github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 08:30:05 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #1083] "initialization error" when using CUDA #47047

New Issue
Closed
opened 2026-04-28 02:53:29 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-28 02:53:29 -05:00
Owner
Copy Link

Originally created by @Martin7-1 on GitHub (Nov 11, 2023).
Original GitHub issue: https://github.com/ollama/ollama/issues/1083

Hi! I'm using Ollama 0.1.9 in Ubuntu and Tesla V100 GPU, when I run ollama serve and do a POST request to embedding by CodeLlama:7b, I encounter error below:

2023/11/11 16:00:46 images.go:824: total blobs: 6
2023/11/11 16:00:46 images.go:831: total unused blobs removed: 0
2023/11/11 16:00:46 routes.go:696: Listening on 127.0.0.1:11434 (version 0.1.9)
2023/11/11 16:02:42 llama.go:290: 65020 MB VRAM available, loading up to 427 GPU layers
2023/11/11 16:02:42 llama.go:415: starting llama runner
2023/11/11 16:02:42 llama.go:473: waiting for llama runner to start responding

CUDA error 3 at /go/src/github.com/jmorganca/ollama/llm/llama.cpp/gguf/ggml-cuda.cu:5661: initialization error
current device: 0
2023/11/11 16:02:43 llama.go:430: 3 at /go/src/github.com/jmorganca/ollama/llm/llama.cpp/gguf/ggml-cuda.cu:5661: initialization error
current device: 0
2023/11/11 16:02:43 llama.go:438: error starting llama runner: llama runner process has terminated
2023/11/11 16:02:43 llama.go:504: llama runner stopped successfully
2023/11/11 16:02:43 llama.go:415: starting llama runner
2023/11/11 16:02:43 llama.go:473: waiting for llama runner to start responding
{"timestamp":1699689763,"level":"WARNING","function":"server_params_parse","line":871,"message":"Not compiled with GPU offload support, --n-gpu-layers option will be ignored. See main README.md for information on enabling GPU BLAS support","n_gpu_layers":-1}
{"timestamp":1699689763,"level":"INFO","function":"main","line":1323,"message":"build info","build":219,"commit":"9e70cc0"}
{"timestamp":1699689763,"level":"INFO","function":"main","line":1325,"message":"system info","n_threads":5,"n_threads_batch":-1,"total_threads":10,"system_info":"AVX = 1 | AVX2 = 0 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | FMA = 0 | NEON = 0 | ARM_FMA = 0 | F16C = 0 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 0 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | "}
llama_model_loader: loaded meta data with 20 key-value pairs and 291 tensors from /root/.ollama/models/blobs/sha256:3a43f93b78ec50f7c4e4dc8bd1cb3fff5a900e7d574c51a6f7495e48486e0dac (version GGUF V2 (latest))

I would be very grateful if anyone can help this.

Originally created by @Martin7-1 on GitHub (Nov 11, 2023). Original GitHub issue: https://github.com/ollama/ollama/issues/1083 Hi! I'm using `Ollama 0.1.9` in `Ubuntu` and Tesla V100 GPU, when I run `ollama serve` and do a `POST` request to embedding by `CodeLlama:7b`, I encounter error below: ```bash 2023/11/11 16:00:46 images.go:824: total blobs: 6 2023/11/11 16:00:46 images.go:831: total unused blobs removed: 0 2023/11/11 16:00:46 routes.go:696: Listening on 127.0.0.1:11434 (version 0.1.9) 2023/11/11 16:02:42 llama.go:290: 65020 MB VRAM available, loading up to 427 GPU layers 2023/11/11 16:02:42 llama.go:415: starting llama runner 2023/11/11 16:02:42 llama.go:473: waiting for llama runner to start responding CUDA error 3 at /go/src/github.com/jmorganca/ollama/llm/llama.cpp/gguf/ggml-cuda.cu:5661: initialization error current device: 0 2023/11/11 16:02:43 llama.go:430: 3 at /go/src/github.com/jmorganca/ollama/llm/llama.cpp/gguf/ggml-cuda.cu:5661: initialization error current device: 0 2023/11/11 16:02:43 llama.go:438: error starting llama runner: llama runner process has terminated 2023/11/11 16:02:43 llama.go:504: llama runner stopped successfully 2023/11/11 16:02:43 llama.go:415: starting llama runner 2023/11/11 16:02:43 llama.go:473: waiting for llama runner to start responding {"timestamp":1699689763,"level":"WARNING","function":"server_params_parse","line":871,"message":"Not compiled with GPU offload support, --n-gpu-layers option will be ignored. See main README.md for information on enabling GPU BLAS support","n_gpu_layers":-1} {"timestamp":1699689763,"level":"INFO","function":"main","line":1323,"message":"build info","build":219,"commit":"9e70cc0"} {"timestamp":1699689763,"level":"INFO","function":"main","line":1325,"message":"system info","n_threads":5,"n_threads_batch":-1,"total_threads":10,"system_info":"AVX = 1 | AVX2 = 0 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | FMA = 0 | NEON = 0 | ARM_FMA = 0 | F16C = 0 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 0 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | "} llama_model_loader: loaded meta data with 20 key-value pairs and 291 tensors from /root/.ollama/models/blobs/sha256:3a43f93b78ec50f7c4e4dc8bd1cb3fff5a900e7d574c51a6f7495e48486e0dac (version GGUF V2 (latest)) ``` I would be very grateful if anyone can help this.
GiteaMirror commented 2026-04-28 02:53:32 -05:00
Author
Owner
Copy Link

@BruceMacD commented on GitHub (Nov 13, 2023):

Hi @Martin7-1,

Thanks for opening the issue. Would you be able to share the output of the nvidia-smi command so that I can narrow down the problem?

<!-- gh-comment-id:1809176181 --> @BruceMacD commented on GitHub (Nov 13, 2023): Hi @Martin7-1, Thanks for opening the issue. Would you be able to share the output of the `nvidia-smi` command so that I can narrow down the problem?
GiteaMirror commented 2026-04-28 02:53:34 -05:00
Author
Owner
Copy Link

@Martin7-1 commented on GitHub (Nov 14, 2023):

Hi! @BruceMacD,
I try to update CUDA version from 10.2 to 11.4 and it finally works, maybe this error happened because the CUDA version was too low.

<!-- gh-comment-id:1809639289 --> @Martin7-1 commented on GitHub (Nov 14, 2023): Hi! @BruceMacD, I try to update CUDA version from 10.2 to 11.4 and it finally works, maybe this error happened because the CUDA version was too low.
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
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#47047
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?