Files
ollama37/llama/runner/cache_test.go
Jesse Gross 2cd11ae365 runner.go: Add unit tests for context shifting
This also makes it easier to truncate long inputs the same as
shifting but does not actually implement it. This type of
truncation has a trade off between quality and time to first
token.
2024-11-26 11:21:35 -08:00

6.5 KiB