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 #5839] CUDA error: CUBLAS_STATUS_NOT_INITIALIZED #3640

New Issue
Closed
opened 2026-04-12 14:25:08 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-12 14:25:08 -05:00
Owner
Copy Link

Originally created by @CaptainDP on GitHub (Jul 22, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/5839

What is the issue?

error msg：
CUDA error: CUBLAS_STATUS_NOT_INITIALIZED
current device: 0, in function cublas_handle at /go/src/github.com/ollama/ollama/llm/llama.cpp/ggml/src/ggml-cuda/common.cuh:826
cublasCreate_v2(&cublas_handles[device])

model：qwen2-sft，use llama.cpp/convert_hf_to_gguf.py transfer to gguf；
env1：ubuntu20+A800：CUDA error: CUBLAS_STATUS_NOT_INITIALIZED
env2：MAC os：is ok

OS

Linux, Docker

GPU

Nvidia

CPU

Intel

Ollama version

ollama version is 0.2.7

Originally created by @CaptainDP on GitHub (Jul 22, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/5839 ### What is the issue? error msg： CUDA error: CUBLAS_STATUS_NOT_INITIALIZED current device: 0, in function cublas_handle at /go/src/github.com/ollama/ollama/llm/llama.cpp/ggml/src/ggml-cuda/common.cuh:826 cublasCreate_v2(&cublas_handles[device]) model：qwen2-sft，use llama.cpp/convert_hf_to_gguf.py transfer to gguf； env1：ubuntu20+A800：CUDA error: CUBLAS_STATUS_NOT_INITIALIZED env2：MAC os：is ok ### OS Linux, Docker ### GPU Nvidia ### CPU Intel ### Ollama version ollama version is 0.2.7
GiteaMirror added the bug label 2026-04-12 14:25:08 -05:00
GiteaMirror commented 2026-04-12 14:25:09 -05:00
Author
Owner
Copy Link

@CaptainDP commented on GitHub (Jul 22, 2024):

full msg：
CUDA error: CUBLAS_STATUS_NOT_INITIALIZED
current device: 0, in function cublas_handle at /go/src/github.com/ollama/ollama/llm/llama.cpp/ggml/src/ggml-cuda/common.cuh:826
cublasCreate_v2(&cublas_handles[device])
GGML_ASSERT: /go/src/github.com/ollama/ollama/llm/llama.cpp/ggml/src/ggml-cuda.cu💯 !"CUDA error"
time=2024-07-19T18:17:53.430+08:00 level=INFO source=server.go:612 msg="waiting for server to become available" status="llm server not responding"
time=2024-07-19T18:17:59.996+08:00 level=INFO source=server.go:612 msg="waiting for server to become available" status="llm server error"
time=2024-07-19T18:18:00.247+08:00 level=ERROR source=sched.go:443 msg="error loading llama server" error="llama runner process has terminated: signal: aborted (core dumped) CUDA error""
[GIN] 2024/07/19 - 18:18:00 | 500 | 17.219251827s | 127.0.0.1 | POST "/api/chat"
time=2024-07-19T18:18:05.644+08:00 level=WARN source=sched.go:634 msg="gpu VRAM usage didn't recover within timeout" seconds=5.397515954 model=/root/.ollama/models/blobs/sha256-01bf5e0739037fb9f63fd3be28135437f89cc1ea27e263f1cd2308ef1c57dd38
time=2024-07-19T18:18:05.865+08:00 level=WARN source=sched.go:634 msg="gpu VRAM usage didn't recover within timeout" seconds=5.618106055 model=/root/.ollama/models/blobs/sha256-01bf5e0739037fb9f63fd3be28135437f89cc1ea27e263f1cd2308ef1c57dd38
time=2024-07-19T18:18:06.115+08:00 level=WARN source=sched.go:634 msg="gpu VRAM usage didn't recover within timeout" seconds=5.868642664 model=/root/.ollama/models/blobs/sha256-01bf5e0739037fb9f63fd3be28135437f89cc1ea27e263f1cd2308ef1c57dd38

<!-- gh-comment-id:2241963105 --> @CaptainDP commented on GitHub (Jul 22, 2024): full msg： CUDA error: CUBLAS_STATUS_NOT_INITIALIZED current device: 0, in function cublas_handle at /go/src/github.com/ollama/ollama/llm/llama.cpp/ggml/src/ggml-cuda/common.cuh:826 cublasCreate_v2(&cublas_handles[device]) GGML_ASSERT: /go/src/github.com/ollama/ollama/llm/llama.cpp/ggml/src/ggml-cuda.cu:100: !"CUDA error" time=2024-07-19T18:17:53.430+08:00 level=INFO source=server.go:612 msg="waiting for server to become available" status="llm server not responding" time=2024-07-19T18:17:59.996+08:00 level=INFO source=server.go:612 msg="waiting for server to become available" status="llm server error" time=2024-07-19T18:18:00.247+08:00 level=ERROR source=sched.go:443 msg="error loading llama server" error="llama runner process has terminated: signal: aborted (core dumped) CUDA error\"" [GIN] 2024/07/19 - 18:18:00 | 500 | 17.219251827s | 127.0.0.1 | POST "/api/chat" time=2024-07-19T18:18:05.644+08:00 level=WARN source=sched.go:634 msg="gpu VRAM usage didn't recover within timeout" seconds=5.397515954 model=/root/.ollama/models/blobs/sha256-01bf5e0739037fb9f63fd3be28135437f89cc1ea27e263f1cd2308ef1c57dd38 time=2024-07-19T18:18:05.865+08:00 level=WARN source=sched.go:634 msg="gpu VRAM usage didn't recover within timeout" seconds=5.618106055 model=/root/.ollama/models/blobs/sha256-01bf5e0739037fb9f63fd3be28135437f89cc1ea27e263f1cd2308ef1c57dd38 time=2024-07-19T18:18:06.115+08:00 level=WARN source=sched.go:634 msg="gpu VRAM usage didn't recover within timeout" seconds=5.868642664 model=/root/.ollama/models/blobs/sha256-01bf5e0739037fb9f63fd3be28135437f89cc1ea27e263f1cd2308ef1c57dd38
GiteaMirror commented 2026-04-12 14:25:11 -05:00
Author
Owner
Copy Link

@CaptainDP commented on GitHub (Jul 22, 2024):

change another GPU is ok

<!-- gh-comment-id:2242232217 --> @CaptainDP commented on GitHub (Jul 22, 2024): change another GPU is ok
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#3640
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?