Alternatives and similar repositories for google_fast_or_slow:

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

• Arenaa / Accelerated-Generation-Techniques
  This repository contains papers for a comprehensive survey on accelerated generation techniques in Large Language Models (LLMs).
  ☆12Updated 7 months ago
• ziplab / QLLM
  [ICLR 2024] This is the official PyTorch implementation of "QLLM: Accurate and Efficient Low-Bitwidth Quantization for Large Language Mod…
  ☆22Updated 10 months ago
• NVlabs / COAT
  ☆52Updated last week
• zhuhanqing / APOLLO
  APOLLO: SGD-like Memory, AdamW-level Performance
  ☆82Updated 2 weeks ago
• teelinsan / parallel-decoding
  Repository of the paper "Accelerating Transformer Inference for Translation via Parallel Decoding"
  ☆114Updated 10 months ago
• ScalingIntelligence / CATS
  ☆23Updated 2 months ago
• hwang595 / Cuttlefish
  The implementation for MLSys 2023 paper: "Cuttlefish: Low-rank Model Training without All The Tuning"
  ☆43Updated last year
• LiqunMa / FBI-LLM
  FBI-LLM: Scaling Up Fully Binarized LLMs from Scratch via Autoregressive Distillation
  ☆46Updated 6 months ago
• GATECH-EIC / Linearized-LLM
  [ICML 2024] When Linear Attention Meets Autoregressive Decoding: Towards More Effective and Efficient Linearized Large Language Models
  ☆28Updated 7 months ago
• yuzhenmao / IceFormer
  Implementation of IceFormer: Accelerated Inference with Long-Sequence Transformers on CPUs (ICLR 2024).
  ☆22Updated 7 months ago
• PiotrNawrot / nano-sparse-attention
  The simplest implementation of recent Sparse Attention patterns for efficient LLM inference.
  ☆56Updated 2 months ago
• cornell-zhang / llm-datatypes
  Codebase for ICML'24 paper: Learning from Students: Applying t-Distributions to Explore Accurate and Efficient Formats for LLMs
  ☆24Updated 6 months ago
• insuhan / hyper-attn
  ☆74Updated last year
• Ying1123 / awesome-neural-symbolic
  A list of awesome neural symbolic papers.
  ☆44Updated 2 years ago
• GATECH-EIC / SuperTickets
  [ECCV 2022] SuperTickets: Drawing Task-Agnostic Lottery Tickets from Supernets via Jointly Architecture Searching and Parameter Pruning
  ☆19Updated 2 years ago
• HuangOwen / RoLoRA
  [EMNLP 2024] RoLoRA: Fine-tuning Rotated Outlier-free LLMs for Effective Weight-Activation Quantization
  ☆27Updated 3 months ago
• CASE-Lab-UMD / Unified-MoE-Compression
  The official implementation of the paper "Demystifying the Compression of Mixture-of-Experts Through a Unified Framework".
  ☆52Updated 2 months ago
• UNITES-Lab / moe-quantization
  Official code for the paper "Examining Post-Training Quantization for Mixture-of-Experts: A Benchmark"
  ☆10Updated 6 months ago
• indri-voice / vit.triton
  VIT inference in triton because, why not?
  ☆22Updated 7 months ago
• VITA-Group / Random-MoE-as-Dropout
  [ICLR 2023] "Sparse MoE as the New Dropout: Scaling Dense and Self-Slimmable Transformers" by Tianlong Chen*, Zhenyu Zhang*, Ajay Jaiswal…
  ☆48Updated last year
• softmax1 / Flash-Attention-Softmax-N
  CUDA and Triton implementations of Flash Attention with SoftmaxN.
  ☆68Updated 7 months ago
• tspeterkim / mixed-precision-from-scratch
  Mixed precision training from scratch with Tensors and CUDA
  ☆21Updated 8 months ago
• alexzhang13 / flashattention2-custom-mask
  Triton implementation of FlashAttention2 that adds Custom Masks.
  ☆88Updated 5 months ago
• metacarbon / shareAtt
  Beyond KV Caching: Shared Attention for Efficient LLMs
  ☆14Updated 6 months ago
• mit-han-lab / patch_conv
  Patch convolution to avoid large GPU memory usage of Conv2D
  ☆82Updated 7 months ago
• ilur98 / DGQ
  Official Code For Dual Grained Quantization: Efficient Fine-Grained Quantization for LLM
  ☆13Updated last year
• mit-han-lab / tinychat-tutorial
  ☆59Updated 2 months ago
• TianjinYellow / EdgeDeviceLLMCompetition-Starting-Kit
  ☆41Updated 2 months ago
• IST-DASLab / QIGen
  Repository for CPU Kernel Generation for LLM Inference
  ☆25Updated last year
• kyegomez / Blockwise-Parallel-Transformer
  32 times longer context window than vanilla Transformers and up to 4 times longer than memory efficient Transformers.
  ☆44Updated last year