mirror of https://github.com/ollama/ollama.git synced 2025-03-20 14:52:59 +01:00

History

Jesse Gross 7121dfa309 runner.go: Retry decoding after defragmentation if needed

Fragmentation of the KV cache can occur due to cache shifting or
different sequences getting processed. Decode uses a heuristic to
decide if it should defrag. However, this heuristic isn't 100%
accurate, so decoding can sometimes fail by surprise.

For these cases, if decode indicates that there is no KV cache space,
we should defrag and then try again.

2024-11-20 12:49:24 -08:00

basic_test.go

Give unicode test more time to run (#7437 )

2024-10-31 13:35:31 -07:00

concurrency_test.go

Give unicode test more time to run (#7437 )

2024-10-31 13:35:31 -07:00

context_test.go

runner.go: Retry decoding after defragmentation if needed

2024-11-20 12:49:24 -08:00

embed_test.go

integration: harden embedding test (#7306 )

2024-10-22 15:25:22 -07:00

llm_image_test.go

Add basic mllama integration tests (#7455 )

2024-10-31 17:25:48 -07:00

llm_test.go

fix concurrency test

2024-08-05 16:36:16 -07:00

max_queue_test.go

fix concurrency test

2024-08-05 16:36:16 -07:00

README.md

Revamp go based integration tests

2024-03-23 14:24:18 +01:00

utils_test.go

Re-introduce the llama package (#5034 )

2024-10-08 08:53:54 -07:00

README.md

Integration Tests

This directory contains integration tests to exercise Ollama end-to-end to verify behavior

By default, these tests are disabled so go test ./... will exercise only unit tests. To run integration tests you must pass the integration tag. go test -tags=integration ./...

The integration tests have 2 modes of operating.

By default, they will start the server on a random port, run the tests, and then shutdown the server.
If OLLAMA_TEST_EXISTING is set to a non-empty string, the tests will run against an existing running server, which can be remote