github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-08 00:51:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #15343] Qwen3.5:9b rocBLAS error from hip error code: 'hipErrorInvalidDeviceFunction':98 ggml_cuda_compute_forward: SOLVE_TRI failed ROCm error: invalid device function #71875

New Issue
Closed
opened 2026-05-05 02:47:58 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-05-05 02:47:58 -05:00
Owner
Copy Link

Originally created by @DaveyBonez on GitHub (Apr 5, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/15343

What is the issue?

Error
500 Internal Server Error: model failed to load, this may be due to resource limitations or an internal error, check ollama server logs for details

windows 11 GPU: RX 9060 XT
only happens with Qwen models.

Relevant log output

time=2026-03-30T13:42:49.541-04:00 level=DEBUG source=runner.go:264 msg="refreshing free memory"
time=2026-03-30T13:42:49.541-04:00 level=DEBUG source=runner.go:328 msg="unable to refresh all GPUs with existing runners, performing bootstrap discovery"
time=2026-03-30T13:42:49.544-04:00 level=INFO source=server.go:432 msg="starting runner" cmd="C:\\Users\\DaveyBoneZ\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 56996"
time=2026-03-30T13:42:49.544-04:00 level=DEBUG source=server.go:433 msg=subprocess HIP_PATH="C:\\Program Files\\AMD\\ROCm\\6.4\\" HIP_PATH_64="C:\\Program Files\\AMD\\ROCm\\6.4\\" HIP_PATH_71="C:\\Program Files\\AMD\\ROCm\\7.1\\" OLLAMA_CONTEXT_LENGTH=32768 OLLAMA_DEBUG=1 OLLAMA_FLASH_ATTENTION=1 OLLAMA_HOST=0.0.0.0 OLLAMA_KV_CACHE_TYPE=q8_0 PATH="C:\\Users\\DaveyBoneZ\\AppData\\Local\\Programs\\Ollama\\lib\\ollama;C:\\Users\\DaveyBoneZ\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\rocm;C:\\WINDOWS\\system32;C:\\WINDOWS;C:\\WINDOWS\\System32\\Wbem;C:\\WINDOWS\\System32\\WindowsPowerShell\\v1.0\\;C:\\WINDOWS\\System32\\OpenSSH\\;C:\\Users\\DaveyBoneZ\\AppData\\Local\\AMD\\AI_Bundle\\VSCode\\bin;C:\\Program Files\\Git\\cmd;C:\\Program Files\\Docker\\Docker\\resources\\bin;C:\\Program Files\\PowerShell\\7\\;C:\\Program Files\\AMD\\ROCm\\7.1\\bin;C:\\Users\\DaveyBoneZ\\AppData\\Local\\Programs\\Python\\Launcher\\;C:\\Users\\DaveyBoneZ\\AppData\\Local\\Microsoft\\WindowsApps;C:\\Users\\DaveyBoneZ\\AppData\\Local\\AMD\\AI_Bundle\\Ollama;C:\\Users\\DaveyBoneZ\\.lmstudio\\bin;C:\\Users\\DaveyBoneZ\\AppData\\Local\\Python\\bin;C:\\Users\\DaveyBoneZ\\AppData\\Local\\Programs\\Ollama" OLLAMA_LIBRARY_PATH=C:\Users\DaveyBoneZ\AppData\Local\Programs\Ollama\lib\ollama;C:\Users\DaveyBoneZ\AppData\Local\Programs\Ollama\lib\ollama\rocm HIP_VISIBLE_DEVICES=0
time=2026-03-30T13:42:49.909-04:00 level=DEBUG source=runner.go:437 msg="bootstrap discovery took" duration=367.4097ms OLLAMA_LIBRARY_PATH="[C:\\Users\\DaveyBoneZ\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\DaveyBoneZ\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\rocm]" extra_envs=map[HIP_VISIBLE_DEVICES:0]
time=2026-03-30T13:42:49.909-04:00 level=DEBUG source=runner.go:40 msg="overall device VRAM discovery took" duration=367.9302ms
time=2026-03-30T13:42:49.910-04:00 level=INFO source=cpu_windows.go:148 msg=packages count=1
time=2026-03-30T13:42:49.910-04:00 level=INFO source=cpu_windows.go:195 msg="" package=0 cores=8 efficiency=0 threads=16
time=2026-03-30T13:42:49.910-04:00 level=DEBUG source=sched.go:220 msg="updating default concurrency" OLLAMA_MAX_LOADED_MODELS=3 gpu_count=1
time=2026-03-30T13:42:49.910-04:00 level=DEBUG source=sched.go:229 msg="loading first model" model=C:\Users\DaveyBoneZ\.ollama\models\blobs\sha256-dec52a44569a2a25341c4e4d3fee25846eed4f6f0b936278e3a3c900bb99d37c
time=2026-03-30T13:42:49.977-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.alignment default=32
time=2026-03-30T13:42:50.013-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.alignment default=32
time=2026-03-30T13:42:50.016-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35.pooling_type default=0
time=2026-03-30T13:42:50.016-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35.attention.head_count_kv default=0
time=2026-03-30T13:42:50.016-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35.expert_count default=0
time=2026-03-30T13:42:50.016-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35.rope.scaling.type default=""
time=2026-03-30T13:42:50.016-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35.rope.type default=""
time=2026-03-30T13:42:50.016-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35.rope.scaling.factor default=1
time=2026-03-30T13:42:50.017-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35.rope.scaling.original_context_length default=0
time=2026-03-30T13:42:50.017-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35.attention.scale default=0
time=2026-03-30T13:42:50.017-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35.expert_count default=0
time=2026-03-30T13:42:50.017-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35.expert_used_count default=0
time=2026-03-30T13:42:50.017-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35.norm_top_k_prob default=true
time=2026-03-30T13:42:50.017-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35.mrope_interleaved default=false
time=2026-03-30T13:42:50.017-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35.vision.attention.layer_norm_epsilon default=9.999999974752427e-07
time=2026-03-30T13:42:50.017-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35.vision.rope.freq_base default=10000
time=2026-03-30T13:42:50.017-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35.vision.num_positional_embeddings default=2304
time=2026-03-30T13:42:50.017-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.add_bos_token default=false
time=2026-03-30T13:42:50.017-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.bos_token_id default=0
time=2026-03-30T13:42:50.017-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.eos_token_ids default="&{size:0 values:[]}"
time=2026-03-30T13:42:50.017-04:00 level=INFO source=server.go:247 msg="enabling flash attention"
time=2026-03-30T13:42:50.018-04:00 level=INFO source=server.go:432 msg="starting runner" cmd="C:\\Users\\DaveyBoneZ\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --model C:\\Users\\DaveyBoneZ\\.ollama\\models\\blobs\\sha256-dec52a44569a2a25341c4e4d3fee25846eed4f6f0b936278e3a3c900bb99d37c --port 57002"
time=2026-03-30T13:42:50.018-04:00 level=DEBUG source=server.go:433 msg=subprocess HIP_PATH="C:\\Program Files\\AMD\\ROCm\\6.4\\" HIP_PATH_64="C:\\Program Files\\AMD\\ROCm\\6.4\\" HIP_PATH_71="C:\\Program Files\\AMD\\ROCm\\7.1\\" OLLAMA_CONTEXT_LENGTH=32768 OLLAMA_DEBUG=1 OLLAMA_FLASH_ATTENTION=1 OLLAMA_HOST=0.0.0.0 OLLAMA_KV_CACHE_TYPE=q8_0 PATH="C:\\Users\\DaveyBoneZ\\AppData\\Local\\Programs\\Ollama\\lib\\ollama;C:\\Users\\DaveyBoneZ\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\rocm;C:\\WINDOWS\\system32;C:\\WINDOWS;C:\\WINDOWS\\System32\\Wbem;C:\\WINDOWS\\System32\\WindowsPowerShell\\v1.0\\;C:\\WINDOWS\\System32\\OpenSSH\\;C:\\Users\\DaveyBoneZ\\AppData\\Local\\AMD\\AI_Bundle\\VSCode\\bin;C:\\Program Files\\Git\\cmd;C:\\Program Files\\Docker\\Docker\\resources\\bin;C:\\Program Files\\PowerShell\\7\\;C:\\Program Files\\AMD\\ROCm\\7.1\\bin;C:\\Users\\DaveyBoneZ\\AppData\\Local\\Programs\\Python\\Launcher\\;C:\\Users\\DaveyBoneZ\\AppData\\Local\\Microsoft\\WindowsApps;C:\\Users\\DaveyBoneZ\\AppData\\Local\\AMD\\AI_Bundle\\Ollama;C:\\Users\\DaveyBoneZ\\.lmstudio\\bin;C:\\Users\\DaveyBoneZ\\AppData\\Local\\Python\\bin;C:\\Users\\DaveyBoneZ\\AppData\\Local\\Programs\\Ollama" OLLAMA_LIBRARY_PATH=C:\Users\DaveyBoneZ\AppData\Local\Programs\Ollama\lib\ollama;C:\Users\DaveyBoneZ\AppData\Local\Programs\Ollama\lib\ollama\rocm HIP_VISIBLE_DEVICES=0
time=2026-03-30T13:42:50.021-04:00 level=INFO source=sched.go:484 msg="system memory" total="31.9 GiB" free="22.8 GiB" free_swap="25.3 GiB"
time=2026-03-30T13:42:50.021-04:00 level=INFO source=sched.go:491 msg="gpu memory" id=0 library=ROCm available="14.4 GiB" free="14.8 GiB" minimum="457.0 MiB" overhead="0 B"
time=2026-03-30T13:42:50.021-04:00 level=INFO source=server.go:759 msg="loading model" "model layers"=33 requested=-1
time=2026-03-30T13:42:50.051-04:00 level=INFO source=runner.go:1411 msg="starting ollama engine"
time=2026-03-30T13:42:50.052-04:00 level=INFO source=runner.go:1446 msg="Server listening on 127.0.0.1:57002"
time=2026-03-30T13:42:50.063-04:00 level=INFO source=runner.go:1284 msg=load request="{Operation:fit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:32768 KvCacheType:q8_0 NumThreads:8 GPULayers:33[ID:0 Layers:33(0..32)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
time=2026-03-30T13:42:50.100-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.alignment default=32
time=2026-03-30T13:42:50.102-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.name default=""
time=2026-03-30T13:42:50.102-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.description default=""
time=2026-03-30T13:42:50.103-04:00 level=INFO source=ggml.go:136 msg="" architecture=qwen35 file_type=Q4_K_M name="" description="" num_tensors=883 num_key_values=52
time=2026-03-30T13:42:50.103-04:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=C:\Users\DaveyBoneZ\AppData\Local\Programs\Ollama\lib\ollama
load_backend: loaded CPU backend from C:\Users\DaveyBoneZ\AppData\Local\Programs\Ollama\lib\ollama\ggml-cpu-haswell.dll
time=2026-03-30T13:42:50.116-04:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=C:\Users\DaveyBoneZ\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 9060 XT, gfx1200 (0x1200), VMM: no, Wave Size: 32, ID: 0
load_backend: loaded ROCm backend from C:\Users\DaveyBoneZ\AppData\Local\Programs\Ollama\lib\ollama\rocm\ggml-hip.dll
time=2026-03-30T13:42:50.142-04:00 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=2026-03-30T13:42:50.146-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35.pooling_type default=0
time=2026-03-30T13:42:50.146-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35.attention.head_count_kv default=0
time=2026-03-30T13:42:50.146-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35.expert_count default=0
time=2026-03-30T13:42:50.146-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35.rope.scaling.type default=""
time=2026-03-30T13:42:50.146-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35.rope.type default=""
time=2026-03-30T13:42:50.146-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35.rope.scaling.factor default=1
time=2026-03-30T13:42:50.146-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35.rope.scaling.original_context_length default=0
time=2026-03-30T13:42:50.146-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35.attention.scale default=0
time=2026-03-30T13:42:50.146-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35.expert_count default=0
time=2026-03-30T13:42:50.146-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35.expert_used_count default=0
time=2026-03-30T13:42:50.146-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35.norm_top_k_prob default=true
time=2026-03-30T13:42:50.146-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35.mrope_interleaved default=false
time=2026-03-30T13:42:50.146-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35.vision.attention.layer_norm_epsilon default=9.999999974752427e-07
time=2026-03-30T13:42:50.146-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35.vision.rope.freq_base default=10000
time=2026-03-30T13:42:50.146-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35.vision.num_positional_embeddings default=2304
time=2026-03-30T13:42:50.146-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.add_bos_token default=false
time=2026-03-30T13:42:50.146-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.bos_token_id default=0
time=2026-03-30T13:42:50.146-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.eos_token_ids default="&{size:0 values:[]}"
time=2026-03-30T13:42:50.544-04:00 level=DEBUG source=ggml.go:852 msg="compute graph" nodes=1258 splits=1
rocBLAS error from hip error code: 'hipErrorInvalidDeviceFunction':98
ggml_cuda_compute_forward: SOLVE_TRI failed
ROCm error: invalid device function
  current device: 0, in function ggml_cuda_compute_forward at C:/a/ollama/ollama/ml/backend/ggml/ggml/src/ggml-cuda/ggml-cuda.cu:2882
  err
C:/a/ollama/ollama/ml/backend/ggml/ggml/src/ggml-cuda/ggml-cuda.cu:94: ROCm error
time=2026-03-30T13:42:51.742-04:00 level=ERROR source=server.go:1207 msg="do load request" error="Post \"http://127.0.0.1:57002/load\": read tcp 127.0.0.1:57007->127.0.0.1:57002: wsarecv: An existing connection was forcibly closed by the remote host."
time=2026-03-30T13:42:51.742-04:00 level=ERROR source=server.go:1207 msg="do load request" error="Post \"http://127.0.0.1:57002/load\": dial tcp 127.0.0.1:57002: connectex: No connection could be made because the target machine actively refused it."
time=2026-03-30T13:42:51.743-04:00 level=INFO source=sched.go:511 msg="Load failed" model=C:\Users\DaveyBoneZ\.ollama\models\blobs\sha256-dec52a44569a2a25341c4e4d3fee25846eed4f6f0b936278e3a3c900bb99d37c error="model failed to load, this may be due to resource limitations or an internal error, check ollama server logs for details"
time=2026-03-30T13:42:51.743-04:00 level=DEBUG source=server.go:1832 msg="stopping llama server" pid=2444
[GIN] 2026/03/30 - 13:42:51 | 500 |    2.3317189s |       127.0.0.1 | POST     "/api/chat"
time=2026-03-30T13:42:51.764-04:00 level=ERROR source=server.go:304 msg="llama runner terminated" error="exit status 1"
[GIN] 2026/03/30 - 13:43:19 | 200 |      1.5188ms |       127.0.0.1 | GET      "/api/tags"
[GIN] 2026/03/30 - 13:43:50 | 200 |       505.2µs |       127.0.0.1 | GET      "/api/tags"

OS

Win 11 pro

GPU

RX 9060 XT

CPU

AMD Ryzen 7 5800X3D

Ollama version

v0.18.3 > Current

Originally created by @DaveyBonez on GitHub (Apr 5, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/15343 ### What is the issue? Error 500 Internal Server Error: model failed to load, this may be due to resource limitations or an internal error, check ollama server logs for details windows 11 GPU: RX 9060 XT only happens with Qwen models. ### Relevant log output ```shell time=2026-03-30T13:42:49.541-04:00 level=DEBUG source=runner.go:264 msg="refreshing free memory" time=2026-03-30T13:42:49.541-04:00 level=DEBUG source=runner.go:328 msg="unable to refresh all GPUs with existing runners, performing bootstrap discovery" time=2026-03-30T13:42:49.544-04:00 level=INFO source=server.go:432 msg="starting runner" cmd="C:\\Users\\DaveyBoneZ\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --port 56996" time=2026-03-30T13:42:49.544-04:00 level=DEBUG source=server.go:433 msg=subprocess HIP_PATH="C:\\Program Files\\AMD\\ROCm\\6.4\\" HIP_PATH_64="C:\\Program Files\\AMD\\ROCm\\6.4\\" HIP_PATH_71="C:\\Program Files\\AMD\\ROCm\\7.1\\" OLLAMA_CONTEXT_LENGTH=32768 OLLAMA_DEBUG=1 OLLAMA_FLASH_ATTENTION=1 OLLAMA_HOST=0.0.0.0 OLLAMA_KV_CACHE_TYPE=q8_0 PATH="C:\\Users\\DaveyBoneZ\\AppData\\Local\\Programs\\Ollama\\lib\\ollama;C:\\Users\\DaveyBoneZ\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\rocm;C:\\WINDOWS\\system32;C:\\WINDOWS;C:\\WINDOWS\\System32\\Wbem;C:\\WINDOWS\\System32\\WindowsPowerShell\\v1.0\\;C:\\WINDOWS\\System32\\OpenSSH\\;C:\\Users\\DaveyBoneZ\\AppData\\Local\\AMD\\AI_Bundle\\VSCode\\bin;C:\\Program Files\\Git\\cmd;C:\\Program Files\\Docker\\Docker\\resources\\bin;C:\\Program Files\\PowerShell\\7\\;C:\\Program Files\\AMD\\ROCm\\7.1\\bin;C:\\Users\\DaveyBoneZ\\AppData\\Local\\Programs\\Python\\Launcher\\;C:\\Users\\DaveyBoneZ\\AppData\\Local\\Microsoft\\WindowsApps;C:\\Users\\DaveyBoneZ\\AppData\\Local\\AMD\\AI_Bundle\\Ollama;C:\\Users\\DaveyBoneZ\\.lmstudio\\bin;C:\\Users\\DaveyBoneZ\\AppData\\Local\\Python\\bin;C:\\Users\\DaveyBoneZ\\AppData\\Local\\Programs\\Ollama" OLLAMA_LIBRARY_PATH=C:\Users\DaveyBoneZ\AppData\Local\Programs\Ollama\lib\ollama;C:\Users\DaveyBoneZ\AppData\Local\Programs\Ollama\lib\ollama\rocm HIP_VISIBLE_DEVICES=0 time=2026-03-30T13:42:49.909-04:00 level=DEBUG source=runner.go:437 msg="bootstrap discovery took" duration=367.4097ms OLLAMA_LIBRARY_PATH="[C:\\Users\\DaveyBoneZ\\AppData\\Local\\Programs\\Ollama\\lib\\ollama C:\\Users\\DaveyBoneZ\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\rocm]" extra_envs=map[HIP_VISIBLE_DEVICES:0] time=2026-03-30T13:42:49.909-04:00 level=DEBUG source=runner.go:40 msg="overall device VRAM discovery took" duration=367.9302ms time=2026-03-30T13:42:49.910-04:00 level=INFO source=cpu_windows.go:148 msg=packages count=1 time=2026-03-30T13:42:49.910-04:00 level=INFO source=cpu_windows.go:195 msg="" package=0 cores=8 efficiency=0 threads=16 time=2026-03-30T13:42:49.910-04:00 level=DEBUG source=sched.go:220 msg="updating default concurrency" OLLAMA_MAX_LOADED_MODELS=3 gpu_count=1 time=2026-03-30T13:42:49.910-04:00 level=DEBUG source=sched.go:229 msg="loading first model" model=C:\Users\DaveyBoneZ\.ollama\models\blobs\sha256-dec52a44569a2a25341c4e4d3fee25846eed4f6f0b936278e3a3c900bb99d37c time=2026-03-30T13:42:49.977-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.alignment default=32 time=2026-03-30T13:42:50.013-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.alignment default=32 time=2026-03-30T13:42:50.016-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35.pooling_type default=0 time=2026-03-30T13:42:50.016-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35.attention.head_count_kv default=0 time=2026-03-30T13:42:50.016-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35.expert_count default=0 time=2026-03-30T13:42:50.016-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35.rope.scaling.type default="" time=2026-03-30T13:42:50.016-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35.rope.type default="" time=2026-03-30T13:42:50.016-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35.rope.scaling.factor default=1 time=2026-03-30T13:42:50.017-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35.rope.scaling.original_context_length default=0 time=2026-03-30T13:42:50.017-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35.attention.scale default=0 time=2026-03-30T13:42:50.017-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35.expert_count default=0 time=2026-03-30T13:42:50.017-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35.expert_used_count default=0 time=2026-03-30T13:42:50.017-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35.norm_top_k_prob default=true time=2026-03-30T13:42:50.017-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35.mrope_interleaved default=false time=2026-03-30T13:42:50.017-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35.vision.attention.layer_norm_epsilon default=9.999999974752427e-07 time=2026-03-30T13:42:50.017-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35.vision.rope.freq_base default=10000 time=2026-03-30T13:42:50.017-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35.vision.num_positional_embeddings default=2304 time=2026-03-30T13:42:50.017-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.add_bos_token default=false time=2026-03-30T13:42:50.017-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.bos_token_id default=0 time=2026-03-30T13:42:50.017-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.eos_token_ids default="&{size:0 values:[]}" time=2026-03-30T13:42:50.017-04:00 level=INFO source=server.go:247 msg="enabling flash attention" time=2026-03-30T13:42:50.018-04:00 level=INFO source=server.go:432 msg="starting runner" cmd="C:\\Users\\DaveyBoneZ\\AppData\\Local\\Programs\\Ollama\\ollama.exe runner --ollama-engine --model C:\\Users\\DaveyBoneZ\\.ollama\\models\\blobs\\sha256-dec52a44569a2a25341c4e4d3fee25846eed4f6f0b936278e3a3c900bb99d37c --port 57002" time=2026-03-30T13:42:50.018-04:00 level=DEBUG source=server.go:433 msg=subprocess HIP_PATH="C:\\Program Files\\AMD\\ROCm\\6.4\\" HIP_PATH_64="C:\\Program Files\\AMD\\ROCm\\6.4\\" HIP_PATH_71="C:\\Program Files\\AMD\\ROCm\\7.1\\" OLLAMA_CONTEXT_LENGTH=32768 OLLAMA_DEBUG=1 OLLAMA_FLASH_ATTENTION=1 OLLAMA_HOST=0.0.0.0 OLLAMA_KV_CACHE_TYPE=q8_0 PATH="C:\\Users\\DaveyBoneZ\\AppData\\Local\\Programs\\Ollama\\lib\\ollama;C:\\Users\\DaveyBoneZ\\AppData\\Local\\Programs\\Ollama\\lib\\ollama\\rocm;C:\\WINDOWS\\system32;C:\\WINDOWS;C:\\WINDOWS\\System32\\Wbem;C:\\WINDOWS\\System32\\WindowsPowerShell\\v1.0\\;C:\\WINDOWS\\System32\\OpenSSH\\;C:\\Users\\DaveyBoneZ\\AppData\\Local\\AMD\\AI_Bundle\\VSCode\\bin;C:\\Program Files\\Git\\cmd;C:\\Program Files\\Docker\\Docker\\resources\\bin;C:\\Program Files\\PowerShell\\7\\;C:\\Program Files\\AMD\\ROCm\\7.1\\bin;C:\\Users\\DaveyBoneZ\\AppData\\Local\\Programs\\Python\\Launcher\\;C:\\Users\\DaveyBoneZ\\AppData\\Local\\Microsoft\\WindowsApps;C:\\Users\\DaveyBoneZ\\AppData\\Local\\AMD\\AI_Bundle\\Ollama;C:\\Users\\DaveyBoneZ\\.lmstudio\\bin;C:\\Users\\DaveyBoneZ\\AppData\\Local\\Python\\bin;C:\\Users\\DaveyBoneZ\\AppData\\Local\\Programs\\Ollama" OLLAMA_LIBRARY_PATH=C:\Users\DaveyBoneZ\AppData\Local\Programs\Ollama\lib\ollama;C:\Users\DaveyBoneZ\AppData\Local\Programs\Ollama\lib\ollama\rocm HIP_VISIBLE_DEVICES=0 time=2026-03-30T13:42:50.021-04:00 level=INFO source=sched.go:484 msg="system memory" total="31.9 GiB" free="22.8 GiB" free_swap="25.3 GiB" time=2026-03-30T13:42:50.021-04:00 level=INFO source=sched.go:491 msg="gpu memory" id=0 library=ROCm available="14.4 GiB" free="14.8 GiB" minimum="457.0 MiB" overhead="0 B" time=2026-03-30T13:42:50.021-04:00 level=INFO source=server.go:759 msg="loading model" "model layers"=33 requested=-1 time=2026-03-30T13:42:50.051-04:00 level=INFO source=runner.go:1411 msg="starting ollama engine" time=2026-03-30T13:42:50.052-04:00 level=INFO source=runner.go:1446 msg="Server listening on 127.0.0.1:57002" time=2026-03-30T13:42:50.063-04:00 level=INFO source=runner.go:1284 msg=load request="{Operation:fit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:32768 KvCacheType:q8_0 NumThreads:8 GPULayers:33[ID:0 Layers:33(0..32)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" time=2026-03-30T13:42:50.100-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.alignment default=32 time=2026-03-30T13:42:50.102-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.name default="" time=2026-03-30T13:42:50.102-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.description default="" time=2026-03-30T13:42:50.103-04:00 level=INFO source=ggml.go:136 msg="" architecture=qwen35 file_type=Q4_K_M name="" description="" num_tensors=883 num_key_values=52 time=2026-03-30T13:42:50.103-04:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=C:\Users\DaveyBoneZ\AppData\Local\Programs\Ollama\lib\ollama load_backend: loaded CPU backend from C:\Users\DaveyBoneZ\AppData\Local\Programs\Ollama\lib\ollama\ggml-cpu-haswell.dll time=2026-03-30T13:42:50.116-04:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=C:\Users\DaveyBoneZ\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 9060 XT, gfx1200 (0x1200), VMM: no, Wave Size: 32, ID: 0 load_backend: loaded ROCm backend from C:\Users\DaveyBoneZ\AppData\Local\Programs\Ollama\lib\ollama\rocm\ggml-hip.dll time=2026-03-30T13:42:50.142-04:00 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=2026-03-30T13:42:50.146-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35.pooling_type default=0 time=2026-03-30T13:42:50.146-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35.attention.head_count_kv default=0 time=2026-03-30T13:42:50.146-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35.expert_count default=0 time=2026-03-30T13:42:50.146-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35.rope.scaling.type default="" time=2026-03-30T13:42:50.146-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35.rope.type default="" time=2026-03-30T13:42:50.146-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35.rope.scaling.factor default=1 time=2026-03-30T13:42:50.146-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35.rope.scaling.original_context_length default=0 time=2026-03-30T13:42:50.146-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35.attention.scale default=0 time=2026-03-30T13:42:50.146-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35.expert_count default=0 time=2026-03-30T13:42:50.146-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35.expert_used_count default=0 time=2026-03-30T13:42:50.146-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35.norm_top_k_prob default=true time=2026-03-30T13:42:50.146-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35.mrope_interleaved default=false time=2026-03-30T13:42:50.146-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35.vision.attention.layer_norm_epsilon default=9.999999974752427e-07 time=2026-03-30T13:42:50.146-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35.vision.rope.freq_base default=10000 time=2026-03-30T13:42:50.146-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=qwen35.vision.num_positional_embeddings default=2304 time=2026-03-30T13:42:50.146-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.add_bos_token default=false time=2026-03-30T13:42:50.146-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.bos_token_id default=0 time=2026-03-30T13:42:50.146-04:00 level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.eos_token_ids default="&{size:0 values:[]}" time=2026-03-30T13:42:50.544-04:00 level=DEBUG source=ggml.go:852 msg="compute graph" nodes=1258 splits=1 rocBLAS error from hip error code: 'hipErrorInvalidDeviceFunction':98 ggml_cuda_compute_forward: SOLVE_TRI failed ROCm error: invalid device function current device: 0, in function ggml_cuda_compute_forward at C:/a/ollama/ollama/ml/backend/ggml/ggml/src/ggml-cuda/ggml-cuda.cu:2882 err C:/a/ollama/ollama/ml/backend/ggml/ggml/src/ggml-cuda/ggml-cuda.cu:94: ROCm error time=2026-03-30T13:42:51.742-04:00 level=ERROR source=server.go:1207 msg="do load request" error="Post \"http://127.0.0.1:57002/load\": read tcp 127.0.0.1:57007->127.0.0.1:57002: wsarecv: An existing connection was forcibly closed by the remote host." time=2026-03-30T13:42:51.742-04:00 level=ERROR source=server.go:1207 msg="do load request" error="Post \"http://127.0.0.1:57002/load\": dial tcp 127.0.0.1:57002: connectex: No connection could be made because the target machine actively refused it." time=2026-03-30T13:42:51.743-04:00 level=INFO source=sched.go:511 msg="Load failed" model=C:\Users\DaveyBoneZ\.ollama\models\blobs\sha256-dec52a44569a2a25341c4e4d3fee25846eed4f6f0b936278e3a3c900bb99d37c error="model failed to load, this may be due to resource limitations or an internal error, check ollama server logs for details" time=2026-03-30T13:42:51.743-04:00 level=DEBUG source=server.go:1832 msg="stopping llama server" pid=2444 [GIN] 2026/03/30 - 13:42:51 | 500 | 2.3317189s | 127.0.0.1 | POST "/api/chat" time=2026-03-30T13:42:51.764-04:00 level=ERROR source=server.go:304 msg="llama runner terminated" error="exit status 1" [GIN] 2026/03/30 - 13:43:19 | 200 | 1.5188ms | 127.0.0.1 | GET "/api/tags" [GIN] 2026/03/30 - 13:43:50 | 200 | 505.2µs | 127.0.0.1 | GET "/api/tags" ``` ### OS Win 11 pro ### GPU RX 9060 XT ### CPU AMD Ryzen 7 5800X3D ### Ollama version [v0.18.3](https://github.com/ollama/ollama/releases/tag/v0.18.3) > Current
GiteaMirror added the bug label 2026-05-05 02:47:58 -05:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#71875
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?