github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 16:40:08 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #1492] 7b model on Colab: CUDA error 2 at /go/src/github.com/jmorganca/ollama/llm/llama.cpp/gguf/ggml-cuda.cu:8001: out of memory #47316

New Issue
Closed
opened 2026-04-28 03:34:48 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-04-28 03:34:48 -05:00
Owner
Copy Link

Originally created by @nnWhisperer on GitHub (Dec 12, 2023).
Original GitHub issue: https://github.com/ollama/ollama/issues/1492

Hello,
On a Google Colab 50GB ram 16GB Vram T4 instance (problem persisted in V100 instance), I install ollama as follows:

!sudo curl -L https://ollama.ai/download/ollama-linux-amd64 -o /usr/bin/ollama
!sudo chmod +x /usr/bin/ollama
!ollama serve

On the terminal I say:
ollama run yarn-mistral:7b-128k
Log gives the following error while of the 16gbVRAM only 4.3 Gb of the VRAM was used :
CUDA error 2 at /go/src/github.com/jmorganca/ollama/llm/llama.cpp/gguf/ggml-cuda.cu:8001: out of memory

Following are the logs received:
output.log

Originally created by @nnWhisperer on GitHub (Dec 12, 2023). Original GitHub issue: https://github.com/ollama/ollama/issues/1492 Hello, On a Google Colab 50GB ram 16GB Vram T4 instance (problem persisted in V100 instance), I install ollama as follows: ``` !sudo curl -L https://ollama.ai/download/ollama-linux-amd64 -o /usr/bin/ollama !sudo chmod +x /usr/bin/ollama !ollama serve ``` On the terminal I say: `ollama run yarn-mistral:7b-128k` Log gives the following error while of the 16gbVRAM only 4.3 Gb of the VRAM was used : `CUDA error 2 at /go/src/github.com/jmorganca/ollama/llm/llama.cpp/gguf/ggml-cuda.cu:8001: out of memory` Following are the logs received: [output.log](https://github.com/jmorganca/ollama/files/13654181/output.log)
GiteaMirror added the bug label 2026-04-28 03:34:48 -05:00
GiteaMirror commented 2026-04-28 03:34:51 -05:00
Author
Owner
Copy Link

@phalexo commented on GitHub (Dec 15, 2023):

@BruceMacD

The OOM bug is hiding somewhere in this folder ./ollama/llm/llama.cpp/gguf

When I copied over this folder from the tag v0.1.11 to the tag clone v0.1.12 the problem in v0.1.12 goes away.

<!-- gh-comment-id:1857242689 --> @phalexo commented on GitHub (Dec 15, 2023): @BruceMacD The OOM bug is hiding somewhere in this folder ./ollama/llm/llama.cpp/gguf When I copied over this folder from the tag v0.1.11 to the tag clone v0.1.12 the problem in v0.1.12 goes away.
GiteaMirror commented 2026-04-28 03:34:51 -05:00
Author
Owner
Copy Link

@phalexo commented on GitHub (Dec 15, 2023):

git clone --recursive https://github.com/jmorganca/ollama.git
cd ollama/llm/llama.cpp
vi generate_linux.go

//go:generate cmake -S ggml -B ggml/build/cuda -DLLAMA_CUBLAS=on -DLLAMA_ACCELERATE=on -DLLAMA_K_QUANTS=on -DLLAMA_CUDA_FORCE_MMQ=on
//go:generate cmake --build ggml/build/cuda --target server --config Release
//go:generate mv ggml/build/cuda/bin/server ggml/build/cuda/bin/ollama-runner
//go:generate cmake -S gguf -B gguf/build/cuda -DLLAMA_CUBLAS=on -DLLAMA_ACCELERATE=on -DLLAMA_K_QUANTS=on -DLLAMA_NATIVE=off -DLLAMA_AVX=on -DLLAMA_AVX2=off -DLLAMA_AVX512=off -DLLAMA_FMA=off -DLLAMA_F16C=off -DLLAMA_CUDA_PEER_MAX_BATCH_SIZE=0 -DLLAMA_CUDA_FORCE_MMQ=on
//go:generate cmake --build gguf/build/cuda --target server --config Release
//go:generate mv gguf/build/cuda/bin/server gguf/build/cuda/bin/ollama-runner

cd ../..
go generate ./...
go build .
<!-- gh-comment-id:1858573478 --> @phalexo commented on GitHub (Dec 15, 2023): ```bash git clone --recursive https://github.com/jmorganca/ollama.git cd ollama/llm/llama.cpp vi generate_linux.go ``` ```go //go:generate cmake -S ggml -B ggml/build/cuda -DLLAMA_CUBLAS=on -DLLAMA_ACCELERATE=on -DLLAMA_K_QUANTS=on -DLLAMA_CUDA_FORCE_MMQ=on //go:generate cmake --build ggml/build/cuda --target server --config Release //go:generate mv ggml/build/cuda/bin/server ggml/build/cuda/bin/ollama-runner //go:generate cmake -S gguf -B gguf/build/cuda -DLLAMA_CUBLAS=on -DLLAMA_ACCELERATE=on -DLLAMA_K_QUANTS=on -DLLAMA_NATIVE=off -DLLAMA_AVX=on -DLLAMA_AVX2=off -DLLAMA_AVX512=off -DLLAMA_FMA=off -DLLAMA_F16C=off -DLLAMA_CUDA_PEER_MAX_BATCH_SIZE=0 -DLLAMA_CUDA_FORCE_MMQ=on //go:generate cmake --build gguf/build/cuda --target server --config Release //go:generate mv gguf/build/cuda/bin/server gguf/build/cuda/bin/ollama-runner ``` ```bash cd ../.. go generate ./... go build . ```
GiteaMirror commented 2026-04-28 03:34:51 -05:00
Author
Owner
Copy Link

@jmorganca commented on GitHub (Jan 14, 2024):

Hi @nnWhisperer this should be fixed as of version 0.1.20. Note, filling large context windows will still cause potential OOM errors, this is being worked on in https://github.com/jmorganca/ollama/issues/1952

<!-- gh-comment-id:1891088375 --> @jmorganca commented on GitHub (Jan 14, 2024): Hi @nnWhisperer this should be fixed as of version 0.1.20. Note, filling large context windows will still cause potential OOM errors, this is being worked on in https://github.com/jmorganca/ollama/issues/1952
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#47316
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?