mirror of https://github.com/ollama/ollama.git
fdb109469f
As we automatically enable flash attention for more models, there are likely some cases where we get it wrong. This allows setting OLLAMA_FLASH_ATTENTION=0 to disable it, even for models that usually have flash attention. |
||
|---|---|---|
| .. | ||
| llm_darwin.go | ||
| llm_linux.go | ||
| llm_windows.go | ||
| memory.go | ||
| memory_test.go | ||
| server.go | ||
| server_test.go | ||
| status.go | ||