yandex-research / swarmLinks
Official code for "SWARM Parallelism: Training Large Models Can Be Surprisingly Communication-Efficient"
☆147Updated last year
Alternatives and similar repositories for swarm
Users that are interested in swarm are comparing it to the libraries listed below
Sorting:
- Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters☆130Updated 11 months ago
- ☆47Updated last year
- Code for the paper "QMoE: Practical Sub-1-Bit Compression of Trillion-Parameter Models".☆278Updated 2 years ago
- Token Omission Via Attention☆127Updated last year
- Code for exploring Based models from "Simple linear attention language models balance the recall-throughput tradeoff"☆243Updated 5 months ago
- train with kittens!☆63Updated 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
- ModuleFormer is a MoE-based architecture that includes two different types of experts: stick-breaking attention heads and feedforward exp…☆225Updated 2 months ago
- ☆203Updated 11 months ago
- Experiments on speculative sampling with Llama models☆126Updated 2 years ago
- Docker image NVIDIA GH200 machines - optimized for vllm serving and hf trainer finetuning☆52Updated 9 months ago
- Code repository for the c-BTM paper☆108Updated 2 years ago
- DeMo: Decoupled Momentum Optimization☆197Updated 11 months ago
- Advanced Ultra-Low Bitrate Compression Techniques for the LLaMA Family of LLMs☆110Updated last year
- An efficent implementation of the method proposed in "The Era of 1-bit LLMs"☆155Updated last year
- Long context evaluation for large language models☆224Updated 8 months ago
- ☆53Updated last year
- Cold Compress is a hackable, lightweight, and open-source toolkit for creating and benchmarking cache compression methods built on top of…☆146Updated last year
- RWKV-7: Surpassing GPT☆100Updated last year
- PB-LLM: Partially Binarized Large Language Models☆157Updated 2 years ago
- Experiment of using Tangent to autodiff triton☆80Updated last year
- Large scale 4D parallelism pre-training for 🤗 transformers in Mixture of Experts *(still work in progress)*☆87Updated last year
- ☆69Updated last year
- Code for paper: "QuIP: 2-Bit Quantization of Large Language Models With Guarantees"☆387Updated last year
- scalable and robust tree-based speculative decoding algorithm☆362Updated 9 months ago
- QuIP quantization☆61Updated last year
- Storing long contexts in tiny caches with self-study☆217Updated last month
- Repo for "LoLCATs: On Low-Rank Linearizing of Large Language Models"☆249Updated 9 months ago
- Demonstration that finetuning RoPE model on larger sequences than the pre-trained model adapts the model context limit☆62Updated 2 years ago
- Code to reproduce "Transformers Can Do Arithmetic with the Right Embeddings", McLeish et al (NeurIPS 2024)☆194Updated last year