Alternatives and similar repositories for specreason

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

• mutonix / pyramidinfer
  ☆45Updated 9 months ago
• hemingkx / SWIFT
  [ICLR 2025] SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration
  ☆53Updated 6 months ago
• hyx1999 / SAM-Decoding
  Official Implementation of SAM-Decoding: Speculative Decoding via Suffix Automaton
  ☆32Updated 7 months ago
• yaof20 / Flash-RL
  Implementation for FP8/INT8 Rollout for RL training without performence drop.
  ☆187Updated last week
• LiuXiaoxuanPKU / OSD
  ☆56Updated 9 months ago
• thunlp / FR-Spec
  [ACL 2025 main] FR-Spec: Frequency-Ranked Speculative Sampling
  ☆41Updated 2 months ago
• OpenSparseLLMs / Linear-MoE
  ☆118Updated 3 months ago
• FFY0 / AdaKV
  The Official Implementation of Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference
  ☆92Updated 2 months ago
• Jingyu6 / speculative_prefill
  ☆43Updated 3 months ago
• machilusZ / FastGen
  This repo contains the source code for: Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs
  ☆39Updated last year
• sail-sg / LongSpec
  LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification
  ☆63Updated 2 months ago
• Zanette-Labs / SpeculativeRejection
  [NeurIPS 2024] Fast Best-of-N Decoding via Speculative Rejection
  ☆51Updated 10 months ago
• Dominic789654 / LongGenBench
  Source code for the paper "LongGenBench: Long-context Generation Benchmark"
  ☆23Updated 11 months ago
• UNITES-Lab / MC-SMoE
  [ICLR 2024 Spotlight] Code for the paper "Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy"
  ☆93Updated 2 months ago
• zyxxmu / cam
  Pytorch implementation of our paper accepted by ICML 2024 -- CaM: Cache Merging for Memory-efficient LLMs Inference
  ☆44Updated last year
• smart-lty / ParallelSpeculativeDecoding
  [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length
  ☆111Updated 5 months ago
• ByteDance-Seed / FlexPrefill
  Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference
  ☆140Updated 3 months ago
• hdong920 / GRIFFIN
  ☆38Updated last year
• andy-yang-1 / DoubleSparse
  16-fold memory access reduction with nearly no loss
  ☆105Updated 5 months ago
• FasterDecoding / SnapKV
  ☆278Updated 2 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…
  ☆84Updated 6 months ago
• shadowpa0327 / Palu
  [ICLR 2025] Palu: Compressing KV-Cache with Low-Rank Projection
  ☆138Updated 6 months ago
• microsoft / SeerAttention
  SeerAttention: Learning Intrinsic Sparse Attention in Your LLMs
  ☆151Updated last month
• Equationliu / Kangaroo
  [NeurIPS 2024] The official implementation of "Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exitin…
  ☆59Updated last year
• SqueezeAILab / SqueezedAttention
  SQUEEZED ATTENTION: Accelerating Long Prompt LLM Inference
  ☆52Updated 9 months ago
• Jikai0Wang / OPT-Tree
  ☆27Updated 3 months ago
• mozhu621 / LongGenBench
  ☆27Updated 7 months ago
• HArmonizedSS / HASS
  Official Implementation of "Learning Harmonized Representations for Speculative Sampling" (HASS)
  ☆45Updated 6 months ago
• BaohaoLiao / RSD
  [ICML 2025] Reward-guided Speculative Decoding (RSD) for efficiency and effectiveness.
  ☆46Updated 4 months ago
• dilab-zju / self-speculative-decoding
  Code associated with the paper **Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding**
  ☆201Updated 7 months ago