FlexFusion / FlexFusionLinks
The official implementation for the intra-stage fusion technique introduced in https://arxiv.org/abs/2409.13221
☆29Updated 9 months ago
Alternatives and similar repositories for FlexFusion
Users that are interested in FlexFusion are comparing it to the libraries listed below
Sorting:
- Accelerating Large-Scale Reasoning Model Inference with Sparse Self-Speculative Decoding☆87Updated 2 months ago
- High performance Transformer implementation in C++.☆150Updated last year
- ☆85Updated 3 months ago
- [NeurIPS 2025] ClusterFusion: Expanding Operator Fusion Scope for LLM Inference via Cluster-Level Collective Primitive☆66Updated 2 months ago
- [NeurIPS 2024] Efficient LLM Scheduling by Learning to Rank☆69Updated last year
- ☆27Updated 10 months ago
- ☆131Updated last year
- Stateful LLM Serving☆95Updated 11 months ago
- ☆79Updated 3 years ago
- NVSHMEM‑Tutorial: Build a DeepEP‑like GPU Buffer☆161Updated 4 months ago
- ☆41Updated 3 months ago
- gLLM: Global Balanced Pipeline Parallelism System for Distributed LLM Serving with Token Throttling☆53Updated 3 weeks ago
- Learning TileLang with 10 puzzles!☆118Updated last week
- A lightweight design for computation-communication overlap.☆219Updated 3 weeks ago
- DeepXTrace is a lightweight tool for precisely diagnosing slow ranks in DeepEP-based environments.☆92Updated 3 weeks ago
- Building the Virtuous Cycle for AI-driven LLM Systems☆151Updated last week
- DLSlime: Flexible & Efficient Heterogeneous Transfer Toolkit☆92Updated 2 weeks ago
- A NCCL extension library, designed to efficiently offload GPU memory allocated by the NCCL communication library.☆90Updated last month
- ☆51Updated 9 months ago
- [EuroSys'25] Mist: Efficient Distributed Training of Large Language Models via Memory-Parallelism Co-Optimization☆21Updated this week
- [OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable☆209Updated last year
- [ICML 2024] Serving LLMs on heterogeneous decentralized clusters.☆34Updated last year
- Nex Venus Communication Library☆72Updated 2 months ago
- ☆80Updated 2 weeks ago
- ☆65Updated 9 months ago
- Tile-based language built for AI computation across all scales☆120Updated this week
- [DAC'25] Official implement of "HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inference"☆101Updated last month
- High-performance distributed data shuffling (all-to-all) library for MoE training and inference☆112Updated last month
- A framework for generating realistic LLM serving workloads☆100Updated 4 months ago
- Allow torch tensor memory to be released and resumed later☆216Updated 3 weeks ago