Qualcomm-AI-research / llm-surgeon

Related projects ⓘ

Alternatives and complementary repositories for llm-surgeon

• JeanKaddour / NoTrainNoGain
  Revisiting Efficient Training Algorithms For Transformer-based Language Models (NeurIPS 2023)
  ☆79Updated last year
• HazyResearch / prefix-linear-attention
  ☆45Updated 4 months ago
• mengxiayu / LLMSuperWeight
  Code for studying the super weight in LLM
  ☆16Updated last week
• epfml / schedules-and-scaling
  ☆53Updated 3 weeks ago
• IST-DASLab / RoSA
  ☆35Updated 9 months ago
• sustcsonglin / mamba-triton
  ☆45Updated 9 months ago
• srush / mamba-primer
  ☆35Updated 7 months ago
• IST-DASLab / SparseFinetuning
  Repository for Sparse Finetuning of LLMs via modified version of the MosaicML llmfoundry
  ☆38Updated 10 months ago
• shikaiqiu / compute-better-spent
  ☆46Updated last month
• gregorbachmann / scaling_mlps
  ☆51Updated 5 months ago
• raymin0223 / fast_robust_early_exit
  Fast and Robust Early-Exiting Framework for Autoregressive Language Models with Synchronized Parallel Decoding (EMNLP 2023 Long)
  ☆53Updated last month
• xiayuqing0622 / customized-flash-attention
  Fast and memory-efficient exact attention
  ☆27Updated last week
• mlfoundations / scaling
  Language models scale reliably with over-training and on downstream tasks
  ☆94Updated 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"
  ☆56Updated last month
• PiotrNawrot / nano-sparse-attention
  The simplest implementation of recent Sparse Attention patterns for efficient LLM inference.
  ☆37Updated this week
• RAIVNLab / MatFormer-OLMo
  Code repository for the public reproduction of the language modelling experiments on "MatFormer: Nested Transformer for Elastic Inference…
  ☆18Updated last year
• amirzandieh / HyperAttention
  Triton Implementation of HyperAttention Algorithm
  ☆46Updated 11 months ago
• smonsays / hypernetwork-attention
  Official code for the paper "Attention as a Hypernetwork"
  ☆23Updated 5 months ago
• Edward-Sun / gpt-accelera
  Simple and efficient pytorch-native transformer training and inference (batched)
  ☆61Updated 7 months ago
• zyushun / hessian-spectrum
  Code for the paper: Why Transformers Need Adam: A Hessian Perspective
  ☆42Updated 6 months ago
• ScalingIntelligence / large_language_monkeys
  ☆55Updated last month
• mgmalek / efficient_cross_entropy
  ☆77Updated 5 months ago
• gregorbachmann / Next-Token-Failures
  ☆69Updated 8 months ago
• insuhan / hyper-attn
  ☆74Updated 11 months ago
• dangxingyu / rnn-icrag
  Official repository of paper "RNNs Are Not Transformers (Yet): The Key Bottleneck on In-context Retrieval"
  ☆24Updated 7 months ago
• kyleliang919 / Online-Subspace-Descent
  This repo is based on https://github.com/jiaweizzhao/GaLore
  ☆19Updated 2 months ago
• NVIDIA / kvpress
  LLM KV cache compression made easy
  ☆64Updated last week
• shreyansh26 / Attention-Mask-Patterns
  Using FlexAttention to compute attention with different masking patterns
  ☆40Updated 2 months ago
• ldery / Bonsai
  Code for "Everybody Prune Now: Structured Pruning of LLMs with only Forward Passes"
  ☆28Updated 7 months ago
• goombalab / phi-mamba
  Official implementation of Phi-Mamba. A MOHAWK-distilled model (Transformers to SSMs: Distilling Quadratic Knowledge to Subquadratic Mode…
  ☆78Updated 2 months ago