gabrielolympie / moe-prunerLinks
A repository aimed at pruning DeepSeek V3, R1 and R1-zero to a usable size
☆67Updated 4 months ago
Alternatives and similar repositories for moe-pruner
Users that are interested in moe-pruner are comparing it to the libraries listed below
Sorting:
- Query-agnostic KV cache eviction: 3–4× reduction in memory and 2× decrease in latency (Qwen3/2.5, Gemma3, LLaMA3)☆98Updated last month
- Lightweight toolkit package to train and fine-tune 1.58bit Language models☆85Updated 3 months ago
- Fused Qwen3 MoE layer for faster training, compatible with HF Transformers, LoRA, 4-bit quant, Unsloth☆167Updated this week
- ☆51Updated last year
- FuseAI Project☆87Updated 7 months ago
- ☆55Updated 3 months ago
- A pipeline for LLM knowledge distillation☆108Updated 4 months ago
- RWKV-7: Surpassing GPT☆94Updated 9 months ago
- QuIP quantization☆57Updated last year
- Spherical Merge Pytorch/HF format Language Models with minimal feature loss.☆135Updated last year
- Easy to use, High Performant Knowledge Distillation for LLMs☆92Updated 3 months ago
- Implementation of the LongRoPE: Extending LLM Context Window Beyond 2 Million Tokens Paper☆149Updated last year
- KV cache compression for high-throughput LLM inference☆136Updated 6 months ago
- Code for KaLM-Embedding models☆91Updated 2 months ago
- ☆86Updated 7 months ago
- ☆48Updated last year
- My Implementation of Q-Sparse: All Large Language Models can be Fully Sparsely-Activated☆33Updated last year
- Parameter-Efficient Sparsity Crafting From Dense to Mixture-of-Experts for Instruction Tuning on General Tasks (EMNLP'24)☆147Updated 11 months ago
- A repository for research on medium sized language models.☆78Updated last year
- Official implementation of the ICML 2024 paper RoSA (Robust Adaptation)☆44Updated last year
- A collection of tricks and tools to speed up transformer models☆170Updated 2 months ago
- ☆80Updated 9 months ago
- This is the official repository for Inheritune.☆112Updated 6 months ago
- ☆38Updated last year
- ☆95Updated 3 weeks ago
- Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs☆189Updated 2 months ago
- My fork os allen AI's OLMo for educational purposes.☆30Updated 8 months ago
- Repository for Sparse Finetuning of LLMs via modified version of the MosaicML llmfoundry☆42Updated last year
- ☆61Updated 5 months ago
- [ICML 2025] |TokenSwift: Lossless Acceleration of Ultra Long Sequence Generation☆113Updated 3 months ago