{"library":"fla-core","type":"library","category":null,"description":"fla-core is a Python library providing efficient, Triton-based implementations of core operations and kernels for state-of-the-art linear attention and state-space models. It serves as a minimal-dependency subset of the larger 'flash-linear-attention' project, focusing on the fundamental computational building blocks. It is currently at version 0.4.2 and follows a regular release cadence, often in conjunction with its parent project, flash-linear-attention.","language":"python","status":"active","version":"0.4.2","tags":["deep-learning","attention","pytorch","gpu","triton","kernels","sequence-modeling","state-space-models"],"last_verified":"Sun May 24","install":[{"cmd":"pip install fla-core","imports":["from fla.modules import FusedRMSNormGated","from fla.ops.kda import chunk_kda","from flash_linear_attention.layers import MultiScaleRetention"]}],"homepage":null,"github":"https://github.com/fla-org/flash-linear-attention","docs":null,"changelog":null,"pypi":"https://pypi.org/project/fla-core/","npm":null,"openapi_spec":null,"status_page":null,"smithery":null,"compatibility":{"summary":{"python_range":"3.10–3.9","success_rate":40,"avg_install_s":66.8,"avg_import_s":null,"wheel_type":"wheel"},"url":"https://checklist.day/v1/registry/fla-core/compatibility"}}