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 #7966] ggml_cuda_cpy_fn: unsupported type combination (q4_0 to f32) in pre-release version #51609

New Issue
Closed
opened 2026-04-28 20:38:10 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-28 20:38:10 -05:00
Owner
Copy Link

Originally created by @dkkb on GitHub (Dec 6, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/7966

What is the issue?

I'm using this model https://huggingface.co/bartowski/Replete-LLM-V2.5-Qwen-32b-GGUF with the v0.5.0 pre-release.
After upgrading to the latest version, I was hoping to see improved performance. However, after making several API calls, I encountered the following error on the client side. I also noticed that GPU memory usage dropped to 0.

error making request: an error was encountered while running the model:
read tcp 127.0.0.1:3914->127.0.0.1:3890: wsarecv: An existing connection was forcibly closed by the remote host

Environment variables:

set OLLAMA_FLASH_ATTENTION=1
set OLLAMA_KV_CACHE_TYPE=q4_0
set CUDA_VISIBLE_DEVICES=xxx
set OLLAMA_HOST=0.0.0.0:11434
set OLLAMA_ORIGINS=*

Server error log:

ggml_cuda_cpy_fn: unsupported type combination (q4_0 to f32)

Maybe same issue with https://github.com/ggerganov/llama.cpp/issues/5652?

Disable the OLLAMA_KV_CACHE_TYPE=q4_0 feature, it seems OK now.

OS

Windows

GPU

Nvidia

CPU

Intel

Ollama version

v0.5.0 pre-release

Originally created by @dkkb on GitHub (Dec 6, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/7966 ### What is the issue? I'm using this model `https://huggingface.co/bartowski/Replete-LLM-V2.5-Qwen-32b-GGUF` with the v0.5.0 pre-release. After upgrading to the latest version, I was hoping to see improved performance. However, after making several API calls, I encountered the following error on the client side. I also noticed that GPU memory usage dropped to 0. ``` error making request: an error was encountered while running the model: read tcp 127.0.0.1:3914->127.0.0.1:3890: wsarecv: An existing connection was forcibly closed by the remote host ``` Environment variables: ``` set OLLAMA_FLASH_ATTENTION=1 set OLLAMA_KV_CACHE_TYPE=q4_0 set CUDA_VISIBLE_DEVICES=xxx set OLLAMA_HOST=0.0.0.0:11434 set OLLAMA_ORIGINS=* ``` Server error log: ``` ggml_cuda_cpy_fn: unsupported type combination (q4_0 to f32) ``` Maybe same issue with https://github.com/ggerganov/llama.cpp/issues/5652? Disable the OLLAMA_KV_CACHE_TYPE=q4_0 feature, it seems OK now. ### OS Windows ### GPU Nvidia ### CPU Intel ### Ollama version v0.5.0 pre-release
GiteaMirror added the bug label 2026-04-28 20:38:10 -05:00
GiteaMirror commented 2026-04-28 20:38:12 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Dec 6, 2024):

https://github.com/ollama/ollama/issues/7938

<!-- gh-comment-id:2522921164 --> @rick-github commented on GitHub (Dec 6, 2024): https://github.com/ollama/ollama/issues/7938
GiteaMirror commented 2026-04-28 20:38:13 -05:00
Author
Owner
Copy Link

@jessegross commented on GitHub (Dec 7, 2024):

Tracking this in the other bug

<!-- gh-comment-id:2524710773 --> @jessegross commented on GitHub (Dec 7, 2024): Tracking this in the other bug
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#51609
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?