Alternatives and similar repositories for CocktailSGD:

Users that are interested in CocktailSGD are comparing it to the libraries listed below

• IST-DASLab / Sparse-Marlin
  Boosting 4-bit inference kernels with 2:4 Sparsity
  ☆64Updated 4 months ago
• IST-DASLab / SparseFinetuning
  Repository for Sparse Finetuning of LLMs via modified version of the MosaicML llmfoundry
  ☆40Updated last year
• DS3Lab / Decentralized_FM_alpha
  ☆19Updated last year
• IST-DASLab / QIGen
  Repository for CPU Kernel Generation for LLM Inference
  ☆25Updated last year
• Edward-Sun / gpt-accelera
  Simple and efficient pytorch-native transformer training and inference (batched)
  ☆66Updated 9 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…
  ☆106Updated 5 months ago
• google-deepmind / asyncdiloco
  ☆41Updated last year
• xiayuqing0622 / flex_head_fa
  Fast and memory-efficient exact attention
  ☆52Updated last month
• ScalingIntelligence / CATS
  ☆23Updated 2 months ago
• tanyuqian / redco
  NAACL '24 (Best Demo Paper RunnerUp) / MlSys @ NeurIPS '23 - RedCoast: A Lightweight Tool to Automate Distributed Training and Inference
  ☆62Updated last month
• shreyansh26 / Attention-Mask-Patterns
  Using FlexAttention to compute attention with different masking patterns
  ☆40Updated 3 months ago
• Zyphra / tree_attention
  Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters
  ☆111Updated last month
• ScalingIntelligence / KernelBench
  KernelBench: Can LLMs Write GPU Kernels? - Benchmark with Torch -> CUDA problems
  ☆91Updated this week
• opengear-project / GEAR
  GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM
  ☆152Updated 6 months ago
• wdlctc / mini-s
  ☆43Updated 2 months ago
• cchan / tccl
  extensible collectives library in triton
  ☆76Updated 3 months ago
• JonasGeiping / linear_cross_entropy_loss
  A fusion of a linear layer and a cross entropy loss, written for pytorch in triton.
  ☆61Updated 5 months ago
• UmerHA / triton_util
  Make triton easier
  ☆42Updated 7 months ago
• siyan-zhao / prepacking
  The source code of our work "Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models"
  ☆58Updated 3 months ago
• hmarkc / parallel-prompt-decoding
  Efficient LLM Inference Acceleration using Prompting
  ☆45Updated 2 months ago
• zankner / Hydra
  ☆40Updated 11 months ago
• shadowpa0327 / Palu
  Code for Palu: Compressing KV-Cache with Low-Rank Projection
  ☆63Updated 2 months ago
• epfml / dynamic-sparse-flash-attention
  ☆135Updated last year
• Infini-AI-Lab / MagicDec
  Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding
  ☆107Updated last month
• FasterDecoding / TEAL
  ☆107Updated 3 months ago
• andy-yang-1 / DoubleSparse
  16-fold memory access reduction with nearly no loss
  ☆63Updated 2 months ago
• srush / triton-autodiff
  Experiment of using Tangent to autodiff triton
  ☆74Updated 11 months ago
• raymin0223 / fast_robust_early_exit
  Fast and Robust Early-Exiting Framework for Autoregressive Language Models with Synchronized Parallel Decoding (EMNLP 2023 Long)
  ☆56Updated 3 months ago
• PiotrNawrot / nano-sparse-attention
  The simplest implementation of recent Sparse Attention patterns for efficient LLM inference.
  ☆55Updated 2 months ago
• berlino / seq_icl
  ☆51Updated 7 months ago