github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-16 21:25:46 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #4226] run llama3-70B-q8_0 error #2636

New Issue
Closed
opened 2026-04-12 12:59:02 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-12 12:59:02 -05:00
Owner
Copy Link

Originally created by @leoHostProject on GitHub (May 7, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/4226

What is the issue?

api call error
message:
{"error":{"message":"timed out waiting for llama runner to start:CUDA error:uncorrectable ECC error encountered
n current device:0,in function ggml cuda_compute_forward at /go/src/github.com/ollama/ollama/11m/1lama.cpp/ggml
-cuda.cu:2300\n err\nGGML_ASSERT:/go/src/github.com/ollama/ollama/11m/1lama.cpp/ggml-cuda.cu:60:!"CUDA error"
""type":"api_error","param"null,"code":null}}

OS

Linux, Docker

GPU

Nvidia

CPU

Intel

Ollama version

No response

Originally created by @leoHostProject on GitHub (May 7, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/4226 ### What is the issue? api call error message: {"error":{"message":"timed out waiting for llama runner to start:CUDA error:uncorrectable ECC error encountered\ n current device:0,in function ggml cuda_compute_forward at /go/src/github.com/ollama/ollama/11m/1lama.cpp/ggml -cuda.cu:2300\n err\nGGML_ASSERT:/go/src/github.com/ollama/ollama/11m/1lama.cpp/ggml-cuda.cu:60:!\"CUDA error\" ""type":"api_error","param"null,"code":null}} ### OS Linux, Docker ### GPU Nvidia ### CPU Intel ### Ollama version _No response_
GiteaMirror added the gpubugnvidia labels 2026-04-12 12:59:02 -05:00
GiteaMirror commented 2026-04-12 12:59:05 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Jul 25, 2024):

I'm able to load this model on a 48G CUDA card.

uncorrectable ECC error encountered sounds like a hardware fault on your GPU.

<!-- gh-comment-id:2251192467 --> @dhiltgen commented on GitHub (Jul 25, 2024): I'm able to load this model on a 48G CUDA card. `uncorrectable ECC error encountered` sounds like a hardware fault on your GPU.
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 gpu nvidia
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#2636
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?