ollama/integration
Daniel Hiltgen 44a6792873
tests: tighten up a few flaky tests (#12271)
Sometimes the context test results are pure emoji's
Thanksgiving has too much variability, so swap for a more straight forward prompt.
2025-09-12 13:59:34 -07:00
..
testdata test: improve scheduler/concurrency stress tests (#11906) 2025-08-15 14:37:54 -07:00
README.md perf: build graph for next batch async to keep GPU busy (#11863) 2025-08-29 14:20:28 -07:00
api_test.go tests: add tool calling integration test (#12232) 2025-09-09 14:01:11 -07:00
basic_test.go perf: build graph for next batch async to keep GPU busy (#11863) 2025-08-29 14:20:28 -07:00
concurrency_test.go tests: reduce stress on CPU to 2 models (#12161) 2025-09-09 09:32:15 -07:00
context_test.go tests: tighten up a few flaky tests (#12271) 2025-09-12 13:59:34 -07:00
embed_test.go tests: reduce stress on CPU to 2 models (#12161) 2025-09-09 09:32:15 -07:00
library_models_test.go Only load supported models on new engine (#11362) 2025-07-11 12:21:54 -07:00
llm_image_test.go perf: build graph for next batch async to keep GPU busy (#11863) 2025-08-29 14:20:28 -07:00
max_queue_test.go perf: build graph for next batch async to keep GPU busy (#11863) 2025-08-29 14:20:28 -07:00
model_arch_test.go int: add performance integration tests (#11173) 2025-07-05 16:07:09 -07:00
model_perf_test.go int: add performance integration tests (#11173) 2025-07-05 16:07:09 -07:00
quantization_test.go Move quantization to new backend (#10363) 2025-05-06 11:20:48 -07:00
utils_test.go tests: tighten up a few flaky tests (#12271) 2025-09-12 13:59:34 -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 ./... Some tests require additional tags to enable to allow scoped testing to keep the duration reasonable. For example, testing a broad set of models requires -tags=integration,models and a longer timeout (~60m or more depending on the speed of your GPU.). To view the current set of tag combinations use find integration -type f | xargs grep "go:build"

The integration tests have 2 modes of operating.

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

[!IMPORTANT] Before running the tests locally without the "test existing" setting, compile ollama from the top of the source tree go build . in addition to GPU support with cmake if applicable on your platform. The integration tests expect to find an ollama binary at the top of the tree.