thu-pacman / FasterMoE
☆65Updated 2 years ago
Related projects: ⓘ
- PyTorch implementation of paper "Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline".☆70Updated last year
- ☆62Updated 3 years ago
- Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity☆166Updated 11 months ago
- ATC23 AE☆42Updated last year
- A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems☆110Updated last month
- PyTorch bindings for CUTLASS grouped GEMM.☆41Updated 3 weeks ago
- Official repository for LightSeq: Sequence Level Parallelism for Distributed Training of Long Context Transformers☆183Updated last month
- ☆37Updated 5 months ago
- PyTorch library for cost-effective, fast and easy serving of MoE models.☆90Updated last month
- (NeurIPS 2022) Automatically finding good model-parallel strategies, especially for complex models and clusters.☆33Updated last year
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆161Updated 2 months ago
- PyTorch bindings for CUTLASS grouped GEMM.☆57Updated 2 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…☆153Updated this week
- ☆29Updated 3 weeks ago
- ☆33Updated 2 weeks ago
- A high-performance distributed deep learning system targeting large-scale and automated distributed training. If you have any interests, …☆101Updated 9 months ago
- Automated Parallelization System and Infrastructure for Multiple Ecosystems☆70Updated last month
- Dynamic Memory Management for Serving LLMs without PagedAttention☆186Updated last month
- A resilient distributed training framework☆78Updated 5 months ago
- ☆83Updated 3 weeks ago
- [ICML 2024] Serving LLMs on heterogeneous decentralized clusters.☆14Updated 4 months ago
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆134Updated 2 months ago
- [IJCAI2023] An automated parallel training system that combines the advantages from both data and model parallelism. If you have any inte…☆51Updated last year
- 16-fold memory access reduction with nearly no loss☆35Updated last month
- ☆30Updated this week
- ☆68Updated 9 months ago
- ☆67Updated last week
- A low-latency & high-throughput serving engine for LLMs☆174Updated last week
- ☆127Updated last month
- An experimental parallel training platform☆46Updated 5 months ago