FlexFusion / FlexFusionLinks
The official implementation for the intra-stage fusion technique introduced in https://arxiv.org/abs/2409.13221
☆25Updated 5 months ago
Alternatives and similar repositories for FlexFusion
Users that are interested in FlexFusion are comparing it to the libraries listed below
Sorting:
- Virtualized Elastic KV Cache for Dynamic GPU Sharing and Beyond☆103Updated this week
- [NeurIPS 2024] Efficient LLM Scheduling by Learning to Rank☆60Updated 11 months ago
- NVSHMEM‑Tutorial: Build a DeepEP‑like GPU Buffer☆138Updated last month
- ☆72Updated last year
- gLLM: Global Balanced Pipeline Parallelism System for Distributed LLM Serving with Token Throttling☆41Updated 2 weeks ago
- ☆124Updated 11 months ago
- ☆65Updated 5 months ago
- Debug print operator for cudagraph debugging☆14Updated last year
- A GPU-optimized system for efficient long-context LLMs decoding with low-bit KV cache.☆60Updated last week
- ☆52Updated 4 months ago
- ☆25Updated 6 months ago
- ☆42Updated 5 months ago
- High performance Transformer implementation in C++.☆135Updated 9 months ago
- [NeurIPS 2025] ClusterFusion: Expanding Operator Fusion Scope for LLM Inference via Cluster-Level Collective Primitive☆43Updated 3 weeks ago
- Stateful LLM Serving☆86Updated 7 months ago
- A lightweight design for computation-communication overlap.☆181Updated last week
- [DAC'25] Official implement of "HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inference"☆72Updated 4 months ago
- nnScaler: Compiling DNN models for Parallel Training☆118Updated 3 weeks ago
- DLSlime: Flexible & Efficient Heterogeneous Transfer Toolkit☆68Updated last week
- Artifact for "Marconi: Prefix Caching for the Era of Hybrid LLMs" [MLSys '25 Outstanding Paper Award, Honorable Mention]☆39Updated 7 months ago
- Tile-based language built for AI computation across all scales☆66Updated 2 weeks ago
- SpInfer: Leveraging Low-Level Sparsity for Efficient Large Language Model Inference on GPUs☆59Updated 6 months ago
- ArkVale: Efficient Generative LLM Inference with Recallable Key-Value Eviction (NIPS'24)☆43Updated 10 months ago
- [OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable☆186Updated last year
- Scalable long-context LLM decoding that leverages sparsity—by treating the KV cache as a vector storage system.☆88Updated last month
- Implement Flash Attention using Cute.☆96Updated 10 months ago
- A framework for generating realistic LLM serving workloads☆67Updated last week
- [ICML 2024] Serving LLMs on heterogeneous decentralized clusters.☆30Updated last year
- DeeperGEMM: crazy optimized version☆72Updated 5 months ago
- Distributed MoE in a Single Kernel [NeurIPS '25]☆85Updated 2 weeks ago