Instructions to use GenomaLabs-com/kv-cache-eviction-mla with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use GenomaLabs-com/kv-cache-eviction-mla with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("GenomaLabs-com/kv-cache-eviction-mla", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
-
B1 validation: multi-step eviction test + transformers compatibility note
GENOMA LABS / researchAdds: - scripts/validate_eviction_random_init.py: 1000-step mock-cache validation exercising the H2O eviction logic across 4 layers with canonical DeepseekV3 cache dimensions (qk_dim=192, v_dim=128, FP16). - notebooks/02_validation_results.md: documented results, interpretation, reproduction instructions. - results/validate_eviction_random_init.csv: per-step cache size + eviction events, 1000 rows. Validation result: PASS. Cache stabilizes at exactly n_sink+budget+n_recent, 3664 eviction events triggered correctly across 916 post-cap steps, 913 steps/sec on CPU. Patch fixes (uncovered by attempting end-to-end with transformers 5.7.0): - Bound forward method called without re-passing self. - Defensive unpacking of original_forward return value (handles 2-tuple modern transformers and 3-tuple older versions). - Return arity matches what original_forward returned, so calling decoder layer unpacks correctly. Roadmap updates: - Multi-step validation marked complete. - API por…1ba26d6