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:
- ☆83Updated 3 months ago
- Accelerating Large-Scale Reasoning Model Inference with Sparse Self-Speculative Decoding☆82Updated 2 months ago
- NVSHMEM‑Tutorial: Build a DeepEP‑like GPU Buffer☆158Updated 4 months ago
- Stateful LLM Serving☆95Updated 10 months ago
- [NeurIPS 2025] ClusterFusion: Expanding Operator Fusion Scope for LLM Inference via Cluster-Level Collective Primitive☆66Updated last month
- ☆78Updated last week
- Nex Venus Communication Library☆72Updated 2 months ago
- gLLM: Global Balanced Pipeline Parallelism System for Distributed LLM Serving with Token Throttling☆53Updated 3 weeks ago
- [NeurIPS 2024] Efficient LLM Scheduling by Learning to Rank☆69Updated last year
- ☆41Updated 3 months ago
- DLSlime: Flexible & Efficient Heterogeneous Transfer Toolkit☆92Updated this week
- Scalable long-context LLM decoding that leverages sparsity—by treating the KV cache as a vector storage system.☆119Updated last month
- ☆130Updated last year
- Building the Virtuous Cycle for AI-driven LLM Systems☆140Updated this week
- A framework for generating realistic LLM serving workloads☆98Updated 3 months ago
- DeepXTrace is a lightweight tool for precisely diagnosing slow ranks in DeepEP-based environments.☆91Updated 2 weeks ago
- A lightweight design for computation-communication overlap.☆213Updated last week
- [EuroSys'25] Mist: Efficient Distributed Training of Large Language Models via Memory-Parallelism Co-Optimization☆21Updated 5 months ago
- Tile-based language built for AI computation across all scales☆119Updated this week
- Accepted to MLSys 2026☆70Updated this week
- NEO is a LLM inference engine built to save the GPU memory crisis by CPU offloading☆81Updated 7 months ago
- ☆27Updated 10 months ago
- ArkVale: Efficient Generative LLM Inference with Recallable Key-Value Eviction (NIPS'24)☆52Updated last year
- Keyformer proposes KV Cache reduction through key tokens identification and without the need for fine-tuning☆59Updated last year
- Multi-Level Triton Runner supporting Python, IR, PTX, and cubin.☆84Updated this week
- ☆79Updated 3 years ago
- [NeurIPS'25 Spotlight] Adaptive Attention Sparsity with Hierarchical Top-p Pruning☆87Updated 2 months ago
- Artifact for "Marconi: Prefix Caching for the Era of Hybrid LLMs" [MLSys '25 Outstanding Paper Award, Honorable Mention]☆49Updated 10 months ago
- DeeperGEMM: crazy optimized version☆73Updated 8 months ago
- ☆50Updated 9 months ago