Alternatives and similar repositories for MCSD:

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

• smart-lty / ParallelSpeculativeDecoding
  [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length
  ☆75Updated this week
• FFY0 / AdaKV
  The Official Implementation of Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference
  ☆71Updated 2 months ago
• Equationliu / Kangaroo
  [NeurIPS 2024] The official implementation of "Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exitin…
  ☆51Updated 9 months ago
• LiuXiaoxuanPKU / OSD
  ☆48Updated 4 months ago
• dilab-zju / self-speculative-decoding
  Code associated with the paper **Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding**
  ☆181Updated 2 months ago
• mutonix / pyramidinfer
  ☆39Updated 4 months ago
• thunlp / Ouroboros
  Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)
  ☆101Updated 3 weeks ago
• ClubieDong / QAQ-KVCacheQuantization
  QAQ: Quality Adaptive Quantization for LLM KV Cache
  ☆49Updated last year
• hdong920 / LESS
  ☆50Updated 11 months ago
• henryzhongsc / longctx_bench
  Official implementation for Yuan & Liu & Zhong et al., KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark o…
  ☆70Updated last month
• hemingkx / SWIFT
  [ICLR 2025] SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration
  ☆45Updated last month
• d-matrix-ai / keyformer-llm
  ☆53Updated last year
• raymin0223 / fast_robust_early_exit
  Fast and Robust Early-Exiting Framework for Autoregressive Language Models with Synchronized Parallel Decoding (EMNLP 2023 Long)
  ☆57Updated 6 months ago
• opengear-project / GEAR
  GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM
  ☆159Updated 9 months ago
• hemingkx / Spec-Bench
  Spec-Bench: A Comprehensive Benchmark and Unified Evaluation Platform for Speculative Decoding (ACL 2024 Findings)
  ☆252Updated 3 weeks ago
• Jingyu6 / speculative_prefill
  ☆21Updated 2 weeks ago
• zyxxmu / cam
  Pytorch implementation of our paper accepted by ICML 2024 -- CaM: Cache Merging for Memory-efficient LLMs Inference
  ☆37Updated 10 months ago
• zhengzangw / Sequence-Scheduling
  PyTorch implementation of paper "Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline".
  ☆85Updated last year
• Jikai0Wang / proj254
  ☆22Updated 3 weeks ago
• FasterDecoding / SnapKV
  ☆235Updated 11 months ago
• NonvolatileMemory / GliDe_with_a_CaPE_ICML_24
  official code for GliDe with a CaPE
  ☆15Updated 8 months ago
• ruikangliu / IntactKV
  Official PyTorch implementation of "IntactKV: Improving Large Language Model Quantization by Keeping Pivot Tokens Intact"
  ☆43Updated 10 months ago
• linfeng93 / BiTA
  An innovative method expediting LLMs via streamlined semi-autoregressive generation and draft verification.
  ☆25Updated last year
• FasterDecoding / TEAL
  ☆122Updated 2 months ago
• microsoft / chunk-attention
  ☆68Updated 4 months ago
• zcli-charlie / Awesome-KV-Cache
  ☆60Updated 6 months ago
• mit-han-lab / Quest
  [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference
  ☆269Updated 4 months ago
• shadowpa0327 / Palu
  [ICLR 2025] Palu: Compressing KV-Cache with Low-Rank Projection
  ☆99Updated last month
• hyx1999 / SAM-Decoding
  Official Implementation of SAM-Decoding: Speculative Decoding via Suffix Automaton
  ☆23Updated 2 months ago
• bytedance / FlexPrefill
  Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference
  ☆82Updated 2 weeks ago