Alternatives and similar repositories for Transkimmer

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

• dilab-zju / self-speculative-decoding
  Code associated with the paper **Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding**
  ☆216Updated 11 months ago
• kssteven418 / BigLittleDecoder
  [NeurIPS'23] Speculative Decoding with Big Little Decoder
  ☆96Updated last year
• NJUNLP / MCSD
  Multi-Candidate Speculative Decoding
  ☆39Updated last year
• RulinShao / LightSeq
  Official repository for DistFlashAttn: Distributed Memory-efficient Attention for Long-context LLMs Training
  ☆221Updated last year
• hdong920 / LESS
  ☆53Updated last year
• HArmonizedSS / HASS
  Official Implementation of "Learning Harmonized Representations for Speculative Sampling" (HASS)
  ☆52Updated 10 months ago
• thu-pacman / FasterMoE
  ☆89Updated 3 years ago
• Equationliu / Kangaroo
  [NeurIPS 2024] The official implementation of "Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exitin…
  ☆64Updated last year
• ClubieDong / QAQ-KVCacheQuantization
  QAQ: Quality Adaptive Quantization for LLM KV Cache
  ☆55Updated last year
• ruikangliu / IntactKV
  [ACL 2024] Official PyTorch implementation of "IntactKV: Improving Large Language Model Quantization by Keeping Pivot Tokens Intact"
  ☆48Updated last year
• linfeng93 / BiTA
  An innovative method expediting LLMs via streamlined semi-autoregressive generation and draft verification.
  ☆26Updated 9 months ago
• thunlp / Ouroboros
  Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)
  ☆113Updated 9 months ago
• Infini-AI-Lab / Sirius
  Sirius, an efficient correction mechanism, which significantly boosts Contextual Sparsity models on reasoning tasks while maintaining its…
  ☆21Updated last year
• UCSB-NLP-Chang / KVLink
  ☆34Updated 3 months ago
• raymin0223 / fast_robust_early_exit
  Fast and Robust Early-Exiting Framework for Autoregressive Language Models with Synchronized Parallel Decoding (EMNLP 2023 Long)
  ☆65Updated last year
• NonvolatileMemory / GliDe_with_a_CaPE_ICML_24
  official code for GliDe with a CaPE
  ☆20Updated last year
• zhuohan123 / terapipe
  ☆77Updated 4 years ago
• kssteven418 / LTP
  [KDD'22] Learned Token Pruning for Transformers
  ☆102Updated 2 years ago
• zhengzangw / Sequence-Scheduling
  PyTorch implementation of paper "Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline".
  ☆93Updated 2 years ago
• LiuXiaoxuanPKU / GACT-ICML
  ☆43Updated 3 years ago
• luuyin / OWL
  Official Pytorch Implementation of "Outlier Weighed Layerwise Sparsity (OWL): A Missing Secret Sauce for Pruning LLMs to High Sparsity"
  ☆78Updated 6 months ago
• FasterDecoding / SnapKV
  ☆299Updated 6 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…
  ☆88Updated 10 months ago
• zankner / Hydra
  ☆51Updated last year
• opengear-project / GEAR
  GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM
  ☆175Updated last year
• mutonix / pyramidinfer
  ☆49Updated last year
• hemingkx / Spec-Bench
  Spec-Bench: A Comprehensive Benchmark and Unified Evaluation Platform for Speculative Decoding (ACL 2024 Findings)
  ☆353Updated 8 months ago
• d-matrix-ai / keyformer-llm
  Keyformer proposes KV Cache reduction through key tokens identification and without the need for fine-tuning
  ☆59Updated last year
• FasterDecoding / TEAL
  ☆157Updated 11 months ago
• yanring / Megatron-MoE-ModelZoo
  Best practices for training DeepSeek, Mixtral, Qwen and other MoE models using Megatron Core.
  ☆152Updated last month