unsloth/studio/backend/tests
Daniel Han 39fe23ded8
Tests for architecture-aware KV cache estimation (#4760)
* test: add 66 tests for architecture-aware KV cache estimation

Covers all 5 estimation paths (MLA, Hybrid Mamba, Sliding Window,
Standard GQA, Legacy), GGUF parser for 8 new metadata fields,
_can_estimate_kv gate conditions, quantization scaling, edge cases,
path priority ordering, and lifecycle (init/unload/reparse).

Zero external dependencies beyond pytest. No GPU or network required.
Cross-platform (Linux, macOS, Windows, WSL).

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

---------

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
2026-04-01 06:13:37 -07:00
..
__init__.py Final cleanup 2026-03-12 18:28:04 +00:00
conftest.py Final cleanup 2026-03-12 18:28:04 +00:00
test_data_recipe_seed.py fix(seed): disable remote code execution in seed inspect dataset loads (#4275) 2026-03-13 19:37:43 +04:00
test_gpu_selection.py [studio] multi gpu: revert to balanced for inference. (#4698) 2026-03-31 01:24:41 -07:00
test_gpu_selection_sandbox.py [Studio] multi gpu finetuning/inference via "balanced_low0/sequential" device_map (#4602) 2026-03-30 02:33:15 -07:00
test_kv_cache_estimation.py Tests for architecture-aware KV cache estimation (#4760) 2026-04-01 06:13:37 -07:00
test_native_context_length.py fix(studio): allow context length slider to reach model's native limit (#4746) 2026-04-01 06:12:52 -07:00
test_transformers_version.py feat: support GGUF export for non-PEFT models + fix venv_t5 switching for local checkpoints (#4455) 2026-03-20 12:13:18 +04:00
test_utils.py [Studio] multi gpu finetuning/inference via "balanced_low0/sequential" device_map (#4602) 2026-03-30 02:33:15 -07:00
test_vram_estimation.py [Studio] multi gpu finetuning/inference via "balanced_low0/sequential" device_map (#4602) 2026-03-30 02:33:15 -07:00