{"categories":[{"label":"Artificial Intelligence","url":"https://skillfed.io/packages/category/scientific-engineering-artificial-intelligence/10"}],"enrichment":{"capability":"Mamba-ssm implements state-space model architectures (Mamba, Mamba-2, Mamba-3) as alternatives to Transformers for sequence modeling, optimized for language tasks and information-dense data.","skillfed_tags":["state-space-models","gpu-required","language-models"],"use_cases":["Replace Transformer blocks in language models when linear-time scaling is critical for long sequences.","Benchmark state-space models against Transformer baselines using pretrained Mamba models on standard NLP tasks.","Integrate Mamba blocks into custom sequence models where selective state-space mechanisms offer efficiency gains.","Fine-tune pretrained Mamba models (130M\u20132.8B parameters) on downstream language tasks via Hugging Face.","Experiment with Mamba-3's MIMO and structured state-space duality for research on sequence modeling architectures."],"what_it_does":"Mamba-ssm provides PyTorch implementations of Mamba state-space model architectures designed to match or exceed Transformer performance on language modeling while maintaining linear or near-linear time complexity. The package exposes multiple abstraction levels: the core selective SSM layer, the Mamba block (wrapping selective SSM), and complete language model backbones with repeating Mamba blocks. It includes three architecture variants\u2014Mamba, Mamba-2, and Mamba-3\u2014each with different parameter efficiency and design principles, along with pretrained models trained on the Pile dataset at scales from 130M to 2.8B parameters.\n\nThe package is built for GPU-accelerated inference and training on NVIDIA hardware, with hardware-aware optimizations inspired by FlashAttention. It requires ten runtime dependencies spanning PyTorch, Triton, specialized kernel libraries (quack-kernels, tilelang, apache-tvm-ffi), and standard ML tools (transformers, einops, packaging). Installation demands careful attention to build isolation and CUDA version compatibility, making it primarily suitable for researchers and practitioners already working in GPU-accelerated deep learning environments.","worth_installing":"Yes, if you have GPU infrastructure (NVIDIA, CUDA 11.6+, Linux) and are researching or deploying sequence models where Transformer alternatives are worth exploring. The active maintenance, zero known vulnerabilities, and permissive license support this. No, if you lack GPU access, need CPU-only inference, or require a simpler install path\u2014the high dependency friction and platform specificity make it unsuitable for casual experimentation or resource-constrained environments."},"id":"mamba-ssm","links":{"html":"https://skillfed.io/packages/mamba-ssm","md":"https://skillfed.io/packages/mamba-ssm.md","pypi":"https://pypi.org/project/mamba-ssm/"},"maintenance":{"status":"active"},"meta":{"latest_release":"2026-05-09","license_spdx":null,"license_treatment":"permissive","name":"mamba-ssm","python_support":"supports_current","summary":"Mamba state-space model"},"popularity":{"monthly_downloads":98525,"position":13076,"tier":"top_15000"},"security":{"n_vulnerabilities":0},"version":"2.3.2.post1"}