Alternatives and similar repositories for Dynasor

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

• FasterDecoding / SnapKV
  ☆296Updated 5 months ago
• astramind-ai / Mixture-of-depths
  Unofficial implementation for the paper "Mixture-of-Depths: Dynamically allocating compute in transformer-based language models"
  ☆176Updated last year
• Infini-AI-Lab / MagicDec
  [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding
  ☆135Updated last year
• Infini-AI-Lab / MagicPIG
  [ICLR2025 Spotlight] MagicPIG: LSH Sampling for Efficient LLM Generation
  ☆245Updated last year
• thunlp / Ouroboros
  Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)
  ☆112Updated 9 months ago
• yaof20 / Flash-RL
  Implementation for FP8/INT8 Rollout for RL training without performence drop.
  ☆282Updated last month
• IsaacRe / vllm-kvcompress
  KV cache compression for high-throughput LLM inference
  ☆148Updated 10 months ago
• QwenLM / ParScale
  Parallel Scaling Law for Language Model — Beyond Parameter and Inference Time Scaling
  ☆465Updated 7 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)".
  ☆87Updated 9 months ago
• SalesforceAIResearch / GemFilter
  ☆85Updated last month
• mit-han-lab / duo-attention
  [ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads
  ☆515Updated 10 months ago
• hyx1999 / SAM-Decoding
  Official Implementation of SAM-Decoding: Speculative Decoding via Suffix Automaton
  ☆39Updated 10 months ago
• opengear-project / GEAR
  GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM
  ☆175Updated last year
• BaohaoLiao / RSD
  [ICML 2025] Reward-guided Speculative Decoding (RSD) for efficiency and effectiveness.
  ☆52Updated 7 months ago
• jeffreysijuntan / lloco
  The official repo for "LLoCo: Learning Long Contexts Offline"
  ☆118Updated last year
• agentica-project / verl-pipeline
  Async pipelined version of Verl
  ☆125Updated 8 months ago
• pan-x-c / EE-LLM
  EE-LLM is a framework for large-scale training and inference of early-exit (EE) large language models (LLMs).
  ☆72Updated last year
• cmu-l3 / l1
  L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning
  ☆258Updated 7 months ago
• FasterDecoding / REST
  REST: Retrieval-Based Speculative Decoding, NAACL 2024
  ☆213Updated 3 months ago
• TemporaryLoRA / Block-Attention
  ☆41Updated 9 months ago
• thu-nics / MoA
  [CoLM'25] The official implementation of the paper <MoA: Mixture of Sparse Attention for Automatic Large Language Model Compression>
  ☆153Updated last month
• HKUNLP / ChunkLlama
  [ICML'24] Data and code for our paper "Training-Free Long-Context Scaling of Large Language Models"
  ☆447Updated last year
• dilab-zju / self-speculative-decoding
  Code associated with the paper **Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding**
  ☆213Updated 10 months ago
• OpenSparseLLMs / Linear-MoE
  ☆126Updated 6 months ago
• thunlp / InfLLM
  The code of our paper "InfLLM: Unveiling the Intrinsic Capacity of LLMs for Understanding Extremely Long Sequences with Training-Free Mem…
  ☆396Updated last year
• GeniusHTX / TALE
  ☆140Updated 3 months ago
• ZihanWang314 / CoE
  Chain of Experts (CoE) enables communication between experts within Mixture-of-Experts (MoE) models
  ☆226Updated last month
• thunlp / FR-Spec
  [ACL 2025 main] FR-Spec: Frequency-Ranked Speculative Sampling
  ☆49Updated 5 months ago
• eqimp / hogwild_llm
  Official PyTorch implementation for Hogwild! Inference: Parallel LLM Generation with a Concurrent Attention Cache
  ☆136Updated 4 months ago
• JT-Ushio / MHA2MLA
  Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs
  ☆198Updated 3 weeks ago