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 #5295] "CUDA error" #49831

New Issue
Closed
opened 2026-04-28 13:06:48 -05:00 by GiteaMirror · 7 comments
GiteaMirror commented 2026-04-28 13:06:48 -05:00
Owner
Copy Link

Originally created by @mayukhpv1997 on GitHub (Jun 26, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/5295

What is the issue?

when running "ollama run llama3" below error shown.

Error: llama runner process has terminated: signal: aborted (core dumped) CUDA error: CUBLAS_STATUS_EXECUTION_FAILED
current device: 0, in function ggml_cuda_mul_mat_batched_cublas at /go/src/github.com/ollama/ollama/llm/llama.cpp/ggml-cuda.cu:1855
cublasGemmBatchedEx(ctx.cublas_handle(), CUBLAS_OP_T, CUBLAS_OP_N, ne01, ne11, ne10, alpha, (const void **) (ptrs_src.get() + 0ne23), CUDA_R_16F, nb01/nb00, (const void **) (ptrs_src.get() + 1ne23), CUDA_R_16F, nb11/nb10, beta, ( void **) (ptrs_dst.get() + 0*ne23), cu_data_type, ne01, ne23, cu_compute_type, CUBLAS_GEMM_DEFAULT_TENSOR_OP)
GGML_ASSERT: /go/src/github.com/ollama/ollama/llm/llama.cpp/ggml-cuda.cu💯 !"CUDA error"

CUDA Version :12.2

OS

Linux

GPU

Nvidia

CPU

Other

Ollama version

0.1.45

Originally created by @mayukhpv1997 on GitHub (Jun 26, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/5295 ### What is the issue? when running "ollama run llama3" below error shown. > Error: llama runner process has terminated: signal: aborted (core dumped) CUDA error: CUBLAS_STATUS_EXECUTION_FAILED current device: 0, in function ggml_cuda_mul_mat_batched_cublas at /go/src/github.com/ollama/ollama/llm/llama.cpp/ggml-cuda.cu:1855 cublasGemmBatchedEx(ctx.cublas_handle(), CUBLAS_OP_T, CUBLAS_OP_N, ne01, ne11, ne10, alpha, (const void **) (ptrs_src.get() + 0*ne23), CUDA_R_16F, nb01/nb00, (const void **) (ptrs_src.get() + 1*ne23), CUDA_R_16F, nb11/nb10, beta, ( void **) (ptrs_dst.get() + 0*ne23), cu_data_type, ne01, ne23, cu_compute_type, CUBLAS_GEMM_DEFAULT_TENSOR_OP) GGML_ASSERT: /go/src/github.com/ollama/ollama/llm/llama.cpp/ggml-cuda.cu:100: !"CUDA error" CUDA Version :12.2 ### OS Linux ### GPU Nvidia ### CPU Other ### Ollama version 0.1.45
GiteaMirror added the bug label 2026-04-28 13:06:48 -05:00
GiteaMirror commented 2026-04-28 13:06:52 -05:00
Author
Owner
Copy Link

@d-kleine commented on GitHub (Jun 26, 2024):

How much vRAM do you have on your GPU?
#4912

<!-- gh-comment-id:2192177759 --> @d-kleine commented on GitHub (Jun 26, 2024): How much vRAM do you have on your GPU? #4912
GiteaMirror commented 2026-04-28 13:06:54 -05:00
Author
Owner
Copy Link

@mayukhpv1997 commented on GitHub (Jun 27, 2024):

32 GB

<!-- gh-comment-id:2193968343 --> @mayukhpv1997 commented on GitHub (Jun 27, 2024): 32 GB
GiteaMirror commented 2026-04-28 13:06:55 -05:00
Author
Owner
Copy Link

@d-kleine commented on GitHub (Jun 27, 2024):

vRAM, not RAM. Which GPU do you have?

<!-- gh-comment-id:2193973030 --> @d-kleine commented on GitHub (Jun 27, 2024): vRAM, not RAM. Which GPU do you have?
GiteaMirror commented 2026-04-28 13:06:56 -05:00
Author
Owner
Copy Link

@mayukhpv1997 commented on GitHub (Jun 28, 2024):

NVIDIA Jetson AGX Orin
36-28-2024 09:53:58 RAM 2081/305/788 (LFb 6415x483) SKAP 8/15286MB (cached MB) CP

[6k0729,0x8729,4%8279,250729,258729,1%2720,729,0x8729,off, off off off] EMC FR EQ 180665 GR3D FREQ @%@[0,0] VIC FRFO 729 APE 174 CVO 256C CPU@38.6750 rboard 290 SOC2035./SC Tolode@28.SC SOC0036.056C CV10-2560 GPU-2560 1838.625C SOC1835.9680 CV20-256C VDD CPU SOC 2200ml/2280MM VDD CPU CV 744MW/244ml VIN SYS SV6 3326mW/357 6M VODO VOD2 1V8A0 663MM/663mW,

<!-- gh-comment-id:2196201285 --> @mayukhpv1997 commented on GitHub (Jun 28, 2024): NVIDIA Jetson AGX Orin 36-28-2024 09:53:58 RAM 2081/305/788 (LFb 6415x483) SKAP 8/15286MB (cached MB) CP [6k0729,0x8729,4%8279,250729,258729,1%2720,729,0x8729,off, off off off] EMC FR EQ 180665 GR3D FREQ @%@[0,0] VIC FRFO 729 APE 174 CVO 256C CPU@38.6750 rboard 290 SOC2035./SC Tolode@28.SC SOC0036.056C CV10-2560 GPU-2560 1838.625C SOC1835.9680 CV20-256C VDD CPU SOC 2200ml/2280MM VDD CPU CV 744MW/244ml VIN SYS SV6 3326mW/357 6M VODO VOD2 1V8A0 663MM/663mW,
GiteaMirror commented 2026-04-28 13:06:56 -05:00
Author
Owner
Copy Link

@d-kleine commented on GitHub (Jun 29, 2024):

Try the above linked issue. Some user have deleted their model and update ollama, maybe this resolves your issue.

<!-- gh-comment-id:2198256602 --> @d-kleine commented on GitHub (Jun 29, 2024): Try the above linked issue. Some user have deleted their model and update ollama, maybe this resolves your issue.
GiteaMirror commented 2026-04-28 13:06:57 -05:00
Author
Owner
Copy Link

@mayukhpv1997 commented on GitHub (Jul 2, 2024):

Issue resolved.
Solution: need to run ollama server in background before "ollama run llama3"
command: ollama serve

<!-- gh-comment-id:2203091503 --> @mayukhpv1997 commented on GitHub (Jul 2, 2024): Issue resolved. Solution: need to run ollama server in background before "ollama run llama3" command: ollama serve
GiteaMirror commented 2026-04-28 13:06:58 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Jul 2, 2024):

You didn't mention which JetPack you're running. We have 2 open issues tracking mismatched bundled CUDA versions #2408 and #4693.

<!-- gh-comment-id:2204462905 --> @dhiltgen commented on GitHub (Jul 2, 2024): You didn't mention which JetPack you're running. We have 2 open issues tracking mismatched bundled CUDA versions #2408 and #4693.
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#49831
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?