info: is_swa_any = 0 print_info: n_embd_head_k = 96 print_info: n_embd_head_v = 96 print_info: n_gqa = 1 print_info: n_embd_k_gqa = 3072 print_info: n_embd_v_gqa = 3072 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: f_attn_scale = 0.0e+00 print_info: n_ff = 8192 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 = 10000.0 print_info: freq_scale_train = 1 print_info: n_ctx_orig_yarn = 4096 print_info: rope_finetuned = unknown print_info: model type = 3B print_info: model params = 3.82 B print_info: general.name = Phi 3.5 Mini Instruct print_info: vocab type = SPM print_info: n_vocab = 32064 print_info: n_merges = 0 print_info: BOS token = 1 '<s>' print_info: EOS token = 32000 '<|endoftext|>' print_info: EOT token = 32007 '<|end|>' print_info: UNK token = 0 '<unk>' print_info: PAD token = 32000 '<|endoftext|>' print_info: LF token = 13 '<0x0A>' print_info: EOG token = 32000 '<|endoftext|>' print_info: EOG token = 32007 '<|end|>' print_info: max token length = 48 load_tensors: loading model tensors, this can take a while... (mmap = false) load_tensors: offloading 32 repeating layers to GPU load_tensors: offloading output layer to GPU load_tensors: offloaded 33/33 layers to GPU load_tensors: CUDA0 model buffer size = 2021.82 MiB load_tensors: CUDA_Host model buffer size = 52.84 MiB llama_context: constructing llama_context llama_context: n_seq_max = 1 llama_context: n_ctx = 4096 llama_context: n_ctx_per_seq = 4096 llama_context: n_batch = 512 llama_context: n_ubatch = 512 llama_context: causal_attn = 1 llama_context: flash_attn = disabled llama_context: kv_unified = false llama_context: freq_base = 10000.0 llama_context: freq_scale = 1 llama_context: n_ctx_per_seq (4096) < n_ctx_train (131072) -- the full capacity of the model will not be utilized llama_context: CUDA_Host output buffer size = 0.13 MiB llama_kv_cache: CUDA0 KV buffer size = 1536.00 MiB llama_kv_cache: size = 1536.00 MiB ( 4096 cells, 32 layers, 1/1 seqs), K (f16): 768.00 MiB, V (f16): 768.00 MiB CUDA error: the resource allocation failed current device: 0, in function cublas_handle at C:/a/ollama/ollama/ml/backend/ggml/ggml/src\ggml-cuda/common.cuh:1020 cublasCreate_v2(&cublas_handles[device]) C:\a\ollama\ollama\ml\backend\ggml\ggml\src\ggml-cuda\ggml-cuda.cu:88: CUDA error time=2025-11-19T11:09:20.824-08:00 level=INFO source=server.go:1328 msg="waiting for server to become available" status="llm server error" time=2025-11-19T11:09:20.854-08:00 level=ERROR source=server.go:265 msg="llama runner terminated" error="exit status 0xc0000409" time=2025-11-19T11:09:21.075-08:00 level=INFO source=sched.go:470 msg="Load failed" model="C:\\Users\\Mr Cat\\.ollama\\models\\blobs\\sha256-b5374915da534cb93df39f03bd4f2cd5a0c533df0d5e21957dc9556c260be9eb" error="llama runner process has terminated: CUDA error" [GIN] 2025/11/19 - 11:09:21 | 500 | 2.4110663s | 127.0.0.1 | POST "/api/chat" [GIN] 2025/11/19 - 11:09:34 | 200 | 4.3007ms | 192.168.50.247 | GET "/api/tags" [GIN] 2025/11/19 - 11:09:34 | 200 | 0s | 192.168.50.247 | GET "/api/ps" [GIN] 2025/11/19 - 11:09:40 | 200 | 4.8104ms | 127.0.0.1 | GET "/api/tags" [GIN] 2025/11/19 - 11:10:10 | 200 | 4.3141ms | 127.0.0.1 | GET "/api/tags" [GIN] 2025/11/19 - 11:10:40 | 200 | 5.7495ms | 127.0.0.1 | GET "/api/tags" ```
GiteaMirror commented 2026-04-12 21:21:15 -05:00
Author
Owner
Copy Link

@jessegross commented on GitHub (Nov 20, 2025):

It looks like in both of these cases in looks like CUDA libraries are being chosen to run with an AMD GPU, rather than ROCm. That type of mismatch is typically what causes those cublasCreate_v2 errors.

re: Vulkan, we prefer to use CUDA or ROCm backends over Vulkan if possible as they are typically faster. The environment variable just enables the possibility of using Vulkan, not forces it.

<!-- gh-comment-id:3555240093 --> @jessegross commented on GitHub (Nov 20, 2025): It looks like in both of these cases in looks like CUDA libraries are being chosen to run with an AMD GPU, rather than ROCm. That type of mismatch is typically what causes those `cublasCreate_v2` errors. re: Vulkan, we prefer to use CUDA or ROCm backends over Vulkan if possible as they are typically faster. The environment variable just enables the possibility of using Vulkan, not forces it.
GiteaMirror commented 2026-04-12 21:21:16 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Nov 20, 2025):

That's an odd one. I haven't seen the CUDA libraries enumerate AMD GPUs. @Oliver-Strange have you set anything up on your system with HIP/ROCm to try to make your GPU work for unmodified CUDA apps?

Can you share a startup log with OLLAMA_DEBUG=2 set so we can see more details on why the CUDA libraries are enumerating your AMD GPU?

<!-- gh-comment-id:3559062431 --> @dhiltgen commented on GitHub (Nov 20, 2025): That's an odd one. I haven't seen the CUDA libraries enumerate AMD GPUs. @Oliver-Strange have you set anything up on your system with HIP/ROCm to try to make your GPU work for unmodified CUDA apps? Can you share a startup log with OLLAMA_DEBUG=2 set so we can see more details on why the CUDA libraries are enumerating your AMD GPU?
GiteaMirror commented 2026-04-12 21:21:16 -05:00
Author
Owner
Copy Link

@Oliver-Strange commented on GitHub (Nov 20, 2025):

@dhiltgen I recently set up Automatic1111 and that took a bit of configuring, but Ollama had been working at the same time.
Looking through the logs, is it normal for the GPU ID to come up as all zeros?

Debug 2:

time=2025-11-20T09:49:57.602-08:00 level=INFO source=routes.go:1544 msg="server config" env="map[CUDA_VISIBLE_DEVICES: GGML_VK_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:4096 OLLAMA_DEBUG:DEBUG-4 OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://0.0.0.0:11434 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\Mr Cat\.ollama\models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:1 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_REMOTES:[ollama.com] OLLAMA_SCHED_SPREAD:false OLLAMA_VULKAN:false ROCR_VISIBLE_DEVICES:]"
time=2025-11-20T09:49:57.619-08:00 level=INFO source=images.go:522 msg="total blobs: 70"
time=2025-11-20T09:49:57.622-08:00 level=INFO source=images.go:529 msg="total unused blobs removed: 0"
time=2025-11-20T09:49:57.624-08:00 level=INFO source=routes.go:1597 msg="Listening on [::]:11434 (version 0.13.0)"
time=2025-11-20T09:49:57.624-08:00 level=DEBUG source=sched.go:120 msg="starting llm scheduler"
time=2025-11-20T09:49:57.625-08:00 level=INFO source=runner.go:67 msg="discovering available GPUs..."
time=2025-11-20T09:49:57.625-08:00 level=TRACE source=runner.go:425 msg="starting runner for device discovery" libDirs="[C:\Users\Mr Cat\AppData\Local\Programs\Ollama\lib\ollama C:\Users\Mr Cat\AppData\Local\Programs\Ollama\lib\ollama\cuda_v12]" extraEnvs=map[]
time=2025-11-20T09:49:57.636-08:00 level=INFO source=server.go:392 msg="starting runner" cmd="C:\Users\Mr Cat\AppData\Local\Programs\Ollama\ollama.exe runner --ollama-engine --port 59761"
time=2025-11-20T09:49:57.636-08:00 level=DEBUG source=server.go:393 msg=subprocess OLLAMA_DEBUG=2 PATH="C:\Users\Mr Cat\AppData\Local\Programs\Ollama\lib\ollama;C:\Users\Mr Cat\AppData\Local\Programs\Ollama\lib\ollama\cuda_v12;C:\Program Files (x86)\Common Files\Oracle\Java\java8path;C:\Program Files (x86)\Common Files\Oracle\Java\javapath;C:\Program Files (x86)\NVIDIA Corporation\PhysX\Common;C:\WINDOWS\system32;C:\WINDOWS;C:\WINDOWS\System32\Wbem;C:\WINDOWS\System32\WindowsPowerShell\v1.0\;C:\WINDOWS\System32\OpenSSH\;C:\Program Files\nodejs\;C:\ProgramData\chocolatey\bin;C:\Program Files\Git\cmd;C:\Program Files\Docker\Docker\resources\bin;C:\ProgramData\DockerDesktop\version-bin;C:\Users\Mr Cat\AppData\Local\Programs\Python\Python39;C:\Users\Mr Cat\AppData\Local\Programs\Python\Python39\Scripts;C:\Program Files\dotnet\;C:\Program Files\PowerShell\7\;C:\Program Files\AMD\ROCm\6.4\bin;G:\Zulda\zluda;C:\Users\Mr Cat\AppData\Local\Programs\Python\Python310\Scripts\;C:\Users\Mr Cat\AppData\Local\Programs\Python\Python310\;C:\Users\Mr Cat\AppData\Local\Programs\Python\Python39\Scripts\;C:\Users\Mr Cat\AppData\Local\Programs\Python\Python39\;C:\Users\Mr Cat\AppData\Local\Microsoft\WindowsApps;C:\Users\Mr Cat\AppData\Local\Programs\Microsoft VS Code\bin;C:\Users\Mr Cat\AppData\Roaming\npm;C:\Program Files (x86)\GitHub CLI\;C:\Users\Mr Cat\AppData\Local\Programs\Python\Python39\Scripts;C:\Users\Mr Cat\AppData\Local\Programs\Python\Python39;;C:\Users\Mr Cat\AppData\Local\Programs\Ollama;C:\Users\Mr Cat\AppData\Local\Programs\Ollama\bin" HIP_PATH_64="C:\Program Files\AMD\ROCm\6.4\" HIP_PATH="C:\Program Files\AMD\ROCm\6.4\" OLLAMA_MODELS="C:\Users\Mr Cat\.ollama\models" OLLAMA_HOST=0.0.0.0 OLLAMA_CONTEXT_LENGTH=4096 OLLAMA_LIBRARY_PATH="C:\Users\Mr Cat\AppData\Local\Programs\Ollama\lib\ollama;C:\Users\Mr Cat\AppData\Local\Programs\Ollama\lib\ollama\cuda_v12"
time=2025-11-20T09:49:57.685-08:00 level=INFO source=runner.go:1398 msg="starting ollama engine"
time=2025-11-20T09:49:57.687-08:00 level=INFO source=runner.go:1433 msg="Server listening on 127.0.0.1:59761"
time=2025-11-20T09:49:57.694-08:00 level=DEBUG source=gguf.go:589 msg=general.architecture type=string
time=2025-11-20T09:49:57.694-08:00 level=DEBUG source=gguf.go:589 msg=tokenizer.ggml.model type=string
time=2025-11-20T09:49:57.694-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=general.alignment default=32
time=2025-11-20T09:49:57.695-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=general.alignment default=32
time=2025-11-20T09:49:57.695-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=general.file_type default=0
time=2025-11-20T09:49:57.695-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=general.name default=""
time=2025-11-20T09:49:57.695-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=general.description default=""
time=2025-11-20T09:49:57.695-08:00 level=INFO source=ggml.go:136 msg="" architecture=llama file_type=unknown name="" description="" num_tensors=0 num_key_values=3
time=2025-11-20T09:49:57.695-08:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path="C:\Users\Mr Cat\AppData\Local\Programs\Ollama\lib\ollama"
load_backend: loaded CPU backend from C:\Users\Mr Cat\AppData\Local\Programs\Ollama\lib\ollama\ggml-cpu-haswell.dll
time=2025-11-20T09:49:57.718-08:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path="C:\Users\Mr Cat\AppData\Local\Programs\Ollama\lib\ollama\cuda_v12"
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: AMD Radeon RX 7800 XT [ZLUDA], compute capability 8.8, VMM: no, ID: GPU-00000000-0000-0000-0000-000000000000
load_backend: loaded CUDA backend from C:\Users\Mr Cat\AppData\Local\Programs\Ollama\lib\ollama\cuda_v12\ggml-cuda.dll
time=2025-11-20T09:49:57.905-08:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 CUDA.0.ARCHS=500,520,600,610,700,750,800,860,890,900,1200 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(clang)
time=2025-11-20T09:49:57.905-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.block_count default=0
time=2025-11-20T09:49:57.905-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.pooling_type default=0
time=2025-11-20T09:49:57.905-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.expert_count default=0
time=2025-11-20T09:49:57.905-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.tokens default="&{size:0 values:[]}"
time=2025-11-20T09:49:57.905-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.scores default="&{size:0 values:[]}"
time=2025-11-20T09:49:57.905-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.token_type default="&{size:0 values:[]}"
time=2025-11-20T09:49:57.905-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.merges default="&{size:0 values:[]}"
time=2025-11-20T09:49:57.905-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.add_bos_token default=true
time=2025-11-20T09:49:57.905-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.bos_token_id default=0
time=2025-11-20T09:49:57.905-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.add_eos_token default=false
time=2025-11-20T09:49:57.905-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.eos_token_id default=0
time=2025-11-20T09:49:57.905-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.eos_token_ids default="&{size:0 values:[]}"
time=2025-11-20T09:49:57.905-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.pre default=""
time=2025-11-20T09:49:57.905-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.block_count default=0
time=2025-11-20T09:49:57.905-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.embedding_length default=0
time=2025-11-20T09:49:57.905-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.attention.head_count default=0
time=2025-11-20T09:49:57.905-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.attention.head_count_kv default=0
time=2025-11-20T09:49:57.905-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.attention.key_length default=0
time=2025-11-20T09:49:57.905-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.rope.dimension_count default=0
time=2025-11-20T09:49:57.905-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.attention.layer_norm_rms_epsilon default=0
time=2025-11-20T09:49:57.905-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.rope.freq_base default=100000
time=2025-11-20T09:49:57.905-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.rope.scaling.factor default=1
time=2025-11-20T09:49:57.906-08:00 level=DEBUG source=runner.go:1373 msg="dummy model load took" duration=212.0376ms
time=2025-11-20T09:49:58.416-08:00 level=DEBUG source=runner.go:1378 msg="gathering device infos took" duration=510.1119ms
time=2025-11-20T09:49:58.416-08:00 level=TRACE source=runner.go:452 msg="runner enumerated devices" OLLAMA_LIBRARY_PATH="[C:\Users\Mr Cat\AppData\Local\Programs\Ollama\lib\ollama C:\Users\Mr Cat\AppData\Local\Programs\Ollama\lib\ollama\cuda_v12]" devices="[{DeviceID:{ID:GPU-00000000-0000-0000-0000-000000000000 Library:CUDA} Name:CUDA0 Description:AMD Radeon RX 7800 XT [ZLUDA] FilterID: Integrated:false PCIID:0000:2d:00.0 TotalMemory:17163091968 FreeMemory:17011408896 ComputeMajor:8 ComputeMinor:8 DriverMajor:12 DriverMinor:2 LibraryPath:[C:\Users\Mr Cat\AppData\Local\Programs\Ollama\lib\ollama C:\Users\Mr Cat\AppData\Local\Programs\Ollama\lib\ollama\cuda_v12]}]"
time=2025-11-20T09:49:58.420-08:00 level=DEBUG source=runner.go:422 msg="bootstrap discovery took" duration=794.5992ms OLLAMA_LIBRARY_PATH="[C:\Users\Mr Cat\AppData\Local\Programs\Ollama\lib\ollama C:\Users\Mr Cat\AppData\Local\Programs\Ollama\lib\ollama\cuda_v12]" extra_envs=map[]
time=2025-11-20T09:49:58.420-08:00 level=TRACE source=runner.go:425 msg="starting runner for device discovery" libDirs="[C:\Users\Mr Cat\AppData\Local\Programs\Ollama\lib\ollama C:\Users\Mr Cat\AppData\Local\Programs\Ollama\lib\ollama\cuda_v13]" extraEnvs=map[]
time=2025-11-20T09:49:58.422-08:00 level=INFO source=server.go:392 msg="starting runner" cmd="C:\Users\Mr Cat\AppData\Local\Programs\Ollama\ollama.exe runner --ollama-engine --port 52427"
time=2025-11-20T09:49:58.422-08:00 level=DEBUG source=server.go:393 msg=subprocess OLLAMA_DEBUG=2 PATH="C:\Users\Mr Cat\AppData\Local\Programs\Ollama\lib\ollama;C:\Users\Mr Cat\AppData\Local\Programs\Ollama\lib\ollama\cuda_v13;C:\Program Files (x86)\Common Files\Oracle\Java\java8path;C:\Program Files (x86)\Common Files\Oracle\Java\javapath;C:\Program Files (x86)\NVIDIA Corporation\PhysX\Common;C:\WINDOWS\system32;C:\WINDOWS;C:\WINDOWS\System32\Wbem;C:\WINDOWS\System32\WindowsPowerShell\v1.0\;C:\WINDOWS\System32\OpenSSH\;C:\Program Files\nodejs\;C:\ProgramData\chocolatey\bin;C:\Program Files\Git\cmd;C:\Program Files\Docker\Docker\resources\bin;C:\ProgramData\DockerDesktop\version-bin;C:\Users\Mr Cat\AppData\Local\Programs\Python\Python39;C:\Users\Mr Cat\AppData\Local\Programs\Python\Python39\Scripts;C:\Program Files\dotnet\;C:\Program Files\PowerShell\7\;C:\Program Files\AMD\ROCm\6.4\bin;G:\Zulda\zluda;C:\Users\Mr Cat\AppData\Local\Programs\Python\Python310\Scripts\;C:\Users\Mr Cat\AppData\Local\Programs\Python\Python310\;C:\Users\Mr Cat\AppData\Local\Programs\Python\Python39\Scripts\;C:\Users\Mr Cat\AppData\Local\Programs\Python\Python39\;C:\Users\Mr Cat\AppData\Local\Microsoft\WindowsApps;C:\Users\Mr Cat\AppData\Local\Programs\Microsoft VS Code\bin;C:\Users\Mr Cat\AppData\Roaming\npm;C:\Program Files (x86)\GitHub CLI\;C:\Users\Mr Cat\AppData\Local\Programs\Python\Python39\Scripts;C:\Users\Mr Cat\AppData\Local\Programs\Python\Python39;;C:\Users\Mr Cat\AppData\Local\Programs\Ollama;C:\Users\Mr Cat\AppData\Local\Programs\Ollama\bin" HIP_PATH_64="C:\Program Files\AMD\ROCm\6.4\" HIP_PATH="C:\Program Files\AMD\ROCm\6.4\" OLLAMA_MODELS="C:\Users\Mr Cat\.ollama\models" OLLAMA_HOST=0.0.0.0 OLLAMA_CONTEXT_LENGTH=4096 OLLAMA_LIBRARY_PATH="C:\Users\Mr Cat\AppData\Local\Programs\Ollama\lib\ollama;C:\Users\Mr Cat\AppData\Local\Programs\Ollama\lib\ollama\cuda_v13"
time=2025-11-20T09:49:58.469-08:00 level=INFO source=runner.go:1398 msg="starting ollama engine"
time=2025-11-20T09:49:58.470-08:00 level=INFO source=runner.go:1433 msg="Server listening on 127.0.0.1:52427"
time=2025-11-20T09:49:58.479-08:00 level=DEBUG source=gguf.go:589 msg=general.architecture type=string
time=2025-11-20T09:49:58.479-08:00 level=DEBUG source=gguf.go:589 msg=tokenizer.ggml.model type=string
time=2025-11-20T09:49:58.479-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=general.alignment default=32
time=2025-11-20T09:49:58.480-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=general.alignment default=32
time=2025-11-20T09:49:58.480-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=general.file_type default=0
time=2025-11-20T09:49:58.480-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=general.name default=""
time=2025-11-20T09:49:58.480-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=general.description default=""
time=2025-11-20T09:49:58.480-08:00 level=INFO source=ggml.go:136 msg="" architecture=llama file_type=unknown name="" description="" num_tensors=0 num_key_values=3
time=2025-11-20T09:49:58.480-08:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path="C:\Users\Mr Cat\AppData\Local\Programs\Ollama\lib\ollama"
load_backend: loaded CPU backend from C:\Users\Mr Cat\AppData\Local\Programs\Ollama\lib\ollama\ggml-cpu-haswell.dll
time=2025-11-20T09:49:58.497-08:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path="C:\Users\Mr Cat\AppData\Local\Programs\Ollama\lib\ollama\cuda_v13"
ggml_cuda_init: failed to initialize CUDA: (null)
load_backend: loaded CUDA backend from C:\Users\Mr Cat\AppData\Local\Programs\Ollama\lib\ollama\cuda_v13\ggml-cuda.dll
time=2025-11-20T09:49:58.584-08:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 compiler=cgo(clang)
time=2025-11-20T09:49:58.584-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.block_count default=0
time=2025-11-20T09:49:58.585-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.pooling_type default=0
time=2025-11-20T09:49:58.585-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.expert_count default=0
time=2025-11-20T09:49:58.585-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.tokens default="&{size:0 values:[]}"
time=2025-11-20T09:49:58.585-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.scores default="&{size:0 values:[]}"
time=2025-11-20T09:49:58.585-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.token_type default="&{size:0 values:[]}"
time=2025-11-20T09:49:58.585-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.merges default="&{size:0 values:[]}"
time=2025-11-20T09:49:58.585-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.add_bos_token default=true
time=2025-11-20T09:49:58.585-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.bos_token_id default=0
time=2025-11-20T09:49:58.585-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.add_eos_token default=false
time=2025-11-20T09:49:58.585-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.eos_token_id default=0
time=2025-11-20T09:49:58.585-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.eos_token_ids default="&{size:0 values:[]}"
time=2025-11-20T09:49:58.585-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.pre default=""
time=2025-11-20T09:49:58.585-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.block_count default=0
time=2025-11-20T09:49:58.585-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.embedding_length default=0
time=2025-11-20T09:49:58.585-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.attention.head_count default=0
time=2025-11-20T09:49:58.585-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.attention.head_count_kv default=0
time=2025-11-20T09:49:58.585-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.attention.key_length default=0
time=2025-11-20T09:49:58.585-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.rope.dimension_count default=0
time=2025-11-20T09:49:58.585-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.attention.layer_norm_rms_epsilon default=0
time=2025-11-20T09:49:58.585-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.rope.freq_base default=100000
time=2025-11-20T09:49:58.585-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.rope.scaling.factor default=1
time=2025-11-20T09:49:58.585-08:00 level=DEBUG source=runner.go:1373 msg="dummy model load took" duration=106.3627ms
time=2025-11-20T09:49:58.585-08:00 level=DEBUG source=runner.go:1378 msg="gathering device infos took" duration=0s
time=2025-11-20T09:49:58.585-08:00 level=TRACE source=runner.go:452 msg="runner enumerated devices" OLLAMA_LIBRARY_PATH="[C:\Users\Mr Cat\AppData\Local\Programs\Ollama\lib\ollama C:\Users\Mr Cat\AppData\Local\Programs\Ollama\lib\ollama\cuda_v13]" devices=[]
time=2025-11-20T09:49:58.585-08:00 level=DEBUG source=runner.go:422 msg="bootstrap discovery took" duration=165.1534ms OLLAMA_LIBRARY_PATH="[C:\Users\Mr Cat\AppData\Local\Programs\Ollama\lib\ollama C:\Users\Mr Cat\AppData\Local\Programs\Ollama\lib\ollama\cuda_v13]" extra_envs=map[]
time=2025-11-20T09:49:58.585-08:00 level=TRACE source=runner.go:425 msg="starting runner for device discovery" libDirs="[C:\Users\Mr Cat\AppData\Local\Programs\Ollama\lib\ollama C:\Users\Mr Cat\AppData\Local\Programs\Ollama\lib\ollama\rocm]" extraEnvs=map[]
time=2025-11-20T09:49:58.586-08:00 level=INFO source=server.go:392 msg="starting runner" cmd="C:\Users\Mr Cat\AppData\Local\Programs\Ollama\ollama.exe runner --ollama-engine --port 63596"
time=2025-11-20T09:49:58.586-08:00 level=DEBUG source=server.go:393 msg=subprocess OLLAMA_DEBUG=2 PATH="C:\Users\Mr Cat\AppData\Local\Programs\Ollama\lib\ollama;C:\Users\Mr Cat\AppData\Local\Programs\Ollama\lib\ollama\rocm;C:\Program Files (x86)\Common Files\Oracle\Java\java8path;C:\Program Files (x86)\Common Files\Oracle\Java\javapath;C:\Program Files (x86)\NVIDIA Corporation\PhysX\Common;C:\WINDOWS\system32;C:\WINDOWS;C:\WINDOWS\System32\Wbem;C:\WINDOWS\System32\WindowsPowerShell\v1.0\;C:\WINDOWS\System32\OpenSSH\;C:\Program Files\nodejs\;C:\ProgramData\chocolatey\bin;C:\Program Files\Git\cmd;C:\Program Files\Docker\Docker\resources\bin;C:\ProgramData\DockerDesktop\version-bin;C:\Users\Mr Cat\AppData\Local\Programs\Python\Python39;C:\Users\Mr Cat\AppData\Local\Programs\Python\Python39\Scripts;C:\Program Files\dotnet\;C:\Program Files\PowerShell\7\;C:\Program Files\AMD\ROCm\6.4\bin;G:\Zulda\zluda;C:\Users\Mr Cat\AppData\Local\Programs\Python\Python310\Scripts\;C:\Users\Mr Cat\AppData\Local\Programs\Python\Python310\;C:\Users\Mr Cat\AppData\Local\Programs\Python\Python39\Scripts\;C:\Users\Mr Cat\AppData\Local\Programs\Python\Python39\;C:\Users\Mr Cat\AppData\Local\Microsoft\WindowsApps;C:\Users\Mr Cat\AppData\Local\Programs\Microsoft VS Code\bin;C:\Users\Mr Cat\AppData\Roaming\npm;C:\Program Files (x86)\GitHub CLI\;C:\Users\Mr Cat\AppData\Local\Programs\Python\Python39\Scripts;C:\Users\Mr Cat\AppData\Local\Programs\Python\Python39;;C:\Users\Mr Cat\AppData\Local\Programs\Ollama;C:\Users\Mr Cat\AppData\Local\Programs\Ollama\bin" HIP_PATH_64="C:\Program Files\AMD\ROCm\6.4\" HIP_PATH="C:\Program Files\AMD\ROCm\6.4\" OLLAMA_MODELS="C:\Users\Mr Cat\.ollama\models" OLLAMA_HOST=0.0.0.0 OLLAMA_CONTEXT_LENGTH=4096 OLLAMA_LIBRARY_PATH="C:\Users\Mr Cat\AppData\Local\Programs\Ollama\lib\ollama;C:\Users\Mr Cat\AppData\Local\Programs\Ollama\lib\ollama\rocm"
time=2025-11-20T09:49:58.624-08:00 level=INFO source=runner.go:1398 msg="starting ollama engine"
time=2025-11-20T09:49:58.626-08:00 level=INFO source=runner.go:1433 msg="Server listening on 127.0.0.1:63596"
time=2025-11-20T09:49:58.632-08:00 level=DEBUG source=gguf.go:589 msg=general.architecture type=string
time=2025-11-20T09:49:58.632-08:00 level=DEBUG source=gguf.go:589 msg=tokenizer.ggml.model type=string
time=2025-11-20T09:49:58.632-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=general.alignment default=32
time=2025-11-20T09:49:58.633-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=general.alignment default=32
time=2025-11-20T09:49:58.633-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=general.file_type default=0
time=2025-11-20T09:49:58.633-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=general.name default=""
time=2025-11-20T09:49:58.633-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=general.description default=""
time=2025-11-20T09:49:58.633-08:00 level=INFO source=ggml.go:136 msg="" architecture=llama file_type=unknown name="" description="" num_tensors=0 num_key_values=3
time=2025-11-20T09:49:58.633-08:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path="C:\Users\Mr Cat\AppData\Local\Programs\Ollama\lib\ollama"
load_backend: loaded CPU backend from C:\Users\Mr Cat\AppData\Local\Programs\Ollama\lib\ollama\ggml-cpu-haswell.dll
time=2025-11-20T09:49:58.648-08:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path="C:\Users\Mr Cat\AppData\Local\Programs\Ollama\lib\ollama\rocm"
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
Device 0: AMD Radeon RX 7800 XT, gfx1101 (0x1101), VMM: no, Wave Size: 32, ID: 0
load_backend: loaded ROCm backend from C:\Users\Mr Cat\AppData\Local\Programs\Ollama\lib\ollama\rocm\ggml-hip.dll
time=2025-11-20T09:49:58.693-08:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 ROCm.0.NO_VMM=1 ROCm.0.NO_PEER_COPY=1 ROCm.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(clang)
time=2025-11-20T09:49:58.693-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.block_count default=0
time=2025-11-20T09:49:58.693-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.pooling_type default=0
time=2025-11-20T09:49:58.693-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.expert_count default=0
time=2025-11-20T09:49:58.693-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.tokens default="&{size:0 values:[]}"
time=2025-11-20T09:49:58.693-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.scores default="&{size:0 values:[]}"
time=2025-11-20T09:49:58.693-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.token_type default="&{size:0 values:[]}"
time=2025-11-20T09:49:58.693-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.merges default="&{size:0 values:[]}"
time=2025-11-20T09:49:58.693-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.add_bos_token default=true
time=2025-11-20T09:49:58.693-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.bos_token_id default=0
time=2025-11-20T09:49:58.693-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.add_eos_token default=false
time=2025-11-20T09:49:58.693-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.eos_token_id default=0
time=2025-11-20T09:49:58.693-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.eos_token_ids default="&{size:0 values:[]}"
time=2025-11-20T09:49:58.693-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.pre default=""
time=2025-11-20T09:49:58.693-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.block_count default=0
time=2025-11-20T09:49:58.693-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.embedding_length default=0
time=2025-11-20T09:49:58.693-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.attention.head_count default=0
time=2025-11-20T09:49:58.693-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.attention.head_count_kv default=0
time=2025-11-20T09:49:58.693-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.attention.key_length default=0
time=2025-11-20T09:49:58.693-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.rope.dimension_count default=0
time=2025-11-20T09:49:58.693-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.attention.layer_norm_rms_epsilon default=0
time=2025-11-20T09:49:58.693-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.rope.freq_base default=100000
time=2025-11-20T09:49:58.693-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.rope.scaling.factor default=1
time=2025-11-20T09:49:58.693-08:00 level=DEBUG source=runner.go:1373 msg="dummy model load took" duration=61.2928ms
ggml_hip_mgmt_init located ADLX version 1.4
ggml_backend_cuda_device_get_memory device 0000:2d:00.0 utilizing AMD specific memory reporting free: 15287189504 total: 17163091968
time=2025-11-20T09:49:58.972-08:00 level=DEBUG source=runner.go:1378 msg="gathering device infos took" duration=278.6073ms
time=2025-11-20T09:49:58.972-08:00 level=TRACE source=runner.go:452 msg="runner enumerated devices" OLLAMA_LIBRARY_PATH="[C:\Users\Mr Cat\AppData\Local\Programs\Ollama\lib\ollama C:\Users\Mr Cat\AppData\Local\Programs\Ollama\lib\ollama\rocm]" devices="[{DeviceID:{ID:0 Library:ROCm} Name:ROCm0 Description:AMD Radeon RX 7800 XT FilterID: Integrated:false PCIID:0000:2d:00.0 TotalMemory:17163091968 FreeMemory:15287189504 ComputeMajor:17 ComputeMinor:1 DriverMajor:60450 DriverMinor:10 LibraryPath:[C:\Users\Mr Cat\AppData\Local\Programs\Ollama\lib\ollama C:\Users\Mr Cat\AppData\Local\Programs\Ollama\lib\ollama\rocm]}]"
time=2025-11-20T09:49:58.973-08:00 level=DEBUG source=runner.go:422 msg="bootstrap discovery took" duration=387.6438ms OLLAMA_LIBRARY_PATH="[C:\Users\Mr Cat\AppData\Local\Programs\Ollama\lib\ollama C:\Users\Mr Cat\AppData\Local\Programs\Ollama\lib\ollama\rocm]" extra_envs=map[]
time=2025-11-20T09:49:58.973-08:00 level=INFO source=runner.go:102 msg="experimental Vulkan support disabled. To enable, set OLLAMA_VULKAN=1"
time=2025-11-20T09:49:58.973-08:00 level=DEBUG source=runner.go:120 msg="evaluating which, if any, devices to filter out" initial_count=2
time=2025-11-20T09:49:58.973-08:00 level=DEBUG source=runner.go:132 msg="verifying if device is supported" library="C:\Users\Mr Cat\AppData\Local\Programs\Ollama\lib\ollama\rocm" description="AMD Radeon RX 7800 XT" compute=gfx1101 id=0 pci_id=0000:2d:00.0
time=2025-11-20T09:49:58.973-08:00 level=TRACE source=runner.go:425 msg="starting runner for device discovery" libDirs="[C:\Users\Mr Cat\AppData\Local\Programs\Ollama\lib\ollama C:\Users\Mr Cat\AppData\Local\Programs\Ollama\lib\ollama\rocm]" extraEnvs="map[GGML_CUDA_INIT:1 HIP_VISIBLE_DEVICES:0]"
time=2025-11-20T09:49:58.974-08:00 level=INFO source=server.go:392 msg="starting runner" cmd="C:\Users\Mr Cat\AppData\Local\Programs\Ollama\ollama.exe runner --ollama-engine --port 53109"
time=2025-11-20T09:49:58.974-08:00 level=DEBUG source=server.go:393 msg=subprocess OLLAMA_DEBUG=2 PATH="C:\Users\Mr Cat\AppData\Local\Programs\Ollama\lib\ollama;C:\Users\Mr Cat\AppData\Local\Programs\Ollama\lib\ollama\rocm;C:\Program Files (x86)\Common Files\Oracle\Java\java8path;C:\Program Files (x86)\Common Files\Oracle\Java\javapath;C:\Program Files (x86)\NVIDIA Corporation\PhysX\Common;C:\WINDOWS\system32;C:\WINDOWS;C:\WINDOWS\System32\Wbem;C:\WINDOWS\System32\WindowsPowerShell\v1.0\;C:\WINDOWS\System32\OpenSSH\;C:\Program Files\nodejs\;C:\ProgramData\chocolatey\bin;C:\Program Files\Git\cmd;C:\Program Files\Docker\Docker\resources\bin;C:\ProgramData\DockerDesktop\version-bin;C:\Users\Mr Cat\AppData\Local\Programs\Python\Python39;C:\Users\Mr Cat\AppData\Local\Programs\Python\Python39\Scripts;C:\Program Files\dotnet\;C:\Program Files\PowerShell\7\;C:\Program Files\AMD\ROCm\6.4\bin;G:\Zulda\zluda;C:\Users\Mr Cat\AppData\Local\Programs\Python\Python310\Scripts\;C:\Users\Mr Cat\AppData\Local\Programs\Python\Python310\;C:\Users\Mr Cat\AppData\Local\Programs\Python\Python39\Scripts\;C:\Users\Mr Cat\AppData\Local\Programs\Python\Python39\;C:\Users\Mr Cat\AppData\Local\Microsoft\WindowsApps;C:\Users\Mr Cat\AppData\Local\Programs\Microsoft VS Code\bin;C:\Users\Mr Cat\AppData\Roaming\npm;C:\Program Files (x86)\GitHub CLI\;C:\Users\Mr Cat\AppData\Local\Programs\Python\Python39\Scripts;C:\Users\Mr Cat\AppData\Local\Programs\Python\Python39;;C:\Users\Mr Cat\AppData\Local\Programs\Ollama;C:\Users\Mr Cat\AppData\Local\Programs\Ollama\bin" HIP_PATH_64="C:\Program Files\AMD\ROCm\6.4\" HIP_PATH="C:\Program Files\AMD\ROCm\6.4\" OLLAMA_MODELS="C:\Users\Mr Cat\.ollama\models" OLLAMA_HOST=0.0.0.0 OLLAMA_CONTEXT_LENGTH=4096 OLLAMA_LIBRARY_PATH="C:\Users\Mr Cat\AppData\Local\Programs\Ollama\lib\ollama;C:\Users\Mr Cat\AppData\Local\Programs\Ollama\lib\ollama\rocm" HIP_VISIBLE_DEVICES=0 GGML_CUDA_INIT=1
time=2025-11-20T09:49:59.015-08:00 level=INFO source=runner.go:1398 msg="starting ollama engine"
time=2025-11-20T09:49:59.016-08:00 level=INFO source=runner.go:1433 msg="Server listening on 127.0.0.1:53109"
time=2025-11-20T09:49:59.020-08:00 level=DEBUG source=gguf.go:589 msg=general.architecture type=string
time=2025-11-20T09:49:59.020-08:00 level=DEBUG source=gguf.go:589 msg=tokenizer.ggml.model type=string
time=2025-11-20T09:49:59.020-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=general.alignment default=32
time=2025-11-20T09:49:59.021-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=general.alignment default=32
time=2025-11-20T09:49:59.021-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=general.file_type default=0
time=2025-11-20T09:49:59.021-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=general.name default=""
time=2025-11-20T09:49:59.021-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=general.description default=""
time=2025-11-20T09:49:59.021-08:00 level=INFO source=ggml.go:136 msg="" architecture=llama file_type=unknown name="" description="" num_tensors=0 num_key_values=3
time=2025-11-20T09:49:59.021-08:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path="C:\Users\Mr Cat\AppData\Local\Programs\Ollama\lib\ollama"
load_backend: loaded CPU backend from C:\Users\Mr Cat\AppData\Local\Programs\Ollama\lib\ollama\ggml-cpu-haswell.dll
time=2025-11-20T09:49:59.036-08:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path="C:\Users\Mr Cat\AppData\Local\Programs\Ollama\lib\ollama\rocm"
ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 ROCm devices:
ggml_cuda_init: initializing rocBLAS on device 0
ggml_cuda_init: rocBLAS initialized on device 0
Device 0: AMD Radeon RX 7800 XT, gfx1101 (0x1101), VMM: no, Wave Size: 32, ID: 0
load_backend: loaded ROCm backend from C:\Users\Mr Cat\AppData\Local\Programs\Ollama\lib\ollama\rocm\ggml-hip.dll
time=2025-11-20T09:50:00.515-08:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 ROCm.0.NO_VMM=1 ROCm.0.NO_PEER_COPY=1 ROCm.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(clang)
time=2025-11-20T09:50:00.515-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.block_count default=0
time=2025-11-20T09:50:00.516-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.pooling_type default=0
time=2025-11-20T09:50:00.516-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.expert_count default=0
time=2025-11-20T09:50:00.516-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.tokens default="&{size:0 values:[]}"
time=2025-11-20T09:50:00.516-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.scores default="&{size:0 values:[]}"
time=2025-11-20T09:50:00.516-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.token_type default="&{size:0 values:[]}"
time=2025-11-20T09:50:00.516-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.merges default="&{size:0 values:[]}"
time=2025-11-20T09:50:00.516-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.add_bos_token default=true
time=2025-11-20T09:50:00.516-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.bos_token_id default=0
time=2025-11-20T09:50:00.516-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.add_eos_token default=false
time=2025-11-20T09:50:00.516-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.eos_token_id default=0
time=2025-11-20T09:50:00.516-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.eos_token_ids default="&{size:0 values:[]}"
time=2025-11-20T09:50:00.516-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.pre default=""
time=2025-11-20T09:50:00.516-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.block_count default=0
time=2025-11-20T09:50:00.516-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.embedding_length default=0
time=2025-11-20T09:50:00.516-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.attention.head_count default=0
time=2025-11-20T09:50:00.516-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.attention.head_count_kv default=0
time=2025-11-20T09:50:00.516-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.attention.key_length default=0
time=2025-11-20T09:50:00.516-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.rope.dimension_count default=0
time=2025-11-20T09:50:00.516-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.attention.layer_norm_rms_epsilon default=0
time=2025-11-20T09:50:00.516-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.rope.freq_base default=100000
time=2025-11-20T09:50:00.516-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.rope.scaling.factor default=1
time=2025-11-20T09:50:00.516-08:00 level=DEBUG source=runner.go:1373 msg="dummy model load took" duration=1.4966791s
ggml_hip_mgmt_init located ADLX version 1.4
ggml_backend_cuda_device_get_memory device 0000:2d:00.0 utilizing AMD specific memory reporting free: 15048114176 total: 17163091968
time=2025-11-20T09:50:00.783-08:00 level=DEBUG source=runner.go:1378 msg="gathering device infos took" duration=266.9357ms
time=2025-11-20T09:50:00.783-08:00 level=TRACE source=runner.go:452 msg="runner enumerated devices" OLLAMA_LIBRARY_PATH="[C:\Users\Mr Cat\AppData\Local\Programs\Ollama\lib\ollama C:\Users\Mr Cat\AppData\Local\Programs\Ollama\lib\ollama\rocm]" devices="[{DeviceID:{ID:0 Library:ROCm} Name:ROCm0 Description:AMD Radeon RX 7800 XT FilterID: Integrated:false PCIID:0000:2d:00.0 TotalMemory:17163091968 FreeMemory:15048114176 ComputeMajor:17 ComputeMinor:1 DriverMajor:60450 DriverMinor:10 LibraryPath:[C:\Users\Mr Cat\AppData\Local\Programs\Ollama\lib\ollama C:\Users\Mr Cat\AppData\Local\Programs\Ollama\lib\ollama\rocm]}]"
time=2025-11-20T09:50:00.784-08:00 level=DEBUG source=runner.go:422 msg="bootstrap discovery took" duration=1.8109574s OLLAMA_LIBRARY_PATH="[C:\Users\Mr Cat\AppData\Local\Programs\Ollama\lib\ollama C:\Users\Mr Cat\AppData\Local\Programs\Ollama\lib\ollama\rocm]" extra_envs="map[GGML_CUDA_INIT:1 HIP_VISIBLE_DEVICES:0]"
time=2025-11-20T09:50:00.784-08:00 level=TRACE source=runner.go:160 msg="supported GPU library combinations before filtering" supported="map[ROCm:map[C:\Users\Mr Cat\AppData\Local\Programs\Ollama\lib\ollama\rocm:map[0:1]]]"
time=2025-11-20T09:50:00.784-08:00 level=DEBUG source=runner.go:179 msg="adjusting filtering IDs" FilterID=0 new_ID=0
time=2025-11-20T09:50:00.784-08:00 level=DEBUG source=runner.go:213 msg="dropping duplicate device" id=0 library=ROCm compute=gfx1101 name=ROCm0 description="AMD Radeon RX 7800 XT" libdirs="C:\Users\Mr Cat\AppData\Local\Programs\Ollama\lib\ollama,C:\Users\Mr Cat\AppData\Local\Programs\Ollama\lib\ollama\rocm" driver=60450.10 pci_id=0000:2d:00.0 type=discrete total="16.0 GiB" available="14.2 GiB"
time=2025-11-20T09:50:00.784-08:00 level=DEBUG source=runner.go:40 msg="GPU bootstrap discovery took" duration=3.1593641s
time=2025-11-20T09:50:00.784-08:00 level=INFO source=types.go:42 msg="inference compute" id=GPU-00000000-0000-0000-0000-000000000000 filter_id="" library=CUDA compute=8.8 name=CUDA0 description="AMD Radeon RX 7800 XT [ZLUDA]" libdirs=ollama,cuda_v12 driver=12.2 pci_id=0000:2d:00.0 type=discrete total="16.0 GiB" available="15.8 GiB"
time=2025-11-20T09:50:00.784-08:00 level=INFO source=routes.go:1638 msg="entering low vram mode" "total vram"="16.0 GiB" threshold="20.0 GiB"
[GIN] 2025/11/20 - 09:50:00 | 200 | 3.0936ms | 127.0.0.1 | GET "/api/version"
[GIN] 2025/11/20 - 09:50:00 | 200 | 10.9782ms | 127.0.0.1 | GET "/api/tags"
time=2025-11-20T09:50:00.803-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=general.alignment default=32
[GIN] 2025/11/20 - 09:50:00 | 200 | 21.2126ms | 127.0.0.1 | POST "/api/show"
[GIN] 2025/11/20 - 09:50:30 | 200 | 4.9077ms | 127.0.0.1 | GET "/api/tags"
[GIN] 2025/11/20 - 09:51:00 | 200 | 4.8302ms | 127.0.0.1 | GET "/api/tags"

<!-- gh-comment-id:3559322086 --> @Oliver-Strange commented on GitHub (Nov 20, 2025): @dhiltgen I recently set up Automatic1111 and that took a bit of configuring, but Ollama had been working at the same time. Looking through the logs, is it normal for the GPU ID to come up as all zeros? Debug 2: time=2025-11-20T09:49:57.602-08:00 level=INFO source=routes.go:1544 msg="server config" env="map[CUDA_VISIBLE_DEVICES: GGML_VK_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:4096 OLLAMA_DEBUG:DEBUG-4 OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://0.0.0.0:11434 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\\Mr Cat\\.ollama\\models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:1 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_REMOTES:[ollama.com] OLLAMA_SCHED_SPREAD:false OLLAMA_VULKAN:false ROCR_VISIBLE_DEVICES:]" time=2025-11-20T09:49:57.619-08:00 level=INFO source=images.go:522 msg="total blobs: 70" time=2025-11-20T09:49:57.622-08:00 level=INFO source=images.go:529 msg="total unused blobs removed: 0" time=2025-11-20T09:49:57.624-08:00 level=INFO source=routes.go:1597 msg="Listening on [::]:11434 (version 0.13.0)" time=2025-11-20T09:49:57.624-08:00 level=DEBUG source=sched.go:120 msg="starting llm scheduler" time=2025-11-20T09:49:57.625-08:00 level=INFO source=runner.go:67 msg="discovering available GPUs..." time=2025-11-20T09:49:57.625-08:00 level=TRACE source=runner.go:425 msg="starting runner for device discovery" libDirs="[C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v12]" extraEnvs=map[] time=2025-11-20T09:49:57.636-08:00 level=INFO source=server.go:392 msg="starting runner" cmd="C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 59761" time=2025-11-20T09:49:57.636-08:00 level=DEBUG source=server.go:393 msg=subprocess OLLAMA_DEBUG=2 PATH="C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Ollama\\lib\\ollama;C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v12;C:\\Program Files (x86)\\Common Files\\Oracle\\Java\\java8path;C:\\Program Files (x86)\\Common Files\\Oracle\\Java\\javapath;C:\\Program Files (x86)\\NVIDIA Corporation\\PhysX\\Common;C:\\WINDOWS\\system32;C:\\WINDOWS;C:\\WINDOWS\\System32\\Wbem;C:\\WINDOWS\\System32\\WindowsPowerShell\\v1.0\\;C:\\WINDOWS\\System32\\OpenSSH\\;C:\\Program Files\\nodejs\\;C:\\ProgramData\\chocolatey\\bin;C:\\Program Files\\Git\\cmd;C:\\Program Files\\Docker\\Docker\\resources\\bin;C:\\ProgramData\\DockerDesktop\\version-bin;C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Python\\Python39;C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Python\\Python39\\Scripts;C:\\Program Files\\dotnet\\;C:\\Program Files\\PowerShell\\7\\;C:\\Program Files\\AMD\\ROCm\\6.4\\bin;G:\\Zulda\\zluda;C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Python\\Python310\\Scripts\\;C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Python\\Python310\\;C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Python\\Python39\\Scripts\\;C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Python\\Python39\\;C:\\Users\\Mr Cat\\AppData\\Local\\Microsoft\\WindowsApps;C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Microsoft VS Code\\bin;C:\\Users\\Mr Cat\\AppData\\Roaming\\npm;C:\\Program Files (x86)\\GitHub CLI\\;C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Python\\Python39\\Scripts;C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Python\\Python39;;C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Ollama;C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Ollama\\bin" HIP_PATH_64="C:\\Program Files\\AMD\\ROCm\\6.4\\" HIP_PATH="C:\\Program Files\\AMD\\ROCm\\6.4\\" OLLAMA_MODELS="C:\\Users\\Mr Cat\\.ollama\\models" OLLAMA_HOST=0.0.0.0 OLLAMA_CONTEXT_LENGTH=4096 OLLAMA_LIBRARY_PATH="C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Ollama\\lib\\ollama;C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v12" time=2025-11-20T09:49:57.685-08:00 level=INFO source=runner.go:1398 msg="starting ollama engine" time=2025-11-20T09:49:57.687-08:00 level=INFO source=runner.go:1433 msg="Server listening on 127.0.0.1:59761" time=2025-11-20T09:49:57.694-08:00 level=DEBUG source=gguf.go:589 msg=general.architecture type=string time=2025-11-20T09:49:57.694-08:00 level=DEBUG source=gguf.go:589 msg=tokenizer.ggml.model type=string time=2025-11-20T09:49:57.694-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=general.alignment default=32 time=2025-11-20T09:49:57.695-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=general.alignment default=32 time=2025-11-20T09:49:57.695-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=general.file_type default=0 time=2025-11-20T09:49:57.695-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=general.name default="" time=2025-11-20T09:49:57.695-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=general.description default="" time=2025-11-20T09:49:57.695-08:00 level=INFO source=ggml.go:136 msg="" architecture=llama file_type=unknown name="" description="" num_tensors=0 num_key_values=3 time=2025-11-20T09:49:57.695-08:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path="C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Ollama\\lib\\ollama" load_backend: loaded CPU backend from C:\Users\Mr Cat\AppData\Local\Programs\Ollama\lib\ollama\ggml-cpu-haswell.dll time=2025-11-20T09:49:57.718-08:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path="C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v12" 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: AMD Radeon RX 7800 XT [ZLUDA], compute capability 8.8, VMM: no, ID: GPU-00000000-0000-0000-0000-000000000000 load_backend: loaded CUDA backend from C:\Users\Mr Cat\AppData\Local\Programs\Ollama\lib\ollama\cuda_v12\ggml-cuda.dll time=2025-11-20T09:49:57.905-08:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 CUDA.0.ARCHS=500,520,600,610,700,750,800,860,890,900,1200 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(clang) time=2025-11-20T09:49:57.905-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.block_count default=0 time=2025-11-20T09:49:57.905-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.pooling_type default=0 time=2025-11-20T09:49:57.905-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.expert_count default=0 time=2025-11-20T09:49:57.905-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.tokens default="&{size:0 values:[]}" time=2025-11-20T09:49:57.905-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.scores default="&{size:0 values:[]}" time=2025-11-20T09:49:57.905-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.token_type default="&{size:0 values:[]}" time=2025-11-20T09:49:57.905-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.merges default="&{size:0 values:[]}" time=2025-11-20T09:49:57.905-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.add_bos_token default=true time=2025-11-20T09:49:57.905-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.bos_token_id default=0 time=2025-11-20T09:49:57.905-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.add_eos_token default=false time=2025-11-20T09:49:57.905-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.eos_token_id default=0 time=2025-11-20T09:49:57.905-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.eos_token_ids default="&{size:0 values:[]}" time=2025-11-20T09:49:57.905-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.pre default="" time=2025-11-20T09:49:57.905-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.block_count default=0 time=2025-11-20T09:49:57.905-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.embedding_length default=0 time=2025-11-20T09:49:57.905-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.attention.head_count default=0 time=2025-11-20T09:49:57.905-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.attention.head_count_kv default=0 time=2025-11-20T09:49:57.905-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.attention.key_length default=0 time=2025-11-20T09:49:57.905-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.rope.dimension_count default=0 time=2025-11-20T09:49:57.905-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.attention.layer_norm_rms_epsilon default=0 time=2025-11-20T09:49:57.905-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.rope.freq_base default=100000 time=2025-11-20T09:49:57.905-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.rope.scaling.factor default=1 time=2025-11-20T09:49:57.906-08:00 level=DEBUG source=runner.go:1373 msg="dummy model load took" duration=212.0376ms time=2025-11-20T09:49:58.416-08:00 level=DEBUG source=runner.go:1378 msg="gathering device infos took" duration=510.1119ms time=2025-11-20T09:49:58.416-08:00 level=TRACE source=runner.go:452 msg="runner enumerated devices" OLLAMA_LIBRARY_PATH="[C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v12]" devices="[{DeviceID:{ID:GPU-00000000-0000-0000-0000-000000000000 Library:CUDA} Name:CUDA0 Description:AMD Radeon RX 7800 XT [ZLUDA] FilterID: Integrated:false PCIID:0000:2d:00.0 TotalMemory:17163091968 FreeMemory:17011408896 ComputeMajor:8 ComputeMinor:8 DriverMajor:12 DriverMinor:2 LibraryPath:[C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v12]}]" time=2025-11-20T09:49:58.420-08:00 level=DEBUG source=runner.go:422 msg="bootstrap discovery took" duration=794.5992ms OLLAMA_LIBRARY_PATH="[C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v12]" extra_envs=map[] time=2025-11-20T09:49:58.420-08:00 level=TRACE source=runner.go:425 msg="starting runner for device discovery" libDirs="[C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v13]" extraEnvs=map[] time=2025-11-20T09:49:58.422-08:00 level=INFO source=server.go:392 msg="starting runner" cmd="C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 52427" time=2025-11-20T09:49:58.422-08:00 level=DEBUG source=server.go:393 msg=subprocess OLLAMA_DEBUG=2 PATH="C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Ollama\\lib\\ollama;C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v13;C:\\Program Files (x86)\\Common Files\\Oracle\\Java\\java8path;C:\\Program Files (x86)\\Common Files\\Oracle\\Java\\javapath;C:\\Program Files (x86)\\NVIDIA Corporation\\PhysX\\Common;C:\\WINDOWS\\system32;C:\\WINDOWS;C:\\WINDOWS\\System32\\Wbem;C:\\WINDOWS\\System32\\WindowsPowerShell\\v1.0\\;C:\\WINDOWS\\System32\\OpenSSH\\;C:\\Program Files\\nodejs\\;C:\\ProgramData\\chocolatey\\bin;C:\\Program Files\\Git\\cmd;C:\\Program Files\\Docker\\Docker\\resources\\bin;C:\\ProgramData\\DockerDesktop\\version-bin;C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Python\\Python39;C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Python\\Python39\\Scripts;C:\\Program Files\\dotnet\\;C:\\Program Files\\PowerShell\\7\\;C:\\Program Files\\AMD\\ROCm\\6.4\\bin;G:\\Zulda\\zluda;C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Python\\Python310\\Scripts\\;C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Python\\Python310\\;C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Python\\Python39\\Scripts\\;C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Python\\Python39\\;C:\\Users\\Mr Cat\\AppData\\Local\\Microsoft\\WindowsApps;C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Microsoft VS Code\\bin;C:\\Users\\Mr Cat\\AppData\\Roaming\\npm;C:\\Program Files (x86)\\GitHub CLI\\;C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Python\\Python39\\Scripts;C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Python\\Python39;;C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Ollama;C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Ollama\\bin" HIP_PATH_64="C:\\Program Files\\AMD\\ROCm\\6.4\\" HIP_PATH="C:\\Program Files\\AMD\\ROCm\\6.4\\" OLLAMA_MODELS="C:\\Users\\Mr Cat\\.ollama\\models" OLLAMA_HOST=0.0.0.0 OLLAMA_CONTEXT_LENGTH=4096 OLLAMA_LIBRARY_PATH="C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Ollama\\lib\\ollama;C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v13" time=2025-11-20T09:49:58.469-08:00 level=INFO source=runner.go:1398 msg="starting ollama engine" time=2025-11-20T09:49:58.470-08:00 level=INFO source=runner.go:1433 msg="Server listening on 127.0.0.1:52427" time=2025-11-20T09:49:58.479-08:00 level=DEBUG source=gguf.go:589 msg=general.architecture type=string time=2025-11-20T09:49:58.479-08:00 level=DEBUG source=gguf.go:589 msg=tokenizer.ggml.model type=string time=2025-11-20T09:49:58.479-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=general.alignment default=32 time=2025-11-20T09:49:58.480-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=general.alignment default=32 time=2025-11-20T09:49:58.480-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=general.file_type default=0 time=2025-11-20T09:49:58.480-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=general.name default="" time=2025-11-20T09:49:58.480-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=general.description default="" time=2025-11-20T09:49:58.480-08:00 level=INFO source=ggml.go:136 msg="" architecture=llama file_type=unknown name="" description="" num_tensors=0 num_key_values=3 time=2025-11-20T09:49:58.480-08:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path="C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Ollama\\lib\\ollama" load_backend: loaded CPU backend from C:\Users\Mr Cat\AppData\Local\Programs\Ollama\lib\ollama\ggml-cpu-haswell.dll time=2025-11-20T09:49:58.497-08:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path="C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v13" ggml_cuda_init: failed to initialize CUDA: (null) load_backend: loaded CUDA backend from C:\Users\Mr Cat\AppData\Local\Programs\Ollama\lib\ollama\cuda_v13\ggml-cuda.dll time=2025-11-20T09:49:58.584-08:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 compiler=cgo(clang) time=2025-11-20T09:49:58.584-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.block_count default=0 time=2025-11-20T09:49:58.585-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.pooling_type default=0 time=2025-11-20T09:49:58.585-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.expert_count default=0 time=2025-11-20T09:49:58.585-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.tokens default="&{size:0 values:[]}" time=2025-11-20T09:49:58.585-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.scores default="&{size:0 values:[]}" time=2025-11-20T09:49:58.585-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.token_type default="&{size:0 values:[]}" time=2025-11-20T09:49:58.585-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.merges default="&{size:0 values:[]}" time=2025-11-20T09:49:58.585-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.add_bos_token default=true time=2025-11-20T09:49:58.585-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.bos_token_id default=0 time=2025-11-20T09:49:58.585-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.add_eos_token default=false time=2025-11-20T09:49:58.585-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.eos_token_id default=0 time=2025-11-20T09:49:58.585-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.eos_token_ids default="&{size:0 values:[]}" time=2025-11-20T09:49:58.585-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.pre default="" time=2025-11-20T09:49:58.585-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.block_count default=0 time=2025-11-20T09:49:58.585-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.embedding_length default=0 time=2025-11-20T09:49:58.585-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.attention.head_count default=0 time=2025-11-20T09:49:58.585-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.attention.head_count_kv default=0 time=2025-11-20T09:49:58.585-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.attention.key_length default=0 time=2025-11-20T09:49:58.585-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.rope.dimension_count default=0 time=2025-11-20T09:49:58.585-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.attention.layer_norm_rms_epsilon default=0 time=2025-11-20T09:49:58.585-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.rope.freq_base default=100000 time=2025-11-20T09:49:58.585-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.rope.scaling.factor default=1 time=2025-11-20T09:49:58.585-08:00 level=DEBUG source=runner.go:1373 msg="dummy model load took" duration=106.3627ms time=2025-11-20T09:49:58.585-08:00 level=DEBUG source=runner.go:1378 msg="gathering device infos took" duration=0s time=2025-11-20T09:49:58.585-08:00 level=TRACE source=runner.go:452 msg="runner enumerated devices" OLLAMA_LIBRARY_PATH="[C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v13]" devices=[] time=2025-11-20T09:49:58.585-08:00 level=DEBUG source=runner.go:422 msg="bootstrap discovery took" duration=165.1534ms OLLAMA_LIBRARY_PATH="[C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\cuda_v13]" extra_envs=map[] time=2025-11-20T09:49:58.585-08:00 level=TRACE source=runner.go:425 msg="starting runner for device discovery" libDirs="[C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\rocm]" extraEnvs=map[] time=2025-11-20T09:49:58.586-08:00 level=INFO source=server.go:392 msg="starting runner" cmd="C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 63596" time=2025-11-20T09:49:58.586-08:00 level=DEBUG source=server.go:393 msg=subprocess OLLAMA_DEBUG=2 PATH="C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Ollama\\lib\\ollama;C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\rocm;C:\\Program Files (x86)\\Common Files\\Oracle\\Java\\java8path;C:\\Program Files (x86)\\Common Files\\Oracle\\Java\\javapath;C:\\Program Files (x86)\\NVIDIA Corporation\\PhysX\\Common;C:\\WINDOWS\\system32;C:\\WINDOWS;C:\\WINDOWS\\System32\\Wbem;C:\\WINDOWS\\System32\\WindowsPowerShell\\v1.0\\;C:\\WINDOWS\\System32\\OpenSSH\\;C:\\Program Files\\nodejs\\;C:\\ProgramData\\chocolatey\\bin;C:\\Program Files\\Git\\cmd;C:\\Program Files\\Docker\\Docker\\resources\\bin;C:\\ProgramData\\DockerDesktop\\version-bin;C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Python\\Python39;C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Python\\Python39\\Scripts;C:\\Program Files\\dotnet\\;C:\\Program Files\\PowerShell\\7\\;C:\\Program Files\\AMD\\ROCm\\6.4\\bin;G:\\Zulda\\zluda;C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Python\\Python310\\Scripts\\;C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Python\\Python310\\;C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Python\\Python39\\Scripts\\;C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Python\\Python39\\;C:\\Users\\Mr Cat\\AppData\\Local\\Microsoft\\WindowsApps;C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Microsoft VS Code\\bin;C:\\Users\\Mr Cat\\AppData\\Roaming\\npm;C:\\Program Files (x86)\\GitHub CLI\\;C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Python\\Python39\\Scripts;C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Python\\Python39;;C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Ollama;C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Ollama\\bin" HIP_PATH_64="C:\\Program Files\\AMD\\ROCm\\6.4\\" HIP_PATH="C:\\Program Files\\AMD\\ROCm\\6.4\\" OLLAMA_MODELS="C:\\Users\\Mr Cat\\.ollama\\models" OLLAMA_HOST=0.0.0.0 OLLAMA_CONTEXT_LENGTH=4096 OLLAMA_LIBRARY_PATH="C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Ollama\\lib\\ollama;C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\rocm" time=2025-11-20T09:49:58.624-08:00 level=INFO source=runner.go:1398 msg="starting ollama engine" time=2025-11-20T09:49:58.626-08:00 level=INFO source=runner.go:1433 msg="Server listening on 127.0.0.1:63596" time=2025-11-20T09:49:58.632-08:00 level=DEBUG source=gguf.go:589 msg=general.architecture type=string time=2025-11-20T09:49:58.632-08:00 level=DEBUG source=gguf.go:589 msg=tokenizer.ggml.model type=string time=2025-11-20T09:49:58.632-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=general.alignment default=32 time=2025-11-20T09:49:58.633-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=general.alignment default=32 time=2025-11-20T09:49:58.633-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=general.file_type default=0 time=2025-11-20T09:49:58.633-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=general.name default="" time=2025-11-20T09:49:58.633-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=general.description default="" time=2025-11-20T09:49:58.633-08:00 level=INFO source=ggml.go:136 msg="" architecture=llama file_type=unknown name="" description="" num_tensors=0 num_key_values=3 time=2025-11-20T09:49:58.633-08:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path="C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Ollama\\lib\\ollama" load_backend: loaded CPU backend from C:\Users\Mr Cat\AppData\Local\Programs\Ollama\lib\ollama\ggml-cpu-haswell.dll time=2025-11-20T09:49:58.648-08:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path="C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\rocm" ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no ggml_cuda_init: found 1 ROCm devices: Device 0: AMD Radeon RX 7800 XT, gfx1101 (0x1101), VMM: no, Wave Size: 32, ID: 0 load_backend: loaded ROCm backend from C:\Users\Mr Cat\AppData\Local\Programs\Ollama\lib\ollama\rocm\ggml-hip.dll time=2025-11-20T09:49:58.693-08:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 ROCm.0.NO_VMM=1 ROCm.0.NO_PEER_COPY=1 ROCm.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(clang) time=2025-11-20T09:49:58.693-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.block_count default=0 time=2025-11-20T09:49:58.693-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.pooling_type default=0 time=2025-11-20T09:49:58.693-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.expert_count default=0 time=2025-11-20T09:49:58.693-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.tokens default="&{size:0 values:[]}" time=2025-11-20T09:49:58.693-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.scores default="&{size:0 values:[]}" time=2025-11-20T09:49:58.693-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.token_type default="&{size:0 values:[]}" time=2025-11-20T09:49:58.693-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.merges default="&{size:0 values:[]}" time=2025-11-20T09:49:58.693-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.add_bos_token default=true time=2025-11-20T09:49:58.693-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.bos_token_id default=0 time=2025-11-20T09:49:58.693-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.add_eos_token default=false time=2025-11-20T09:49:58.693-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.eos_token_id default=0 time=2025-11-20T09:49:58.693-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.eos_token_ids default="&{size:0 values:[]}" time=2025-11-20T09:49:58.693-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.pre default="" time=2025-11-20T09:49:58.693-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.block_count default=0 time=2025-11-20T09:49:58.693-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.embedding_length default=0 time=2025-11-20T09:49:58.693-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.attention.head_count default=0 time=2025-11-20T09:49:58.693-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.attention.head_count_kv default=0 time=2025-11-20T09:49:58.693-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.attention.key_length default=0 time=2025-11-20T09:49:58.693-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.rope.dimension_count default=0 time=2025-11-20T09:49:58.693-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.attention.layer_norm_rms_epsilon default=0 time=2025-11-20T09:49:58.693-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.rope.freq_base default=100000 time=2025-11-20T09:49:58.693-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.rope.scaling.factor default=1 time=2025-11-20T09:49:58.693-08:00 level=DEBUG source=runner.go:1373 msg="dummy model load took" duration=61.2928ms ggml_hip_mgmt_init located ADLX version 1.4 ggml_backend_cuda_device_get_memory device 0000:2d:00.0 utilizing AMD specific memory reporting free: 15287189504 total: 17163091968 time=2025-11-20T09:49:58.972-08:00 level=DEBUG source=runner.go:1378 msg="gathering device infos took" duration=278.6073ms time=2025-11-20T09:49:58.972-08:00 level=TRACE source=runner.go:452 msg="runner enumerated devices" OLLAMA_LIBRARY_PATH="[C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\rocm]" devices="[{DeviceID:{ID:0 Library:ROCm} Name:ROCm0 Description:AMD Radeon RX 7800 XT FilterID: Integrated:false PCIID:0000:2d:00.0 TotalMemory:17163091968 FreeMemory:15287189504 ComputeMajor:17 ComputeMinor:1 DriverMajor:60450 DriverMinor:10 LibraryPath:[C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\rocm]}]" time=2025-11-20T09:49:58.973-08:00 level=DEBUG source=runner.go:422 msg="bootstrap discovery took" duration=387.6438ms OLLAMA_LIBRARY_PATH="[C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\rocm]" extra_envs=map[] time=2025-11-20T09:49:58.973-08:00 level=INFO source=runner.go:102 msg="experimental Vulkan support disabled. To enable, set OLLAMA_VULKAN=1" time=2025-11-20T09:49:58.973-08:00 level=DEBUG source=runner.go:120 msg="evaluating which, if any, devices to filter out" initial_count=2 time=2025-11-20T09:49:58.973-08:00 level=DEBUG source=runner.go:132 msg="verifying if device is supported" library="C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\rocm" description="AMD Radeon RX 7800 XT" compute=gfx1101 id=0 pci_id=0000:2d:00.0 time=2025-11-20T09:49:58.973-08:00 level=TRACE source=runner.go:425 msg="starting runner for device discovery" libDirs="[C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\rocm]" extraEnvs="map[GGML_CUDA_INIT:1 HIP_VISIBLE_DEVICES:0]" time=2025-11-20T09:49:58.974-08:00 level=INFO source=server.go:392 msg="starting runner" cmd="C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 53109" time=2025-11-20T09:49:58.974-08:00 level=DEBUG source=server.go:393 msg=subprocess OLLAMA_DEBUG=2 PATH="C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Ollama\\lib\\ollama;C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\rocm;C:\\Program Files (x86)\\Common Files\\Oracle\\Java\\java8path;C:\\Program Files (x86)\\Common Files\\Oracle\\Java\\javapath;C:\\Program Files (x86)\\NVIDIA Corporation\\PhysX\\Common;C:\\WINDOWS\\system32;C:\\WINDOWS;C:\\WINDOWS\\System32\\Wbem;C:\\WINDOWS\\System32\\WindowsPowerShell\\v1.0\\;C:\\WINDOWS\\System32\\OpenSSH\\;C:\\Program Files\\nodejs\\;C:\\ProgramData\\chocolatey\\bin;C:\\Program Files\\Git\\cmd;C:\\Program Files\\Docker\\Docker\\resources\\bin;C:\\ProgramData\\DockerDesktop\\version-bin;C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Python\\Python39;C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Python\\Python39\\Scripts;C:\\Program Files\\dotnet\\;C:\\Program Files\\PowerShell\\7\\;C:\\Program Files\\AMD\\ROCm\\6.4\\bin;G:\\Zulda\\zluda;C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Python\\Python310\\Scripts\\;C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Python\\Python310\\;C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Python\\Python39\\Scripts\\;C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Python\\Python39\\;C:\\Users\\Mr Cat\\AppData\\Local\\Microsoft\\WindowsApps;C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Microsoft VS Code\\bin;C:\\Users\\Mr Cat\\AppData\\Roaming\\npm;C:\\Program Files (x86)\\GitHub CLI\\;C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Python\\Python39\\Scripts;C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Python\\Python39;;C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Ollama;C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Ollama\\bin" HIP_PATH_64="C:\\Program Files\\AMD\\ROCm\\6.4\\" HIP_PATH="C:\\Program Files\\AMD\\ROCm\\6.4\\" OLLAMA_MODELS="C:\\Users\\Mr Cat\\.ollama\\models" OLLAMA_HOST=0.0.0.0 OLLAMA_CONTEXT_LENGTH=4096 OLLAMA_LIBRARY_PATH="C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Ollama\\lib\\ollama;C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\rocm" HIP_VISIBLE_DEVICES=0 GGML_CUDA_INIT=1 time=2025-11-20T09:49:59.015-08:00 level=INFO source=runner.go:1398 msg="starting ollama engine" time=2025-11-20T09:49:59.016-08:00 level=INFO source=runner.go:1433 msg="Server listening on 127.0.0.1:53109" time=2025-11-20T09:49:59.020-08:00 level=DEBUG source=gguf.go:589 msg=general.architecture type=string time=2025-11-20T09:49:59.020-08:00 level=DEBUG source=gguf.go:589 msg=tokenizer.ggml.model type=string time=2025-11-20T09:49:59.020-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=general.alignment default=32 time=2025-11-20T09:49:59.021-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=general.alignment default=32 time=2025-11-20T09:49:59.021-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=general.file_type default=0 time=2025-11-20T09:49:59.021-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=general.name default="" time=2025-11-20T09:49:59.021-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=general.description default="" time=2025-11-20T09:49:59.021-08:00 level=INFO source=ggml.go:136 msg="" architecture=llama file_type=unknown name="" description="" num_tensors=0 num_key_values=3 time=2025-11-20T09:49:59.021-08:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path="C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Ollama\\lib\\ollama" load_backend: loaded CPU backend from C:\Users\Mr Cat\AppData\Local\Programs\Ollama\lib\ollama\ggml-cpu-haswell.dll time=2025-11-20T09:49:59.036-08:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path="C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\rocm" ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no ggml_cuda_init: found 1 ROCm devices: ggml_cuda_init: initializing rocBLAS on device 0 ggml_cuda_init: rocBLAS initialized on device 0 Device 0: AMD Radeon RX 7800 XT, gfx1101 (0x1101), VMM: no, Wave Size: 32, ID: 0 load_backend: loaded ROCm backend from C:\Users\Mr Cat\AppData\Local\Programs\Ollama\lib\ollama\rocm\ggml-hip.dll time=2025-11-20T09:50:00.515-08:00 level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 ROCm.0.NO_VMM=1 ROCm.0.NO_PEER_COPY=1 ROCm.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(clang) time=2025-11-20T09:50:00.515-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.block_count default=0 time=2025-11-20T09:50:00.516-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.pooling_type default=0 time=2025-11-20T09:50:00.516-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.expert_count default=0 time=2025-11-20T09:50:00.516-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.tokens default="&{size:0 values:[]}" time=2025-11-20T09:50:00.516-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.scores default="&{size:0 values:[]}" time=2025-11-20T09:50:00.516-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.token_type default="&{size:0 values:[]}" time=2025-11-20T09:50:00.516-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.merges default="&{size:0 values:[]}" time=2025-11-20T09:50:00.516-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.add_bos_token default=true time=2025-11-20T09:50:00.516-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.bos_token_id default=0 time=2025-11-20T09:50:00.516-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.add_eos_token default=false time=2025-11-20T09:50:00.516-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.eos_token_id default=0 time=2025-11-20T09:50:00.516-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.eos_token_ids default="&{size:0 values:[]}" time=2025-11-20T09:50:00.516-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=tokenizer.ggml.pre default="" time=2025-11-20T09:50:00.516-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.block_count default=0 time=2025-11-20T09:50:00.516-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.embedding_length default=0 time=2025-11-20T09:50:00.516-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.attention.head_count default=0 time=2025-11-20T09:50:00.516-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.attention.head_count_kv default=0 time=2025-11-20T09:50:00.516-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.attention.key_length default=0 time=2025-11-20T09:50:00.516-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.rope.dimension_count default=0 time=2025-11-20T09:50:00.516-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.attention.layer_norm_rms_epsilon default=0 time=2025-11-20T09:50:00.516-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.rope.freq_base default=100000 time=2025-11-20T09:50:00.516-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=llama.rope.scaling.factor default=1 time=2025-11-20T09:50:00.516-08:00 level=DEBUG source=runner.go:1373 msg="dummy model load took" duration=1.4966791s ggml_hip_mgmt_init located ADLX version 1.4 ggml_backend_cuda_device_get_memory device 0000:2d:00.0 utilizing AMD specific memory reporting free: 15048114176 total: 17163091968 time=2025-11-20T09:50:00.783-08:00 level=DEBUG source=runner.go:1378 msg="gathering device infos took" duration=266.9357ms time=2025-11-20T09:50:00.783-08:00 level=TRACE source=runner.go:452 msg="runner enumerated devices" OLLAMA_LIBRARY_PATH="[C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\rocm]" devices="[{DeviceID:{ID:0 Library:ROCm} Name:ROCm0 Description:AMD Radeon RX 7800 XT FilterID: Integrated:false PCIID:0000:2d:00.0 TotalMemory:17163091968 FreeMemory:15048114176 ComputeMajor:17 ComputeMinor:1 DriverMajor:60450 DriverMinor:10 LibraryPath:[C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\rocm]}]" time=2025-11-20T09:50:00.784-08:00 level=DEBUG source=runner.go:422 msg="bootstrap discovery took" duration=1.8109574s OLLAMA_LIBRARY_PATH="[C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\rocm]" extra_envs="map[GGML_CUDA_INIT:1 HIP_VISIBLE_DEVICES:0]" time=2025-11-20T09:50:00.784-08:00 level=TRACE source=runner.go:160 msg="supported GPU library combinations before filtering" supported="map[ROCm:map[C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\rocm:map[0:1]]]" time=2025-11-20T09:50:00.784-08:00 level=DEBUG source=runner.go:179 msg="adjusting filtering IDs" FilterID=0 new_ID=0 time=2025-11-20T09:50:00.784-08:00 level=DEBUG source=runner.go:213 msg="dropping duplicate device" id=0 library=ROCm compute=gfx1101 name=ROCm0 description="AMD Radeon RX 7800 XT" libdirs="C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Ollama\\lib\\ollama,C:\\Users\\Mr Cat\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\rocm" driver=60450.10 pci_id=0000:2d:00.0 type=discrete total="16.0 GiB" available="14.2 GiB" time=2025-11-20T09:50:00.784-08:00 level=DEBUG source=runner.go:40 msg="GPU bootstrap discovery took" duration=3.1593641s time=2025-11-20T09:50:00.784-08:00 level=INFO source=types.go:42 msg="inference compute" id=GPU-00000000-0000-0000-0000-000000000000 filter_id="" library=CUDA compute=8.8 name=CUDA0 description="AMD Radeon RX 7800 XT [ZLUDA]" libdirs=ollama,cuda_v12 driver=12.2 pci_id=0000:2d:00.0 type=discrete total="16.0 GiB" available="15.8 GiB" time=2025-11-20T09:50:00.784-08:00 level=INFO source=routes.go:1638 msg="entering low vram mode" "total vram"="16.0 GiB" threshold="20.0 GiB" [GIN] 2025/11/20 - 09:50:00 | 200 | 3.0936ms | 127.0.0.1 | GET "/api/version" [GIN] 2025/11/20 - 09:50:00 | 200 | 10.9782ms | 127.0.0.1 | GET "/api/tags" time=2025-11-20T09:50:00.803-08:00 level=DEBUG source=ggml.go:278 msg="key with type not found" key=general.alignment default=32 [GIN] 2025/11/20 - 09:50:00 | 200 | 21.2126ms | 127.0.0.1 | POST "/api/show" [GIN] 2025/11/20 - 09:50:30 | 200 | 4.9077ms | 127.0.0.1 | GET "/api/tags" [GIN] 2025/11/20 - 09:51:00 | 200 | 4.8302ms | 127.0.0.1 | GET "/api/tags"
GiteaMirror commented 2026-04-12 21:21:17 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Nov 21, 2025):

Looking at the logs, it seems like you have https://github.com/vosen/ZLUDA on your system, which is why the AMD GPU is being found via CUDA instead of ROCm.

I'm not sure what would be involved in adding support for this, but for now, try to disable this when you're using Ollama so we correctly use ROCm instead.

<!-- gh-comment-id:3564650971 --> @dhiltgen commented on GitHub (Nov 21, 2025): Looking at the logs, it seems like you have https://github.com/vosen/ZLUDA on your system, which is why the AMD GPU is being found via CUDA instead of ROCm. I'm not sure what would be involved in adding support for this, but for now, try to disable this when you're using Ollama so we correctly use ROCm instead.
GiteaMirror commented 2026-04-12 21:21:17 -05:00
Author
Owner
Copy Link

@Oliver-Strange commented on GitHub (Nov 22, 2025):

Removing Zulda from Path resolved this issue. Thank you for all your help!

<!-- gh-comment-id:3565098919 --> @Oliver-Strange commented on GitHub (Nov 22, 2025): Removing Zulda from Path resolved this issue. Thank you for all your help!
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 amd feature request windows
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#8615
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?