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:
- NVSHMEM‑Tutorial: Build a DeepEP‑like GPU Buffer☆128Updated last week
- [NeurIPS 2024] Efficient LLM Scheduling by Learning to Rank☆59Updated 10 months ago
- [DAC'25] Official implement of "HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inference"☆71Updated 3 months ago
- kvcached: Elastic KV cache for dynamic GPU sharing and efficient multi-LLM inference.☆93Updated this week
- ☆71Updated last year
- DLSlime: Flexible & Efficient Heterogeneous Transfer Toolkit☆67Updated this week
- DeepXTrace is a lightweight tool for precisely diagnosing slow ranks in DeepEP-based environments.☆51Updated last week
- ArkVale: Efficient Generative LLM Inference with Recallable Key-Value Eviction (NIPS'24)☆43Updated 9 months ago
- A GPU-optimized system for efficient long-context LLMs decoding with low-bit KV cache.☆59Updated 3 weeks ago
- High performance Transformer implementation in C++.☆134Updated 8 months ago
- A lightweight design for computation-communication overlap.☆171Updated last week
- ☆55Updated last year
- ☆64Updated 5 months ago
- DeeperGEMM: crazy optimized version☆70Updated 4 months ago
- Artifact for "Marconi: Prefix Caching for the Era of Hybrid LLMs" [MLSys '25 Outstanding Paper Award, Honorable Mention]☆32Updated 6 months ago
- Stateful LLM Serving☆85Updated 6 months ago
- SpInfer: Leveraging Low-Level Sparsity for Efficient Large Language Model Inference on GPUs☆57Updated 6 months ago
- ☆24Updated 6 months ago
- Triton multi-level runner, include IR/PTX/cubin.☆54Updated this week
- gLLM: Global Balanced Pipeline Parallelism System for Distributed LLM Serving with Token Throttling☆41Updated last week
- Tile-based language built for AI computation across all scales☆59Updated last week
- [OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable☆183Updated last year
- Triton adapter for Ascend. Mirror of https://gitee.com/ascend/triton-ascend☆74Updated this week
- ☆42Updated 4 months ago
- ☆123Updated 10 months ago
- Implement Flash Attention using Cute.☆95Updated 9 months ago
- [NeurIPS 2025] ClusterFusion: Expanding Operator Fusion Scope for LLM Inference via Cluster-Level Collective Primitive☆18Updated last week
- ☆39Updated last year
- [ICML 2024] Serving LLMs on heterogeneous decentralized clusters.☆30Updated last year
- Scalable long-context LLM decoding that leverages sparsity—by treating the KV cache as a vector storage system.☆81Updated last week