Alternatives and similar repositories for speculative_mamba

Users that are interested in speculative_mamba are comparing it to the libraries listed below

• hahnyuan / ASVD4LLM
  Activation-aware Singular Value Decomposition for Compressing Large Language Models
  ☆66Updated 6 months ago
• mengxiayu / LLMSuperWeight
  Code for studying the super weight in LLM
  ☆100Updated 5 months ago
• Infini-AI-Lab / Sirius
  Sirius, an efficient correction mechanism, which significantly boosts Contextual Sparsity models on reasoning tasks while maintaining its…
  ☆21Updated 8 months ago
• FasterDecoding / TEAL
  ☆128Updated 3 months ago
• IST-DASLab / QuEST
  Work in progress.
  ☆62Updated last month
• jiwonsong-dev / SLEB
  Official Implementation of SLEB: Streamlining LLMs through Redundancy Verification and Elimination of Transformer Blocks
  ☆37Updated 3 months ago
• berlino / seq_icl
  ☆52Updated 11 months ago
• xiayuqing0622 / flex_head_fa
  Fast and memory-efficient exact attention
  ☆68Updated 2 months ago
• XunhaoLai / native-sparse-attention-triton
  Efficient triton implementation of Native Sparse Attention.
  ☆147Updated this week
• shadowpa0327 / Palu
  [ICLR 2025] Palu: Compressing KV-Cache with Low-Rank Projection
  ☆108Updated 2 months ago
• ScalingIntelligence / CATS
  ☆25Updated 6 months ago
• shawntan / stickbreaking-attention
  Stick-breaking attention
  ☆53Updated 2 months ago
• RobertCsordas / moeut
  ☆78Updated 8 months ago
• nil0x9 / flash-muon
  Flash-Muon: An Efficient Implementation of Muon Optimizer
  ☆103Updated last week
• insuhan / hyper-attn
  ☆81Updated last year
• thu-ml / ReMoE
  [ICLR2025] Codebase for "ReMoE: Fully Differentiable Mixture-of-Experts with ReLU Routing", built on Megatron-LM.
  ☆72Updated 4 months ago
• CASE-Lab-UMD / Unified-MoE-Compression
  The official implementation of the paper "Towards Efficient Mixture of Experts: A Holistic Study of Compression Techniques (TMLR)".
  ☆67Updated last month
• sustcsonglin / fla-tilelang
  ☆20Updated 2 months ago
• luuyin / OWL
  Official Pytorch Implementation of "Outlier Weighed Layerwise Sparsity (OWL): A Missing Secret Sauce for Pruning LLMs to High Sparsity"
  ☆66Updated 10 months ago
• NVIDIA / ngpt
  Normalized Transformer (nGPT)
  ☆176Updated 5 months ago
• AnswerDotAI / cold-compress
  Cold Compress is a hackable, lightweight, and open-source toolkit for creating and benchmarking cache compression methods built on top of…
  ☆131Updated 9 months ago
• Qualcomm-AI-research / lr-qat
  ☆36Updated 6 months ago
• mit-han-lab / x-attention
  XAttention: Block Sparse Attention with Antidiagonal Scoring
  ☆147Updated this week
• wdlctc / mini-s
  ☆51Updated 6 months ago
• proger / accelerated-scan
  Accelerated First Order Parallel Associative Scan
  ☆182Updated 8 months ago
• Zyphra / tree_attention
  Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters
  ☆126Updated 5 months ago
• NVlabs / GatedDeltaNet
  [ICLR 2025] Official PyTorch Implementation of Gated Delta Networks: Improving Mamba2 with Delta Rule
  ☆161Updated last month
• athms / mad-lab
  A MAD laboratory to improve AI architecture designs 🧪
  ☆115Updated 4 months ago
• andy-yang-1 / DoubleSparse
  16-fold memory access reduction with nearly no loss
  ☆93Updated last month
• PiotrNawrot / nano-sparse-attention
  The simplest implementation of recent Sparse Attention patterns for efficient LLM inference.
  ☆60Updated 3 months ago