-
There are several cases where I conditionally exclude properties from an object, or where I store an embedded collection as an object, indexed by IDs. For example, one might want to only show public i…
-
如题,想使用还要先搭建编译环境,试用成本确实不小,能否放出几个常用端的安装包?
-
confirm working using zluda + stable diffusion via GPU [here](https://github.com/vosen/ZLUDA/issues/59#issuecomment-2002005732)
```
C:\Users\ken>d:\ZLUDA\zluda.exe -- ollama.exe serve
time=2024-0…
-
## General Issues
I am following the documentation(https://m3db.io/docs/quickstart/binaries/):
1) I have downloaded the binaries and extracted them to a directory
2) I fixed the system variables
…
-
Is it possible to manipulate the kv cache for llama models?
A common use case during inference is to strike/remove values from the kv cache when regenerating or editing generated outputs, so the ll…
-
An embedded db is used to cache sample-encode results. The current db sled isn't an ideal for here as it doesn't support concurrent access from multiple processes. There have also been a couple of rep…
-
### What is the issue?
This is possibly related to the fix for #4028. I updated to the 0.1.33 release and pulled the latest `mixtral:8x22b-instruct-v0.1-q4_0` (`6a0910fa6dc1`), so I'm running an 80…
-
### What happened?
ggml_cuda_compute_forward: RMS_NORM failed
CUDA error: invalid device function
current device: 0, in function ggml_cuda_compute_forward at ggml/src/ggml-cuda.cu:2288
err
GG…
-
### Describe the bug
Attempting to load a model after running the update-wizard-macos today (the version from a day or two ago worked fine) fails with the stack trace log included below.
Notabl…
-
### What is the issue?
After debugging for a while (see https://github.com/ollama/ollama/issues/5143#issuecomment-2265824021 and https://github.com/ollama/ollama/issues/5143#issuecomment-2265892604…