Alternatives and similar repositories for moe-pruner

Users that are interested in moe-pruner are comparing it to the libraries listed below

• woct0rdho / transformers-qwen3-moe-fused
  Fused Qwen3 MoE layer for faster training, compatible with HF Transformers, LoRA, 4-bit quant, Unsloth
  ☆220Updated last week
• wdlctc / headinfer
  ☆63Updated 7 months ago
• tiiuae / onebitllms
  Lightweight toolkit package to train and fine-tune 1.58bit Language models
  ☆104Updated 7 months ago
• 18907305772 / FuseAI
  FuseAI Project
  ☆88Updated 11 months ago
• wuhy68 / Parameter-Efficient-MoE
  Parameter-Efficient Sparsity Crafting From Dense to Mixture-of-Experts for Instruction Tuning on General Tasks (EMNLP'24)
  ☆147Updated last year
• JT-Ushio / MHA2MLA
  Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs
  ☆198Updated last month
• golololologol / LLM-Distillery
  A pipeline for LLM knowledge distillation
  ☆112Updated 9 months ago
• chu-tianxiang / QuIP-for-all
  QuIP quantization
  ☆61Updated last year
• Digitous / LLM-SLERP-Merge
  Spherical Merge Pytorch/HF format Language Models with minimal feature loss.
  ☆141Updated 2 years ago
• SkyworkAI / MindLink
  ☆99Updated 5 months ago
• SalesforceAIResearch / GemFilter
  ☆85Updated last month
• jshuadvd / LongRoPE
  Implementation of the LongRoPE: Extending LLM Context Window Beyond 2 Million Tokens Paper
  ☆151Updated last year
• sanyalsunny111 / LLM-Inheritune
  This is the official repository for Inheritune.
  ☆117Updated 10 months ago
• BlinkDL / modded-nanogpt-rwkv
  RWKV-7: Surpassing GPT
  ☆103Updated last year
• SeunghyunSEO / optimized_hf_llama_class_for_training
  ☆48Updated last year
• agokrani / distillKitPlus
  Easy to use, High Performant Knowledge Distillation for LLMs
  ☆96Updated 8 months ago
• Zyphra / Zyda_processing
  ☆39Updated last year
• nyunAI / PruneGPT
  ☆51Updated last year
• DeepAuto-AI / hip-attention
  Training-free Post-training Efficient Sub-quadratic Complexity Attention. Implemented with OpenAI Triton.
  ☆148Updated 2 months ago
• frankxwang / dpo-prefix-sharing
  DPO, but faster 🚀
  ☆46Updated last year
• kyleliang919 / Super_Muon
  ☆66Updated 9 months ago
• NickL77 / BaldEagle
  3x Faster Inference; Unofficial implementation of EAGLE Speculative Decoding
  ☆82Updated 6 months ago
• IsaacRe / vllm-kvcompress
  KV cache compression for high-throughput LLM inference
  ☆148Updated 11 months ago
• TRI-ML / linear_open_lm
  A repository for research on medium sized language models.
  ☆77Updated last year
• OpenMOSE / RWKV-Infer
  A large-scale RWKV v7(World, PRWKV, Hybrid-RWKV) inference. Capable of inference by combining multiple states(Pseudo MoE). Easy to deploy…
  ☆46Updated 2 months ago
• xichen-fy / Fira
  Fira: Can We Achieve Full-rank Training of LLMs Under Low-rank Constraint?
  ☆119Updated last year
• bigai-nlco / TokenSwift
  [ICML 2025] |TokenSwift: Lossless Acceleration of Ultra Long Sequence Generation
  ☆118Updated 7 months ago
• NormXU / Consistent-DynamicNTKRoPE
  An Experiment on Dynamic NTK Scaling RoPE
  ☆64Updated 2 years ago
• SkyworkAI / Skywork-MoE
  Skywork-MoE: A Deep Dive into Training Techniques for Mixture-of-Experts Language Models
  ☆138Updated last year
• snu-mllab / KVzip
  [NeurIPS'25 Oral] Query-agnostic KV cache eviction: 3–4× reduction in memory and 2× decrease in latency (Qwen3/2.5, Gemma3, LLaMA3)
  ☆178Updated last week