yandex-research / swarm

Related projects: ⓘ

• IST-DASLab / qmoe
  Code for the paper "QMoE: Practical Sub-1-Bit Compression of Trillion-Parameter Models".
  ☆258Updated 10 months ago
• FasterDecoding / BitDelta
  ☆174Updated 4 months ago
• Zyphra / tree_attention
  Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters
  ☆94Updated 2 weeks ago
• schwartz-lab-NLP / TOVA
  Token Omission Via Attention
  ☆118Updated 7 months ago
• kernelmachine / cbtm
  Code repository for the c-BTM paper
  ☆105Updated 11 months ago
• astramind-ai / BitMat
  An efficent implementation of the method proposed in "The Era of 1-bit LLMs"
  ☆155Updated 2 months ago
• hahnyuan / PB-LLM
  PB-LLM: Partially Binarized Large Language Models
  ☆143Updated 10 months ago
• chu-tianxiang / QuIP-for-all
  QuIP quantization
  ☆41Updated 6 months ago
• google-deepmind / asyncdiloco
  ☆38Updated 8 months ago
• efeslab / fiddler
  Fast Inference of MoE Models with CPU-GPU Orchestration
  ☆163Updated 3 months ago
• HazyResearch / based
  Code for exploring Based models from "Simple linear attention language models balance the recall-throughput tradeoff"
  ☆206Updated last month
• jeffreysijuntan / lloco
  The official repo for "LLoCo: Learning Long Contexts Offline"
  ☆104Updated 3 months ago
• HanGuo97 / flute
  Fast Matrix Multiplications for Lookup Table-Quantized LLMs
  ☆156Updated this week
• shawntan / scattermoe
  Triton-based implementation of Sparse Mixture of Experts.
  ☆166Updated last month
• DS3Lab / CocktailSGD
  ☆24Updated last year
• koayon / awesome-adaptive-computation
  A curated reading list of research in Adaptive Computation, Dynamic Compute & Mixture of Experts (MoE). Inference time compute as seen in…
  ☆123Updated last month
• siyan-zhao / prepacking
  The source code of our work "Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models"
  ☆57Updated 5 months ago
• Digitous / LLM-SLERP-Merge
  Spherical Merge Pytorch/HF format Language Models with minimal feature loss.
  ☆107Updated last year
• GreenBitAI / low_bit_llama
  Advanced Ultra-Low Bitrate Compression Techniques for the LLaMA Family of LLMs
  ☆109Updated 8 months ago
• HanGuo97 / lq-lora
  ☆117Updated 7 months ago
• dust-tt / llama-ssp
  Experiments on speculative sampling with Llama models
  ☆114Updated last year
• llm-random / llm-random
  ☆169Updated this week
• minyoungg / LTE
  ☆61Updated 2 months ago
• AnswerDotAI / cold-compress
  Cold Compress is a hackable, lightweight, and open-source toolkit for creating and benchmarking cache compression methods built on top of…
  ☆73Updated last month
• cloneofsimo / min-fsdp
  ☆68Updated 2 months ago
• euclaise / supertrainer2000
  ☆48Updated 6 months ago
• Cornell-RelaxML / QuIP
  Code for paper: "QuIP: 2-Bit Quantization of Large Language Models With Guarantees"
  ☆339Updated 6 months ago
• IBM / ModuleFormer
  ModuleFormer is a MoE-based architecture that includes two different types of experts: stick-breaking attention heads and feedforward exp…
  ☆218Updated 5 months ago
• mobiusml / gemlite
  Simple and fast low-bit matmul kernels in CUDA
  ☆48Updated this week
• imoneoi / multipack_sampler
  Multipack distributed sampler for fast padding-free training of LLMs
  ☆170Updated last month