thu-pacman / FasterMoELinks
☆85Updated 3 years ago
Alternatives and similar repositories for FasterMoE
Users that are interested in FasterMoE are comparing it to the libraries listed below
Sorting:
- PyTorch implementation of paper "Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline".☆90Updated 2 years ago
- Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity☆217Updated last year
- nnScaler: Compiling DNN models for Parallel Training☆115Updated this week
- Official repository for DistFlashAttn: Distributed Memory-efficient Attention for Long-context LLMs Training☆214Updated last year
- ☆75Updated 4 years ago
- ☆54Updated last year
- ATC23 AE☆46Updated 2 years ago
- PyTorch bindings for CUTLASS grouped GEMM.☆109Updated 2 months ago
- [ICML 2024] Serving LLMs on heterogeneous decentralized clusters.☆27Updated last year
- ☆56Updated 8 months ago
- ☆78Updated 4 months ago
- [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length☆106Updated 4 months ago
- ☆113Updated 9 months ago
- A resilient distributed training framework☆94Updated last year
- PyTorch bindings for CUTLASS grouped GEMM.☆135Updated last month
- ☆68Updated last year
- ☆43Updated last year
- ☆332Updated last year
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆165Updated last year
- ☆77Updated 10 months ago
- A simple calculation for LLM MFU.☆43Updated 5 months ago
- Official implementation of ICML 2024 paper "ExCP: Extreme LLM Checkpoint Compression via Weight-Momentum Joint Shrinking".☆48Updated last year
- 16-fold memory access reduction with nearly no loss☆104Updated 4 months ago
- Stateful LLM Serving☆81Updated 5 months ago
- [NeurIPS 2024] Efficient LLM Scheduling by Learning to Rank☆57Updated 9 months ago
- [NeurIPS 2024] The official implementation of "Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exitin…☆59Updated last year
- [OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable☆176Updated 11 months ago
- PyTorch library for cost-effective, fast and easy serving of MoE models.☆221Updated last month
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆319Updated last year
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆321Updated last month