Mirrors/llm-server-docs
1
0
Fork 0
mirror of https://github.com/varunvasudeva1/llm-server-docs.git synced 2025-12-16 11:37:45 +01:00
Code Issues Packages Projects Releases Wiki Activity

Ollama AMD compatibility update

Browse Source
This commit is contained in:
Varun Vasudeva
2024-03-26 16:24:22 -05:00
parent 40b28b6461
commit 1fcfc658cc
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
README.md
View File

@@ -12,7 +12,7 @@ The process involves installing the NVIDIA drivers, setting the GPU power limit,
This guide assumes that we're working with a system with one or more Nvidia GPUs and an Intel CPU. It should be identical for an AMD CPU (but I haven't verified this). This guide assumes that we're working with a system with one or more Nvidia GPUs and an Intel CPU. It should be identical for an AMD CPU (but I haven't verified this).
The same cannot be said for AMD GPUs. Specifically for `ollama`, [there's work being done](https://github.com/ollama/ollama/issues/738#issuecomment-1974874171) to support ROCm but it still isn't stable in the way most people would hope it is for a reliable server. However, used Nvidia cards are a good deal nowadays (as of Mar 2024). [Ollama now natively supports AMD GPUs](https://ollama.com/blog/amd-preview) so those with AMD cards can now enjoy accelerated inference as well.
This guide was built around the following system: This guide was built around the following system:
- CPU: Intel Core i5-12600KF - CPU: Intel Core i5-12600KF