tilde-research / MoMoE-implLinks
Memory optimized Mixture of Experts
☆72Updated 5 months ago
Alternatives and similar repositories for MoMoE-impl
Users that are interested in MoMoE-impl are comparing it to the libraries listed below
Sorting:
- The evaluation framework for training-free sparse attention in LLMs☆106Updated 2 months ago
- Pytorch Distributed native training library for LLMs/VLMs with OOTB Hugging Face support☆214Updated this week
- Load compute kernels from the Hub☆352Updated last week
- Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters☆131Updated last year
- Flash-Muon: An Efficient Implementation of Muon Optimizer☆223Updated 6 months ago
- Simple & Scalable Pretraining for Neural Architecture Research☆305Updated 2 weeks ago
- A scalable asynchronous reinforcement learning implementation with in-flight weight updates.☆336Updated this week
- [ICML 2025] From Low Rank Gradient Subspace Stabilization to Low-Rank Weights: Observations, Theories and Applications☆52Updated last month
- LM engine is a library for pretraining/finetuning LLMs☆102Updated this week
- ☆133Updated 6 months ago
- ☆54Updated last year
- Official implementation for Training LLMs with MXFP4☆115Updated 8 months ago
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆135Updated last year
- Repo hosting codes and materials related to speeding LLMs' inference using token merging.☆37Updated 2 months ago
- Storing long contexts in tiny caches with self-study☆226Updated 2 weeks ago
- Official PyTorch implementation for Hogwild! Inference: Parallel LLM Generation with a Concurrent Attention Cache☆136Updated 4 months ago
- Fast and memory-efficient exact attention☆75Updated 9 months ago
- ArcticTraining is a framework designed to simplify and accelerate the post-training process for large language models (LLMs)☆261Updated last week
- 🔥 LLM-powered GPU kernel synthesis: Train models to convert PyTorch ops into optimized Triton kernels via SFT+RL. Multi-turn compilation…☆109Updated last month
- Simple and efficient DeepSeek V3 SFT using pipeline parallel and expert parallel, with both FP8 and BF16 trainings☆101Updated 4 months ago
- KV cache compression for high-throughput LLM inference☆148Updated 10 months ago
- The simplest implementation of recent Sparse Attention patterns for efficient LLM inference.☆91Updated 5 months ago
- ☆60Updated 6 months ago
- Cold Compress is a hackable, lightweight, and open-source toolkit for creating and benchmarking cache compression methods built on top of…☆146Updated last year
- The source code of our work "Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models" [AISTATS …☆60Updated last year
- Block Transformer: Global-to-Local Language Modeling for Fast Inference (NeurIPS 2024)☆162Updated 8 months ago
- OpenTinker is an RL-as-a-Service infrastructure for foundation models☆229Updated this week
- EvaByte: Efficient Byte-level Language Models at Scale☆111Updated 8 months ago
- DPO, but faster 🚀☆46Updated last year
- ☆47Updated last year