search

hhao / ollama

Get up and running with Llama 3, Mistral, Gemma, and other large language models.
https://ollama.com
MIT License
4 stars 0 forks source link

when I input image the process will hang forever #1

Open goodskillprogramer opened 3 weeks ago

goodskillprogramer commented 3 weeks ago

What is the issue?

if I only input text ,the model works ok. But when I added a image ,it will hang and there will be no output. below is the consol；

llama_new_context_with_model: graph nodes = 1030 llama_new_context_with_model: graph splits = 2 INFO [main] model loaded | tid="140026374909952" timestamp=1718185245 time=2024-06-12T09:40:45.713Z level=INFO source=server.go:567 msg="llama runner started in 2.26 seconds" [GIN] 2024/06/12 - 09:40:46 | 200 | 3.363909682s | 127.0.0.1 | POST "/api/chat" [GIN] 2024/06/12 - 09:40:46 | 200 | 204.205184ms | 127.0.0.1 | POST "/v1/chat/completions"

OS

Linux

GPU

Nvidia

CPU

No response

Ollama version

No response

bnvnvnv commented 3 weeks ago

the same

Forevery1 commented 3 weeks ago

the same

gabrielssimoes commented 1 week ago

Same here, both for CPU and GPU.

OS Linux

GPU Nvidia

willianfco commented 6 days ago

Same here, using on Docker. The endpoint generate hangs forever.