yandex-research / swarm
Official code for "SWARM Parallelism: Training Large Models Can Be Surprisingly Communication-Efficient"
☆128Updated 11 months ago
Related projects ⓘ
Alternatives and complementary repositories for swarm
- Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters☆104Updated last month
- ☆39Updated 10 months ago
- Experiments on speculative sampling with Llama models☆118Updated last year
- Triton-based implementation of Sparse Mixture of Experts.☆185Updated last month
- Code for the paper "QMoE: Practical Sub-1-Bit Compression of Trillion-Parameter Models".☆262Updated last year
- Cold Compress is a hackable, lightweight, and open-source toolkit for creating and benchmarking cache compression methods built on top of…☆87Updated 3 months ago
- The official repo for "LLoCo: Learning Long Contexts Offline"☆113Updated 5 months ago
- PB-LLM: Partially Binarized Large Language Models☆148Updated last year
- ☆184Updated last month
- Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆79Updated this week
- QuIP quantization☆46Updated 8 months ago
- ☆99Updated last month
- An efficent implementation of the method proposed in "The Era of 1-bit LLMs"☆154Updated last month
- Token Omission Via Attention☆120Updated last month
- ☆38Updated 4 months ago
- Fast Matrix Multiplications for Lookup Table-Quantized LLMs☆187Updated this week
- ☆122Updated 10 months ago
- The source code of our work "Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models"☆56Updated last month
- Multipack distributed sampler for fast padding-free training of LLMs☆178Updated 3 months ago
- ModuleFormer is a MoE-based architecture that includes two different types of experts: stick-breaking attention heads and feedforward exp…☆216Updated 7 months ago
- Code for paper: "QuIP: 2-Bit Quantization of Large Language Models With Guarantees"☆350Updated 8 months ago
- Repo for "LoLCATs: On Low-Rank Linearizing of Large Language Models"☆177Updated last month
- ☆96Updated last month
- ☆35Updated 3 weeks ago
- Fast Inference of MoE Models with CPU-GPU Orchestration☆172Updated this week
- Layer-Condensed KV cache w/ 10 times larger batch size, fewer params and less computation. Dramatic speed up with better task performance…☆139Updated this week
- Simple and fast low-bit matmul kernels in CUDA / Triton☆145Updated last week
- ☆24Updated last year
- Explorations into some recent techniques surrounding speculative decoding☆212Updated last year
- ☆49Updated 6 months ago