github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 08:02:14 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #10671] 6K context, only thtough API: error loading llama server "timed out waiting for llama runner to start: context canceled" #7016

New Issue
Closed
opened 2026-04-12 18:54:39 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-12 18:54:39 -05:00
Owner
Copy Link

Originally created by @j2l on GitHub (May 12, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/10671

What is the issue?

For DSR1 14B and Gemma3 12B on a Ubuntu22+RTX3060 (12GB VRAM, 24GB RAM) with a 6K tokens long context:

  • Using ollama run, both models can ingest and reply correctly.
  • Using the API, for both, I get the error: error loading llama server "timed out waiting for llama runner to start: context canceled"

Seems to be a loading timeout issue to me.

Relevant log output

time=2025-05-12T10:42:14.669Z level=INFO source=sched.go:517 msg="updated VRAM based on existing loaded models" gpu=GPU-b04b66c1-d5eb-66df-899a-6e62a122d319 library=cuda total="11.7 GiB" available="616.9 MiB"

time=2025-05-12T10:42:15.447Z level=WARN source=ggml.go:152 msg="key not found" key=general.alignment default=32

time=2025-05-12T10:42:15.485Z level=WARN source=ggml.go:152 msg="key not found" key=general.alignment default=32

time=2025-05-12T10:42:15.636Z level=INFO source=server.go:106 msg="system memory" total="23.3 GiB" free="16.8 GiB" free_swap="12.9 GiB"

time=2025-05-12T10:42:15.637Z level=INFO source=server.go:139 msg=offload library=cuda layers.requested=-1 layers.model=49 layers.offload=48 layers.split="" memory.available="[11.1 GiB]" memory.gpu_overhead="0 B" memory.required.full="11.4 GiB" memory.required.partial="10.6 GiB" memory.required.kv="992.0 MiB" memory.required.allocations="[10.6 GiB]" memory.weights.total="6.8 GiB" memory.weights.repeating="6.0 GiB" memory.weights.nonrepeating="787.5 MiB" memory.graph.full="519.5 MiB" memory.graph.partial="1.3 GiB" projector.weights="795.9 MiB" projector.graph="1.0 GiB"

time=2025-05-12T10:42:15.708Z level=WARN source=ggml.go:152 msg="key not found" key=general.alignment default=32

time=2025-05-12T10:42:15.709Z level=WARN source=ggml.go:152 msg="key not found" key=tokenizer.ggml.add_eot_token default=false

time=2025-05-12T10:42:15.714Z level=WARN source=ggml.go:152 msg="key not found" key=gemma3.attention.layer_norm_rms_epsilon default=9.999999974752427e-07

time=2025-05-12T10:42:15.714Z level=WARN source=ggml.go:152 msg="key not found" key=gemma3.rope.local.freq_base default=10000

time=2025-05-12T10:42:15.714Z level=WARN source=ggml.go:152 msg="key not found" key=gemma3.rope.global.freq_base default=1e+06

time=2025-05-12T10:42:15.714Z level=WARN source=ggml.go:152 msg="key not found" key=gemma3.rope.freq_scale default=1

time=2025-05-12T10:42:15.714Z level=WARN source=ggml.go:152 msg="key not found" key=gemma3.mm_tokens_per_image default=256

time=2025-05-12T10:42:15.714Z level=INFO source=server.go:410 msg="starting llama server" cmd="/usr/bin/ollama runner --ollama-engine --model /root/.ollama/models/blobs/sha256-adca500fad9b54c565ae672184e0c9eb690eb6014ba63f8ec13849d4f73a32d3 --ctx-size 8192 --batch-size 512 --n-gpu-layers 48 --threads 6 --parallel 1 --port 44559"

time=2025-05-12T10:42:15.715Z level=INFO source=sched.go:452 msg="loaded runners" count=1

time=2025-05-12T10:42:15.715Z level=INFO source=server.go:589 msg="waiting for llama runner to start responding"

time=2025-05-12T10:42:15.715Z level=INFO source=server.go:623 msg="waiting for server to become available" status="llm server not responding"

time=2025-05-12T10:42:15.724Z level=INFO source=runner.go:851 msg="starting ollama engine"

time=2025-05-12T10:42:15.724Z level=INFO source=runner.go:914 msg="Server listening on 127.0.0.1:44559"

time=2025-05-12T10:42:15.792Z level=WARN source=ggml.go:152 msg="key not found" key=general.alignment default=32

time=2025-05-12T10:42:15.793Z level=WARN source=ggml.go:152 msg="key not found" key=general.name default=""

time=2025-05-12T10:42:15.793Z level=WARN source=ggml.go:152 msg="key not found" key=general.description default=""

time=2025-05-12T10:42:15.793Z level=INFO source=ggml.go:72 msg="" architecture=gemma3 file_type=Q4_K_M name="" description="" num_tensors=1065 num_key_values=36

load_backend: loaded CPU backend from /usr/lib/ollama/libggml-cpu-haswell.so

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 GeForce RTX 3060, compute capability 8.6, VMM: yes

load_backend: loaded CUDA backend from /usr/lib/ollama/cuda_v12/libggml-cuda.so

time=2025-05-12T10:42:15.847Z level=INFO source=ggml.go:103 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 CUDA.0.ARCHS=500,600,610,700,750,800,860,870,890,900,1200 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(gcc)

time=2025-05-12T10:42:15.939Z level=INFO source=ggml.go:298 msg="model weights" buffer=CPU size="2.3 GiB"

time=2025-05-12T10:42:15.939Z level=INFO source=ggml.go:298 msg="model weights" buffer=CUDA0 size="6.0 GiB"

time=2025-05-12T10:42:15.966Z level=INFO source=server.go:623 msg="waiting for server to become available" status="llm server loading model"

time=2025-05-12T10:42:29.765Z level=WARN source=server.go:596 msg="client connection closed before server finished loading, aborting load"

time=2025-05-12T10:42:29.765Z level=ERROR source=sched.go:458 msg="error loading llama server" error="timed out waiting for llama runner to start: context canceled"

[GIN] 2025/05/12 - 10:42:29 | 499 | 15.422711327s |      172.17.0.1 | POST     "/api/generate"

time=2025-05-12T10:42:34.924Z level=WARN source=sched.go:655 msg="gpu VRAM usage didn't recover within timeout" seconds=5.158672739 model=/root/.ollama/models/blobs/sha256-adca500fad9b54c565ae672184e0c9eb690eb6014ba63f8ec13849d4f73a32d3

time=2025-05-12T10:42:35.174Z level=WARN source=sched.go:655 msg="gpu VRAM usage didn't recover within timeout" seconds=5.408708976 model=/root/.ollama/models/blobs/sha256-adca500fad9b54c565ae672184e0c9eb690eb6014ba63f8ec13849d4f73a32d3

time=2025-05-12T10:42:35.424Z level=WARN source=sched.go:655 msg="gpu VRAM usage didn't recover within timeout" seconds=5.6590568359999995 model=/root/.ollama/models/blobs/sha256-adca500fad9b54c565ae672184e0c9eb690eb6014ba63f8ec13849d4f73a32d3

OS

Docker

GPU

Nvidia

CPU

Intel

Ollama version

0.6.8

Originally created by @j2l on GitHub (May 12, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/10671 ### What is the issue? For DSR1 14B and Gemma3 12B on a Ubuntu22+RTX3060 (12GB VRAM, 24GB RAM) with a 6K tokens long context: - Using `ollama run`, both models can ingest and reply correctly. - Using the API, for both, I get the error: error loading llama server "timed out waiting for llama runner to start: context canceled" Seems to be a loading timeout issue to me. ### Relevant log output ```shell time=2025-05-12T10:42:14.669Z level=INFO source=sched.go:517 msg="updated VRAM based on existing loaded models" gpu=GPU-b04b66c1-d5eb-66df-899a-6e62a122d319 library=cuda total="11.7 GiB" available="616.9 MiB" time=2025-05-12T10:42:15.447Z level=WARN source=ggml.go:152 msg="key not found" key=general.alignment default=32 time=2025-05-12T10:42:15.485Z level=WARN source=ggml.go:152 msg="key not found" key=general.alignment default=32 time=2025-05-12T10:42:15.636Z level=INFO source=server.go:106 msg="system memory" total="23.3 GiB" free="16.8 GiB" free_swap="12.9 GiB" time=2025-05-12T10:42:15.637Z level=INFO source=server.go:139 msg=offload library=cuda layers.requested=-1 layers.model=49 layers.offload=48 layers.split="" memory.available="[11.1 GiB]" memory.gpu_overhead="0 B" memory.required.full="11.4 GiB" memory.required.partial="10.6 GiB" memory.required.kv="992.0 MiB" memory.required.allocations="[10.6 GiB]" memory.weights.total="6.8 GiB" memory.weights.repeating="6.0 GiB" memory.weights.nonrepeating="787.5 MiB" memory.graph.full="519.5 MiB" memory.graph.partial="1.3 GiB" projector.weights="795.9 MiB" projector.graph="1.0 GiB" time=2025-05-12T10:42:15.708Z level=WARN source=ggml.go:152 msg="key not found" key=general.alignment default=32 time=2025-05-12T10:42:15.709Z level=WARN source=ggml.go:152 msg="key not found" key=tokenizer.ggml.add_eot_token default=false time=2025-05-12T10:42:15.714Z level=WARN source=ggml.go:152 msg="key not found" key=gemma3.attention.layer_norm_rms_epsilon default=9.999999974752427e-07 time=2025-05-12T10:42:15.714Z level=WARN source=ggml.go:152 msg="key not found" key=gemma3.rope.local.freq_base default=10000 time=2025-05-12T10:42:15.714Z level=WARN source=ggml.go:152 msg="key not found" key=gemma3.rope.global.freq_base default=1e+06 time=2025-05-12T10:42:15.714Z level=WARN source=ggml.go:152 msg="key not found" key=gemma3.rope.freq_scale default=1 time=2025-05-12T10:42:15.714Z level=WARN source=ggml.go:152 msg="key not found" key=gemma3.mm_tokens_per_image default=256 time=2025-05-12T10:42:15.714Z level=INFO source=server.go:410 msg="starting llama server" cmd="/usr/bin/ollama runner --ollama-engine --model /root/.ollama/models/blobs/sha256-adca500fad9b54c565ae672184e0c9eb690eb6014ba63f8ec13849d4f73a32d3 --ctx-size 8192 --batch-size 512 --n-gpu-layers 48 --threads 6 --parallel 1 --port 44559" time=2025-05-12T10:42:15.715Z level=INFO source=sched.go:452 msg="loaded runners" count=1 time=2025-05-12T10:42:15.715Z level=INFO source=server.go:589 msg="waiting for llama runner to start responding" time=2025-05-12T10:42:15.715Z level=INFO source=server.go:623 msg="waiting for server to become available" status="llm server not responding" time=2025-05-12T10:42:15.724Z level=INFO source=runner.go:851 msg="starting ollama engine" time=2025-05-12T10:42:15.724Z level=INFO source=runner.go:914 msg="Server listening on 127.0.0.1:44559" time=2025-05-12T10:42:15.792Z level=WARN source=ggml.go:152 msg="key not found" key=general.alignment default=32 time=2025-05-12T10:42:15.793Z level=WARN source=ggml.go:152 msg="key not found" key=general.name default="" time=2025-05-12T10:42:15.793Z level=WARN source=ggml.go:152 msg="key not found" key=general.description default="" time=2025-05-12T10:42:15.793Z level=INFO source=ggml.go:72 msg="" architecture=gemma3 file_type=Q4_K_M name="" description="" num_tensors=1065 num_key_values=36 load_backend: loaded CPU backend from /usr/lib/ollama/libggml-cpu-haswell.so 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 GeForce RTX 3060, compute capability 8.6, VMM: yes load_backend: loaded CUDA backend from /usr/lib/ollama/cuda_v12/libggml-cuda.so time=2025-05-12T10:42:15.847Z level=INFO source=ggml.go:103 msg=system CPU.0.SSE3=1 CPU.0.SSSE3=1 CPU.0.AVX=1 CPU.0.AVX2=1 CPU.0.F16C=1 CPU.0.FMA=1 CPU.0.BMI2=1 CPU.0.LLAMAFILE=1 CPU.1.LLAMAFILE=1 CUDA.0.ARCHS=500,600,610,700,750,800,860,870,890,900,1200 CUDA.0.USE_GRAPHS=1 CUDA.0.PEER_MAX_BATCH_SIZE=128 compiler=cgo(gcc) time=2025-05-12T10:42:15.939Z level=INFO source=ggml.go:298 msg="model weights" buffer=CPU size="2.3 GiB" time=2025-05-12T10:42:15.939Z level=INFO source=ggml.go:298 msg="model weights" buffer=CUDA0 size="6.0 GiB" time=2025-05-12T10:42:15.966Z level=INFO source=server.go:623 msg="waiting for server to become available" status="llm server loading model" time=2025-05-12T10:42:29.765Z level=WARN source=server.go:596 msg="client connection closed before server finished loading, aborting load" time=2025-05-12T10:42:29.765Z level=ERROR source=sched.go:458 msg="error loading llama server" error="timed out waiting for llama runner to start: context canceled" [GIN] 2025/05/12 - 10:42:29 | 499 | 15.422711327s | 172.17.0.1 | POST "/api/generate" time=2025-05-12T10:42:34.924Z level=WARN source=sched.go:655 msg="gpu VRAM usage didn't recover within timeout" seconds=5.158672739 model=/root/.ollama/models/blobs/sha256-adca500fad9b54c565ae672184e0c9eb690eb6014ba63f8ec13849d4f73a32d3 time=2025-05-12T10:42:35.174Z level=WARN source=sched.go:655 msg="gpu VRAM usage didn't recover within timeout" seconds=5.408708976 model=/root/.ollama/models/blobs/sha256-adca500fad9b54c565ae672184e0c9eb690eb6014ba63f8ec13849d4f73a32d3 time=2025-05-12T10:42:35.424Z level=WARN source=sched.go:655 msg="gpu VRAM usage didn't recover within timeout" seconds=5.6590568359999995 model=/root/.ollama/models/blobs/sha256-adca500fad9b54c565ae672184e0c9eb690eb6014ba63f8ec13849d4f73a32d3 ``` ### OS Docker ### GPU Nvidia ### CPU Intel ### Ollama version 0.6.8
GiteaMirror added the bug label 2026-04-12 18:54:39 -05:00
GiteaMirror commented 2026-04-12 18:54:41 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (May 12, 2025):

time=2025-05-12T10:42:29.765Z level=WARN source=server.go:596 msg="client connection closed before server finished loading, aborting load"

Client has a ~15 second timeout.

<!-- gh-comment-id:2872051022 --> @rick-github commented on GitHub (May 12, 2025): ``` time=2025-05-12T10:42:29.765Z level=WARN source=server.go:596 msg="client connection closed before server finished loading, aborting load" ``` Client has a ~15 second timeout.
GiteaMirror commented 2026-04-12 18:54:41 -05:00
Author
Owner
Copy Link

@j2l commented on GitHub (May 12, 2025):

@rick-github thank you!
I have no idea how to change it in svelte 3. Well, I'll have to dig.

<!-- gh-comment-id:2873248717 --> @j2l commented on GitHub (May 12, 2025): @rick-github thank you! I have no idea how to change it in svelte 3. Well, I'll have to dig.
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#7016
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?