thu-pacman / SmartMoE-AELinks
ATC23 AE
☆45Updated 2 years ago
Alternatives and similar repositories for SmartMoE-AE
Users that are interested in SmartMoE-AE are comparing it to the libraries listed below
Sorting:
- ☆84Updated 3 years ago
- ☆54Updated last year
- [USENIX ATC '24] Accelerating the Training of Large Language Models using Efficient Activation Rematerialization and Optimal Hybrid Paral…☆55Updated 10 months ago
- ☆74Updated 4 years ago
- Sequence-level 1F1B schedule for LLMs.☆28Updated last week
- ☆77Updated 2 months ago
- PyTorch implementation of paper "Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline".☆88Updated 2 years ago
- ☆103Updated 7 months ago
- 16-fold memory access reduction with nearly no loss☆99Updated 3 months ago
- [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length☆90Updated 2 months ago
- Odysseus: Playground of LLM Sequence Parallelism☆70Updated last year
- A simple calculation for LLM MFU.☆38Updated 3 months ago
- Compare different hardware platforms via the Roofline Model for LLM inference tasks.☆100Updated last year
- Summary of system papers/frameworks/codes/tools on training or serving large model☆57Updated last year
- Explore Inter-layer Expert Affinity in MoE Model Inference☆9Updated last year
- nnScaler: Compiling DNN models for Parallel Training☆113Updated last week
- ☆141Updated 3 months ago
- ☆96Updated 9 months ago
- Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity☆214Updated last year
- ☆148Updated 11 months ago
- A GPU-optimized system for efficient long-context LLMs decoding with low-bit KV cache.☆47Updated 2 weeks ago
- Chimera: bidirectional pipeline parallelism for efficiently training large-scale models.☆67Updated 3 months ago
- Sequence-level 1F1B schedule for LLMs.☆17Updated last year
- Implement some method of LLM KV Cache Sparsity☆32Updated last year
- Official repository for DistFlashAttn: Distributed Memory-efficient Attention for Long-context LLMs Training☆210Updated 10 months ago
- A MoE impl for PyTorch, [ATC'23] SmartMoE☆64Updated last year
- [NeurIPS 2024] The official implementation of "Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exitin…☆57Updated last year
- [ICML 2024] Serving LLMs on heterogeneous decentralized clusters.☆26Updated last year
- PyTorch bindings for CUTLASS grouped GEMM.☆127Updated 5 months ago
- ☆62Updated last year