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

[GH-ISSUE #14094] Title: Ollama fails to use GPU for any model on Ubuntu 22.04.5 LTS despite CUDA being installed #55715

New Issue
Closed
opened 2026-04-29 09:37:42 -05:00 by GiteaMirror · 4 comments
GiteaMirror commented 2026-04-29 09:37:42 -05:00
Owner
Copy Link

Originally created by @gymm-betrayer on GitHub (Feb 5, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/14094

What is the issue?

We are running Ollama on Ubuntu 22.04.5 LTS and NVIDIA RTX 4090 GPUs (24GB VRAM). However, no models — not even small ones like qwen3:8b — are being offloaded to the GPU. All inference runs entirely on CPU.

Relevant log output

time=2026-02-05T22:08:17.055+08:00 level=INFO source=ggml.go:136 msg="" architecture=qwen3vlmoe file_type=Q4_K_M name="" description="" num_tensors=1038 num_key_values=43
time=2026-02-05T22:08:17.055+08:00 level=INFO source=ggml.go:104 msg=system CPU.0.LLAMAFILE=1 compiler=cgo(gcc)
time=2026-02-05T22:08:17.694+08:00 level=INFO source=runner.go:1278 msg=load request="{Operation:alloc LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:4096 KvCacheType: NumThreads:72 GPULayers:[] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
time=2026-02-05T22:08:18.625+08:00 level=INFO source=runner.go:1278 msg=load request="{Operation:commit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:4096 KvCacheType: NumThreads:72 GPULayers:[] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
time=2026-02-05T22:08:18.625+08:00 level=INFO source=ggml.go:482 msg="offloading 0 repeating layers to GPU"
time=2026-02-05T22:08:18.626+08:00 level=INFO source=ggml.go:486 msg="offloading output layer to CPU"
time=2026-02-05T22:08:18.626+08:00 level=INFO source=ggml.go:494 msg="offloaded 0/49 layers to GPU"
time=2026-02-05T22:08:18.626+08:00 level=INFO source=device.go:245 msg="model weights" device=CPU size="18.2 GiB"
time=2026-02-05T22:08:18.626+08:00 level=INFO source=device.go:256 msg="kv cache" device=CPU size="384.0 MiB"
time=2026-02-05T22:08:18.626+08:00 level=INFO source=device.go:267 msg="compute graph" device=CPU size="364.0 MiB"
time=2026-02-05T22:08:18.626+08:00 level=INFO source=device.go:272 msg="total memory" size="19.0 GiB"
time=2026-02-05T22:08:18.626+08:00 level=INFO source=sched.go:517 msg="loaded runners" count=1
time=2026-02-05T22:08:18.626+08:00 level=INFO source=server.go:1338 msg="waiting for llama runner to start responding"
time=2026-02-05T22:08:18.626+08:00 level=INFO source=server.go:1372 msg="waiting for server to become available" status="llm server loading model"
time=2026-02-05T22:08:19.637+08:00 level=INFO source=server.go:1376 msg="llama runner started in 2.71 seconds"

OS

Linux

GPU

Nvidia

CPU

No response

Ollama version

0.1.35

Originally created by @gymm-betrayer on GitHub (Feb 5, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/14094 ### What is the issue? We are running Ollama on Ubuntu 22.04.5 LTS and NVIDIA RTX 4090 GPUs (24GB VRAM). However, no models — not even small ones like qwen3:8b — are being offloaded to the GPU. All inference runs entirely on CPU. ### Relevant log output ```shell time=2026-02-05T22:08:17.055+08:00 level=INFO source=ggml.go:136 msg="" architecture=qwen3vlmoe file_type=Q4_K_M name="" description="" num_tensors=1038 num_key_values=43 time=2026-02-05T22:08:17.055+08:00 level=INFO source=ggml.go:104 msg=system CPU.0.LLAMAFILE=1 compiler=cgo(gcc) time=2026-02-05T22:08:17.694+08:00 level=INFO source=runner.go:1278 msg=load request="{Operation:alloc LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:4096 KvCacheType: NumThreads:72 GPULayers:[] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" time=2026-02-05T22:08:18.625+08:00 level=INFO source=runner.go:1278 msg=load request="{Operation:commit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:4096 KvCacheType: NumThreads:72 GPULayers:[] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" time=2026-02-05T22:08:18.625+08:00 level=INFO source=ggml.go:482 msg="offloading 0 repeating layers to GPU" time=2026-02-05T22:08:18.626+08:00 level=INFO source=ggml.go:486 msg="offloading output layer to CPU" time=2026-02-05T22:08:18.626+08:00 level=INFO source=ggml.go:494 msg="offloaded 0/49 layers to GPU" time=2026-02-05T22:08:18.626+08:00 level=INFO source=device.go:245 msg="model weights" device=CPU size="18.2 GiB" time=2026-02-05T22:08:18.626+08:00 level=INFO source=device.go:256 msg="kv cache" device=CPU size="384.0 MiB" time=2026-02-05T22:08:18.626+08:00 level=INFO source=device.go:267 msg="compute graph" device=CPU size="364.0 MiB" time=2026-02-05T22:08:18.626+08:00 level=INFO source=device.go:272 msg="total memory" size="19.0 GiB" time=2026-02-05T22:08:18.626+08:00 level=INFO source=sched.go:517 msg="loaded runners" count=1 time=2026-02-05T22:08:18.626+08:00 level=INFO source=server.go:1338 msg="waiting for llama runner to start responding" time=2026-02-05T22:08:18.626+08:00 level=INFO source=server.go:1372 msg="waiting for server to become available" status="llm server loading model" time=2026-02-05T22:08:19.637+08:00 level=INFO source=server.go:1376 msg="llama runner started in 2.71 seconds" ``` ### OS Linux ### GPU Nvidia ### CPU _No response_ ### Ollama version 0.1.35
GiteaMirror added the bugneeds more info labels 2026-04-29 09:37:42 -05:00
GiteaMirror commented 2026-04-29 09:37:45 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Feb 5, 2026):

time=2026-02-05T22:08:17.055+08:00 level=INFO source=ggml.go:104 msg=system CPU.0.LLAMAFILE=1 compiler=cgo(gcc)

No accelerated backends found. Post the full log from the start.

<!-- gh-comment-id:3854102588 --> @rick-github commented on GitHub (Feb 5, 2026): ``` time=2026-02-05T22:08:17.055+08:00 level=INFO source=ggml.go:104 msg=system CPU.0.LLAMAFILE=1 compiler=cgo(gcc) ``` No accelerated backends found. Post the full log from the start.
GiteaMirror commented 2026-04-29 09:37:46 -05:00
Author
Owner
Copy Link

@gymm-betrayer commented on GitHub (Feb 5, 2026):

time=2026-02-05T22:08:02.541+08:00 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: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/host/.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=2026-02-05T22:08:02.587+08:00 level=INFO source=images.go:493 msg="total blobs: 6"
time=2026-02-05T22:08:02.587+08:00 level=INFO source=images.go:500 msg="total unused blobs removed: 0"
time=2026-02-05T22:08:02.587+08:00 level=INFO source=routes.go:1607 msg="Listening on 127.0.0.1:11434 (version 0.13.5)"
time=2026-02-05T22:08:02.588+08:00 level=INFO source=runner.go:67 msg="discovering available GPUs..."
time=2026-02-05T22:08:02.589+08:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 44581"
time=2026-02-05T22:08:02.642+08:00 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="251.5 GiB" available="234.5 GiB"
time=2026-02-05T22:08:02.642+08:00 level=INFO source=routes.go:1648 msg="entering low vram mode" "total vram"="0 B" threshold="20.0 GiB"
time=2026-02-05T22:08:16.923+08:00 level=INFO source=server.go:245 msg="enabling flash attention"
time=2026-02-05T22:08:16.923+08:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --model /home/host/.ollama/models/blobs/sha256-b1da6f96a2e40e5db05b6066d799c69411225b336bfa20ef1b002c223ed4b190 --port 39601"
time=2026-02-05T22:08:16.924+08:00 level=INFO source=sched.go:443 msg="system memory" total="251.5 GiB" free="234.2 GiB" free_swap="0 B"
time=2026-02-05T22:08:16.924+08:00 level=INFO source=server.go:746 msg="loading model" "model layers"=49 requested=-1
time=2026-02-05T22:08:16.955+08:00 level=INFO source=runner.go:1405 msg="starting ollama engine"
time=2026-02-05T22:08:16.955+08:00 level=INFO source=runner.go:1440 msg="Server listening on 127.0.0.1:39601"
time=2026-02-05T22:08:16.960+08:00 level=INFO source=runner.go:1278 msg=load request="{Operation:fit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:4096 KvCacheType: NumThreads:72 GPULayers:[] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
time=2026-02-05T22:08:17.055+08:00 level=INFO source=ggml.go:136 msg="" architecture=qwen3vlmoe file_type=Q4_K_M name="" description="" num_tensors=1038 num_key_values=43
time=2026-02-05T22:08:17.055+08:00 level=INFO source=ggml.go:104 msg=system CPU.0.LLAMAFILE=1 compiler=cgo(gcc)
time=2026-02-05T22:08:17.694+08:00 level=INFO source=runner.go:1278 msg=load request="{Operation:alloc LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:4096 KvCacheType: NumThreads:72 GPULayers:[] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
time=2026-02-05T22:08:18.625+08:00 level=INFO source=runner.go:1278 msg=load request="{Operation:commit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:4096 KvCacheType: NumThreads:72 GPULayers:[] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
time=2026-02-05T22:08:18.625+08:00 level=INFO source=ggml.go:482 msg="offloading 0 repeating layers to GPU"
time=2026-02-05T22:08:18.626+08:00 level=INFO source=ggml.go:486 msg="offloading output layer to CPU"
time=2026-02-05T22:08:18.626+08:00 level=INFO source=ggml.go:494 msg="offloaded 0/49 layers to GPU"
time=2026-02-05T22:08:18.626+08:00 level=INFO source=device.go:245 msg="model weights" device=CPU size="18.2 GiB"
time=2026-02-05T22:08:18.626+08:00 level=INFO source=device.go:256 msg="kv cache" device=CPU size="384.0 MiB"
time=2026-02-05T22:08:18.626+08:00 level=INFO source=device.go:267 msg="compute graph" device=CPU size="364.0 MiB"
time=2026-02-05T22:08:18.626+08:00 level=INFO source=device.go:272 msg="total memory" size="19.0 GiB"
time=2026-02-05T22:08:18.626+08:00 level=INFO source=sched.go:517 msg="loaded runners" count=1
time=2026-02-05T22:08:18.626+08:00 level=INFO source=server.go:1338 msg="waiting for llama runner to start responding"
time=2026-02-05T22:08:18.626+08:00 level=INFO source=server.go:1372 msg="waiting for server to become available" status="llm server loading model"
time=2026-02-05T22:08:19.637+08:00 level=INFO source=server.go:1376 msg="llama runner started in 2.71 seconds"
[GIN] 2026/02/05 - 22:18:16 | 500 | 10m0s | 127.0.0.1 | POST "/api/chat"
[GIN] 2026/02/05 - 22:23:28 | 500 | 5m0s | 127.0.0.1 | POST "/api/chat"
[GIN] 2026/02/05 - 23:01:01 | 404 | 812.961µs | 127.0.0.1 | POST "/api/generate"
time=2026-02-05T23:01:12.940+08:00 level=INFO source=server.go:245 msg="enabling flash attention"
time=2026-02-05T23:01:12.941+08:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --model /home/host/.ollama/models/blobs/sha256-b1da6f96a2e40e5db05b6066d799c69411225b336bfa20ef1b002c223ed4b190 --port 40739"
time=2026-02-05T23:01:12.941+08:00 level=INFO source=sched.go:443 msg="system memory" total="251.5 GiB" free="234.3 GiB" free_swap="0 B"
time=2026-02-05T23:01:12.941+08:00 level=INFO source=server.go:746 msg="loading model" "model layers"=49 requested=-1
time=2026-02-05T23:01:12.972+08:00 level=INFO source=runner.go:1405 msg="starting ollama engine"
time=2026-02-05T23:01:12.973+08:00 level=INFO source=runner.go:1440 msg="Server listening on 127.0.0.1:40739"
time=2026-02-05T23:01:12.975+08:00 level=INFO source=runner.go:1278 msg=load request="{Operation:fit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:4096 KvCacheType: NumThreads:72 GPULayers:[] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
time=2026-02-05T23:01:13.061+08:00 level=INFO source=ggml.go:136 msg="" architecture=qwen3vlmoe file_type=Q4_K_M name="" description="" num_tensors=1038 num_key_values=43
time=2026-02-05T23:01:13.062+08:00 level=INFO source=ggml.go:104 msg=system CPU.0.LLAMAFILE=1 compiler=cgo(gcc)
time=2026-02-05T23:01:13.702+08:00 level=INFO source=runner.go:1278 msg=load request="{Operation:alloc LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:4096 KvCacheType: NumThreads:72 GPULayers:[] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
time=2026-02-05T23:01:14.654+08:00 level=INFO source=runner.go:1278 msg=load request="{Operation:commit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:4096 KvCacheType: NumThreads:72 GPULayers:[] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
time=2026-02-05T23:01:14.655+08:00 level=INFO source=ggml.go:482 msg="offloading 0 repeating layers to GPU"
time=2026-02-05T23:01:14.655+08:00 level=INFO source=ggml.go:486 msg="offloading output layer to CPU"
time=2026-02-05T23:01:14.655+08:00 level=INFO source=ggml.go:494 msg="offloaded 0/49 layers to GPU"
time=2026-02-05T23:01:14.655+08:00 level=INFO source=device.go:245 msg="model weights" device=CPU size="18.2 GiB"
time=2026-02-05T23:01:14.655+08:00 level=INFO source=device.go:256 msg="kv cache" device=CPU size="384.0 MiB"
time=2026-02-05T23:01:14.655+08:00 level=INFO source=device.go:267 msg="compute graph" device=CPU size="364.0 MiB"
time=2026-02-05T23:01:14.655+08:00 level=INFO source=device.go:272 msg="total memory" size="19.0 GiB"

<!-- gh-comment-id:3854259792 --> @gymm-betrayer commented on GitHub (Feb 5, 2026): time=2026-02-05T22:08:02.541+08:00 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: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/host/.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=2026-02-05T22:08:02.587+08:00 level=INFO source=images.go:493 msg="total blobs: 6" time=2026-02-05T22:08:02.587+08:00 level=INFO source=images.go:500 msg="total unused blobs removed: 0" time=2026-02-05T22:08:02.587+08:00 level=INFO source=routes.go:1607 msg="Listening on 127.0.0.1:11434 (version 0.13.5)" time=2026-02-05T22:08:02.588+08:00 level=INFO source=runner.go:67 msg="discovering available GPUs..." time=2026-02-05T22:08:02.589+08:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --port 44581" time=2026-02-05T22:08:02.642+08:00 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="251.5 GiB" available="234.5 GiB" time=2026-02-05T22:08:02.642+08:00 level=INFO source=routes.go:1648 msg="entering low vram mode" "total vram"="0 B" threshold="20.0 GiB" time=2026-02-05T22:08:16.923+08:00 level=INFO source=server.go:245 msg="enabling flash attention" time=2026-02-05T22:08:16.923+08:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --model /home/host/.ollama/models/blobs/sha256-b1da6f96a2e40e5db05b6066d799c69411225b336bfa20ef1b002c223ed4b190 --port 39601" time=2026-02-05T22:08:16.924+08:00 level=INFO source=sched.go:443 msg="system memory" total="251.5 GiB" free="234.2 GiB" free_swap="0 B" time=2026-02-05T22:08:16.924+08:00 level=INFO source=server.go:746 msg="loading model" "model layers"=49 requested=-1 time=2026-02-05T22:08:16.955+08:00 level=INFO source=runner.go:1405 msg="starting ollama engine" time=2026-02-05T22:08:16.955+08:00 level=INFO source=runner.go:1440 msg="Server listening on 127.0.0.1:39601" time=2026-02-05T22:08:16.960+08:00 level=INFO source=runner.go:1278 msg=load request="{Operation:fit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:4096 KvCacheType: NumThreads:72 GPULayers:[] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" time=2026-02-05T22:08:17.055+08:00 level=INFO source=ggml.go:136 msg="" architecture=qwen3vlmoe file_type=Q4_K_M name="" description="" num_tensors=1038 num_key_values=43 time=2026-02-05T22:08:17.055+08:00 level=INFO source=ggml.go:104 msg=system CPU.0.LLAMAFILE=1 compiler=cgo(gcc) time=2026-02-05T22:08:17.694+08:00 level=INFO source=runner.go:1278 msg=load request="{Operation:alloc LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:4096 KvCacheType: NumThreads:72 GPULayers:[] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" time=2026-02-05T22:08:18.625+08:00 level=INFO source=runner.go:1278 msg=load request="{Operation:commit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:4096 KvCacheType: NumThreads:72 GPULayers:[] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" time=2026-02-05T22:08:18.625+08:00 level=INFO source=ggml.go:482 msg="offloading 0 repeating layers to GPU" time=2026-02-05T22:08:18.626+08:00 level=INFO source=ggml.go:486 msg="offloading output layer to CPU" time=2026-02-05T22:08:18.626+08:00 level=INFO source=ggml.go:494 msg="offloaded 0/49 layers to GPU" time=2026-02-05T22:08:18.626+08:00 level=INFO source=device.go:245 msg="model weights" device=CPU size="18.2 GiB" time=2026-02-05T22:08:18.626+08:00 level=INFO source=device.go:256 msg="kv cache" device=CPU size="384.0 MiB" time=2026-02-05T22:08:18.626+08:00 level=INFO source=device.go:267 msg="compute graph" device=CPU size="364.0 MiB" time=2026-02-05T22:08:18.626+08:00 level=INFO source=device.go:272 msg="total memory" size="19.0 GiB" time=2026-02-05T22:08:18.626+08:00 level=INFO source=sched.go:517 msg="loaded runners" count=1 time=2026-02-05T22:08:18.626+08:00 level=INFO source=server.go:1338 msg="waiting for llama runner to start responding" time=2026-02-05T22:08:18.626+08:00 level=INFO source=server.go:1372 msg="waiting for server to become available" status="llm server loading model" time=2026-02-05T22:08:19.637+08:00 level=INFO source=server.go:1376 msg="llama runner started in 2.71 seconds" [GIN] 2026/02/05 - 22:18:16 | 500 | 10m0s | 127.0.0.1 | POST "/api/chat" [GIN] 2026/02/05 - 22:23:28 | 500 | 5m0s | 127.0.0.1 | POST "/api/chat" [GIN] 2026/02/05 - 23:01:01 | 404 | 812.961µs | 127.0.0.1 | POST "/api/generate" time=2026-02-05T23:01:12.940+08:00 level=INFO source=server.go:245 msg="enabling flash attention" time=2026-02-05T23:01:12.941+08:00 level=INFO source=server.go:429 msg="starting runner" cmd="/usr/local/bin/ollama runner --ollama-engine --model /home/host/.ollama/models/blobs/sha256-b1da6f96a2e40e5db05b6066d799c69411225b336bfa20ef1b002c223ed4b190 --port 40739" time=2026-02-05T23:01:12.941+08:00 level=INFO source=sched.go:443 msg="system memory" total="251.5 GiB" free="234.3 GiB" free_swap="0 B" time=2026-02-05T23:01:12.941+08:00 level=INFO source=server.go:746 msg="loading model" "model layers"=49 requested=-1 time=2026-02-05T23:01:12.972+08:00 level=INFO source=runner.go:1405 msg="starting ollama engine" time=2026-02-05T23:01:12.973+08:00 level=INFO source=runner.go:1440 msg="Server listening on 127.0.0.1:40739" time=2026-02-05T23:01:12.975+08:00 level=INFO source=runner.go:1278 msg=load request="{Operation:fit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:4096 KvCacheType: NumThreads:72 GPULayers:[] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" time=2026-02-05T23:01:13.061+08:00 level=INFO source=ggml.go:136 msg="" architecture=qwen3vlmoe file_type=Q4_K_M name="" description="" num_tensors=1038 num_key_values=43 time=2026-02-05T23:01:13.062+08:00 level=INFO source=ggml.go:104 msg=system CPU.0.LLAMAFILE=1 compiler=cgo(gcc) time=2026-02-05T23:01:13.702+08:00 level=INFO source=runner.go:1278 msg=load request="{Operation:alloc LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:4096 KvCacheType: NumThreads:72 GPULayers:[] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" time=2026-02-05T23:01:14.654+08:00 level=INFO source=runner.go:1278 msg=load request="{Operation:commit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:4096 KvCacheType: NumThreads:72 GPULayers:[] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" time=2026-02-05T23:01:14.655+08:00 level=INFO source=ggml.go:482 msg="offloading 0 repeating layers to GPU" time=2026-02-05T23:01:14.655+08:00 level=INFO source=ggml.go:486 msg="offloading output layer to CPU" time=2026-02-05T23:01:14.655+08:00 level=INFO source=ggml.go:494 msg="offloaded 0/49 layers to GPU" time=2026-02-05T23:01:14.655+08:00 level=INFO source=device.go:245 msg="model weights" device=CPU size="18.2 GiB" time=2026-02-05T23:01:14.655+08:00 level=INFO source=device.go:256 msg="kv cache" device=CPU size="384.0 MiB" time=2026-02-05T23:01:14.655+08:00 level=INFO source=device.go:267 msg="compute graph" device=CPU size="364.0 MiB" time=2026-02-05T23:01:14.655+08:00 level=INFO source=device.go:272 msg="total memory" size="19.0 GiB"
GiteaMirror commented 2026-04-29 09:37:47 -05:00
Author
Owner
Copy Link

@gymm-betrayer commented on GitHub (Feb 5, 2026):

@rick-github This is our full log. Please check.

<!-- gh-comment-id:3854280005 --> @gymm-betrayer commented on GitHub (Feb 5, 2026): @rick-github This is our full log. Please check.
GiteaMirror commented 2026-04-29 09:37:47 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Feb 5, 2026):

Set OLLAMA_DEBUG=2 in the server environment, restart the ollama server, and post the output of:

journalctl -u ollama --no-pager --since "$(systemctl show ollama --property=ActiveEnterTimestamp --value)" | sed -ne '/server config/,/inference compute/p'
<!-- gh-comment-id:3854325438 --> @rick-github commented on GitHub (Feb 5, 2026): Set `OLLAMA_DEBUG=2` in the [server environment](https://github.com/ollama/ollama/blob/main/docs/faq.mdx#setting-environment-variables-on-linux), restart the ollama server, and post the output of: ``` journalctl -u ollama --no-pager --since "$(systemctl show ollama --property=ActiveEnterTimestamp --value)" | sed -ne '/server config/,/inference compute/p' ```
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 needs more info
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#55715
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?