library/docs-ollama
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Sync ollama docs from 82f905cd on 2026-07-12

Browse Source
This commit is contained in:
The Librarian
2026-07-12 04:00:08 +00:00
parent 70feb5e845
commit 6d510760b7
24 changed files with 1013 additions and 314 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/faq.mdx
+1 -1
View File
@@ -343,7 +343,7 @@ When loading a new model, Ollama evaluates the required VRAM for the model again
## How can I enable Flash Attention?
Flash Attention is a feature of most modern models that can significantly reduce memory usage as the context size grows. To enable Flash Attention, set the `OLLAMA_FLASH_ATTENTION` environment variable to `1` when starting the Ollama server.
Flash Attention is a feature of most modern models that can significantly reduce memory usage as the context size grows. Ollama uses Flash Attention automatically when the selected backend and devices support it. To force Flash Attention on, set `OLLAMA_FLASH_ATTENTION=1` when starting the Ollama server. To disable it, set `OLLAMA_FLASH_ATTENTION=0`.
## How can I set the quantization type for the K/V cache?