FlexFusion / FlexFusionLinks
The official implementation for the intra-stage fusion technique introduced in https://arxiv.org/abs/2409.13221
☆25Updated 4 months ago
Alternatives and similar repositories for FlexFusion
Users that are interested in FlexFusion are comparing it to the libraries listed below
Sorting:
- kvcached: Elastic KV cache for dynamic GPU sharing and efficient multi-LLM inference.☆66Updated this week
- ☆69Updated last year
- [NeurIPS 2024] Efficient LLM Scheduling by Learning to Rank☆58Updated 10 months ago
- [DAC'25] Official implement of "HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inference"☆69Updated 2 months ago
- A lightweight design for computation-communication overlap.☆160Updated last week
- ☆55Updated last year
- High performance Transformer implementation in C++.☆129Updated 7 months ago
- ☆116Updated 9 months ago
- A framework for generating realistic LLM serving workloads☆54Updated 2 months ago
- gLLM: Global Balanced Pipeline Parallelism System for Distributed LLM Serving with Token Throttling☆39Updated last week
- ☆23Updated 5 months ago
- [ICML 2024] Serving LLMs on heterogeneous decentralized clusters.☆29Updated last year
- ☆40Updated 4 months ago
- A GPU-optimized system for efficient long-context LLMs decoding with low-bit KV cache.☆58Updated this week
- Summary of some awesome work for optimizing LLM inference☆103Updated 3 months ago
- [OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable☆181Updated 11 months ago
- InfiniGen: Efficient Generative Inference of Large Language Models with Dynamic KV Cache Management (OSDI'24)☆152Updated last year
- Stateful LLM Serving☆81Updated 5 months ago
- DeeperGEMM: crazy optimized version☆70Updated 3 months ago
- ArkVale: Efficient Generative LLM Inference with Recallable Key-Value Eviction (NIPS'24)☆43Updated 8 months ago
- Scalable long-context LLM decoding that leverages sparsity—by treating the KV cache as a vector storage system.☆77Updated last week
- Tile-based language built for AI computation across all scales☆47Updated this week
- ☆78Updated 4 months ago
- SpInfer: Leveraging Low-Level Sparsity for Efficient Large Language Model Inference on GPUs☆57Updated 5 months ago
- NVSHMEM‑Tutorial: Build a DeepEP‑like GPU Buffer☆37Updated this week
- Explore Inter-layer Expert Affinity in MoE Model Inference☆13Updated last year
- nnScaler: Compiling DNN models for Parallel Training☆118Updated this week
- ☆63Updated 4 months ago
- DeepXTrace is a lightweight tool for precisely diagnosing slow ranks in DeepEP-based environments.☆47Updated this week
- Artifact for "Marconi: Prefix Caching for the Era of Hybrid LLMs" [MLSys '25 Outstanding Paper Award, Honorable Mention]☆21Updated 5 months ago