github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 00:22:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #13569] Ollama does not use GPU for AMD Radeon RX 6800 XT #70994

New Issue
Closed
opened 2026-05-04 23:41:32 -05:00 by GiteaMirror · 7 comments
GiteaMirror commented 2026-05-04 23:41:32 -05:00
Owner
Copy Link

Originally created by @Tusenka on GitHub (Dec 26, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/13569

What is the issue?

ollama ps

blackened/t-lite:latest f7dfa19f99d5 15 GB 100% CPU 4096 4 minutes from now

lspci:

08:00.0 VGA compatible controller: Advanced Micro Devices, Inc. [AMD/ATI] Navi 21 [Radeon RX 6800/6800 XT / 6900 XT] (rev c1)

OS:

DISTRIB_ID=Ubuntu
DISTRIB_RELEASE=25.10
DISTRIB_CODENAME=questing
DISTRIB_DESCRIPTION="Ubuntu 25.10"

There no warns about gpu but it utilizes only cpu.

Relevant log output

logs:

> `time=2025-12-26T17:49:41.398+03:00 level=INFO source=routes.go:1554 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_LENGOLLAMA_CONTEXT_LENGTH:4096TH:4096` OLLAMA_DEBUG:INFO OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://127.0.0.1:11434 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:/home/cas12/.ollama/models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:1 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://* vscode-file://*] OLLAMA_REMOTES:[ollama.com] OLLAMA_SCHED_SPREAD:false OLLAMA_VULKAN:false ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]"
> time=2025-12-26T17:49:41.399+03:00 level=INFO source=images.go:493 msg="total blobs: 8"
> time=2025-12-26T17:49:41.399+03:00 level=INFO source=images.go:500 msg="total unused blobs removed: 0"
> time=2025-12-26T17:49:41.08:00.0 VGA compatible controller: Advanced Micro Devices, Inc. [AMD/ATI] Navi 21 [Radeon RX 6800/6800 XT / 6900 XT] (rev c1)
399+03:00 level=INFO source=routes.go:1607 msg="Listening on 127.0.0.1:11434 (version 0.13.5)"
> time=2025-12-26T17:49:41.399+03:00 level=INFO source=runner.go:67 msg="discovering available GPUs..."
> time=2025-12-26T17:49:41.400+03:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 46787"
> time=2025-12-26T17:49:41.433+03:00 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="30.7 GiB" available="18.2 GiB"
> time=2025-12-26T17:49:41.433+03:00 level=INFO source=routes.go:1648 msg="entering low vram mode" "total vram"="0 B" threshold="20.0 GiB"

OS

Linux

GPU

AMD

CPU

AMD

Ollama version

0.13.5

Originally created by @Tusenka on GitHub (Dec 26, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/13569 ### What is the issue? `ollama ps` > blackened/t-lite:latest f7dfa19f99d5 15 GB 100% CPU 4096 4 minutes from now `lspci: ` > `08:00.0 VGA compatible controller: Advanced Micro Devices, Inc. [AMD/ATI] Navi 21 [Radeon RX 6800/6800 XT / 6900 XT] (rev c1) > ` OS: > DISTRIB_ID=Ubuntu DISTRIB_RELEASE=25.10 DISTRIB_CODENAME=questing DISTRIB_DESCRIPTION="Ubuntu 25.10" There no warns about gpu but it utilizes only cpu. ### Relevant log output ```shell logs: > `time=2025-12-26T17:49:41.398+03:00 level=INFO source=routes.go:1554 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_LENGOLLAMA_CONTEXT_LENGTH:4096TH:4096` OLLAMA_DEBUG:INFO OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://127.0.0.1:11434 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:/home/cas12/.ollama/models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:1 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://* vscode-file://*] OLLAMA_REMOTES:[ollama.com] OLLAMA_SCHED_SPREAD:false OLLAMA_VULKAN:false ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]" > time=2025-12-26T17:49:41.399+03:00 level=INFO source=images.go:493 msg="total blobs: 8" > time=2025-12-26T17:49:41.399+03:00 level=INFO source=images.go:500 msg="total unused blobs removed: 0" > time=2025-12-26T17:49:41.08:00.0 VGA compatible controller: Advanced Micro Devices, Inc. [AMD/ATI] Navi 21 [Radeon RX 6800/6800 XT / 6900 XT] (rev c1) 399+03:00 level=INFO source=routes.go:1607 msg="Listening on 127.0.0.1:11434 (version 0.13.5)" > time=2025-12-26T17:49:41.399+03:00 level=INFO source=runner.go:67 msg="discovering available GPUs..." > time=2025-12-26T17:49:41.400+03:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 46787" > time=2025-12-26T17:49:41.433+03:00 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="30.7 GiB" available="18.2 GiB" > time=2025-12-26T17:49:41.433+03:00 level=INFO source=routes.go:1648 msg="entering low vram mode" "total vram"="0 B" threshold="20.0 GiB" ``` ### OS Linux ### GPU AMD ### CPU AMD ### Ollama version 0.13.5
GiteaMirror added the bug label 2026-05-04 23:41:32 -05:00
GiteaMirror commented 2026-05-04 23:41:34 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Dec 26, 2025):

Set OLLAMA_DEBUG=2 in the server environment and post the log.

<!-- gh-comment-id:3692982285 --> @rick-github commented on GitHub (Dec 26, 2025): Set `OLLAMA_DEBUG=2` in the server environment and post the log.
GiteaMirror commented 2026-05-04 23:41:35 -05:00
Author
Owner
Copy Link

@anumukul commented on GitHub (Dec 26, 2025):

Hi, I’d like to take this issue and can deliver a fix within 24 hours.
I’ve worked on similar projects before and have relevant experience, so I should be able to handle this efficiently.

<!-- gh-comment-id:3693471274 --> @anumukul commented on GitHub (Dec 26, 2025): Hi, I’d like to take this issue and can deliver a fix within 24 hours. I’ve worked on similar projects before and have relevant experience, so I should be able to handle this efficiently.
GiteaMirror commented 2026-05-04 23:41:35 -05:00
Author
Owner
Copy Link

@Tusenka commented on GitHub (Dec 29, 2025):

@rick-github, @anumukul here is the logs:

time=2025-12-29T10:47:27.882+03:00 level=INFO source=routes.go:1554 msg="server config" env="map[CUDA_VISIBLE_DEVICES: GGML_VK_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:4096 OLLAMA_DEBUG:DEBUG-4 OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://127.0.0.1:11434 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:/home/cas12/.ollama/models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:1 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://* vscode-file://*] OLLAMA_REMOTES:[ollama.com] OLLAMA_SCHED_SPREAD:false OLLAMA_VULKAN:false ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]"
time=2025-12-29T10:47:27.888+03:00 level=INFO source=images.go:493 msg="total blobs: 13"
time=2025-12-29T10:47:27.889+03:00 level=INFO source=images.go:500 msg="total unused blobs removed: 0"
time=2025-12-29T10:47:27.890+03:00 level=INFO source=routes.go:1607 msg="Listening on 127.0.0.1:11434 (version 0.13.5)"
time=2025-12-29T10:47:27.890+03:00 level=DEBUG source=sched.go:120 msg="starting llm scheduler"
time=2025-12-29T10:47:27.891+03:00 level=INFO source=runner.go:67 msg="discovering available GPUs..."
time=2025-12-29T10:47:27.891+03:00 level=TRACE source=runner.go:440 msg="starting runner for device discovery" libDirs=[/usr/local/lib/ollama] extraEnvs=map[]
time=2025-12-29T10:47:27.893+03:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 41009"
time=2025-12-29T10:47:27.893+03:00 level=DEBUG source=server.go:430 msg=subprocess PATH=/home/cas12/.codon/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/games:/usr/local/games:/snap/bin:/snap/bin:/home/cas12/.local/bin OLLAMA_DEBUG=2 LD_LIBRARY_PATH=/usr/local/lib/ollama OLLAMA_LIBRARY_PATH=/usr/local/lib/ollama
time=2025-12-29T10:47:27.926+03:00 level=INFO source=runner.go:1405 msg="starting ollama engine"
time=2025-12-29T10:47:27.927+03:00 level=INFO source=runner.go:1440 msg="Server listening on 127.0.0.1:41009"
time=2025-12-29T10:47:27.936+03:00 level=DEBUG source=gguf.go:589 msg=general.architecture type=string
time=2025-12-29T10:47:27.936+03:00 level=DEBUG source=gguf.go:589 msg=tokenizer.ggml.model type=string
time=2025-12-29T10:47:27.937+03:00 level=DEBUG source=ggml.go:282 msg="key with type not found" key=general.alignment default=32
time=2025-12-29T10:47:27.937+03:00 level=DEBUG source=ggml.go:282 msg="key with type not found" key=general.alignment default=32
time=2025-12-29T10:47:27.937+03:00 level=DEBUG source=ggml.go:282 msg="key with type not found" key=general.file_type default=0
time=2025-12-29T10:47:27.937+03:00 level=DEBUG source=ggml.go:282 msg="key with type not found" key=general.name default=""
time=2025-12-29T10:47:27.937+03:00 level=DEBUG source=ggml.go:282 msg="key with type not found" key=general.description default=""
time=2025-12-29T10:47:27.937+03:00 level=INFO source=ggml.go:136 msg="" architecture=llama file_type=unknown name="" description="" num_tensors=0 num_key_values=3
time=2025-12-29T10:47:27.937+03:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=/usr/local/lib/ollama
time=2025-12-29T10:47:27.939+03:00 level=INFO source=ggml.go:104 msg=system CPU.0.LLAMAFILE=1 compiler=cgo(gcc)
time=2025-12-29T10:47:27.946+03:00 level=DEBUG source=ggml.go:282 msg="key with type not found" key=llama.block_count default=0
time=2025-12-29T10:47:27.946+03:00 level=DEBUG source=ggml.go:282 msg="key with type not found" key=llama.pooling_type default=0
time=2025-12-29T10:47:27.946+03:00 level=DEBUG source=ggml.go:282 msg="key with type not found" key=llama.expert_count default=0
time=2025-12-29T10:47:27.946+03:00 level=DEBUG source=ggml.go:282 msg="key with type not found" key=tokenizer.ggml.tokens default="&{size:0 values:[]}"
time=2025-12-29T10:47:27.946+03:00 level=DEBUG source=ggml.go:282 msg="key with type not found" key=tokenizer.ggml.scores default="&{size:0 values:[]}"
time=2025-12-29T10:47:27.946+03:00 level=DEBUG source=ggml.go:282 msg="key with type not found" key=tokenizer.ggml.token_type default="&{size:0 values:[]}"
time=2025-12-29T10:47:27.946+03:00 level=DEBUG source=ggml.go:282 msg="key with type not found" key=tokenizer.ggml.merges default="&{size:0 values:[]}"
time=2025-12-29T10:47:27.946+03:00 level=DEBUG source=ggml.go:282 msg="key with type not found" key=tokenizer.ggml.add_bos_token default=true
time=2025-12-29T10:47:27.946+03:00 level=DEBUG source=ggml.go:282 msg="key with type not found" key=tokenizer.ggml.bos_token_id default=0
time=2025-12-29T10:47:27.946+03:00 level=DEBUG source=ggml.go:282 msg="key with type not found" key=tokenizer.ggml.add_eos_token default=false
time=2025-12-29T10:47:27.946+03:00 level=DEBUG source=ggml.go:282 msg="key with type not found" key=tokenizer.ggml.eos_token_id default=0
time=2025-12-29T10:47:27.946+03:00 level=DEBUG source=ggml.go:282 msg="key with type not found" key=tokenizer.ggml.eos_token_ids default="&{size:0 values:[]}"
time=2025-12-29T10:47:27.946+03:00 level=DEBUG source=ggml.go:282 msg="key with type not found" key=tokenizer.ggml.pre default=""
time=2025-12-29T10:47:27.947+03:00 level=DEBUG source=ggml.go:282 msg="key with type not found" key=llama.block_count default=0
time=2025-12-29T10:47:27.947+03:00 level=DEBUG source=ggml.go:282 msg="key with type not found" key=llama.embedding_length default=0
time=2025-12-29T10:47:27.947+03:00 level=DEBUG source=ggml.go:282 msg="key with type not found" key=llama.attention.head_count default=0
time=2025-12-29T10:47:27.947+03:00 level=DEBUG source=ggml.go:282 msg="key with type not found" key=llama.attention.head_count_kv default=0
time=2025-12-29T10:47:27.947+03:00 level=DEBUG source=ggml.go:282 msg="key with type not found" key=llama.attention.key_length default=0
time=2025-12-29T10:47:27.947+03:00 level=DEBUG source=ggml.go:282 msg="key with type not found" key=llama.rope.dimension_count default=0
time=2025-12-29T10:47:27.947+03:00 level=DEBUG source=ggml.go:282 msg="key with type not found" key=llama.attention.layer_norm_rms_epsilon default=0
time=2025-12-29T10:47:27.947+03:00 level=DEBUG source=ggml.go:282 msg="key with type not found" key=llama.rope.freq_base default=100000
time=2025-12-29T10:47:27.947+03:00 level=DEBUG source=ggml.go:282 msg="key with type not found" key=llama.rope.scaling.factor default=1
time=2025-12-29T10:47:27.948+03:00 level=DEBUG source=runner.go:1380 msg="dummy model load took" duration=11.74997ms
time=2025-12-29T10:47:27.948+03:00 level=DEBUG source=runner.go:1385 msg="gathering device infos took" duration=812ns
time=2025-12-29T10:47:27.948+03:00 level=TRACE source=runner.go:467 msg="runner enumerated devices" OLLAMA_LIBRARY_PATH=[/usr/local/lib/ollama] devices=[]
time=2025-12-29T10:47:27.948+03:00 level=DEBUG source=runner.go:437 msg="bootstrap discovery took" duration=57.102631ms OLLAMA_LIBRARY_PATH=[/usr/local/lib/ollama] extra_envs=map[]
time=2025-12-29T10:47:27.948+03:00 level=DEBUG source=runner.go:124 msg="evaluating which, if any, devices to filter out" initial_count=0
time=2025-12-29T10:47:27.948+03:00 level=TRACE source=runner.go:174 msg="supported GPU library combinations before filtering" supported=map[]
time=2025-12-29T10:47:27.948+03:00 level=DEBUG source=runner.go:40 msg="GPU bootstrap discovery took" duration=58.025186ms
time=2025-12-29T10:47:27.949+03:00 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="30.7 GiB" available="15.9 GiB"
time=2025-12-29T10:47:27.949+03:00 level=INFO source=routes.go:1648 msg="entering low vram mode" "total vram"="0 B" threshold="20.0 GiB"

Thank you

<!-- gh-comment-id:3695756810 --> @Tusenka commented on GitHub (Dec 29, 2025): @rick-github, @anumukul here is the logs: > time=2025-12-29T10:47:27.882+03:00 level=INFO source=routes.go:1554 msg="server config" env="map[CUDA_VISIBLE_DEVICES: GGML_VK_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_CONTEXT_LENGTH:4096 OLLAMA_DEBUG:DEBUG-4 OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://127.0.0.1:11434 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:/home/cas12/.ollama/models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NEW_ENGINE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:1 OLLAMA_ORIGINS:[http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://* vscode-file://*] OLLAMA_REMOTES:[ollama.com] OLLAMA_SCHED_SPREAD:false OLLAMA_VULKAN:false ROCR_VISIBLE_DEVICES: http_proxy: https_proxy: no_proxy:]" time=2025-12-29T10:47:27.888+03:00 level=INFO source=images.go:493 msg="total blobs: 13" time=2025-12-29T10:47:27.889+03:00 level=INFO source=images.go:500 msg="total unused blobs removed: 0" time=2025-12-29T10:47:27.890+03:00 level=INFO source=routes.go:1607 msg="Listening on 127.0.0.1:11434 (version 0.13.5)" time=2025-12-29T10:47:27.890+03:00 level=DEBUG source=sched.go:120 msg="starting llm scheduler" time=2025-12-29T10:47:27.891+03:00 level=INFO source=runner.go:67 msg="discovering available GPUs..." time=2025-12-29T10:47:27.891+03:00 level=TRACE source=runner.go:440 msg="starting runner for device discovery" libDirs=[/usr/local/lib/ollama] extraEnvs=map[] time=2025-12-29T10:47:27.893+03:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 41009" time=2025-12-29T10:47:27.893+03:00 level=DEBUG source=server.go:430 msg=subprocess PATH=/home/cas12/.codon/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/games:/usr/local/games:/snap/bin:/snap/bin:/home/cas12/.local/bin OLLAMA_DEBUG=2 LD_LIBRARY_PATH=/usr/local/lib/ollama OLLAMA_LIBRARY_PATH=/usr/local/lib/ollama time=2025-12-29T10:47:27.926+03:00 level=INFO source=runner.go:1405 msg="starting ollama engine" time=2025-12-29T10:47:27.927+03:00 level=INFO source=runner.go:1440 msg="Server listening on 127.0.0.1:41009" time=2025-12-29T10:47:27.936+03:00 level=DEBUG source=gguf.go:589 msg=general.architecture type=string time=2025-12-29T10:47:27.936+03:00 level=DEBUG source=gguf.go:589 msg=tokenizer.ggml.model type=string time=2025-12-29T10:47:27.937+03:00 level=DEBUG source=ggml.go:282 msg="key with type not found" key=general.alignment default=32 time=2025-12-29T10:47:27.937+03:00 level=DEBUG source=ggml.go:282 msg="key with type not found" key=general.alignment default=32 time=2025-12-29T10:47:27.937+03:00 level=DEBUG source=ggml.go:282 msg="key with type not found" key=general.file_type default=0 time=2025-12-29T10:47:27.937+03:00 level=DEBUG source=ggml.go:282 msg="key with type not found" key=general.name default="" time=2025-12-29T10:47:27.937+03:00 level=DEBUG source=ggml.go:282 msg="key with type not found" key=general.description default="" time=2025-12-29T10:47:27.937+03:00 level=INFO source=ggml.go:136 msg="" architecture=llama file_type=unknown name="" description="" num_tensors=0 num_key_values=3 time=2025-12-29T10:47:27.937+03:00 level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=/usr/local/lib/ollama time=2025-12-29T10:47:27.939+03:00 level=INFO source=ggml.go:104 msg=system CPU.0.LLAMAFILE=1 compiler=cgo(gcc) time=2025-12-29T10:47:27.946+03:00 level=DEBUG source=ggml.go:282 msg="key with type not found" key=llama.block_count default=0 time=2025-12-29T10:47:27.946+03:00 level=DEBUG source=ggml.go:282 msg="key with type not found" key=llama.pooling_type default=0 time=2025-12-29T10:47:27.946+03:00 level=DEBUG source=ggml.go:282 msg="key with type not found" key=llama.expert_count default=0 time=2025-12-29T10:47:27.946+03:00 level=DEBUG source=ggml.go:282 msg="key with type not found" key=tokenizer.ggml.tokens default="&{size:0 values:[]}" time=2025-12-29T10:47:27.946+03:00 level=DEBUG source=ggml.go:282 msg="key with type not found" key=tokenizer.ggml.scores default="&{size:0 values:[]}" time=2025-12-29T10:47:27.946+03:00 level=DEBUG source=ggml.go:282 msg="key with type not found" key=tokenizer.ggml.token_type default="&{size:0 values:[]}" time=2025-12-29T10:47:27.946+03:00 level=DEBUG source=ggml.go:282 msg="key with type not found" key=tokenizer.ggml.merges default="&{size:0 values:[]}" time=2025-12-29T10:47:27.946+03:00 level=DEBUG source=ggml.go:282 msg="key with type not found" key=tokenizer.ggml.add_bos_token default=true time=2025-12-29T10:47:27.946+03:00 level=DEBUG source=ggml.go:282 msg="key with type not found" key=tokenizer.ggml.bos_token_id default=0 time=2025-12-29T10:47:27.946+03:00 level=DEBUG source=ggml.go:282 msg="key with type not found" key=tokenizer.ggml.add_eos_token default=false time=2025-12-29T10:47:27.946+03:00 level=DEBUG source=ggml.go:282 msg="key with type not found" key=tokenizer.ggml.eos_token_id default=0 time=2025-12-29T10:47:27.946+03:00 level=DEBUG source=ggml.go:282 msg="key with type not found" key=tokenizer.ggml.eos_token_ids default="&{size:0 values:[]}" time=2025-12-29T10:47:27.946+03:00 level=DEBUG source=ggml.go:282 msg="key with type not found" key=tokenizer.ggml.pre default="" time=2025-12-29T10:47:27.947+03:00 level=DEBUG source=ggml.go:282 msg="key with type not found" key=llama.block_count default=0 time=2025-12-29T10:47:27.947+03:00 level=DEBUG source=ggml.go:282 msg="key with type not found" key=llama.embedding_length default=0 time=2025-12-29T10:47:27.947+03:00 level=DEBUG source=ggml.go:282 msg="key with type not found" key=llama.attention.head_count default=0 time=2025-12-29T10:47:27.947+03:00 level=DEBUG source=ggml.go:282 msg="key with type not found" key=llama.attention.head_count_kv default=0 time=2025-12-29T10:47:27.947+03:00 level=DEBUG source=ggml.go:282 msg="key with type not found" key=llama.attention.key_length default=0 time=2025-12-29T10:47:27.947+03:00 level=DEBUG source=ggml.go:282 msg="key with type not found" key=llama.rope.dimension_count default=0 time=2025-12-29T10:47:27.947+03:00 level=DEBUG source=ggml.go:282 msg="key with type not found" key=llama.attention.layer_norm_rms_epsilon default=0 time=2025-12-29T10:47:27.947+03:00 level=DEBUG source=ggml.go:282 msg="key with type not found" key=llama.rope.freq_base default=100000 time=2025-12-29T10:47:27.947+03:00 level=DEBUG source=ggml.go:282 msg="key with type not found" key=llama.rope.scaling.factor default=1 time=2025-12-29T10:47:27.948+03:00 level=DEBUG source=runner.go:1380 msg="dummy model load took" duration=11.74997ms time=2025-12-29T10:47:27.948+03:00 level=DEBUG source=runner.go:1385 msg="gathering device infos took" duration=812ns time=2025-12-29T10:47:27.948+03:00 level=TRACE source=runner.go:467 msg="runner enumerated devices" OLLAMA_LIBRARY_PATH=[/usr/local/lib/ollama] devices=[] time=2025-12-29T10:47:27.948+03:00 level=DEBUG source=runner.go:437 msg="bootstrap discovery took" duration=57.102631ms OLLAMA_LIBRARY_PATH=[/usr/local/lib/ollama] extra_envs=map[] time=2025-12-29T10:47:27.948+03:00 level=DEBUG source=runner.go:124 msg="evaluating which, if any, devices to filter out" initial_count=0 time=2025-12-29T10:47:27.948+03:00 level=TRACE source=runner.go:174 msg="supported GPU library combinations before filtering" supported=map[] time=2025-12-29T10:47:27.948+03:00 level=DEBUG source=runner.go:40 msg="GPU bootstrap discovery took" duration=58.025186ms time=2025-12-29T10:47:27.949+03:00 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="30.7 GiB" available="15.9 GiB" time=2025-12-29T10:47:27.949+03:00 level=INFO source=routes.go:1648 msg="entering low vram mode" "total vram"="0 B" threshold="20.0 GiB" Thank you
GiteaMirror commented 2026-05-04 23:41:36 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Dec 29, 2025):

What's the output of:

ls -lR /usr/local/lib/ollama
<!-- gh-comment-id:3695763690 --> @rick-github commented on GitHub (Dec 29, 2025): What's the output of: ``` ls -lR /usr/local/lib/ollama ```
GiteaMirror commented 2026-05-04 23:41:37 -05:00
Author
Owner
Copy Link

@Tusenka commented on GitHub (Dec 30, 2025):

Image

/usr/local/lib/ollama:
total 4
drwx------ 2 root root 4096 Dec 25 15:47 cuda_v12

/usr/local/lib/ollama/cuda_v12:
total 507352
lrwxrwxrwx 1 root root 21 Dec 19 00:26 libcublas.so.12 -> libcublas.so.12.8.4.1
-rwxr-xr-x 1 root root 116388640 Jul 8 2015 libcublas.so.12.8.4.1
lrwxrwxrwx 1 root root 23 Dec 19 00:26 libcublasLt.so.12 -> libcublasLt.so.12.8.4.1
-rwx------ 1 root root 402396672 Dec 25 15:52 libcublasLt.so.12.8.4.1
-rwxr-xr-x 1 root root 728800 Jul 8 2015 libcudart.so.12.8.90

<!-- gh-comment-id:3698601433 --> @Tusenka commented on GitHub (Dec 30, 2025): <img width="2067" height="397" alt="Image" src="https://github.com/user-attachments/assets/909a429c-c6a0-4a82-90e2-54b6d094779b" /> > /usr/local/lib/ollama: > total 4 > drwx------ 2 root root 4096 Dec 25 15:47 cuda_v12 > > /usr/local/lib/ollama/cuda_v12: > total 507352 > lrwxrwxrwx 1 root root 21 Dec 19 00:26 libcublas.so.12 -> libcublas.so.12.8.4.1 > -rwxr-xr-x 1 root root 116388640 Jul 8 2015 libcublas.so.12.8.4.1 > lrwxrwxrwx 1 root root 23 Dec 19 00:26 libcublasLt.so.12 -> libcublasLt.so.12.8.4.1 > -rwx------ 1 root root 402396672 Dec 25 15:52 libcublasLt.so.12.8.4.1 > -rwxr-xr-x 1 root root 728800 Jul 8 2015 libcudart.so.12.8.90
GiteaMirror commented 2026-05-04 23:41:37 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Dec 30, 2025):

Your installation is incomplete, it should look like this:

/usr/local/lib/ollama:
total 6476
drwxr-xr-x 2 root root    4096 Dez 18 22:26 cuda_v12
drwxr-xr-x 2 root root    4096 Dez 18 22:22 cuda_v13
lrwxrwxrwx 1 root root      17 Dez 18 22:07 libggml-base.so -> libggml-base.so.0
lrwxrwxrwx 1 root root      21 Dez 18 22:07 libggml-base.so.0 -> libggml-base.so.0.0.0
-rwxr-xr-x 1 root root  744056 Dez 18 22:07 libggml-base.so.0.0.0
-rwxr-xr-x 1 root root  873912 Dez 18 22:07 libggml-cpu-alderlake.so
-rwxr-xr-x 1 root root  873912 Dez 18 22:07 libggml-cpu-haswell.so
-rwxr-xr-x 1 root root 1009080 Dez 18 22:07 libggml-cpu-icelake.so
-rwxr-xr-x 1 root root  820728 Dez 18 22:07 libggml-cpu-sandybridge.so
-rwxr-xr-x 1 root root 1009080 Dez 18 22:07 libggml-cpu-skylakex.so
-rwxr-xr-x 1 root root  636536 Dez 18 22:07 libggml-cpu-sse42.so
-rwxr-xr-x 1 root root  632472 Dez 18 22:07 libggml-cpu-x64.so
drwxr-xr-x 2 root root    4096 Dez 18 22:07 vulkan

/usr/local/lib/ollama/cuda_v12:
total 2477724
lrwxrwxrwx 1 root root         23 Dez 18 22:26 libcublasLt.so.12 -> libcublasLt.so.12.8.4.1
-rwxr-xr-x 1 root root  751771728 Jul  8  2015 libcublasLt.so.12.8.4.1
lrwxrwxrwx 1 root root         21 Dez 18 22:26 libcublas.so.12 -> libcublas.so.12.8.4.1
-rwxr-xr-x 1 root root  116388640 Jul  8  2015 libcublas.so.12.8.4.1
lrwxrwxrwx 1 root root         20 Dez 18 22:26 libcudart.so.12 -> libcudart.so.12.8.90
-rwxr-xr-x 1 root root     728800 Jul  8  2015 libcudart.so.12.8.90
-rwxr-xr-x 1 root root 1668281616 Dez 18 22:26 libggml-cuda.so

/usr/local/lib/ollama/cuda_v13:
total 949156
lrwxrwxrwx 1 root root        23 Dez 18 22:22 libcublasLt.so.13 -> libcublasLt.so.13.1.0.3
-rwxr-xr-x 1 root root 541595600 Jul  8  2015 libcublasLt.so.13.1.0.3
lrwxrwxrwx 1 root root        21 Dez 18 22:22 libcublas.so.13 -> libcublas.so.13.1.0.3
-rwxr-xr-x 1 root root  54177976 Jul  8  2015 libcublas.so.13.1.0.3
lrwxrwxrwx 1 root root        20 Dez 18 22:22 libcudart.so.13 -> libcudart.so.13.0.96
-rwxr-xr-x 1 root root    704288 Jul  8  2015 libcudart.so.13.0.96
-rwxr-xr-x 1 root root 375444752 Dez 18 22:22 libggml-cuda.so

/usr/local/lib/ollama/vulkan:
total 55364
-rwxr-xr-x 1 root root 52220200 Dez 18 22:07 libggml-vulkan.so
lrwxrwxrwx 1 root root       20 Dez 18 22:07 libvulkan.so.1 -> libvulkan.so.1.4.321
-rwxr-xr-x 1 root root  4466776 Dez 18 22:06 libvulkan.so.1.4.321

How did you install ollama? I recommend re-installing with:

curl -fsSL https://ollama.com/install.sh | sh
<!-- gh-comment-id:3699199103 --> @rick-github commented on GitHub (Dec 30, 2025): Your installation is incomplete, it should look like this: ``` /usr/local/lib/ollama: total 6476 drwxr-xr-x 2 root root 4096 Dez 18 22:26 cuda_v12 drwxr-xr-x 2 root root 4096 Dez 18 22:22 cuda_v13 lrwxrwxrwx 1 root root 17 Dez 18 22:07 libggml-base.so -> libggml-base.so.0 lrwxrwxrwx 1 root root 21 Dez 18 22:07 libggml-base.so.0 -> libggml-base.so.0.0.0 -rwxr-xr-x 1 root root 744056 Dez 18 22:07 libggml-base.so.0.0.0 -rwxr-xr-x 1 root root 873912 Dez 18 22:07 libggml-cpu-alderlake.so -rwxr-xr-x 1 root root 873912 Dez 18 22:07 libggml-cpu-haswell.so -rwxr-xr-x 1 root root 1009080 Dez 18 22:07 libggml-cpu-icelake.so -rwxr-xr-x 1 root root 820728 Dez 18 22:07 libggml-cpu-sandybridge.so -rwxr-xr-x 1 root root 1009080 Dez 18 22:07 libggml-cpu-skylakex.so -rwxr-xr-x 1 root root 636536 Dez 18 22:07 libggml-cpu-sse42.so -rwxr-xr-x 1 root root 632472 Dez 18 22:07 libggml-cpu-x64.so drwxr-xr-x 2 root root 4096 Dez 18 22:07 vulkan /usr/local/lib/ollama/cuda_v12: total 2477724 lrwxrwxrwx 1 root root 23 Dez 18 22:26 libcublasLt.so.12 -> libcublasLt.so.12.8.4.1 -rwxr-xr-x 1 root root 751771728 Jul 8 2015 libcublasLt.so.12.8.4.1 lrwxrwxrwx 1 root root 21 Dez 18 22:26 libcublas.so.12 -> libcublas.so.12.8.4.1 -rwxr-xr-x 1 root root 116388640 Jul 8 2015 libcublas.so.12.8.4.1 lrwxrwxrwx 1 root root 20 Dez 18 22:26 libcudart.so.12 -> libcudart.so.12.8.90 -rwxr-xr-x 1 root root 728800 Jul 8 2015 libcudart.so.12.8.90 -rwxr-xr-x 1 root root 1668281616 Dez 18 22:26 libggml-cuda.so /usr/local/lib/ollama/cuda_v13: total 949156 lrwxrwxrwx 1 root root 23 Dez 18 22:22 libcublasLt.so.13 -> libcublasLt.so.13.1.0.3 -rwxr-xr-x 1 root root 541595600 Jul 8 2015 libcublasLt.so.13.1.0.3 lrwxrwxrwx 1 root root 21 Dez 18 22:22 libcublas.so.13 -> libcublas.so.13.1.0.3 -rwxr-xr-x 1 root root 54177976 Jul 8 2015 libcublas.so.13.1.0.3 lrwxrwxrwx 1 root root 20 Dez 18 22:22 libcudart.so.13 -> libcudart.so.13.0.96 -rwxr-xr-x 1 root root 704288 Jul 8 2015 libcudart.so.13.0.96 -rwxr-xr-x 1 root root 375444752 Dez 18 22:22 libggml-cuda.so /usr/local/lib/ollama/vulkan: total 55364 -rwxr-xr-x 1 root root 52220200 Dez 18 22:07 libggml-vulkan.so lrwxrwxrwx 1 root root 20 Dez 18 22:07 libvulkan.so.1 -> libvulkan.so.1.4.321 -rwxr-xr-x 1 root root 4466776 Dez 18 22:06 libvulkan.so.1.4.321 ``` How did you install ollama? I recommend re-installing with: ``` curl -fsSL https://ollama.com/install.sh | sh ```
GiteaMirror commented 2026-05-04 23:41:38 -05:00
Author
Owner
Copy Link

@Tusenka commented on GitHub (Jan 5, 2026):

@rick-github , thank you so much!
I was able to run ollama by reinstalling it and installing drivers for AMD:
sudo tar zxf ollama-linux-amd64-rocm.tgz -C /usr

<!-- gh-comment-id:3709079296 --> @Tusenka commented on GitHub (Jan 5, 2026): @rick-github , thank you so much! I was able to run ollama by reinstalling it and installing drivers for AMD: ` sudo tar zxf ollama-linux-amd64-rocm.tgz -C /usr`
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#70994
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?