{"library":"dsalt","type":"library","category":null,"description":"dsalt (Dynamic Sparse Attention with Landmark Tokens) is a high-performance Triton-based implementation of sparse attention for transformers. Version 0.4.34 supports PyTorch and provides fused kernels for landmark token selection and sparse attention computation, targeting long-context LLM inference and training. Released monthly.","language":"python","status":"active","version":"0.4.34","tags":["sparse-attention","triton","long-context","transformers"],"last_verified":"Sun Jun 07","install":[{"cmd":"pip install dsalt","imports":["from dsalt import DynamicSparseAttention"]},{"cmd":"pip install dsalt[dev]","imports":[]}],"homepage":"https://github.com/LeonardoCofone/dsalt-library","github":"https://github.com/LeonardoCofone/dsalt-library","docs":null,"changelog":null,"pypi":null,"npm":null,"openapi_spec":null,"status_page":null,"smithery":null,"compatibility":null}