-
### What is the issue?
If I try to run the `llama3.2-vision` model using `ollama run llama3.2-vision` on my Arch Linux machine, I get this error:
```
Error: llama runner process has terminated: GG…
-
Currently I'm learning this tool, I'm probably just missing some settings but I don't know which one. While trying to set up image generation I ran into this problem.
Version: KoboldCpp - Version 1…
-
### What is the issue?
On certain API requests, the server throws a segmentation fault error and the API responds with a HTTP 500. So far, I have encountered this twice in thousands of requests. Unfo…
-
When available VRAM becomes low, it looks like the Vulkan backend now allocates compute buffer on the shared memory, which causes very significant slowdowns, even if there is actually enough VRAM avai…
-
OS: 22.04.1-Ubuntu
Python: Python 3.12.2
Build fails for llama-cpp-python
```
$ pip install -r requirements.txt
...
Building wheels for collected packages: llama-cpp-python
Building wheel…
-
So with
```
tabby_x86_64-manylinux2014-cuda122/llama-server -m /home/mte90/.tabby/models/TabbyML/StarCoder2-7B/ggml/model-00001-of-00001.gguf --cont-batching --port 30890 -np 1 --log-disable --ctx-…
-
According to this https://github.com/ggerganov/llama.cpp/discussions/336#discussioncomment-11184134, there is a new CoreML API and an ANE backend might be possible to implement with latest Apple softw…
-
### What happened?
I tried this combination when I ran what I thought was a Vulkan-enabled build and it said I needed to enable BLAS support to get GPU acceleration, but it was actually just a CPU bu…
-
Hello.
I have an Intel ARC A380 and I'm using Ollama with IPEX-LLM using this script with Ubuntu:
```
#!/bin/bash
# Activate conda environment
source /home/nikos/miniforge3/etc/profile.d/cond…
-
I complied this repositories on my Debian 12 PC,but it was failed.
error:
error: ‘ggml_flash_attn’ was not declared in this scope; did you mean ‘ggml_flash_attn_ext’?
681 | struct …