github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 16:11:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #1413] OOM Error on Bad CUDA Driver #47264

New Issue
Closed
opened 2026-04-28 03:29:10 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-28 03:29:10 -05:00
Owner
Copy Link

Originally created by @farhanhubble on GitHub (Dec 7, 2023).
Original GitHub issue: https://github.com/ollama/ollama/issues/1413

Ollama version: 0.1.1
Reproduction:

  • nvidia-smi

    Failed to initialize NVML: Driver/library version mismatch
NVML library version: 535.129

  • Run server

    IP='0.0.0.0'
PORT='11434'
EXE='bin/ollama'
ARGS='serve'
ENV="OLLAMA_HOST=$IP:$PORT'"
CMD="$ENV $EXE $ARGS"
echo Running $CMD
eval $CMD

  • Try embedding a slightly long payload

    import requests
response = requests.post('http://localhost:11434/api/embeddings', json={
    'model': 'llama2:latest',
    'prompt': 'Here is an article about llamas...'*30
})

  • Error

    CUDA error 2 at /go/src/github.com/jmorganca/ollama/llm/llama.cpp/ggml/ggml-cuda.cu:4856: out of memory

  • Logs

    {"timestamp":1701923173,"level":"INFO","function":"main","line":1192,"message":"system info","n_threads":32,"total_threads":64,"system_info":"AVX = 1 | AVX2 = 1 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | FMA = 1 | NEON = 0 | ARM_FMA = 0 | F16C = 1 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 1 | SSE3 = 1 | VSX = 0 | "}
llama.cpp: loading model from [REDACTED]
llama_model_load_internal: format     = ggjt v3 (latest)
llama_model_load_internal: n_vocab    = 32000
llama_model_load_internal: n_ctx      = 2048
llama_model_load_internal: n_embd     = 4096
llama_model_load_internal: n_mult     = 256
llama_model_load_internal: n_head     = 32
llama_model_load_internal: n_head_kv  = 32
llama_model_load_internal: n_layer    = 32
llama_model_load_internal: n_rot      = 128
llama_model_load_internal: n_gqa      = 1
llama_model_load_internal: rnorm_eps  = 5.0e-06
llama_model_load_internal: n_ff       = 11008
llama_model_load_internal: freq_base  = 10000.0
llama_model_load_internal: freq_scale = 1
llama_model_load_internal: ftype      = 2 (mostly Q4_0)
llama_model_load_internal: model size = 7B
llama_model_load_internal: ggml ctx size =    0.08 MB
llama_model_load_internal: using CUDA for GPU acceleration
llama_model_load_internal: mem required  = 4013.73 MB (+ 1024.00 MB per state)
llama_model_load_internal: offloading 0 repeating layers to GPU
llama_model_load_internal: offloaded 0/35 layers to GPU
llama_model_load_internal: total VRAM used: 384 MB
llama_new_context_with_model: kv self size  = 1024.00 MB

  • Fix: Hide GPU with CUDA_VISIBLE_DEVICES=''

Originally created by @farhanhubble on GitHub (Dec 7, 2023). Original GitHub issue: https://github.com/ollama/ollama/issues/1413 **Ollama version**: 0.1.1 **Reproduction**: - `nvidia-smi` ``` Failed to initialize NVML: Driver/library version mismatch NVML library version: 535.129 ``` - Run server ``` IP='0.0.0.0' PORT='11434' EXE='bin/ollama' ARGS='serve' ENV="OLLAMA_HOST=$IP:$PORT'" CMD="$ENV $EXE $ARGS" echo Running $CMD eval $CMD ``` - Try embedding a slightly long payload ``` import requests response = requests.post('http://localhost:11434/api/embeddings', json={ 'model': 'llama2:latest', 'prompt': 'Here is an article about llamas...'*30 }) ``` - Error ``` CUDA error 2 at /go/src/github.com/jmorganca/ollama/llm/llama.cpp/ggml/ggml-cuda.cu:4856: out of memory ``` - Logs ``` {"timestamp":1701923173,"level":"INFO","function":"main","line":1192,"message":"system info","n_threads":32,"total_threads":64,"system_info":"AVX = 1 | AVX2 = 1 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | FMA = 1 | NEON = 0 | ARM_FMA = 0 | F16C = 1 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 1 | SSE3 = 1 | VSX = 0 | "} llama.cpp: loading model from [REDACTED] llama_model_load_internal: format = ggjt v3 (latest) llama_model_load_internal: n_vocab = 32000 llama_model_load_internal: n_ctx = 2048 llama_model_load_internal: n_embd = 4096 llama_model_load_internal: n_mult = 256 llama_model_load_internal: n_head = 32 llama_model_load_internal: n_head_kv = 32 llama_model_load_internal: n_layer = 32 llama_model_load_internal: n_rot = 128 llama_model_load_internal: n_gqa = 1 llama_model_load_internal: rnorm_eps = 5.0e-06 llama_model_load_internal: n_ff = 11008 llama_model_load_internal: freq_base = 10000.0 llama_model_load_internal: freq_scale = 1 llama_model_load_internal: ftype = 2 (mostly Q4_0) llama_model_load_internal: model size = 7B llama_model_load_internal: ggml ctx size = 0.08 MB llama_model_load_internal: using CUDA for GPU acceleration llama_model_load_internal: mem required = 4013.73 MB (+ 1024.00 MB per state) llama_model_load_internal: offloading 0 repeating layers to GPU llama_model_load_internal: offloaded 0/35 layers to GPU llama_model_load_internal: total VRAM used: 384 MB llama_new_context_with_model: kv self size = 1024.00 MB ``` - Fix: Hide GPU with ` CUDA_VISIBLE_DEVICES=''`
GiteaMirror added the bug label 2026-04-28 03:29:10 -05:00
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#47264
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?