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 #13904] Ollama Docker with strange delay #9097

New Issue
Closed
opened 2026-04-12 21:56:54 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-12 21:56:54 -05:00
Owner
Copy Link

Originally created by @thomas-meier85 on GitHub (Jan 25, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/13904

What is the issue?

I'm having strange delays when using Ollama over docker (compose).

Basic information:
Ubuntu 24.04 LTS, Current Docker Version
Nvidia RTX 6000 pro Max-Q - 96GB DDR7 VRAM
512GB of System Memory

Nvidia-SMI output:
Sun Jan 25 15:48:18 2026
+-----------------------------------------------------------------------------------------+
| NVIDIA-SMI 580.95.05 Driver Version: 590.48.01 CUDA Version: 13.1 |
+-----------------------------------------+------------------------+----------------------+
| GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. |
| | | MIG M. |
|=========================================+========================+======================|
| 0 NVIDIA RTX PRO 6000 Blac... On | 00000000:17:00.0 Off | Off |
| 30% 39C P8 5W / 300W | 14343MiB / 97887MiB | 0% Default |
| | | N/A |
+-----------------------------------------+------------------------+----------------------+

Interesting as well:
When I stop the container by "docker compose stop Ollama" and start it again, I don't have the 30s delay.
But when I start the "container by docker compose up -d" the first request of every model takes 30s.

Please let me know in case you need more information or logs.

Best
Thomas

Relevant log output

**Scenario 1: Docker container started, prompt "Chat" - Model: gpt-oss:20b**
**I takes around 30s to start the Ollama runner**
time=2026-01-25T14:42:32.062Z level=DEBUG source=runner.go:264 msg="refreshing free memory"
time=2026-01-25T14:42:32.062Z level=DEBUG source=runner.go:328 msg="unable to refresh all GPUs with existing runners, performing bootstrap discovery"
time=2026-01-25T14:42:32.063Z level=INFO source=server.go:429 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 43921"
time=2026-01-25T14:42:32.063Z level=DEBUG source=server.go:430 msg=subprocess PATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin OLLAMA_LLM_LIBRARY=cuda_v13 OLLAMA_KEEP_ALIVE=-1 OLLAMA_HOST=0.0.0.0 OLLAMA_DEBUG=true OLLAMA_FLASH_ATTENTION=1 LD_LIBRARY_PATH=/usr/lib/ollama:/usr/lib/ollama/cuda_v13:/usr/local/nvidia/l
ib:/usr/local/nvidia/lib64 OLLAMA_LIBRARY_PATH=/usr/lib/ollama:/usr/lib/ollama/cuda_v13
time=2026-01-25T14:42:32.208Z level=DEBUG source=runner.go:437 msg="bootstrap discovery took" duration=145.477131ms OLLAMA_LIBRARY_PATH="[/usr/lib/ollama /usr/lib/ollama/cuda_v13]" extra_envs=map[]
time=2026-01-25T14:42:32.208Z level=DEBUG source=runner.go:40 msg="overall device VRAM discovery took" duration=145.670137ms
time=2026-01-25T14:42:32.213Z level=WARN source=cpu_linux.go:130 msg="failed to parse CPU allowed micro secs" error="strconv.ParseInt: parsing \"max\": invalid syntax"
time=2026-01-25T14:42:32.213Z level=DEBUG source=sched.go:195 msg="updating default concurrency" OLLAMA_MAX_LOADED_MODELS=3 gpu_count=1
time=2026-01-25T14:42:32.250Z level=DEBUG source=ggml.go:298 msg="key with type not found" key=general.alignment default=32
time=2026-01-25T14:42:32.251Z level=DEBUG source=sched.go:220 msg="loading first model" model=/root/.ollama/models/blobs/sha256-e7b273f9636059a689e3ddcab3716e4f65abe0143ac978e46673ad0e52d09efb
time=2026-01-25T14:42:32.412Z level=DEBUG source=ggml.go:298 msg="key with type not found" key=general.alignment default=32
time=2026-01-25T14:42:32.413Z level=DEBUG source=ggml.go:298 msg="key with type not found" key=gptoss.pooling_type default=0
time=2026-01-25T14:42:32.413Z level=INFO source=server.go:245 msg="enabling flash attention"
time=2026-01-25T14:42:32.413Z level=INFO source=server.go:429 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --model /root/.ollama/models/blobs/sha256-e7b273f9636059a689e3ddcab3716e4f65abe0143ac978e46673ad0e52d09efb --port 46675"
time=2026-01-25T14:42:32.413Z level=DEBUG source=server.go:430 msg=subprocess PATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin OLLAMA_LLM_LIBRARY=cuda_v13 OLLAMA_KEEP_ALIVE=-1 OLLAMA_HOST=0.0.0.0 OLLAMA_DEBUG=true OLLAMA_FLASH_ATTENTION=1 LD_LIBRARY_PATH=/usr/lib/ollama:/usr/lib/ollama/cuda_v13:/usr/local/nvidia/l
ib:/usr/local/nvidia/lib64 OLLAMA_LIBRARY_PATH=/usr/lib/ollama:/usr/lib/ollama/cuda_v13
time=2026-01-25T14:42:32.414Z level=INFO source=sched.go:452 msg="system memory" total="503.4 GiB" free="503.2 GiB" free_swap="4.0 GiB"
time=2026-01-25T14:42:32.414Z level=INFO source=sched.go:459 msg="gpu memory" id=GPU-7f2d3c91-8c50-7c91-e17f-ac3279c58604 library=CUDA available="93.4 GiB" free="93.9 GiB" minimum="457.0 MiB" overhead="0 B"
time=2026-01-25T14:42:32.414Z level=INFO source=server.go:755 msg="loading model" "model layers"=25 requested=-1
time=2026-01-25T14:42:32.434Z level=INFO source=runner.go:1405 msg="starting ollama engine"
time=2026-01-25T14:42:32.434Z level=INFO source=runner.go:1440 msg="Server listening on 127.0.0.1:46675"
time=2026-01-25T14:42:32.437Z level=INFO source=runner.go:1278 msg=load request="{Operation:fit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:8192 KvCacheType: NumThreads:24 GPULayers:25[ID:GPU-7f2d3c91-8c50-7c91-e17f-ac3279c58604 Layers:25(0..24)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
time=2026-01-25T14:42:32.518Z level=DEBUG source=ggml.go:298 msg="key with type not found" key=general.alignment default=32
time=2026-01-25T14:42:32.519Z level=DEBUG source=ggml.go:298 msg="key with type not found" key=general.name default=""
time=2026-01-25T14:42:32.519Z level=DEBUG source=ggml.go:298 msg="key with type not found" key=general.description default=""
time=2026-01-25T14:42:32.519Z level=INFO source=ggml.go:136 msg="" architecture=gptoss file_type=MXFP4 name="" description="" num_tensors=459 num_key_values=32
time=2026-01-25T14:42:32.519Z level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=/usr/lib/ollama
load_backend: loaded CPU backend from /usr/lib/ollama/libggml-cpu-icelake.so
time=2026-01-25T14:42:32.527Z level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=/usr/lib/ollama/cuda_v13
ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 CUDA devices:
  Device 0: NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition, compute capability 12.0, VMM: yes, ID: GPU-7f2d3c91-8c50-7c91-e17f-ac3279c58604
load_backend: loaded CUDA backend from /usr/lib/ollama/cuda_v13/libggml-cuda.so
time=2026-01-25T14:42:32.614Z level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.AVX512=1 CPU.0.AVX512_VBMI=1 CPU.0.AVX512_VNNI=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 CUDA.0.ARCHS=750,800,860,870,890,900,1000,1030,1100,1200,1210 CUDA.0.USE_GRAPHS=
1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(gcc)
time=2026-01-25T14:42:32.617Z level=DEBUG source=ggml.go:298 msg="key with type not found" key=gptoss.pooling_type default=0
time=2026-01-25T14:42:51.557Z level=DEBUG source=ggml.go:852 msg="compute graph" nodes=1399 splits=2
time=2026-01-25T14:43:00.007Z level=DEBUG source=ggml.go:852 msg="compute graph" nodes=1399 splits=2
time=2026-01-25T14:43:00.008Z level=DEBUG source=device.go:240 msg="model weights" device=CUDA0 size="11.8 GiB"
time=2026-01-25T14:43:00.008Z level=DEBUG source=device.go:245 msg="model weights" device=CPU size="1.1 GiB"
time=2026-01-25T14:43:00.008Z level=DEBUG source=device.go:251 msg="kv cache" device=CUDA0 size="300.0 MiB"
time=2026-01-25T14:43:00.008Z level=DEBUG source=device.go:262 msg="compute graph" device=CUDA0 size="160.6 MiB"
time=2026-01-25T14:43:00.008Z level=DEBUG source=device.go:267 msg="compute graph" device=CPU size="5.6 MiB"
time=2026-01-25T14:43:00.008Z level=DEBUG source=device.go:272 msg="total memory" size="13.3 GiB"
time=2026-01-25T14:43:00.008Z level=DEBUG source=server.go:780 msg=memory success=true required.InputWeights=1158266880 required.CPU.Graph=5898240 required.CUDA0.ID=GPU-7f2d3c91-8c50-7c91-e17f-ac3279c58604 required.CUDA0.Weights="[477628928 477628928 477628928 477628928 477628928 477628928 477628928 477628928 477628928 477628928 4
77628928 477628928 477628928 477628928 477628928 477628928 477628928 477628928 477628928 477628928 477628928 477628928 477628928 477628928 1158278400]" required.CUDA0.Cache="[9437184 16777216 9437184 16777216 9437184 16777216 9437184 16777216 9437184 16777216 9437184 16777216 9437184 16777216 9437184 16777216 9437184 16777216 9437
184 16777216 9437184 16777216 9437184 16777216 0]" required.CUDA0.Graph=168433792
time=2026-01-25T14:43:00.008Z level=DEBUG source=server.go:974 msg="available gpu" id=GPU-7f2d3c91-8c50-7c91-e17f-ac3279c58604 library=CUDA "available layer vram"="93.3 GiB" backoff=0.00 minimum="457.0 MiB" overhead="0 B" graph="160.6 MiB"
time=2026-01-25T14:43:00.008Z level=DEBUG source=server.go:791 msg="new layout created" layers="25[ID:GPU-7f2d3c91-8c50-7c91-e17f-ac3279c58604 Layers:25(0..24)]"
time=2026-01-25T14:43:00.009Z level=INFO source=runner.go:1278 msg=load request="{Operation:alloc LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:8192 KvCacheType: NumThreads:24 GPULayers:25[ID:GPU-7f2d3c91-8c50-7c91-e17f-ac3279c58604 Layers:25(0..24)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}
"
time=2026-01-25T14:43:00.078Z level=DEBUG source=ggml.go:298 msg="key with type not found" key=general.alignment default=32
time=2026-01-25T14:43:00.082Z level=DEBUG source=ggml.go:298 msg="key with type not found" key=gptoss.pooling_type default=0
time=2026-01-25T14:43:00.147Z level=DEBUG source=ggml.go:852 msg="compute graph" nodes=1399 splits=2
time=2026-01-25T14:43:00.151Z level=DEBUG source=ggml.go:852 msg="compute graph" nodes=1399 splits=2
time=2026-01-25T14:43:00.151Z level=DEBUG source=device.go:240 msg="model weights" device=CUDA0 size="11.8 GiB"
time=2026-01-25T14:43:00.151Z level=DEBUG source=device.go:245 msg="model weights" device=CPU size="1.1 GiB"
time=2026-01-25T14:43:00.151Z level=DEBUG source=device.go:251 msg="kv cache" device=CUDA0 size="300.0 MiB"
time=2026-01-25T14:43:00.151Z level=DEBUG source=device.go:262 msg="compute graph" device=CUDA0 size="160.6 MiB"
time=2026-01-25T14:43:00.151Z level=DEBUG source=device.go:267 msg="compute graph" device=CPU size="5.6 MiB"
time=2026-01-25T14:43:00.151Z level=DEBUG source=device.go:272 msg="total memory" size="13.3 GiB"
time=2026-01-25T14:43:00.151Z level=DEBUG source=server.go:780 msg=memory success=true required.InputWeights=1158266880 required.CPU.Graph=5898240 required.CUDA0.ID=GPU-7f2d3c91-8c50-7c91-e17f-ac3279c58604 required.CUDA0.Weights="[477628928 477628928 477628928 477628928 477628928 477628928 477628928 477628928 477628928 477628928 4
77628928 477628928 477628928 477628928 477628928 477628928 477628928 477628928 477628928 477628928 477628928 477628928 477628928 477628928 1158278400]" required.CUDA0.Cache="[9437184 16777216 9437184 16777216 9437184 16777216 9437184 16777216 9437184 16777216 9437184 16777216 9437184 16777216 9437184 16777216 9437184 16777216 9437
184 16777216 9437184 16777216 9437184 16777216 0]" required.CUDA0.Graph=168433792
time=2026-01-25T14:43:00.151Z level=DEBUG source=server.go:974 msg="available gpu" id=GPU-7f2d3c91-8c50-7c91-e17f-ac3279c58604 library=CUDA "available layer vram"="93.3 GiB" backoff=0.00 minimum="457.0 MiB" overhead="0 B" graph="160.6 MiB"
time=2026-01-25T14:43:00.152Z level=DEBUG source=server.go:791 msg="new layout created" layers="25[ID:GPU-7f2d3c91-8c50-7c91-e17f-ac3279c58604 Layers:25(0..24)]"
time=2026-01-25T14:43:00.152Z level=INFO source=runner.go:1278 msg=load request="{Operation:commit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:8192 KvCacheType: NumThreads:24 GPULayers:25[ID:GPU-7f2d3c91-8c50-7c91-e17f-ac3279c58604 Layers:25(0..24)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false
}"
time=2026-01-25T14:43:00.152Z level=INFO source=ggml.go:482 msg="offloading 24 repeating layers to GPU"
time=2026-01-25T14:43:00.153Z level=INFO source=ggml.go:489 msg="offloading output layer to GPU"
time=2026-01-25T14:43:00.153Z level=INFO source=ggml.go:494 msg="offloaded 25/25 layers to GPU"
time=2026-01-25T14:43:00.153Z level=INFO source=device.go:240 msg="model weights" device=CUDA0 size="11.8 GiB"
time=2026-01-25T14:43:00.153Z level=INFO source=device.go:245 msg="model weights" device=CPU size="1.1 GiB"
time=2026-01-25T14:43:00.153Z level=INFO source=device.go:251 msg="kv cache" device=CUDA0 size="300.0 MiB"
time=2026-01-25T14:43:00.153Z level=INFO source=device.go:262 msg="compute graph" device=CUDA0 size="160.6 MiB"
time=2026-01-25T14:43:00.153Z level=INFO source=device.go:267 msg="compute graph" device=CPU size="5.6 MiB"
time=2026-01-25T14:43:00.153Z level=INFO source=device.go:272 msg="total memory" size="13.3 GiB"
time=2026-01-25T14:43:00.153Z level=INFO source=sched.go:526 msg="loaded runners" count=1
time=2026-01-25T14:43:00.153Z level=INFO source=server.go:1347 msg="waiting for llama runner to start responding"
time=2026-01-25T14:43:00.154Z level=INFO source=server.go:1381 msg="waiting for server to become available" status="llm server loading model"
time=2026-01-25T14:43:00.154Z level=DEBUG source=server.go:1391 msg="model load progress 0.00"
time=2026-01-25T14:43:00.405Z level=DEBUG source=server.go:1391 msg="model load progress 0.05"
time=2026-01-25T14:43:00.656Z level=DEBUG source=server.go:1391 msg="model load progress 0.09"
time=2026-01-25T14:43:00.907Z level=DEBUG source=server.go:1391 msg="model load progress 0.14"
time=2026-01-25T14:43:01.158Z level=DEBUG source=server.go:1391 msg="model load progress 0.18"
time=2026-01-25T14:43:01.410Z level=DEBUG source=server.go:1391 msg="model load progress 0.22"
time=2026-01-25T14:43:01.661Z level=DEBUG source=server.go:1391 msg="model load progress 0.27"
time=2026-01-25T14:43:01.912Z level=DEBUG source=server.go:1391 msg="model load progress 0.30"
time=2026-01-25T14:43:02.164Z level=DEBUG source=server.go:1391 msg="model load progress 0.35"
time=2026-01-25T14:43:02.415Z level=DEBUG source=server.go:1391 msg="model load progress 0.48"
time=2026-01-25T14:43:02.666Z level=DEBUG source=server.go:1391 msg="model load progress 0.64"
time=2026-01-25T14:43:02.916Z level=DEBUG source=server.go:1391 msg="model load progress 0.82"
time=2026-01-25T14:43:03.168Z level=DEBUG source=server.go:1391 msg="model load progress 0.95"
time=2026-01-25T14:43:03.348Z level=DEBUG source=ggml.go:298 msg="key with type not found" key=gptoss.pooling_type default=0
**time=2026-01-25T14:43:03.420Z level=INFO source=server.go:1385 msg="llama runner started in 31.01 seconds"**
time=2026-01-25T14:43:03.420Z level=DEBUG source=sched.go:538 msg="finished setting up" runner.name=registry.ollama.ai/library/gpt-oss:latest runner.inference="[{ID:GPU-7f2d3c91-8c50-7c91-e17f-ac3279c58604 Library:CUDA}]" runner.size="13.3 GiB" runner.vram="13.3 GiB" runner.parallel=1 runner.pid=103 runner.model=/root/.ollama/mode
ls/blobs/sha256-e7b273f9636059a689e3ddcab3716e4f65abe0143ac978e46673ad0e52d09efb runner.num_ctx=8192
time=2026-01-25T14:43:03.421Z level=DEBUG source=server.go:1533 msg="completion request" images=0 prompt=306 format=""
time=2026-01-25T14:43:03.498Z level=DEBUG source=cache.go:142 msg="loading cache slot" id=0 cache=0 prompt=68 used=0 remaining=68

**Scenario 1: Docker container already started - Model manually unloaded, prompt "Chat" - Model: gpt-oss:20b**
**I takes around 3s to start the Ollama runner**
time=2026-01-25T14:40:26.488Z level=DEBUG source=runner.go:264 msg="refreshing free memory"
time=2026-01-25T14:40:26.488Z level=DEBUG source=runner.go:328 msg="unable to refresh all GPUs with existing runners, performing bootstrap discovery"
time=2026-01-25T14:40:26.489Z level=INFO source=server.go:429 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 38037"
time=2026-01-25T14:40:26.489Z level=DEBUG source=server.go:430 msg=subprocess PATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin OLLAMA_DEBUG=true OLLAMA_FLASH_ATTENTION=1 OLLAMA_LLM_LIBRARY=cuda_v13 OLLAMA_KEEP_ALIVE=-1 OLLAMA_HOST=0.0.0.0 LD_LIBRARY_PATH=/usr/lib/ollama:/usr/lib/ollama/cuda_v13:/usr/local/nvidia/l
ib:/usr/local/nvidia/lib64 OLLAMA_LIBRARY_PATH=/usr/lib/ollama:/usr/lib/ollama/cuda_v13
time=2026-01-25T14:40:26.627Z level=DEBUG source=runner.go:437 msg="bootstrap discovery took" duration=139.130954ms OLLAMA_LIBRARY_PATH="[/usr/lib/ollama /usr/lib/ollama/cuda_v13]" extra_envs=map[]
time=2026-01-25T14:40:26.628Z level=DEBUG source=runner.go:40 msg="overall device VRAM discovery took" duration=139.384896ms
time=2026-01-25T14:40:26.632Z level=WARN source=cpu_linux.go:130 msg="failed to parse CPU allowed micro secs" error="strconv.ParseInt: parsing \"max\": invalid syntax"
time=2026-01-25T14:40:26.671Z level=DEBUG source=ggml.go:298 msg="key with type not found" key=general.alignment default=32
time=2026-01-25T14:40:26.671Z level=DEBUG source=sched.go:220 msg="loading first model" model=/root/.ollama/models/blobs/sha256-e7b273f9636059a689e3ddcab3716e4f65abe0143ac978e46673ad0e52d09efb
time=2026-01-25T14:40:26.831Z level=DEBUG source=ggml.go:298 msg="key with type not found" key=general.alignment default=32
time=2026-01-25T14:40:26.832Z level=DEBUG source=ggml.go:298 msg="key with type not found" key=gptoss.pooling_type default=0
time=2026-01-25T14:40:26.832Z level=INFO source=server.go:245 msg="enabling flash attention"
time=2026-01-25T14:40:26.832Z level=INFO source=server.go:429 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --model /root/.ollama/models/blobs/sha256-e7b273f9636059a689e3ddcab3716e4f65abe0143ac978e46673ad0e52d09efb --port 37943"
time=2026-01-25T14:40:26.832Z level=DEBUG source=server.go:430 msg=subprocess PATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin OLLAMA_DEBUG=true OLLAMA_FLASH_ATTENTION=1 OLLAMA_LLM_LIBRARY=cuda_v13 OLLAMA_KEEP_ALIVE=-1 OLLAMA_HOST=0.0.0.0 LD_LIBRARY_PATH=/usr/lib/ollama:/usr/lib/ollama/cuda_v13:/usr/local/nvidia/l
ib:/usr/local/nvidia/lib64 OLLAMA_LIBRARY_PATH=/usr/lib/ollama:/usr/lib/ollama/cuda_v13
time=2026-01-25T14:40:26.833Z level=INFO source=sched.go:452 msg="system memory" total="503.4 GiB" free="503.2 GiB" free_swap="4.0 GiB"
time=2026-01-25T14:40:26.833Z level=INFO source=sched.go:459 msg="gpu memory" id=GPU-7f2d3c91-8c50-7c91-e17f-ac3279c58604 library=CUDA available="93.4 GiB" free="93.9 GiB" minimum="457.0 MiB" overhead="0 B"
time=2026-01-25T14:40:26.833Z level=INFO source=server.go:755 msg="loading model" "model layers"=25 requested=-1
time=2026-01-25T14:40:26.853Z level=INFO source=runner.go:1405 msg="starting ollama engine"
time=2026-01-25T14:40:26.853Z level=INFO source=runner.go:1440 msg="Server listening on 127.0.0.1:37943"
time=2026-01-25T14:40:26.857Z level=INFO source=runner.go:1278 msg=load request="{Operation:fit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:8192 KvCacheType: NumThreads:24 GPULayers:25[ID:GPU-7f2d3c91-8c50-7c91-e17f-ac3279c58604 Layers:25(0..24)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}"
time=2026-01-25T14:40:26.935Z level=DEBUG source=ggml.go:298 msg="key with type not found" key=general.alignment default=32
time=2026-01-25T14:40:26.936Z level=DEBUG source=ggml.go:298 msg="key with type not found" key=general.name default=""
time=2026-01-25T14:40:26.936Z level=DEBUG source=ggml.go:298 msg="key with type not found" key=general.description default=""
time=2026-01-25T14:40:26.936Z level=INFO source=ggml.go:136 msg="" architecture=gptoss file_type=MXFP4 name="" description="" num_tensors=459 num_key_values=32
time=2026-01-25T14:40:26.936Z level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=/usr/lib/ollama
load_backend: loaded CPU backend from /usr/lib/ollama/libggml-cpu-icelake.so
time=2026-01-25T14:40:26.944Z level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=/usr/lib/ollama/cuda_v13
ggml_cuda_init: GGML_CUDA_FORCE_MMQ:    no
ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no
ggml_cuda_init: found 1 CUDA devices:
  Device 0: NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition, compute capability 12.0, VMM: yes, ID: GPU-7f2d3c91-8c50-7c91-e17f-ac3279c58604
load_backend: loaded CUDA backend from /usr/lib/ollama/cuda_v13/libggml-cuda.so
time=2026-01-25T14:40:27.033Z level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.AVX512=1 CPU.0.AVX512_VBMI=1 CPU.0.AVX512_VNNI=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 CUDA.0.ARCHS=750,800,860,870,890,900,1000,1030,1100,1200,1210 CUDA.0.USE_GRAPHS=
1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(gcc)
time=2026-01-25T14:40:27.035Z level=DEBUG source=ggml.go:298 msg="key with type not found" key=gptoss.pooling_type default=0
time=2026-01-25T14:40:27.588Z level=DEBUG source=ggml.go:852 msg="compute graph" nodes=1399 splits=2
time=2026-01-25T14:40:27.615Z level=DEBUG source=ggml.go:852 msg="compute graph" nodes=1399 splits=2
time=2026-01-25T14:40:27.616Z level=DEBUG source=device.go:240 msg="model weights" device=CUDA0 size="11.8 GiB"
time=2026-01-25T14:40:27.616Z level=DEBUG source=device.go:245 msg="model weights" device=CPU size="1.1 GiB"
time=2026-01-25T14:40:27.616Z level=DEBUG source=device.go:251 msg="kv cache" device=CUDA0 size="300.0 MiB"
time=2026-01-25T14:40:27.616Z level=DEBUG source=device.go:262 msg="compute graph" device=CUDA0 size="160.6 MiB"
time=2026-01-25T14:40:27.616Z level=DEBUG source=device.go:267 msg="compute graph" device=CPU size="5.6 MiB"
time=2026-01-25T14:40:27.616Z level=DEBUG source=device.go:272 msg="total memory" size="13.3 GiB"
time=2026-01-25T14:40:27.616Z level=DEBUG source=server.go:780 msg=memory success=true required.InputWeights=1158266880 required.CPU.Graph=5898240 required.CUDA0.ID=GPU-7f2d3c91-8c50-7c91-e17f-ac3279c58604 required.CUDA0.Weights="[477628928 477628928 477628928 477628928 477628928 477628928 477628928 477628928 477628928 477628928 4
77628928 477628928 477628928 477628928 477628928 477628928 477628928 477628928 477628928 477628928 477628928 477628928 477628928 477628928 1158278400]" required.CUDA0.Cache="[9437184 16777216 9437184 16777216 9437184 16777216 9437184 16777216 9437184 16777216 9437184 16777216 9437184 16777216 9437184 16777216 9437184 16777216 9437
184 16777216 9437184 16777216 9437184 16777216 0]" required.CUDA0.Graph=168433792
time=2026-01-25T14:40:27.616Z level=DEBUG source=server.go:974 msg="available gpu" id=GPU-7f2d3c91-8c50-7c91-e17f-ac3279c58604 library=CUDA "available layer vram"="93.3 GiB" backoff=0.00 minimum="457.0 MiB" overhead="0 B" graph="160.6 MiB"
time=2026-01-25T14:40:27.617Z level=DEBUG source=server.go:791 msg="new layout created" layers="25[ID:GPU-7f2d3c91-8c50-7c91-e17f-ac3279c58604 Layers:25(0..24)]"
time=2026-01-25T14:40:27.617Z level=INFO source=runner.go:1278 msg=load request="{Operation:alloc LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:8192 KvCacheType: NumThreads:24 GPULayers:25[ID:GPU-7f2d3c91-8c50-7c91-e17f-ac3279c58604 Layers:25(0..24)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}
"
time=2026-01-25T14:40:27.688Z level=DEBUG source=ggml.go:298 msg="key with type not found" key=general.alignment default=32
time=2026-01-25T14:40:27.692Z level=DEBUG source=ggml.go:298 msg="key with type not found" key=gptoss.pooling_type default=0
time=2026-01-25T14:40:27.756Z level=DEBUG source=ggml.go:852 msg="compute graph" nodes=1399 splits=2
time=2026-01-25T14:40:27.760Z level=DEBUG source=ggml.go:852 msg="compute graph" nodes=1399 splits=2
time=2026-01-25T14:40:27.761Z level=DEBUG source=device.go:240 msg="model weights" device=CUDA0 size="11.8 GiB"
time=2026-01-25T14:40:27.761Z level=DEBUG source=device.go:245 msg="model weights" device=CPU size="1.1 GiB"
time=2026-01-25T14:40:27.761Z level=DEBUG source=device.go:251 msg="kv cache" device=CUDA0 size="300.0 MiB"
time=2026-01-25T14:40:27.761Z level=DEBUG source=device.go:262 msg="compute graph" device=CUDA0 size="160.6 MiB"
time=2026-01-25T14:40:27.761Z level=DEBUG source=device.go:267 msg="compute graph" device=CPU size="5.6 MiB"
time=2026-01-25T14:40:27.761Z level=DEBUG source=device.go:272 msg="total memory" size="13.3 GiB"
time=2026-01-25T14:40:27.761Z level=DEBUG source=server.go:780 msg=memory success=true required.InputWeights=1158266880 required.CPU.Graph=5898240 required.CUDA0.ID=GPU-7f2d3c91-8c50-7c91-e17f-ac3279c58604 required.CUDA0.Weights="[477628928 477628928 477628928 477628928 477628928 477628928 477628928 477628928 477628928 477628928 4
77628928 477628928 477628928 477628928 477628928 477628928 477628928 477628928 477628928 477628928 477628928 477628928 477628928 477628928 1158278400]" required.CUDA0.Cache="[9437184 16777216 9437184 16777216 9437184 16777216 9437184 16777216 9437184 16777216 9437184 16777216 9437184 16777216 9437184 16777216 9437184 16777216 9437
184 16777216 9437184 16777216 9437184 16777216 0]" required.CUDA0.Graph=168433792
time=2026-01-25T14:40:27.761Z level=DEBUG source=server.go:974 msg="available gpu" id=GPU-7f2d3c91-8c50-7c91-e17f-ac3279c58604 library=CUDA "available layer vram"="93.3 GiB" backoff=0.00 minimum="457.0 MiB" overhead="0 B" graph="160.6 MiB"
time=2026-01-25T14:40:27.761Z level=DEBUG source=server.go:791 msg="new layout created" layers="25[ID:GPU-7f2d3c91-8c50-7c91-e17f-ac3279c58604 Layers:25(0..24)]"
time=2026-01-25T14:40:27.762Z level=INFO source=runner.go:1278 msg=load request="{Operation:commit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:8192 KvCacheType: NumThreads:24 GPULayers:25[ID:GPU-7f2d3c91-8c50-7c91-e17f-ac3279c58604 Layers:25(0..24)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false
}"
time=2026-01-25T14:40:27.762Z level=INFO source=ggml.go:482 msg="offloading 24 repeating layers to GPU"
time=2026-01-25T14:40:27.762Z level=INFO source=ggml.go:489 msg="offloading output layer to GPU"
time=2026-01-25T14:40:27.762Z level=INFO source=ggml.go:494 msg="offloaded 25/25 layers to GPU"
time=2026-01-25T14:40:27.763Z level=INFO source=device.go:240 msg="model weights" device=CUDA0 size="11.8 GiB"
time=2026-01-25T14:40:27.763Z level=INFO source=device.go:245 msg="model weights" device=CPU size="1.1 GiB"
time=2026-01-25T14:40:27.763Z level=INFO source=device.go:251 msg="kv cache" device=CUDA0 size="300.0 MiB"
time=2026-01-25T14:40:27.763Z level=INFO source=device.go:262 msg="compute graph" device=CUDA0 size="160.6 MiB"
time=2026-01-25T14:40:27.763Z level=INFO source=device.go:267 msg="compute graph" device=CPU size="5.6 MiB"
time=2026-01-25T14:40:27.763Z level=INFO source=device.go:272 msg="total memory" size="13.3 GiB"
time=2026-01-25T14:40:27.763Z level=INFO source=sched.go:526 msg="loaded runners" count=1
time=2026-01-25T14:40:27.763Z level=INFO source=server.go:1347 msg="waiting for llama runner to start responding"
time=2026-01-25T14:40:27.763Z level=INFO source=server.go:1381 msg="waiting for server to become available" status="llm server loading model"
time=2026-01-25T14:40:27.763Z level=DEBUG source=server.go:1391 msg="model load progress 0.00"
time=2026-01-25T14:40:28.014Z level=DEBUG source=server.go:1391 msg="model load progress 0.12"
time=2026-01-25T14:40:28.265Z level=DEBUG source=server.go:1391 msg="model load progress 0.27"
time=2026-01-25T14:40:28.515Z level=DEBUG source=server.go:1391 msg="model load progress 0.41"
time=2026-01-25T14:40:28.766Z level=DEBUG source=server.go:1391 msg="model load progress 0.55"
time=2026-01-25T14:40:29.017Z level=DEBUG source=server.go:1391 msg="model load progress 0.72"
time=2026-01-25T14:40:29.268Z level=DEBUG source=server.go:1391 msg="model load progress 0.90"
time=2026-01-25T14:40:29.519Z level=DEBUG source=server.go:1391 msg="model load progress 0.98"
time=2026-01-25T14:40:29.602Z level=DEBUG source=ggml.go:298 msg="key with type not found" key=gptoss.pooling_type default=0
**time=2026-01-25T14:40:29.771Z level=INFO source=server.go:1385 msg="llama runner started in 2.94 seconds"**
time=2026-01-25T14:40:29.772Z level=DEBUG source=sched.go:538 msg="finished setting up" runner.name=registry.ollama.ai/library/gpt-oss:latest runner.inference="[{ID:GPU-7f2d3c91-8c50-7c91-e17f-ac3279c58604 Library:CUDA}]" runner.size="13.3 GiB" runner.vram="13.3 GiB" runner.parallel=1 runner.pid=217 runner.model=/root/.ollama/mode
ls/blobs/sha256-e7b273f9636059a689e3ddcab3716e4f65abe0143ac978e46673ad0e52d09efb runner.num_ctx=8192
time=2026-01-25T14:40:29.772Z level=DEBUG source=server.go:1533 msg="completion request" images=0 prompt=306 format=""
time=2026-01-25T14:40:29.858Z level=DEBUG source=cache.go:142 msg="loading cache slot" id=0 cache=0 prompt=68 used=0 remaining=68

OS

Linux

GPU

Nvidia

CPU

Intel

Ollama version

latest

Originally created by @thomas-meier85 on GitHub (Jan 25, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/13904 ### What is the issue? I'm having strange delays when using Ollama over docker (compose). Basic information: Ubuntu 24.04 LTS, Current Docker Version Nvidia RTX 6000 pro Max-Q - 96GB DDR7 VRAM 512GB of System Memory Nvidia-SMI output: Sun Jan 25 15:48:18 2026 +-----------------------------------------------------------------------------------------+ | NVIDIA-SMI 580.95.05 Driver Version: 590.48.01 CUDA Version: 13.1 | +-----------------------------------------+------------------------+----------------------+ | GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC | | Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. | | | | MIG M. | |=========================================+========================+======================| | 0 NVIDIA RTX PRO 6000 Blac... On | 00000000:17:00.0 Off | Off | | 30% 39C P8 5W / 300W | 14343MiB / 97887MiB | 0% Default | | | | N/A | +-----------------------------------------+------------------------+----------------------+ Interesting as well: When I stop the container by "docker compose stop Ollama" and start it again, I don't have the 30s delay. But when I start the "container by docker compose up -d" the first request of every model takes 30s. Please let me know in case you need more information or logs. Best Thomas ### Relevant log output ```shell **Scenario 1: Docker container started, prompt "Chat" - Model: gpt-oss:20b** **I takes around 30s to start the Ollama runner** time=2026-01-25T14:42:32.062Z level=DEBUG source=runner.go:264 msg="refreshing free memory" time=2026-01-25T14:42:32.062Z level=DEBUG source=runner.go:328 msg="unable to refresh all GPUs with existing runners, performing bootstrap discovery" time=2026-01-25T14:42:32.063Z level=INFO source=server.go:429 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 43921" time=2026-01-25T14:42:32.063Z level=DEBUG source=server.go:430 msg=subprocess PATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin OLLAMA_LLM_LIBRARY=cuda_v13 OLLAMA_KEEP_ALIVE=-1 OLLAMA_HOST=0.0.0.0 OLLAMA_DEBUG=true OLLAMA_FLASH_ATTENTION=1 LD_LIBRARY_PATH=/usr/lib/ollama:/usr/lib/ollama/cuda_v13:/usr/local/nvidia/l ib:/usr/local/nvidia/lib64 OLLAMA_LIBRARY_PATH=/usr/lib/ollama:/usr/lib/ollama/cuda_v13 time=2026-01-25T14:42:32.208Z level=DEBUG source=runner.go:437 msg="bootstrap discovery took" duration=145.477131ms OLLAMA_LIBRARY_PATH="[/usr/lib/ollama /usr/lib/ollama/cuda_v13]" extra_envs=map[] time=2026-01-25T14:42:32.208Z level=DEBUG source=runner.go:40 msg="overall device VRAM discovery took" duration=145.670137ms time=2026-01-25T14:42:32.213Z level=WARN source=cpu_linux.go:130 msg="failed to parse CPU allowed micro secs" error="strconv.ParseInt: parsing \"max\": invalid syntax" time=2026-01-25T14:42:32.213Z level=DEBUG source=sched.go:195 msg="updating default concurrency" OLLAMA_MAX_LOADED_MODELS=3 gpu_count=1 time=2026-01-25T14:42:32.250Z level=DEBUG source=ggml.go:298 msg="key with type not found" key=general.alignment default=32 time=2026-01-25T14:42:32.251Z level=DEBUG source=sched.go:220 msg="loading first model" model=/root/.ollama/models/blobs/sha256-e7b273f9636059a689e3ddcab3716e4f65abe0143ac978e46673ad0e52d09efb time=2026-01-25T14:42:32.412Z level=DEBUG source=ggml.go:298 msg="key with type not found" key=general.alignment default=32 time=2026-01-25T14:42:32.413Z level=DEBUG source=ggml.go:298 msg="key with type not found" key=gptoss.pooling_type default=0 time=2026-01-25T14:42:32.413Z level=INFO source=server.go:245 msg="enabling flash attention" time=2026-01-25T14:42:32.413Z level=INFO source=server.go:429 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --model /root/.ollama/models/blobs/sha256-e7b273f9636059a689e3ddcab3716e4f65abe0143ac978e46673ad0e52d09efb --port 46675" time=2026-01-25T14:42:32.413Z level=DEBUG source=server.go:430 msg=subprocess PATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin OLLAMA_LLM_LIBRARY=cuda_v13 OLLAMA_KEEP_ALIVE=-1 OLLAMA_HOST=0.0.0.0 OLLAMA_DEBUG=true OLLAMA_FLASH_ATTENTION=1 LD_LIBRARY_PATH=/usr/lib/ollama:/usr/lib/ollama/cuda_v13:/usr/local/nvidia/l ib:/usr/local/nvidia/lib64 OLLAMA_LIBRARY_PATH=/usr/lib/ollama:/usr/lib/ollama/cuda_v13 time=2026-01-25T14:42:32.414Z level=INFO source=sched.go:452 msg="system memory" total="503.4 GiB" free="503.2 GiB" free_swap="4.0 GiB" time=2026-01-25T14:42:32.414Z level=INFO source=sched.go:459 msg="gpu memory" id=GPU-7f2d3c91-8c50-7c91-e17f-ac3279c58604 library=CUDA available="93.4 GiB" free="93.9 GiB" minimum="457.0 MiB" overhead="0 B" time=2026-01-25T14:42:32.414Z level=INFO source=server.go:755 msg="loading model" "model layers"=25 requested=-1 time=2026-01-25T14:42:32.434Z level=INFO source=runner.go:1405 msg="starting ollama engine" time=2026-01-25T14:42:32.434Z level=INFO source=runner.go:1440 msg="Server listening on 127.0.0.1:46675" time=2026-01-25T14:42:32.437Z level=INFO source=runner.go:1278 msg=load request="{Operation:fit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:8192 KvCacheType: NumThreads:24 GPULayers:25[ID:GPU-7f2d3c91-8c50-7c91-e17f-ac3279c58604 Layers:25(0..24)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" time=2026-01-25T14:42:32.518Z level=DEBUG source=ggml.go:298 msg="key with type not found" key=general.alignment default=32 time=2026-01-25T14:42:32.519Z level=DEBUG source=ggml.go:298 msg="key with type not found" key=general.name default="" time=2026-01-25T14:42:32.519Z level=DEBUG source=ggml.go:298 msg="key with type not found" key=general.description default="" time=2026-01-25T14:42:32.519Z level=INFO source=ggml.go:136 msg="" architecture=gptoss file_type=MXFP4 name="" description="" num_tensors=459 num_key_values=32 time=2026-01-25T14:42:32.519Z level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=/usr/lib/ollama load_backend: loaded CPU backend from /usr/lib/ollama/libggml-cpu-icelake.so time=2026-01-25T14:42:32.527Z level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=/usr/lib/ollama/cuda_v13 ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no ggml_cuda_init: found 1 CUDA devices: Device 0: NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition, compute capability 12.0, VMM: yes, ID: GPU-7f2d3c91-8c50-7c91-e17f-ac3279c58604 load_backend: loaded CUDA backend from /usr/lib/ollama/cuda_v13/libggml-cuda.so time=2026-01-25T14:42:32.614Z level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.AVX512=1 CPU.0.AVX512_VBMI=1 CPU.0.AVX512_VNNI=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 CUDA.0.ARCHS=750,800,860,870,890,900,1000,1030,1100,1200,1210 CUDA.0.USE_GRAPHS= 1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(gcc) time=2026-01-25T14:42:32.617Z level=DEBUG source=ggml.go:298 msg="key with type not found" key=gptoss.pooling_type default=0 time=2026-01-25T14:42:51.557Z level=DEBUG source=ggml.go:852 msg="compute graph" nodes=1399 splits=2 time=2026-01-25T14:43:00.007Z level=DEBUG source=ggml.go:852 msg="compute graph" nodes=1399 splits=2 time=2026-01-25T14:43:00.008Z level=DEBUG source=device.go:240 msg="model weights" device=CUDA0 size="11.8 GiB" time=2026-01-25T14:43:00.008Z level=DEBUG source=device.go:245 msg="model weights" device=CPU size="1.1 GiB" time=2026-01-25T14:43:00.008Z level=DEBUG source=device.go:251 msg="kv cache" device=CUDA0 size="300.0 MiB" time=2026-01-25T14:43:00.008Z level=DEBUG source=device.go:262 msg="compute graph" device=CUDA0 size="160.6 MiB" time=2026-01-25T14:43:00.008Z level=DEBUG source=device.go:267 msg="compute graph" device=CPU size="5.6 MiB" time=2026-01-25T14:43:00.008Z level=DEBUG source=device.go:272 msg="total memory" size="13.3 GiB" time=2026-01-25T14:43:00.008Z level=DEBUG source=server.go:780 msg=memory success=true required.InputWeights=1158266880 required.CPU.Graph=5898240 required.CUDA0.ID=GPU-7f2d3c91-8c50-7c91-e17f-ac3279c58604 required.CUDA0.Weights="[477628928 477628928 477628928 477628928 477628928 477628928 477628928 477628928 477628928 477628928 4 77628928 477628928 477628928 477628928 477628928 477628928 477628928 477628928 477628928 477628928 477628928 477628928 477628928 477628928 1158278400]" required.CUDA0.Cache="[9437184 16777216 9437184 16777216 9437184 16777216 9437184 16777216 9437184 16777216 9437184 16777216 9437184 16777216 9437184 16777216 9437184 16777216 9437 184 16777216 9437184 16777216 9437184 16777216 0]" required.CUDA0.Graph=168433792 time=2026-01-25T14:43:00.008Z level=DEBUG source=server.go:974 msg="available gpu" id=GPU-7f2d3c91-8c50-7c91-e17f-ac3279c58604 library=CUDA "available layer vram"="93.3 GiB" backoff=0.00 minimum="457.0 MiB" overhead="0 B" graph="160.6 MiB" time=2026-01-25T14:43:00.008Z level=DEBUG source=server.go:791 msg="new layout created" layers="25[ID:GPU-7f2d3c91-8c50-7c91-e17f-ac3279c58604 Layers:25(0..24)]" time=2026-01-25T14:43:00.009Z level=INFO source=runner.go:1278 msg=load request="{Operation:alloc LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:8192 KvCacheType: NumThreads:24 GPULayers:25[ID:GPU-7f2d3c91-8c50-7c91-e17f-ac3279c58604 Layers:25(0..24)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false} " time=2026-01-25T14:43:00.078Z level=DEBUG source=ggml.go:298 msg="key with type not found" key=general.alignment default=32 time=2026-01-25T14:43:00.082Z level=DEBUG source=ggml.go:298 msg="key with type not found" key=gptoss.pooling_type default=0 time=2026-01-25T14:43:00.147Z level=DEBUG source=ggml.go:852 msg="compute graph" nodes=1399 splits=2 time=2026-01-25T14:43:00.151Z level=DEBUG source=ggml.go:852 msg="compute graph" nodes=1399 splits=2 time=2026-01-25T14:43:00.151Z level=DEBUG source=device.go:240 msg="model weights" device=CUDA0 size="11.8 GiB" time=2026-01-25T14:43:00.151Z level=DEBUG source=device.go:245 msg="model weights" device=CPU size="1.1 GiB" time=2026-01-25T14:43:00.151Z level=DEBUG source=device.go:251 msg="kv cache" device=CUDA0 size="300.0 MiB" time=2026-01-25T14:43:00.151Z level=DEBUG source=device.go:262 msg="compute graph" device=CUDA0 size="160.6 MiB" time=2026-01-25T14:43:00.151Z level=DEBUG source=device.go:267 msg="compute graph" device=CPU size="5.6 MiB" time=2026-01-25T14:43:00.151Z level=DEBUG source=device.go:272 msg="total memory" size="13.3 GiB" time=2026-01-25T14:43:00.151Z level=DEBUG source=server.go:780 msg=memory success=true required.InputWeights=1158266880 required.CPU.Graph=5898240 required.CUDA0.ID=GPU-7f2d3c91-8c50-7c91-e17f-ac3279c58604 required.CUDA0.Weights="[477628928 477628928 477628928 477628928 477628928 477628928 477628928 477628928 477628928 477628928 4 77628928 477628928 477628928 477628928 477628928 477628928 477628928 477628928 477628928 477628928 477628928 477628928 477628928 477628928 1158278400]" required.CUDA0.Cache="[9437184 16777216 9437184 16777216 9437184 16777216 9437184 16777216 9437184 16777216 9437184 16777216 9437184 16777216 9437184 16777216 9437184 16777216 9437 184 16777216 9437184 16777216 9437184 16777216 0]" required.CUDA0.Graph=168433792 time=2026-01-25T14:43:00.151Z level=DEBUG source=server.go:974 msg="available gpu" id=GPU-7f2d3c91-8c50-7c91-e17f-ac3279c58604 library=CUDA "available layer vram"="93.3 GiB" backoff=0.00 minimum="457.0 MiB" overhead="0 B" graph="160.6 MiB" time=2026-01-25T14:43:00.152Z level=DEBUG source=server.go:791 msg="new layout created" layers="25[ID:GPU-7f2d3c91-8c50-7c91-e17f-ac3279c58604 Layers:25(0..24)]" time=2026-01-25T14:43:00.152Z level=INFO source=runner.go:1278 msg=load request="{Operation:commit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:8192 KvCacheType: NumThreads:24 GPULayers:25[ID:GPU-7f2d3c91-8c50-7c91-e17f-ac3279c58604 Layers:25(0..24)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false }" time=2026-01-25T14:43:00.152Z level=INFO source=ggml.go:482 msg="offloading 24 repeating layers to GPU" time=2026-01-25T14:43:00.153Z level=INFO source=ggml.go:489 msg="offloading output layer to GPU" time=2026-01-25T14:43:00.153Z level=INFO source=ggml.go:494 msg="offloaded 25/25 layers to GPU" time=2026-01-25T14:43:00.153Z level=INFO source=device.go:240 msg="model weights" device=CUDA0 size="11.8 GiB" time=2026-01-25T14:43:00.153Z level=INFO source=device.go:245 msg="model weights" device=CPU size="1.1 GiB" time=2026-01-25T14:43:00.153Z level=INFO source=device.go:251 msg="kv cache" device=CUDA0 size="300.0 MiB" time=2026-01-25T14:43:00.153Z level=INFO source=device.go:262 msg="compute graph" device=CUDA0 size="160.6 MiB" time=2026-01-25T14:43:00.153Z level=INFO source=device.go:267 msg="compute graph" device=CPU size="5.6 MiB" time=2026-01-25T14:43:00.153Z level=INFO source=device.go:272 msg="total memory" size="13.3 GiB" time=2026-01-25T14:43:00.153Z level=INFO source=sched.go:526 msg="loaded runners" count=1 time=2026-01-25T14:43:00.153Z level=INFO source=server.go:1347 msg="waiting for llama runner to start responding" time=2026-01-25T14:43:00.154Z level=INFO source=server.go:1381 msg="waiting for server to become available" status="llm server loading model" time=2026-01-25T14:43:00.154Z level=DEBUG source=server.go:1391 msg="model load progress 0.00" time=2026-01-25T14:43:00.405Z level=DEBUG source=server.go:1391 msg="model load progress 0.05" time=2026-01-25T14:43:00.656Z level=DEBUG source=server.go:1391 msg="model load progress 0.09" time=2026-01-25T14:43:00.907Z level=DEBUG source=server.go:1391 msg="model load progress 0.14" time=2026-01-25T14:43:01.158Z level=DEBUG source=server.go:1391 msg="model load progress 0.18" time=2026-01-25T14:43:01.410Z level=DEBUG source=server.go:1391 msg="model load progress 0.22" time=2026-01-25T14:43:01.661Z level=DEBUG source=server.go:1391 msg="model load progress 0.27" time=2026-01-25T14:43:01.912Z level=DEBUG source=server.go:1391 msg="model load progress 0.30" time=2026-01-25T14:43:02.164Z level=DEBUG source=server.go:1391 msg="model load progress 0.35" time=2026-01-25T14:43:02.415Z level=DEBUG source=server.go:1391 msg="model load progress 0.48" time=2026-01-25T14:43:02.666Z level=DEBUG source=server.go:1391 msg="model load progress 0.64" time=2026-01-25T14:43:02.916Z level=DEBUG source=server.go:1391 msg="model load progress 0.82" time=2026-01-25T14:43:03.168Z level=DEBUG source=server.go:1391 msg="model load progress 0.95" time=2026-01-25T14:43:03.348Z level=DEBUG source=ggml.go:298 msg="key with type not found" key=gptoss.pooling_type default=0 **time=2026-01-25T14:43:03.420Z level=INFO source=server.go:1385 msg="llama runner started in 31.01 seconds"** time=2026-01-25T14:43:03.420Z level=DEBUG source=sched.go:538 msg="finished setting up" runner.name=registry.ollama.ai/library/gpt-oss:latest runner.inference="[{ID:GPU-7f2d3c91-8c50-7c91-e17f-ac3279c58604 Library:CUDA}]" runner.size="13.3 GiB" runner.vram="13.3 GiB" runner.parallel=1 runner.pid=103 runner.model=/root/.ollama/mode ls/blobs/sha256-e7b273f9636059a689e3ddcab3716e4f65abe0143ac978e46673ad0e52d09efb runner.num_ctx=8192 time=2026-01-25T14:43:03.421Z level=DEBUG source=server.go:1533 msg="completion request" images=0 prompt=306 format="" time=2026-01-25T14:43:03.498Z level=DEBUG source=cache.go:142 msg="loading cache slot" id=0 cache=0 prompt=68 used=0 remaining=68 **Scenario 1: Docker container already started - Model manually unloaded, prompt "Chat" - Model: gpt-oss:20b** **I takes around 3s to start the Ollama runner** time=2026-01-25T14:40:26.488Z level=DEBUG source=runner.go:264 msg="refreshing free memory" time=2026-01-25T14:40:26.488Z level=DEBUG source=runner.go:328 msg="unable to refresh all GPUs with existing runners, performing bootstrap discovery" time=2026-01-25T14:40:26.489Z level=INFO source=server.go:429 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --port 38037" time=2026-01-25T14:40:26.489Z level=DEBUG source=server.go:430 msg=subprocess PATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin OLLAMA_DEBUG=true OLLAMA_FLASH_ATTENTION=1 OLLAMA_LLM_LIBRARY=cuda_v13 OLLAMA_KEEP_ALIVE=-1 OLLAMA_HOST=0.0.0.0 LD_LIBRARY_PATH=/usr/lib/ollama:/usr/lib/ollama/cuda_v13:/usr/local/nvidia/l ib:/usr/local/nvidia/lib64 OLLAMA_LIBRARY_PATH=/usr/lib/ollama:/usr/lib/ollama/cuda_v13 time=2026-01-25T14:40:26.627Z level=DEBUG source=runner.go:437 msg="bootstrap discovery took" duration=139.130954ms OLLAMA_LIBRARY_PATH="[/usr/lib/ollama /usr/lib/ollama/cuda_v13]" extra_envs=map[] time=2026-01-25T14:40:26.628Z level=DEBUG source=runner.go:40 msg="overall device VRAM discovery took" duration=139.384896ms time=2026-01-25T14:40:26.632Z level=WARN source=cpu_linux.go:130 msg="failed to parse CPU allowed micro secs" error="strconv.ParseInt: parsing \"max\": invalid syntax" time=2026-01-25T14:40:26.671Z level=DEBUG source=ggml.go:298 msg="key with type not found" key=general.alignment default=32 time=2026-01-25T14:40:26.671Z level=DEBUG source=sched.go:220 msg="loading first model" model=/root/.ollama/models/blobs/sha256-e7b273f9636059a689e3ddcab3716e4f65abe0143ac978e46673ad0e52d09efb time=2026-01-25T14:40:26.831Z level=DEBUG source=ggml.go:298 msg="key with type not found" key=general.alignment default=32 time=2026-01-25T14:40:26.832Z level=DEBUG source=ggml.go:298 msg="key with type not found" key=gptoss.pooling_type default=0 time=2026-01-25T14:40:26.832Z level=INFO source=server.go:245 msg="enabling flash attention" time=2026-01-25T14:40:26.832Z level=INFO source=server.go:429 msg="starting runner" cmd="/usr/bin/ollama runner --ollama-engine --model /root/.ollama/models/blobs/sha256-e7b273f9636059a689e3ddcab3716e4f65abe0143ac978e46673ad0e52d09efb --port 37943" time=2026-01-25T14:40:26.832Z level=DEBUG source=server.go:430 msg=subprocess PATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin OLLAMA_DEBUG=true OLLAMA_FLASH_ATTENTION=1 OLLAMA_LLM_LIBRARY=cuda_v13 OLLAMA_KEEP_ALIVE=-1 OLLAMA_HOST=0.0.0.0 LD_LIBRARY_PATH=/usr/lib/ollama:/usr/lib/ollama/cuda_v13:/usr/local/nvidia/l ib:/usr/local/nvidia/lib64 OLLAMA_LIBRARY_PATH=/usr/lib/ollama:/usr/lib/ollama/cuda_v13 time=2026-01-25T14:40:26.833Z level=INFO source=sched.go:452 msg="system memory" total="503.4 GiB" free="503.2 GiB" free_swap="4.0 GiB" time=2026-01-25T14:40:26.833Z level=INFO source=sched.go:459 msg="gpu memory" id=GPU-7f2d3c91-8c50-7c91-e17f-ac3279c58604 library=CUDA available="93.4 GiB" free="93.9 GiB" minimum="457.0 MiB" overhead="0 B" time=2026-01-25T14:40:26.833Z level=INFO source=server.go:755 msg="loading model" "model layers"=25 requested=-1 time=2026-01-25T14:40:26.853Z level=INFO source=runner.go:1405 msg="starting ollama engine" time=2026-01-25T14:40:26.853Z level=INFO source=runner.go:1440 msg="Server listening on 127.0.0.1:37943" time=2026-01-25T14:40:26.857Z level=INFO source=runner.go:1278 msg=load request="{Operation:fit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:8192 KvCacheType: NumThreads:24 GPULayers:25[ID:GPU-7f2d3c91-8c50-7c91-e17f-ac3279c58604 Layers:25(0..24)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false}" time=2026-01-25T14:40:26.935Z level=DEBUG source=ggml.go:298 msg="key with type not found" key=general.alignment default=32 time=2026-01-25T14:40:26.936Z level=DEBUG source=ggml.go:298 msg="key with type not found" key=general.name default="" time=2026-01-25T14:40:26.936Z level=DEBUG source=ggml.go:298 msg="key with type not found" key=general.description default="" time=2026-01-25T14:40:26.936Z level=INFO source=ggml.go:136 msg="" architecture=gptoss file_type=MXFP4 name="" description="" num_tensors=459 num_key_values=32 time=2026-01-25T14:40:26.936Z level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=/usr/lib/ollama load_backend: loaded CPU backend from /usr/lib/ollama/libggml-cpu-icelake.so time=2026-01-25T14:40:26.944Z level=DEBUG source=ggml.go:94 msg="ggml backend load all from path" path=/usr/lib/ollama/cuda_v13 ggml_cuda_init: GGML_CUDA_FORCE_MMQ: no ggml_cuda_init: GGML_CUDA_FORCE_CUBLAS: no ggml_cuda_init: found 1 CUDA devices: Device 0: NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition, compute capability 12.0, VMM: yes, ID: GPU-7f2d3c91-8c50-7c91-e17f-ac3279c58604 load_backend: loaded CUDA backend from /usr/lib/ollama/cuda_v13/libggml-cuda.so time=2026-01-25T14:40:27.033Z level=INFO source=ggml.go:104 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.AVX512=1 CPU.0.AVX512_VBMI=1 CPU.0.AVX512_VNNI=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 CUDA.0.ARCHS=750,800,860,870,890,900,1000,1030,1100,1200,1210 CUDA.0.USE_GRAPHS= 1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(gcc) time=2026-01-25T14:40:27.035Z level=DEBUG source=ggml.go:298 msg="key with type not found" key=gptoss.pooling_type default=0 time=2026-01-25T14:40:27.588Z level=DEBUG source=ggml.go:852 msg="compute graph" nodes=1399 splits=2 time=2026-01-25T14:40:27.615Z level=DEBUG source=ggml.go:852 msg="compute graph" nodes=1399 splits=2 time=2026-01-25T14:40:27.616Z level=DEBUG source=device.go:240 msg="model weights" device=CUDA0 size="11.8 GiB" time=2026-01-25T14:40:27.616Z level=DEBUG source=device.go:245 msg="model weights" device=CPU size="1.1 GiB" time=2026-01-25T14:40:27.616Z level=DEBUG source=device.go:251 msg="kv cache" device=CUDA0 size="300.0 MiB" time=2026-01-25T14:40:27.616Z level=DEBUG source=device.go:262 msg="compute graph" device=CUDA0 size="160.6 MiB" time=2026-01-25T14:40:27.616Z level=DEBUG source=device.go:267 msg="compute graph" device=CPU size="5.6 MiB" time=2026-01-25T14:40:27.616Z level=DEBUG source=device.go:272 msg="total memory" size="13.3 GiB" time=2026-01-25T14:40:27.616Z level=DEBUG source=server.go:780 msg=memory success=true required.InputWeights=1158266880 required.CPU.Graph=5898240 required.CUDA0.ID=GPU-7f2d3c91-8c50-7c91-e17f-ac3279c58604 required.CUDA0.Weights="[477628928 477628928 477628928 477628928 477628928 477628928 477628928 477628928 477628928 477628928 4 77628928 477628928 477628928 477628928 477628928 477628928 477628928 477628928 477628928 477628928 477628928 477628928 477628928 477628928 1158278400]" required.CUDA0.Cache="[9437184 16777216 9437184 16777216 9437184 16777216 9437184 16777216 9437184 16777216 9437184 16777216 9437184 16777216 9437184 16777216 9437184 16777216 9437 184 16777216 9437184 16777216 9437184 16777216 0]" required.CUDA0.Graph=168433792 time=2026-01-25T14:40:27.616Z level=DEBUG source=server.go:974 msg="available gpu" id=GPU-7f2d3c91-8c50-7c91-e17f-ac3279c58604 library=CUDA "available layer vram"="93.3 GiB" backoff=0.00 minimum="457.0 MiB" overhead="0 B" graph="160.6 MiB" time=2026-01-25T14:40:27.617Z level=DEBUG source=server.go:791 msg="new layout created" layers="25[ID:GPU-7f2d3c91-8c50-7c91-e17f-ac3279c58604 Layers:25(0..24)]" time=2026-01-25T14:40:27.617Z level=INFO source=runner.go:1278 msg=load request="{Operation:alloc LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:8192 KvCacheType: NumThreads:24 GPULayers:25[ID:GPU-7f2d3c91-8c50-7c91-e17f-ac3279c58604 Layers:25(0..24)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false} " time=2026-01-25T14:40:27.688Z level=DEBUG source=ggml.go:298 msg="key with type not found" key=general.alignment default=32 time=2026-01-25T14:40:27.692Z level=DEBUG source=ggml.go:298 msg="key with type not found" key=gptoss.pooling_type default=0 time=2026-01-25T14:40:27.756Z level=DEBUG source=ggml.go:852 msg="compute graph" nodes=1399 splits=2 time=2026-01-25T14:40:27.760Z level=DEBUG source=ggml.go:852 msg="compute graph" nodes=1399 splits=2 time=2026-01-25T14:40:27.761Z level=DEBUG source=device.go:240 msg="model weights" device=CUDA0 size="11.8 GiB" time=2026-01-25T14:40:27.761Z level=DEBUG source=device.go:245 msg="model weights" device=CPU size="1.1 GiB" time=2026-01-25T14:40:27.761Z level=DEBUG source=device.go:251 msg="kv cache" device=CUDA0 size="300.0 MiB" time=2026-01-25T14:40:27.761Z level=DEBUG source=device.go:262 msg="compute graph" device=CUDA0 size="160.6 MiB" time=2026-01-25T14:40:27.761Z level=DEBUG source=device.go:267 msg="compute graph" device=CPU size="5.6 MiB" time=2026-01-25T14:40:27.761Z level=DEBUG source=device.go:272 msg="total memory" size="13.3 GiB" time=2026-01-25T14:40:27.761Z level=DEBUG source=server.go:780 msg=memory success=true required.InputWeights=1158266880 required.CPU.Graph=5898240 required.CUDA0.ID=GPU-7f2d3c91-8c50-7c91-e17f-ac3279c58604 required.CUDA0.Weights="[477628928 477628928 477628928 477628928 477628928 477628928 477628928 477628928 477628928 477628928 4 77628928 477628928 477628928 477628928 477628928 477628928 477628928 477628928 477628928 477628928 477628928 477628928 477628928 477628928 1158278400]" required.CUDA0.Cache="[9437184 16777216 9437184 16777216 9437184 16777216 9437184 16777216 9437184 16777216 9437184 16777216 9437184 16777216 9437184 16777216 9437184 16777216 9437 184 16777216 9437184 16777216 9437184 16777216 0]" required.CUDA0.Graph=168433792 time=2026-01-25T14:40:27.761Z level=DEBUG source=server.go:974 msg="available gpu" id=GPU-7f2d3c91-8c50-7c91-e17f-ac3279c58604 library=CUDA "available layer vram"="93.3 GiB" backoff=0.00 minimum="457.0 MiB" overhead="0 B" graph="160.6 MiB" time=2026-01-25T14:40:27.761Z level=DEBUG source=server.go:791 msg="new layout created" layers="25[ID:GPU-7f2d3c91-8c50-7c91-e17f-ac3279c58604 Layers:25(0..24)]" time=2026-01-25T14:40:27.762Z level=INFO source=runner.go:1278 msg=load request="{Operation:commit LoraPath:[] Parallel:1 BatchSize:512 FlashAttention:Enabled KvSize:8192 KvCacheType: NumThreads:24 GPULayers:25[ID:GPU-7f2d3c91-8c50-7c91-e17f-ac3279c58604 Layers:25(0..24)] MultiUserCache:false ProjectorPath: MainGPU:0 UseMmap:false }" time=2026-01-25T14:40:27.762Z level=INFO source=ggml.go:482 msg="offloading 24 repeating layers to GPU" time=2026-01-25T14:40:27.762Z level=INFO source=ggml.go:489 msg="offloading output layer to GPU" time=2026-01-25T14:40:27.762Z level=INFO source=ggml.go:494 msg="offloaded 25/25 layers to GPU" time=2026-01-25T14:40:27.763Z level=INFO source=device.go:240 msg="model weights" device=CUDA0 size="11.8 GiB" time=2026-01-25T14:40:27.763Z level=INFO source=device.go:245 msg="model weights" device=CPU size="1.1 GiB" time=2026-01-25T14:40:27.763Z level=INFO source=device.go:251 msg="kv cache" device=CUDA0 size="300.0 MiB" time=2026-01-25T14:40:27.763Z level=INFO source=device.go:262 msg="compute graph" device=CUDA0 size="160.6 MiB" time=2026-01-25T14:40:27.763Z level=INFO source=device.go:267 msg="compute graph" device=CPU size="5.6 MiB" time=2026-01-25T14:40:27.763Z level=INFO source=device.go:272 msg="total memory" size="13.3 GiB" time=2026-01-25T14:40:27.763Z level=INFO source=sched.go:526 msg="loaded runners" count=1 time=2026-01-25T14:40:27.763Z level=INFO source=server.go:1347 msg="waiting for llama runner to start responding" time=2026-01-25T14:40:27.763Z level=INFO source=server.go:1381 msg="waiting for server to become available" status="llm server loading model" time=2026-01-25T14:40:27.763Z level=DEBUG source=server.go:1391 msg="model load progress 0.00" time=2026-01-25T14:40:28.014Z level=DEBUG source=server.go:1391 msg="model load progress 0.12" time=2026-01-25T14:40:28.265Z level=DEBUG source=server.go:1391 msg="model load progress 0.27" time=2026-01-25T14:40:28.515Z level=DEBUG source=server.go:1391 msg="model load progress 0.41" time=2026-01-25T14:40:28.766Z level=DEBUG source=server.go:1391 msg="model load progress 0.55" time=2026-01-25T14:40:29.017Z level=DEBUG source=server.go:1391 msg="model load progress 0.72" time=2026-01-25T14:40:29.268Z level=DEBUG source=server.go:1391 msg="model load progress 0.90" time=2026-01-25T14:40:29.519Z level=DEBUG source=server.go:1391 msg="model load progress 0.98" time=2026-01-25T14:40:29.602Z level=DEBUG source=ggml.go:298 msg="key with type not found" key=gptoss.pooling_type default=0 **time=2026-01-25T14:40:29.771Z level=INFO source=server.go:1385 msg="llama runner started in 2.94 seconds"** time=2026-01-25T14:40:29.772Z level=DEBUG source=sched.go:538 msg="finished setting up" runner.name=registry.ollama.ai/library/gpt-oss:latest runner.inference="[{ID:GPU-7f2d3c91-8c50-7c91-e17f-ac3279c58604 Library:CUDA}]" runner.size="13.3 GiB" runner.vram="13.3 GiB" runner.parallel=1 runner.pid=217 runner.model=/root/.ollama/mode ls/blobs/sha256-e7b273f9636059a689e3ddcab3716e4f65abe0143ac978e46673ad0e52d09efb runner.num_ctx=8192 time=2026-01-25T14:40:29.772Z level=DEBUG source=server.go:1533 msg="completion request" images=0 prompt=306 format="" time=2026-01-25T14:40:29.858Z level=DEBUG source=cache.go:142 msg="loading cache slot" id=0 cache=0 prompt=68 used=0 remaining=68 ``` ### OS Linux ### GPU Nvidia ### CPU Intel ### Ollama version latest
GiteaMirror added the bug label 2026-04-12 21:56:54 -05:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#9097
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?