github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 16:11:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #9288] When running DEEPSEEK with Ollama, model crashes occur(2) #68112

New Issue
Closed
opened 2026-05-04 12:34:04 -05:00 by GiteaMirror · 7 comments
GiteaMirror commented 2026-05-04 12:34:04 -05:00
Owner
Copy Link

Originally created by @mjdp168 on GitHub (Feb 22, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/9288

What is the issue?

After the previous #9248 incident, I followed the methods suggested by everyone and used the code:

from deepseek-r1:671b
system """nice！"""
PARAMETER num_ctx 16384
PARAMETER num_predict 4096

However, the model crashes during the latter half of the loading process, displaying the error message:
Error: llama runner process has terminated: exit status 2.
Please help me resolve this issue.

Relevant log output

time=2025-02-21T09:19:17.047+08:00 level=INFO source=logging.go:50 msg="ollama app started"
time=2025-02-21T09:19:17.058+08:00 level=INFO source=lifecycle.go:19 msg="app config" env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://0.0.0.0:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:2562047h47m16.854775807s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:C:\\Users\\mj\\.ollama\\models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:0 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://*] OLLAMA_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES:]"
time=2025-02-21T09:19:17.111+08:00 level=INFO source=server.go:182 msg="unable to connect to server"
time=2025-02-21T09:19:17.112+08:00 level=INFO source=server.go:141 msg="starting server..."
time=2025-02-21T09:19:17.119+08:00 level=INFO source=server.go:127 msg="started ollama server with pid 17736"
time=2025-02-21T09:19:17.119+08:00 level=INFO source=server.go:129 msg="ollama server logs C:\\Users\\mj\\AppData\\Local\\Ollama\\server.log"
time=2025-02-22T18:08:18.183+08:00 level=INFO source=lifecycle.go:89 msg="Waiting for ollama server to shutdown..."
time=2025-02-22T18:08:18.197+08:00 level=INFO source=server.go:158 msg="server shutdown with exit code 0"
time=2025-02-22T18:08:18.197+08:00 level=INFO source=lifecycle.go:93 msg="Ollama app exiting"

OS

Windows

GPU

No response

CPU

AMD

Ollama version

0.511

Originally created by @mjdp168 on GitHub (Feb 22, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/9288 ### What is the issue? After the previous #9248 incident, I followed the methods suggested by everyone and used the code: from deepseek-r1:671b system """nice！""" PARAMETER num_ctx 16384 PARAMETER num_predict 4096 However, the model crashes during the latter half of the loading process, displaying the error message: **Error: llama runner process has terminated: exit status 2.** Please help me resolve this issue. ### Relevant log output ```shell time=2025-02-21T09:19:17.047+08:00 level=INFO source=logging.go:50 msg="ollama app started" time=2025-02-21T09:19:17.058+08:00 level=INFO source=lifecycle.go:19 msg="app config" env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://0.0.0.0:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:2562047h47m16.854775807s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:C:\\Users\\mj\\.ollama\\models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:0 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://*] OLLAMA_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES:]" time=2025-02-21T09:19:17.111+08:00 level=INFO source=server.go:182 msg="unable to connect to server" time=2025-02-21T09:19:17.112+08:00 level=INFO source=server.go:141 msg="starting server..." time=2025-02-21T09:19:17.119+08:00 level=INFO source=server.go:127 msg="started ollama server with pid 17736" time=2025-02-21T09:19:17.119+08:00 level=INFO source=server.go:129 msg="ollama server logs C:\\Users\\mj\\AppData\\Local\\Ollama\\server.log" time=2025-02-22T18:08:18.183+08:00 level=INFO source=lifecycle.go:89 msg="Waiting for ollama server to shutdown..." time=2025-02-22T18:08:18.197+08:00 level=INFO source=server.go:158 msg="server shutdown with exit code 0" time=2025-02-22T18:08:18.197+08:00 level=INFO source=lifecycle.go:93 msg="Ollama app exiting" ``` ### OS Windows ### GPU _No response_ ### CPU AMD ### Ollama version 0.511
GiteaMirror added the bug label 2026-05-04 12:34:04 -05:00
GiteaMirror commented 2026-05-04 12:34:07 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Feb 22, 2025):

Add server log.

<!-- gh-comment-id:2676150695 --> @rick-github commented on GitHub (Feb 22, 2025): Add server log.
GiteaMirror commented 2026-05-04 12:34:08 -05:00
Author
Owner
Copy Link

@mjdp168 commented on GitHub (Feb 22, 2025):

2025/02/22 18:11:02 routes.go:1186: INFO server config env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://0.0.0.0:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:2562047h47m16.854775807s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:C:\Users\mj\.ollama\models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:0 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://*] OLLAMA_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES:]"
time=2025-02-22T18:11:02.451+08:00 level=INFO source=images.go:432 msg="total blobs: 7"
time=2025-02-22T18:11:02.452+08:00 level=INFO source=images.go:439 msg="total unused blobs removed: 0"
time=2025-02-22T18:11:02.453+08:00 level=INFO source=routes.go:1237 msg="Listening on [::]:11434 (version 0.5.11)"
time=2025-02-22T18:11:02.453+08:00 level=INFO source=gpu.go:217 msg="looking for compatible GPUs"
time=2025-02-22T18:11:02.453+08:00 level=INFO source=gpu_windows.go:167 msg=packages count=1
time=2025-02-22T18:11:02.453+08:00 level=INFO source=gpu_windows.go:214 msg="" package=0 cores=64 efficiency=0 threads=64
time=2025-02-22T18:11:02.462+08:00 level=INFO source=gpu.go:377 msg="no compatible GPUs were discovered"
time=2025-02-22T18:11:02.462+08:00 level=INFO source=types.go:130 msg="inference compute" id=0 library=cpu variant="" compute="" driver=0.0 name="" total="511.9 GiB" available="494.5 GiB"
[GIN] 2025/02/22 - 18:12:36 | 200 | 0s | 127.0.0.1 | HEAD "/"
[GIN] 2025/02/22 - 18:12:36 | 200 | 23.7311ms | 127.0.0.1 | POST "/api/create"

<!-- gh-comment-id:2676156338 --> @mjdp168 commented on GitHub (Feb 22, 2025): 2025/02/22 18:11:02 routes.go:1186: INFO server config env="map[CUDA_VISIBLE_DEVICES: GPU_DEVICE_ORDINAL: HIP_VISIBLE_DEVICES: HSA_OVERRIDE_GFX_VERSION: HTTPS_PROXY: HTTP_PROXY: NO_PROXY: OLLAMA_DEBUG:false OLLAMA_FLASH_ATTENTION:false OLLAMA_GPU_OVERHEAD:0 OLLAMA_HOST:http://0.0.0.0:11434 OLLAMA_INTEL_GPU:false OLLAMA_KEEP_ALIVE:2562047h47m16.854775807s OLLAMA_KV_CACHE_TYPE: OLLAMA_LLM_LIBRARY: OLLAMA_LOAD_TIMEOUT:5m0s OLLAMA_MAX_LOADED_MODELS:0 OLLAMA_MAX_QUEUE:512 OLLAMA_MODELS:C:\\Users\\mj\\.ollama\\models OLLAMA_MULTIUSER_CACHE:false OLLAMA_NOHISTORY:false OLLAMA_NOPRUNE:false OLLAMA_NUM_PARALLEL:0 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://*] OLLAMA_SCHED_SPREAD:false ROCR_VISIBLE_DEVICES:]" time=2025-02-22T18:11:02.451+08:00 level=INFO source=images.go:432 msg="total blobs: 7" time=2025-02-22T18:11:02.452+08:00 level=INFO source=images.go:439 msg="total unused blobs removed: 0" time=2025-02-22T18:11:02.453+08:00 level=INFO source=routes.go:1237 msg="Listening on [::]:11434 (version 0.5.11)" time=2025-02-22T18:11:02.453+08:00 level=INFO source=gpu.go:217 msg="looking for compatible GPUs" time=2025-02-22T18:11:02.453+08:00 level=INFO source=gpu_windows.go:167 msg=packages count=1 time=2025-02-22T18:11:02.453+08:00 level=INFO source=gpu_windows.go:214 msg="" package=0 cores=64 efficiency=0 threads=64 time=2025-02-22T18:11:02.462+08:00 level=INFO source=gpu.go:377 msg="no compatible GPUs were discovered" time=2025-02-22T18:11:02.462+08:00 level=INFO source=types.go:130 msg="inference compute" id=0 library=cpu variant="" compute="" driver=0.0 name="" total="511.9 GiB" available="494.5 GiB" [GIN] 2025/02/22 - 18:12:36 | 200 | 0s | 127.0.0.1 | HEAD "/" [GIN] 2025/02/22 - 18:12:36 | 200 | 23.7311ms | 127.0.0.1 | POST "/api/create"
GiteaMirror commented 2026-05-04 12:34:08 -05:00
Author
Owner
Copy Link

@mjdp168 commented on GitHub (Feb 22, 2025):

@rick-github ，thank

<!-- gh-comment-id:2676156514 --> @mjdp168 commented on GitHub (Feb 22, 2025): @rick-github ，thank
GiteaMirror commented 2026-05-04 12:34:09 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Feb 22, 2025):

Add server log from when the error occurs.

<!-- gh-comment-id:2676157983 --> @rick-github commented on GitHub (Feb 22, 2025): Add server log from when the error occurs.
GiteaMirror commented 2026-05-04 12:34:10 -05:00
Author
Owner
Copy Link

@mjdp168 commented on GitHub (Feb 22, 2025):

thank ，That's it just now

<!-- gh-comment-id:2676162024 --> @mjdp168 commented on GitHub (Feb 22, 2025): thank ，That's it just now
GiteaMirror commented 2026-05-04 12:34:11 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Feb 22, 2025):

There are no errors in this log.

<!-- gh-comment-id:2676163204 --> @rick-github commented on GitHub (Feb 22, 2025): There are no errors in this log.
GiteaMirror commented 2026-05-04 12:34:14 -05:00
Author
Owner
Copy Link

@ENUMERA8OR commented on GitHub (Feb 26, 2025):

How many parameters model are you trying to run? Make sure that nothing else is running at the moment when you try to run the model, that might consume necessary computational resources.

<!-- gh-comment-id:2685736548 --> @ENUMERA8OR commented on GitHub (Feb 26, 2025): How many parameters model are you trying to run? Make sure that nothing else is running at the moment when you try to run the model, that might consume necessary computational resources.
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#68112
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?