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 #2831] Windows: connection forcibly closes when adding image to llava prompt - CUDA out of memory #48233

New Issue
Closed
opened 2026-04-28 07:17:08 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-28 07:17:08 -05:00
Owner
Copy Link

Originally created by @jakobhoeg on GitHub (Feb 29, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/2831

Originally assigned to: @dhiltgen on GitHub.

I'm trying to use llava to identify a photo and it gives this error:

>>> What is in this image? /users/jakob/desktop/jakob.jpg
Added image '/users/jakob/desktop/jakob.jpg'
Error: Post "http://127.0.0.1:11434/api/chat": read tcp 127.0.0.1:55783->127.0.0.1:11434: wsarecv: An existing connection was forcibly closed by the remote host.

This is the server.log:

CUDA error: out of memory
clip_model_load: model name:   openai/clip-vit-large-patch14-336
clip_model_load: description:  image encoder for LLaVA
clip_model_load: GGUF version: 3
clip_model_load: alignment:    32
clip_model_load: n_tensors:    377
clip_model_load: n_kv:         19
clip_model_load: ftype:        f16

clip_model_load: loaded meta data with 19 key-value pairs and 377 tensors from C:\Users\jakob\.ollama\models\blobs\sha256-72d6f08a42f656d36b356dbe0920675899a99ce21192fd66266fb7d82ed07539
clip_model_load: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
clip_model_load: - kv   0:                       general.architecture str              = clip
clip_model_load: - kv   1:                      clip.has_text_encoder bool             = false
clip_model_load: - kv   2:                    clip.has_vision_encoder bool             = true
clip_model_load: - kv   3:                   clip.has_llava_projector bool             = true
clip_model_load: - kv   4:                          general.file_type u32              = 1
clip_model_load: - kv   5:                               general.name str              = openai/clip-vit-large-patch14-336
clip_model_load: - kv   6:                        general.description str              = image encoder for LLaVA
clip_model_load: - kv   7:                        clip.projector_type str              = mlp
clip_model_load: - kv   8:                     clip.vision.image_size u32              = 336
clip_model_load: - kv   9:                     clip.vision.patch_size u32              = 14
clip_model_load: - kv  10:               clip.vision.embedding_length u32              = 1024
clip_model_load: - kv  11:            clip.vision.feed_forward_length u32              = 4096
clip_model_load: - kv  12:                 clip.vision.projection_dim u32              = 768
clip_model_load: - kv  13:           clip.vision.attention.head_count u32              = 16
clip_model_load: - kv  14:   clip.vision.attention.layer_norm_epsilon f32              = 0.000010
clip_model_load: - kv  15:                    clip.vision.block_count u32              = 23
clip_model_load: - kv  16:                     clip.vision.image_mean arr[f32,3]       = [0.481455, 0.457828, 0.408211]
clip_model_load: - kv  17:                      clip.vision.image_std arr[f32,3]       = [0.268630, 0.261303, 0.275777]
clip_model_load: - kv  18:                              clip.use_gelu bool             = false
clip_model_load: - type  f32:  235 tensors
clip_model_load: - type  f16:  142 tensors
clip_model_load: CLIP using CUDA backend
clip_model_load: text_encoder:   0
clip_model_load: vision_encoder: 1
clip_model_load: llava_projector:  1
clip_model_load: model size:     595.49 MB
clip_model_load: metadata size:  0.14 MB
clip_model_load: params backend buffer size =  595.49 MB (377 tensors)
clip_model_load: compute allocated memory: 32.89 MB
encode_image_with_clip: image embedding created: 576 tokens

encode_image_with_clip: image encoded in   239.12 ms by CLIP (    0.42 ms per image patch)
  current device: 0, in function ggml_cuda_pool_malloc_vmm at C:\Users\jeff\git\ollama\llm\llama.cpp\ggml-cuda.cu:7990
  cuMemSetAccess(g_cuda_pool_addr[device] + g_cuda_pool_size[device], reserve_size, &access, 1)
GGML_ASSERT: C:\Users\jeff\git\ollama\llm\llama.cpp\ggml-cuda.cu:243: !"CUDA error"```
Originally created by @jakobhoeg on GitHub (Feb 29, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/2831 Originally assigned to: @dhiltgen on GitHub. I'm trying to use llava to identify a photo and it gives this error: ``` >>> What is in this image? /users/jakob/desktop/jakob.jpg Added image '/users/jakob/desktop/jakob.jpg' Error: Post "http://127.0.0.1:11434/api/chat": read tcp 127.0.0.1:55783->127.0.0.1:11434: wsarecv: An existing connection was forcibly closed by the remote host. ``` This is the server.log: ```time=2024-02-29T13:19:37.052+01:00 level=INFO source=dyn_ext_server.go:171 msg="loaded 1 images" CUDA error: out of memory clip_model_load: model name: openai/clip-vit-large-patch14-336 clip_model_load: description: image encoder for LLaVA clip_model_load: GGUF version: 3 clip_model_load: alignment: 32 clip_model_load: n_tensors: 377 clip_model_load: n_kv: 19 clip_model_load: ftype: f16 clip_model_load: loaded meta data with 19 key-value pairs and 377 tensors from C:\Users\jakob\.ollama\models\blobs\sha256-72d6f08a42f656d36b356dbe0920675899a99ce21192fd66266fb7d82ed07539 clip_model_load: Dumping metadata keys/values. Note: KV overrides do not apply in this output. clip_model_load: - kv 0: general.architecture str = clip clip_model_load: - kv 1: clip.has_text_encoder bool = false clip_model_load: - kv 2: clip.has_vision_encoder bool = true clip_model_load: - kv 3: clip.has_llava_projector bool = true clip_model_load: - kv 4: general.file_type u32 = 1 clip_model_load: - kv 5: general.name str = openai/clip-vit-large-patch14-336 clip_model_load: - kv 6: general.description str = image encoder for LLaVA clip_model_load: - kv 7: clip.projector_type str = mlp clip_model_load: - kv 8: clip.vision.image_size u32 = 336 clip_model_load: - kv 9: clip.vision.patch_size u32 = 14 clip_model_load: - kv 10: clip.vision.embedding_length u32 = 1024 clip_model_load: - kv 11: clip.vision.feed_forward_length u32 = 4096 clip_model_load: - kv 12: clip.vision.projection_dim u32 = 768 clip_model_load: - kv 13: clip.vision.attention.head_count u32 = 16 clip_model_load: - kv 14: clip.vision.attention.layer_norm_epsilon f32 = 0.000010 clip_model_load: - kv 15: clip.vision.block_count u32 = 23 clip_model_load: - kv 16: clip.vision.image_mean arr[f32,3] = [0.481455, 0.457828, 0.408211] clip_model_load: - kv 17: clip.vision.image_std arr[f32,3] = [0.268630, 0.261303, 0.275777] clip_model_load: - kv 18: clip.use_gelu bool = false clip_model_load: - type f32: 235 tensors clip_model_load: - type f16: 142 tensors clip_model_load: CLIP using CUDA backend clip_model_load: text_encoder: 0 clip_model_load: vision_encoder: 1 clip_model_load: llava_projector: 1 clip_model_load: model size: 595.49 MB clip_model_load: metadata size: 0.14 MB clip_model_load: params backend buffer size = 595.49 MB (377 tensors) clip_model_load: compute allocated memory: 32.89 MB encode_image_with_clip: image embedding created: 576 tokens encode_image_with_clip: image encoded in 239.12 ms by CLIP ( 0.42 ms per image patch) current device: 0, in function ggml_cuda_pool_malloc_vmm at C:\Users\jeff\git\ollama\llm\llama.cpp\ggml-cuda.cu:7990 cuMemSetAccess(g_cuda_pool_addr[device] + g_cuda_pool_size[device], reserve_size, &access, 1) GGML_ASSERT: C:\Users\jeff\git\ollama\llm\llama.cpp\ggml-cuda.cu:243: !"CUDA error"```
GiteaMirror added the bugwindows labels 2026-04-28 07:17:08 -05:00
GiteaMirror commented 2026-04-28 07:17:12 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Jun 1, 2024):

I would suggest giving the latest release a try to see if that improves the situation. That said, these may ultimately be due to https://github.com/ollama/ollama/issues/4599 which I'm still working on.

<!-- gh-comment-id:2143586404 --> @dhiltgen commented on GitHub (Jun 1, 2024): I would suggest giving the latest release a try to see if that improves the situation. That said, these may ultimately be due to https://github.com/ollama/ollama/issues/4599 which I'm still working on.
GiteaMirror commented 2026-04-28 07:17:15 -05:00
Author
Owner
Copy Link

@jakobhoeg commented on GitHub (Jun 4, 2024):

I would suggest giving the latest release a try to see if that improves the situation. That said, these may ultimately be due to #4599 which I'm still working on.

That fixed it, thanks!

<!-- gh-comment-id:2147379279 --> @jakobhoeg commented on GitHub (Jun 4, 2024): > I would suggest giving the latest release a try to see if that improves the situation. That said, these may ultimately be due to #4599 which I'm still working on. That fixed it, thanks!
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 windows
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#48233
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?