github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 08:30:05 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #14527] Support for AMD Radeon 760M (RDNA 3 iGPU) GPU Offloading #55937

New Issue
Closed
opened 2026-04-29 09:58:20 -05:00 by GiteaMirror · 4 comments
GiteaMirror commented 2026-04-29 09:58:20 -05:00
Owner
Copy Link

Originally created by @StigThomsen on GitHub (Mar 1, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/14527

Summary:
Ollama does not detect or support GPU offloading for the AMD Radeon 760M (RDNA 3 integrated GPU), despite ROCm 7.2 and Vulkan being correctly installed and functional. Ollama silently falls back to CPU mode with no errors, even when OLLAMA_VULKAN=1 and other relevant environment variables are set.
Expected Behavior:

Ollama should detect the Radeon 760M (RDNA 3 iGPU) and offload layers to the GPU when OLLAMA_VULKAN=1 is enabled.
Logs should indicate successful GPU detection and layer offloading (e.g., offloaded X/41 layers to GPU).
Actual Behavior:

Ollama logs show devices=[] and total_vram="0 B", indicating no GPU was detected.
Ollama falls back to CPU-only mode (id=cpu) with no errors or warnings about GPU incompatibility.

Environment Details

OS: Ubuntu 24.04 (Noble Numbat)
Kernel: 6.8.0-101-generic
CPU: AMD Ryzen 5 7640HS (6 cores/12 threads)
GPU: AMD Radeon 760M (RDNA 3, integrated)
RAM: 32GB
ROCm: 7.2.0
Vulkan: Working (confirmed with vulkaninfo | grep "GPU id")
Ollama Version: 0.17.4

Ollama startup logs (snips)
level=TRACE source=runner.go:467 msg="runner enumerated devices" OLLAMA_LIBRARY_PATH="[/usr/local/lib/ollama /usr/local/lib/ollama/vulkan]" devices=[]
level=INFO source=routes.go:1768 msg="vram-based default context" total_vram="0 B" default_num_ctx=4096
level=INFO source=types.go:60 msg="inference compute" id=cpu library=cpu compute="" name=cpu description=cpu libdirs=ollama driver="" pci_id="" type="" total="25.2 GiB" available="23.7 GiB"

vulkaninfo | grep "GPU id"
'DISPLAY' environment variable not set... skipping surface info
GPU id = 0 (AMD Radeon Graphics (RADV PHOENIX))
GPU id = 1 (llvmpipe (LLVM 20.1.2, 256 bits))
GPU id = 0 (AMD Radeon Graphics (RADV PHOENIX))
GPU id = 1 (llvmpipe (LLVM 20.1.2, 256 bits))
GPU id = 0 (AMD Radeon Graphics (RADV PHOENIX))
GPU id = 1 (llvmpipe (LLVM 20.1.2, 256 bits))
GPU id = 0 (AMD Radeon Graphics (RADV PHOENIX))
GPU id = 1 (llvmpipe (LLVM 20.1.2, 256 bits))

ROCm-SMI Output (GPU Detection)
$ rocm-smi
========================= ROCm System Management Interface =========================
=================================== Concise Info ===================================
GPU[0] : get_power_cap, Not supported on the given system
GPU Temp (DieEdge) AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% Mem%
0 37.0c 4.185W None 2400Mhz 0% auto Unsupported 1% 0%

$ rocm-smi --showmeminfo vram
========================= ROCm System Management Interface =========================
=============================== Memory Usage (Bytes) ===============================
GPU[0] : VRAM Total Memory (B): 6442450944
GPU[0] : VRAM Total Used Memory (B): 72192000

Ollama Environment Variables
[Service]
Environment="OLLAMA_HOST=0.0.0.0:11434"
Environment="OLLAMA_DEBUG=2"
Environment="AMD_LOG_LEVEL=3"
Environment="OLLAMA_AMD_GPU=1"
Environment="OLLAMA_VULKAN=1"

Additional Context

The Radeon 760M is an RDNA 3 integrated GPU with 6GB of shared VRAM (confirmed via rocm-smi).
ROCm and Vulkan are working correctly and detect the GPU.
Ollama’s GPU discovery process does not recognize the Radeon 760M as a compatible device, even with OLLAMA_VULKAN=1.

Originally created by @StigThomsen on GitHub (Mar 1, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/14527 Summary: Ollama does not detect or support GPU offloading for the AMD Radeon 760M (RDNA 3 integrated GPU), despite ROCm 7.2 and Vulkan being correctly installed and functional. Ollama silently falls back to CPU mode with no errors, even when OLLAMA_VULKAN=1 and other relevant environment variables are set. Expected Behavior: Ollama should detect the Radeon 760M (RDNA 3 iGPU) and offload layers to the GPU when OLLAMA_VULKAN=1 is enabled. Logs should indicate successful GPU detection and layer offloading (e.g., offloaded X/41 layers to GPU). Actual Behavior: Ollama logs show devices=[] and total_vram="0 B", indicating no GPU was detected. Ollama falls back to CPU-only mode (id=cpu) with no errors or warnings about GPU incompatibility. Environment Details OS: Ubuntu 24.04 (Noble Numbat) Kernel: 6.8.0-101-generic CPU: AMD Ryzen 5 7640HS (6 cores/12 threads) GPU: AMD Radeon 760M (RDNA 3, integrated) RAM: 32GB ROCm: 7.2.0 Vulkan: Working (confirmed with vulkaninfo | grep "GPU id") Ollama Version: 0.17.4 Ollama startup logs (snips) level=TRACE source=runner.go:467 msg="runner enumerated devices" OLLAMA_LIBRARY_PATH="[/usr/local/lib/ollama /usr/local/lib/ollama/vulkan]" devices=[] level=INFO source=routes.go:1768 msg="vram-based default context" total_vram="0 B" default_num_ctx=4096 level=INFO source=types.go:60 msg="inference compute" id=cpu library=cpu compute="" name=cpu description=cpu libdirs=ollama driver="" pci_id="" type="" total="25.2 GiB" available="23.7 GiB" vulkaninfo | grep "GPU id" 'DISPLAY' environment variable not set... skipping surface info GPU id = 0 (AMD Radeon Graphics (RADV PHOENIX)) GPU id = 1 (llvmpipe (LLVM 20.1.2, 256 bits)) GPU id = 0 (AMD Radeon Graphics (RADV PHOENIX)) GPU id = 1 (llvmpipe (LLVM 20.1.2, 256 bits)) GPU id = 0 (AMD Radeon Graphics (RADV PHOENIX)) GPU id = 1 (llvmpipe (LLVM 20.1.2, 256 bits)) GPU id = 0 (AMD Radeon Graphics (RADV PHOENIX)) GPU id = 1 (llvmpipe (LLVM 20.1.2, 256 bits)) ROCm-SMI Output (GPU Detection) $ rocm-smi ========================= ROCm System Management Interface ========================= =================================== Concise Info =================================== GPU[0] : get_power_cap, Not supported on the given system GPU Temp (DieEdge) AvgPwr SCLK MCLK Fan Perf PwrCap VRAM% GPU% Mem% 0 37.0c 4.185W None 2400Mhz 0% auto Unsupported 1% 0% $ rocm-smi --showmeminfo vram ========================= ROCm System Management Interface ========================= =============================== Memory Usage (Bytes) =============================== GPU[0] : VRAM Total Memory (B): 6442450944 GPU[0] : VRAM Total Used Memory (B): 72192000 Ollama Environment Variables [Service] Environment="OLLAMA_HOST=0.0.0.0:11434" Environment="OLLAMA_DEBUG=2" Environment="AMD_LOG_LEVEL=3" Environment="OLLAMA_AMD_GPU=1" Environment="OLLAMA_VULKAN=1" Additional Context The Radeon 760M is an RDNA 3 integrated GPU with 6GB of shared VRAM (confirmed via rocm-smi). ROCm and Vulkan are working correctly and detect the GPU. Ollama’s GPU discovery process does not recognize the Radeon 760M as a compatible device, even with OLLAMA_VULKAN=1.
GiteaMirror added the feature request label 2026-04-29 09:58:20 -05:00
GiteaMirror commented 2026-04-29 09:58:22 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Mar 1, 2026):

Set OLLAMA_DEBUG=2 in the server environment and post the log from the start up to and including the line that contains inference compute.

<!-- gh-comment-id:3979854629 --> @rick-github commented on GitHub (Mar 1, 2026): Set `OLLAMA_DEBUG=2` in the server environment and post the log from the start up to and including the line that contains `inference compute`.
GiteaMirror commented 2026-04-29 09:58:23 -05:00
Author
Owner
Copy Link

@StigThomsen commented on GitHub (Mar 1, 2026):

My pleasure :-)

Mar 01 11:06:25 ai-server systemd[1]: Started ollama.service - Ollama Service.
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.107Z level=INFO source=routes.go:1663 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:0 OLLAMA_DEBUG:DEBUG-4 OLLAMA_EDITOR: 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:/usr/share/ollama/.ollama/models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NO_CLOUD: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:true ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]"
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.107Z level=INFO source=routes.go:1665 msg="Ollama cloud disabled: false"
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.107Z level=INFO source=images.go:473 msg="total blobs: 17"
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.107Z level=INFO source=images.go:480 msg="total unused blobs removed: 0"
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.108Z level=INFO source=routes.go:1718 msg="Listening on [::]:11434 (version 0.17.4)"
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.108Z level=DEBUG source=sched.go:147 msg="starting llm scheduler"
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.108Z level=INFO source=runner.go:67 msg="discovering available GPUs..."
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.108Z level=TRACE source=runner.go:440 msg="starting runner for device discovery" libDirs="[/usr/local/lib/ollama /usr/local/lib/ollama/cuda_v13]" extraEnvs=map[]
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.109Z level=INFO source=server.go:431 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 42233"
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.109Z level=DEBUG source=server.go:432 msg=subprocess PATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/games:/usr/local/games:/snap/bin OLLAMA_HOST=0.0.0.0:11434 OLLAMA_DEBUG=2 OLLAMA_AMD_GPU=1 OLLAMA_VULKAN=1 LD_LIBRARY_PATH=/usr/local/lib/ollama:/usr/local/lib/ollama/cuda_v13 OLLAMA_LIBRARY_PATH=/usr/local/lib/ollama:/usr/local/lib/ollama/cuda_v13
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.117Z level=INFO source=runner.go:1411 msg="starting ollama engine"
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.118Z level=INFO source=runner.go:1446 msg="Server listening on 127.0.0.1:42233"
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.120Z level=DEBUG source=gguf.go:604 msg=general.architecture type=string
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.120Z level=DEBUG source=gguf.go:604 msg=tokenizer.ggml.model type=string
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.120Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.alignment default=32
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.120Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.alignment default=32
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.121Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.file_type default=0
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.121Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.name default=""
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.121Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.description default=""
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.121Z level=INFO source=ggml.go:136 msg="" architecture=llama file_type=unknown name="" description="" num_tensors=0 num_key_values=3
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.121Z level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=/usr/local/lib/ollama
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.122Z level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=/usr/local/lib/ollama/cuda_v13
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.123Z level=INFO source=ggml.go:104 msg=system CPU.0.LLAMAFILE=1 compiler=cgo(gcc)
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.123Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.block_count default=0
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.123Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.pooling_type default=0
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.123Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.expert_count default=0
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.123Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.tokens default="&{size:0 values:[]}"
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.123Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.scores default="&{size:0 values:[]}"
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.123Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.token_type default="&{size:0 values:[]}"
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.123Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.merges default="&{size:0 values:[]}"
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.123Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.add_bos_token default=true
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.123Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.bos_token_id default=0
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.123Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.add_eos_token default=false
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.123Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.eos_token_id default=0
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.123Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.eos_token_ids default="&{size:0 values:[]}"
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.123Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.pre default=""
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.123Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.block_count default=0
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.123Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.embedding_length default=0
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.123Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.attention.head_count default=0
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.123Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.attention.head_count_kv default=0
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.123Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.attention.key_length default=0
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.123Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.rope.dimension_count default=0
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.123Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.attention.layer_norm_rms_epsilon default=0
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.123Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.rope.freq_base default=100000
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.123Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.rope.scaling.factor default=1
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.123Z level=DEBUG source=runner.go:1386 msg="dummy model load took" duration=3.093638ms
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.123Z level=DEBUG source=runner.go:1391 msg="gathering device infos took" duration=291ns
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.123Z level=TRACE source=runner.go:467 msg="runner enumerated devices" OLLAMA_LIBRARY_PATH="[/usr/local/lib/ollama /usr/local/lib/ollama/cuda_v13]" devices=[]
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.124Z level=DEBUG source=runner.go:437 msg="bootstrap discovery took" duration=15.025827ms OLLAMA_LIBRARY_PATH="[/usr/local/lib/ollama /usr/local/lib/ollama/cuda_v13]" extra_envs=map[]
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.124Z level=TRACE source=runner.go:440 msg="starting runner for device discovery" libDirs="[/usr/local/lib/ollama /usr/local/lib/ollama/rocm]" extraEnvs=map[]
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.124Z level=INFO source=server.go:431 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 38811"
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.124Z level=DEBUG source=server.go:432 msg=subprocess PATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/games:/usr/local/games:/snap/bin OLLAMA_HOST=0.0.0.0:11434 OLLAMA_DEBUG=2 OLLAMA_AMD_GPU=1 OLLAMA_VULKAN=1 LD_LIBRARY_PATH=/usr/local/lib/ollama:/usr/local/lib/ollama/rocm OLLAMA_LIBRARY_PATH=/usr/local/lib/ollama:/usr/local/lib/ollama/rocm
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.132Z level=INFO source=runner.go:1411 msg="starting ollama engine"
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.133Z level=INFO source=runner.go:1446 msg="Server listening on 127.0.0.1:38811"
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.135Z level=DEBUG source=gguf.go:604 msg=general.architecture type=string
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.135Z level=DEBUG source=gguf.go:604 msg=tokenizer.ggml.model type=string
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.135Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.alignment default=32
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.135Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.alignment default=32
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.135Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.file_type default=0
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.136Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.name default=""
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.136Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.description default=""
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.136Z level=INFO source=ggml.go:136 msg="" architecture=llama file_type=unknown name="" description="" num_tensors=0 num_key_values=3
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.136Z level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=/usr/local/lib/ollama
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.137Z level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=/usr/local/lib/ollama/rocm
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.138Z level=INFO source=ggml.go:104 msg=system CPU.0.LLAMAFILE=1 compiler=cgo(gcc)
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.138Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.block_count default=0
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.139Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.pooling_type default=0
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.139Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.expert_count default=0
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.139Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.tokens default="&{size:0 values:[]}"
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.139Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.scores default="&{size:0 values:[]}"
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.139Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.token_type default="&{size:0 values:[]}"
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.139Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.merges default="&{size:0 values:[]}"
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.139Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.add_bos_token default=true
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.139Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.bos_token_id default=0
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.139Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.add_eos_token default=false
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.139Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.eos_token_id default=0
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.139Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.eos_token_ids default="&{size:0 values:[]}"
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.139Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.pre default=""
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.139Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.block_count default=0
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.139Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.embedding_length default=0
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.139Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.attention.head_count default=0
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.139Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.attention.head_count_kv default=0
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.139Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.attention.key_length default=0
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.139Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.rope.dimension_count default=0
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.139Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.attention.layer_norm_rms_epsilon default=0
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.139Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.rope.freq_base default=100000
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.139Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.rope.scaling.factor default=1
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.139Z level=DEBUG source=runner.go:1386 msg="dummy model load took" duration=3.854374ms
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.139Z level=DEBUG source=runner.go:1391 msg="gathering device infos took" duration=681ns
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.139Z level=TRACE source=runner.go:467 msg="runner enumerated devices" OLLAMA_LIBRARY_PATH="[/usr/local/lib/ollama /usr/local/lib/ollama/rocm]" devices=[]
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.139Z level=DEBUG source=runner.go:437 msg="bootstrap discovery took" duration=15.693312ms OLLAMA_LIBRARY_PATH="[/usr/local/lib/ollama /usr/local/lib/ollama/rocm]" extra_envs=map[]
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.139Z level=TRACE source=runner.go:440 msg="starting runner for device discovery" libDirs="[/usr/local/lib/ollama /usr/local/lib/ollama/vulkan]" extraEnvs=map[]
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.139Z level=INFO source=server.go:431 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 34175"
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.139Z level=DEBUG source=server.go:432 msg=subprocess PATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/games:/usr/local/games:/snap/bin OLLAMA_HOST=0.0.0.0:11434 OLLAMA_DEBUG=2 OLLAMA_AMD_GPU=1 OLLAMA_VULKAN=1 LD_LIBRARY_PATH=/usr/local/lib/ollama:/usr/local/lib/ollama/vulkan OLLAMA_LIBRARY_PATH=/usr/local/lib/ollama:/usr/local/lib/ollama/vulkan
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.148Z level=INFO source=runner.go:1411 msg="starting ollama engine"
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.148Z level=INFO source=runner.go:1446 msg="Server listening on 127.0.0.1:34175"
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.151Z level=DEBUG source=gguf.go:604 msg=general.architecture type=string
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.151Z level=DEBUG source=gguf.go:604 msg=tokenizer.ggml.model type=string
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.151Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.alignment default=32
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.151Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.alignment default=32
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.151Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.file_type default=0
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.151Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.name default=""
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.151Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.description default=""
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.151Z level=INFO source=ggml.go:136 msg="" architecture=llama file_type=unknown name="" description="" num_tensors=0 num_key_values=3
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.151Z level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=/usr/local/lib/ollama
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.152Z level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=/usr/local/lib/ollama/vulkan
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.153Z level=INFO source=ggml.go:104 msg=system CPU.0.LLAMAFILE=1 compiler=cgo(gcc)
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.153Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.block_count default=0
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.153Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.pooling_type default=0
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.153Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.expert_count default=0
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.153Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.tokens default="&{size:0 values:[]}"
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.153Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.scores default="&{size:0 values:[]}"
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.153Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.token_type default="&{size:0 values:[]}"
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.153Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.merges default="&{size:0 values:[]}"
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.153Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.add_bos_token default=true
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.153Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.bos_token_id default=0
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.153Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.add_eos_token default=false
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.153Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.eos_token_id default=0
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.153Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.eos_token_ids default="&{size:0 values:[]}"
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.153Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.pre default=""
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.153Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.block_count default=0
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.153Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.embedding_length default=0
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.153Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.attention.head_count default=0
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.153Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.attention.head_count_kv default=0
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.153Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.attention.key_length default=0
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.153Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.rope.dimension_count default=0
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.153Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.attention.layer_norm_rms_epsilon default=0
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.153Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.rope.freq_base default=100000
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.153Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.rope.scaling.factor default=1
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.153Z level=DEBUG source=runner.go:1386 msg="dummy model load took" duration=2.765596ms
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.153Z level=DEBUG source=runner.go:1391 msg="gathering device infos took" duration=200ns
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.154Z level=TRACE source=runner.go:467 msg="runner enumerated devices" OLLAMA_LIBRARY_PATH="[/usr/local/lib/ollama /usr/local/lib/ollama/vulkan]" devices=[]
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.154Z level=DEBUG source=runner.go:437 msg="bootstrap discovery took" duration=14.350126ms OLLAMA_LIBRARY_PATH="[/usr/local/lib/ollama /usr/local/lib/ollama/vulkan]" extra_envs=map[]
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.154Z level=TRACE source=runner.go:440 msg="starting runner for device discovery" libDirs="[/usr/local/lib/ollama /usr/local/lib/ollama/cuda_v12]" extraEnvs=map[]
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.154Z level=INFO source=server.go:431 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 43309"
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.154Z level=DEBUG source=server.go:432 msg=subprocess PATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/games:/usr/local/games:/snap/bin OLLAMA_HOST=0.0.0.0:11434 OLLAMA_DEBUG=2 OLLAMA_AMD_GPU=1 OLLAMA_VULKAN=1 LD_LIBRARY_PATH=/usr/local/lib/ollama:/usr/local/lib/ollama/cuda_v12 OLLAMA_LIBRARY_PATH=/usr/local/lib/ollama:/usr/local/lib/ollama/cuda_v12
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.163Z level=INFO source=runner.go:1411 msg="starting ollama engine"
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.163Z level=INFO source=runner.go:1446 msg="Server listening on 127.0.0.1:43309"
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.165Z level=DEBUG source=gguf.go:604 msg=general.architecture type=string
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.165Z level=DEBUG source=gguf.go:604 msg=tokenizer.ggml.model type=string
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.165Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.alignment default=32
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.165Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.alignment default=32
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.165Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.file_type default=0
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.165Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.name default=""
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.165Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.description default=""
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.165Z level=INFO source=ggml.go:136 msg="" architecture=llama file_type=unknown name="" description="" num_tensors=0 num_key_values=3
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.165Z level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=/usr/local/lib/ollama
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.166Z level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=/usr/local/lib/ollama/cuda_v12
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.168Z level=INFO source=ggml.go:104 msg=system CPU.0.LLAMAFILE=1 compiler=cgo(gcc)
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.168Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.block_count default=0
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.168Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.pooling_type default=0
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.168Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.expert_count default=0
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.168Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.tokens default="&{size:0 values:[]}"
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.168Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.scores default="&{size:0 values:[]}"
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.168Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.token_type default="&{size:0 values:[]}"
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.168Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.merges default="&{size:0 values:[]}"
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.168Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.add_bos_token default=true
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.168Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.bos_token_id default=0
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.168Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.add_eos_token default=false
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.168Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.eos_token_id default=0
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.168Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.eos_token_ids default="&{size:0 values:[]}"
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.168Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.pre default=""
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.168Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.block_count default=0
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.168Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.embedding_length default=0
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.168Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.attention.head_count default=0
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.168Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.attention.head_count_kv default=0
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.168Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.attention.key_length default=0
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.168Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.rope.dimension_count default=0
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.168Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.attention.layer_norm_rms_epsilon default=0
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.168Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.rope.freq_base default=100000
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.168Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.rope.scaling.factor default=1
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.168Z level=DEBUG source=runner.go:1386 msg="dummy model load took" duration=3.807558ms
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.168Z level=DEBUG source=runner.go:1391 msg="gathering device infos took" duration=220ns
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.168Z level=TRACE source=runner.go:467 msg="runner enumerated devices" OLLAMA_LIBRARY_PATH="[/usr/local/lib/ollama /usr/local/lib/ollama/cuda_v12]" devices=[]
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.169Z level=DEBUG source=runner.go:437 msg="bootstrap discovery took" duration=14.880079ms OLLAMA_LIBRARY_PATH="[/usr/local/lib/ollama /usr/local/lib/ollama/cuda_v12]" extra_envs=map[]
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.169Z level=DEBUG source=runner.go:124 msg="evaluating which, if any, devices to filter out" initial_count=0
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.169Z level=TRACE source=runner.go:174 msg="supported GPU library combinations before filtering" supported=map[]
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.169Z level=DEBUG source=runner.go:40 msg="GPU bootstrap discovery took" duration=60.604196ms
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.169Z level=INFO source=types.go:60 msg="inference compute" id=cpu library=cpu compute="" name=cpu description=cpu libdirs=ollama driver="" pci_id="" type="" total="25.2 GiB" available="23.8 GiB"
Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.169Z level=INFO source=routes.go:1768 msg="vram-based default context" total_vram="0 B" default_num_ctx=4096
<!-- gh-comment-id:3979928536 --> @StigThomsen commented on GitHub (Mar 1, 2026): My pleasure :-) ``` Mar 01 11:06:25 ai-server systemd[1]: Started ollama.service - Ollama Service. Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.107Z level=INFO source=routes.go:1663 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:0 OLLAMA_DEBUG:DEBUG-4 OLLAMA_EDITOR: 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:/usr/share/ollama/.ollama/models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NO_CLOUD: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:true ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]" Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.107Z level=INFO source=routes.go:1665 msg="Ollama cloud disabled: false" Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.107Z level=INFO source=images.go:473 msg="total blobs: 17" Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.107Z level=INFO source=images.go:480 msg="total unused blobs removed: 0" Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.108Z level=INFO source=routes.go:1718 msg="Listening on [::]:11434 (version 0.17.4)" Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.108Z level=DEBUG source=sched.go:147 msg="starting llm scheduler" Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.108Z level=INFO source=runner.go:67 msg="discovering available GPUs..." Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.108Z level=TRACE source=runner.go:440 msg="starting runner for device discovery" libDirs="[/usr/local/lib/ollama /usr/local/lib/ollama/cuda_v13]" extraEnvs=map[] Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.109Z level=INFO source=server.go:431 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 42233" Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.109Z level=DEBUG source=server.go:432 msg=subprocess PATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/games:/usr/local/games:/snap/bin OLLAMA_HOST=0.0.0.0:11434 OLLAMA_DEBUG=2 OLLAMA_AMD_GPU=1 OLLAMA_VULKAN=1 LD_LIBRARY_PATH=/usr/local/lib/ollama:/usr/local/lib/ollama/cuda_v13 OLLAMA_LIBRARY_PATH=/usr/local/lib/ollama:/usr/local/lib/ollama/cuda_v13 Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.117Z level=INFO source=runner.go:1411 msg="starting ollama engine" Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.118Z level=INFO source=runner.go:1446 msg="Server listening on 127.0.0.1:42233" Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.120Z level=DEBUG source=gguf.go:604 msg=general.architecture type=string Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.120Z level=DEBUG source=gguf.go:604 msg=tokenizer.ggml.model type=string Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.120Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.alignment default=32 Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.120Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.alignment default=32 Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.121Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.file_type default=0 Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.121Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.name default="" Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.121Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.description default="" Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.121Z level=INFO source=ggml.go:136 msg="" architecture=llama file_type=unknown name="" description="" num_tensors=0 num_key_values=3 Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.121Z level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=/usr/local/lib/ollama Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.122Z level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=/usr/local/lib/ollama/cuda_v13 Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.123Z level=INFO source=ggml.go:104 msg=system CPU.0.LLAMAFILE=1 compiler=cgo(gcc) Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.123Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.block_count default=0 Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.123Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.pooling_type default=0 Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.123Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.expert_count default=0 Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.123Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.tokens default="&{size:0 values:[]}" Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.123Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.scores default="&{size:0 values:[]}" Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.123Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.token_type default="&{size:0 values:[]}" Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.123Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.merges default="&{size:0 values:[]}" Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.123Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.add_bos_token default=true Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.123Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.bos_token_id default=0 Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.123Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.add_eos_token default=false Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.123Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.eos_token_id default=0 Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.123Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.eos_token_ids default="&{size:0 values:[]}" Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.123Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.pre default="" Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.123Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.block_count default=0 Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.123Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.embedding_length default=0 Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.123Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.attention.head_count default=0 Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.123Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.attention.head_count_kv default=0 Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.123Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.attention.key_length default=0 Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.123Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.rope.dimension_count default=0 Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.123Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.attention.layer_norm_rms_epsilon default=0 Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.123Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.rope.freq_base default=100000 Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.123Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.rope.scaling.factor default=1 Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.123Z level=DEBUG source=runner.go:1386 msg="dummy model load took" duration=3.093638ms Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.123Z level=DEBUG source=runner.go:1391 msg="gathering device infos took" duration=291ns Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.123Z level=TRACE source=runner.go:467 msg="runner enumerated devices" OLLAMA_LIBRARY_PATH="[/usr/local/lib/ollama /usr/local/lib/ollama/cuda_v13]" devices=[] Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.124Z level=DEBUG source=runner.go:437 msg="bootstrap discovery took" duration=15.025827ms OLLAMA_LIBRARY_PATH="[/usr/local/lib/ollama /usr/local/lib/ollama/cuda_v13]" extra_envs=map[] Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.124Z level=TRACE source=runner.go:440 msg="starting runner for device discovery" libDirs="[/usr/local/lib/ollama /usr/local/lib/ollama/rocm]" extraEnvs=map[] Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.124Z level=INFO source=server.go:431 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 38811" Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.124Z level=DEBUG source=server.go:432 msg=subprocess PATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/games:/usr/local/games:/snap/bin OLLAMA_HOST=0.0.0.0:11434 OLLAMA_DEBUG=2 OLLAMA_AMD_GPU=1 OLLAMA_VULKAN=1 LD_LIBRARY_PATH=/usr/local/lib/ollama:/usr/local/lib/ollama/rocm OLLAMA_LIBRARY_PATH=/usr/local/lib/ollama:/usr/local/lib/ollama/rocm Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.132Z level=INFO source=runner.go:1411 msg="starting ollama engine" Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.133Z level=INFO source=runner.go:1446 msg="Server listening on 127.0.0.1:38811" Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.135Z level=DEBUG source=gguf.go:604 msg=general.architecture type=string Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.135Z level=DEBUG source=gguf.go:604 msg=tokenizer.ggml.model type=string Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.135Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.alignment default=32 Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.135Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.alignment default=32 Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.135Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.file_type default=0 Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.136Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.name default="" Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.136Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.description default="" Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.136Z level=INFO source=ggml.go:136 msg="" architecture=llama file_type=unknown name="" description="" num_tensors=0 num_key_values=3 Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.136Z level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=/usr/local/lib/ollama Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.137Z level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=/usr/local/lib/ollama/rocm Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.138Z level=INFO source=ggml.go:104 msg=system CPU.0.LLAMAFILE=1 compiler=cgo(gcc) Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.138Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.block_count default=0 Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.139Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.pooling_type default=0 Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.139Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.expert_count default=0 Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.139Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.tokens default="&{size:0 values:[]}" Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.139Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.scores default="&{size:0 values:[]}" Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.139Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.token_type default="&{size:0 values:[]}" Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.139Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.merges default="&{size:0 values:[]}" Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.139Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.add_bos_token default=true Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.139Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.bos_token_id default=0 Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.139Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.add_eos_token default=false Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.139Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.eos_token_id default=0 Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.139Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.eos_token_ids default="&{size:0 values:[]}" Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.139Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.pre default="" Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.139Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.block_count default=0 Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.139Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.embedding_length default=0 Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.139Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.attention.head_count default=0 Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.139Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.attention.head_count_kv default=0 Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.139Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.attention.key_length default=0 Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.139Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.rope.dimension_count default=0 Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.139Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.attention.layer_norm_rms_epsilon default=0 Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.139Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.rope.freq_base default=100000 Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.139Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.rope.scaling.factor default=1 Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.139Z level=DEBUG source=runner.go:1386 msg="dummy model load took" duration=3.854374ms Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.139Z level=DEBUG source=runner.go:1391 msg="gathering device infos took" duration=681ns Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.139Z level=TRACE source=runner.go:467 msg="runner enumerated devices" OLLAMA_LIBRARY_PATH="[/usr/local/lib/ollama /usr/local/lib/ollama/rocm]" devices=[] Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.139Z level=DEBUG source=runner.go:437 msg="bootstrap discovery took" duration=15.693312ms OLLAMA_LIBRARY_PATH="[/usr/local/lib/ollama /usr/local/lib/ollama/rocm]" extra_envs=map[] Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.139Z level=TRACE source=runner.go:440 msg="starting runner for device discovery" libDirs="[/usr/local/lib/ollama /usr/local/lib/ollama/vulkan]" extraEnvs=map[] Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.139Z level=INFO source=server.go:431 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 34175" Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.139Z level=DEBUG source=server.go:432 msg=subprocess PATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/games:/usr/local/games:/snap/bin OLLAMA_HOST=0.0.0.0:11434 OLLAMA_DEBUG=2 OLLAMA_AMD_GPU=1 OLLAMA_VULKAN=1 LD_LIBRARY_PATH=/usr/local/lib/ollama:/usr/local/lib/ollama/vulkan OLLAMA_LIBRARY_PATH=/usr/local/lib/ollama:/usr/local/lib/ollama/vulkan Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.148Z level=INFO source=runner.go:1411 msg="starting ollama engine" Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.148Z level=INFO source=runner.go:1446 msg="Server listening on 127.0.0.1:34175" Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.151Z level=DEBUG source=gguf.go:604 msg=general.architecture type=string Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.151Z level=DEBUG source=gguf.go:604 msg=tokenizer.ggml.model type=string Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.151Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.alignment default=32 Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.151Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.alignment default=32 Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.151Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.file_type default=0 Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.151Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.name default="" Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.151Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.description default="" Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.151Z level=INFO source=ggml.go:136 msg="" architecture=llama file_type=unknown name="" description="" num_tensors=0 num_key_values=3 Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.151Z level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=/usr/local/lib/ollama Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.152Z level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=/usr/local/lib/ollama/vulkan Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.153Z level=INFO source=ggml.go:104 msg=system CPU.0.LLAMAFILE=1 compiler=cgo(gcc) Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.153Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.block_count default=0 Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.153Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.pooling_type default=0 Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.153Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.expert_count default=0 Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.153Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.tokens default="&{size:0 values:[]}" Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.153Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.scores default="&{size:0 values:[]}" Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.153Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.token_type default="&{size:0 values:[]}" Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.153Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.merges default="&{size:0 values:[]}" Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.153Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.add_bos_token default=true Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.153Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.bos_token_id default=0 Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.153Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.add_eos_token default=false Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.153Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.eos_token_id default=0 Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.153Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.eos_token_ids default="&{size:0 values:[]}" Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.153Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.pre default="" Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.153Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.block_count default=0 Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.153Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.embedding_length default=0 Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.153Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.attention.head_count default=0 Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.153Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.attention.head_count_kv default=0 Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.153Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.attention.key_length default=0 Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.153Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.rope.dimension_count default=0 Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.153Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.attention.layer_norm_rms_epsilon default=0 Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.153Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.rope.freq_base default=100000 Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.153Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.rope.scaling.factor default=1 Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.153Z level=DEBUG source=runner.go:1386 msg="dummy model load took" duration=2.765596ms Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.153Z level=DEBUG source=runner.go:1391 msg="gathering device infos took" duration=200ns Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.154Z level=TRACE source=runner.go:467 msg="runner enumerated devices" OLLAMA_LIBRARY_PATH="[/usr/local/lib/ollama /usr/local/lib/ollama/vulkan]" devices=[] Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.154Z level=DEBUG source=runner.go:437 msg="bootstrap discovery took" duration=14.350126ms OLLAMA_LIBRARY_PATH="[/usr/local/lib/ollama /usr/local/lib/ollama/vulkan]" extra_envs=map[] Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.154Z level=TRACE source=runner.go:440 msg="starting runner for device discovery" libDirs="[/usr/local/lib/ollama /usr/local/lib/ollama/cuda_v12]" extraEnvs=map[] Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.154Z level=INFO source=server.go:431 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 43309" Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.154Z level=DEBUG source=server.go:432 msg=subprocess PATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/games:/usr/local/games:/snap/bin OLLAMA_HOST=0.0.0.0:11434 OLLAMA_DEBUG=2 OLLAMA_AMD_GPU=1 OLLAMA_VULKAN=1 LD_LIBRARY_PATH=/usr/local/lib/ollama:/usr/local/lib/ollama/cuda_v12 OLLAMA_LIBRARY_PATH=/usr/local/lib/ollama:/usr/local/lib/ollama/cuda_v12 Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.163Z level=INFO source=runner.go:1411 msg="starting ollama engine" Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.163Z level=INFO source=runner.go:1446 msg="Server listening on 127.0.0.1:43309" Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.165Z level=DEBUG source=gguf.go:604 msg=general.architecture type=string Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.165Z level=DEBUG source=gguf.go:604 msg=tokenizer.ggml.model type=string Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.165Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.alignment default=32 Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.165Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.alignment default=32 Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.165Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.file_type default=0 Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.165Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.name default="" Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.165Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=general.description default="" Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.165Z level=INFO source=ggml.go:136 msg="" architecture=llama file_type=unknown name="" description="" num_tensors=0 num_key_values=3 Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.165Z level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=/usr/local/lib/ollama Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.166Z level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=/usr/local/lib/ollama/cuda_v12 Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.168Z level=INFO source=ggml.go:104 msg=system CPU.0.LLAMAFILE=1 compiler=cgo(gcc) Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.168Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.block_count default=0 Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.168Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.pooling_type default=0 Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.168Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.expert_count default=0 Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.168Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.tokens default="&{size:0 values:[]}" Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.168Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.scores default="&{size:0 values:[]}" Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.168Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.token_type default="&{size:0 values:[]}" Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.168Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.merges default="&{size:0 values:[]}" Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.168Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.add_bos_token default=true Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.168Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.bos_token_id default=0 Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.168Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.add_eos_token default=false Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.168Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.eos_token_id default=0 Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.168Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.eos_token_ids default="&{size:0 values:[]}" Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.168Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=tokenizer.ggml.pre default="" Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.168Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.block_count default=0 Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.168Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.embedding_length default=0 Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.168Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.attention.head_count default=0 Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.168Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.attention.head_count_kv default=0 Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.168Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.attention.key_length default=0 Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.168Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.rope.dimension_count default=0 Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.168Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.attention.layer_norm_rms_epsilon default=0 Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.168Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.rope.freq_base default=100000 Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.168Z level=DEBUG source=ggml.go:324 msg="key with type not found" key=llama.rope.scaling.factor default=1 Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.168Z level=DEBUG source=runner.go:1386 msg="dummy model load took" duration=3.807558ms Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.168Z level=DEBUG source=runner.go:1391 msg="gathering device infos took" duration=220ns Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.168Z level=TRACE source=runner.go:467 msg="runner enumerated devices" OLLAMA_LIBRARY_PATH="[/usr/local/lib/ollama /usr/local/lib/ollama/cuda_v12]" devices=[] Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.169Z level=DEBUG source=runner.go:437 msg="bootstrap discovery took" duration=14.880079ms OLLAMA_LIBRARY_PATH="[/usr/local/lib/ollama /usr/local/lib/ollama/cuda_v12]" extra_envs=map[] Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.169Z level=DEBUG source=runner.go:124 msg="evaluating which, if any, devices to filter out" initial_count=0 Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.169Z level=TRACE source=runner.go:174 msg="supported GPU library combinations before filtering" supported=map[] Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.169Z level=DEBUG source=runner.go:40 msg="GPU bootstrap discovery took" duration=60.604196ms Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.169Z level=INFO source=types.go:60 msg="inference compute" id=cpu library=cpu compute="" name=cpu description=cpu libdirs=ollama driver="" pci_id="" type="" total="25.2 GiB" available="23.8 GiB" Mar 01 11:06:25 ai-server ollama[83615]: time=2026-03-01T11:06:25.169Z level=INFO source=routes.go:1768 msg="vram-based default context" total_vram="0 B" default_num_ctx=4096 ```
GiteaMirror commented 2026-04-29 09:58:24 -05:00
Author
Owner
Copy Link

@StigThomsen commented on GitHub (Mar 2, 2026):

After hours and hours of debugging, I got to the root cause being : libggml-hip.so is compiled as CUDA, not HIP
nm -D /usr/local/lib/ollama/rocm/libggml-hip.so | grep -E "T ggml_backend"

T ggml_backend_cuda_buffer_type
T ggml_backend_cuda_get_device_count
T ggml_backend_cuda_get_device_description
T ggml_backend_cuda_get_device_memory
T ggml_backend_cuda_host_buffer_type
T ggml_backend_cuda_init
T ggml_backend_cuda_reg ← CUDA, not HIP
T ggml_backend_cuda_split_buffer_type
T ggml_backend_init
T ggml_backend_is_cuda

I figured this couldn't be on purpose. So I re-installed Ollama and there it was, full on GPU offloading.

Case closed, AMD 760M is supported through ROCm.

<!-- gh-comment-id:3983448702 --> @StigThomsen commented on GitHub (Mar 2, 2026): After hours and hours of debugging, I got to the root cause being : libggml-hip.so is compiled as CUDA, not HIP nm -D /usr/local/lib/ollama/rocm/libggml-hip.so | grep -E "T ggml_backend" T ggml_backend_cuda_buffer_type T ggml_backend_cuda_get_device_count T ggml_backend_cuda_get_device_description T ggml_backend_cuda_get_device_memory T ggml_backend_cuda_host_buffer_type T ggml_backend_cuda_init T ggml_backend_cuda_reg ← CUDA, not HIP T ggml_backend_cuda_split_buffer_type T ggml_backend_init T ggml_backend_is_cuda I figured this couldn't be on purpose. So I re-installed Ollama and there it was, full on GPU offloading. Case closed, AMD 760M is supported through ROCm.
GiteaMirror commented 2026-04-29 09:58:26 -05:00
Author
Owner
Copy Link

@singlerider commented on GitHub (Mar 10, 2026):

@StigThomsen

So I re-installed Ollama and there it was, full on GPU offloading.

edit
I got it working after re-installing in-place finished completely.

<!-- gh-comment-id:4029766695 --> @singlerider commented on GitHub (Mar 10, 2026): @StigThomsen >So I re-installed Ollama and there it was, full on GPU offloading. *edit* I got it working after re-installing in-place finished completely.
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 feature request
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#55937
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?