Stars
ERASE: Eliminating Redundant Visual Tokens via Adaptive Two-Stage Token Pruning
Repository to host and maintain SCALE-Sim code
PyTorch implementation of Audio Flamingo: Series of Advanced Audio Understanding Language Models
A minimal tensor processing unit (TPU), inspired by Google's TPU V2 and V1
[ACL Findings 2026] Official Implementation of "FastKV: Decoupling of Context Reduction and KV Cache Compression for Prefill-Decoding Acceleration"
[ICML 2024] Official Implementation of SLEB: Streamlining LLMs through Redundancy Verification and Elimination of Transformer Blocks
QUICK: Quantization-aware Interleaving and Conflict-free Kernel for efficient LLM inference
A curated list for Efficient Large Language Models
A curated collection of papers, benchmarks, surveys, and tools for model quantization, covering low-bit networks, LLMs, multimodal and generative models, vector and lattice quantization, and effici…
[ICML'21 Oral] I-BERT: Integer-only BERT Quantization
Google AI 2018 BERT pytorch implementation
Tutorials on implementing a few sequence-to-sequence (seq2seq) models with PyTorch and TorchText.
A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch
CUDA Templates and Python DSLs for High-Performance Linear Algebra
This is a BNN_Kernel on PyTorch for 1-bit networks in image data processing
IBM Research CUDA Implementation for the H2O version of the LightGBM package (v2.2.4)
Accompanying code for the paper "Zero-shot Knowledge Transfer via Adversarial Belief Matching"
Knowledge Extraction with No Observable Data (NeurIPS 2019)
Efficient computing methods developed by Huawei Noah's Ark Lab
Training neural networks with back-prop, feedback-alignment and direct feedback-alignment
Examples demonstrating available options to program multiple GPUs in a single node or a cluster
Models and examples built with TensorFlow