thu-pacman / SmartMoE-AE
ATC23 AE
☆43Updated last year
Related projects ⓘ
Alternatives and complementary repositories for SmartMoE-AE
- ☆63Updated 3 months ago
- ☆70Updated 2 years ago
- [USENIX ATC '24] Accelerating the Training of Large Language Models using Efficient Activation Rematerialization and Optimal Hybrid Paral…☆46Updated 3 months ago
- A high-performance distributed deep learning system targeting large-scale and automated distributed training. If you have any interests, …☆105Updated 10 months ago
- PyTorch implementation of paper "Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline".☆74Updated last year
- ☆34Updated 2 months ago
- ☆41Updated 5 months ago
- A MoE impl for PyTorch, [ATC'23] SmartMoE☆57Updated last year
- ☆42Updated 7 months ago
- Since the emergence of chatGPT in 2022, the acceleration of Large Language Model has become increasingly important. Here is a list of pap…☆166Updated this week
- PyTorch bindings for CUTLASS grouped GEMM.☆67Updated 3 months ago
- ☆42Updated last month
- Summary of system papers/frameworks/codes/tools on training or serving large model☆56Updated 10 months ago
- ☆79Updated 2 months ago
- Official implementation of ICML 2024 paper "ExCP: Extreme LLM Checkpoint Compression via Weight-Momentum Joint Shrinking".☆40Updated 3 months ago
- Sequence-level 1F1B schedule for LLMs.☆17Updated 5 months ago
- nnScaler: Compiling DNN models for Parallel Training☆62Updated 2 weeks ago
- ☆65Updated 3 years ago
- [ACL 2024] A novel QAT with Self-Distillation framework to enhance ultra low-bit LLMs.☆79Updated 5 months ago
- Official repository for LightSeq: Sequence Level Parallelism for Distributed Training of Long Context Transformers☆196Updated 2 months ago
- PyTorch library for cost-effective, fast and easy serving of MoE models.☆101Updated 2 months ago
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆195Updated last week
- A tiny yet powerful LLM inference system tailored for researching purpose. vLLM-equivalent performance with only 2k lines of code (2% of …☆98Updated 4 months ago
- The official code for paper "parallel speculative decoding with adaptive draft length."☆21Updated 2 months ago
- ☆130Updated 3 months ago
- Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity☆177Updated last year
- ☆74Updated 10 months ago
- MagicPIG: LSH Sampling for Efficient LLM Generation☆43Updated last week
- Code associated with the paper **Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding**☆135Updated 5 months ago
- [ICML 2024] Serving LLMs on heterogeneous decentralized clusters.☆15Updated 6 months ago