[NeurIPS 2025] ClusterFusion: Expanding Operator Fusion Scope for LLM Inference via Cluster-Level Collective Primitive
☆66Dec 11, 2025Updated 3 months ago
Alternatives and similar repositories for ClusterFusion
Users that are interested in ClusterFusion are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆18Mar 4, 2025Updated last year
- ☆36Dec 9, 2025Updated 3 months ago
- ☆18Apr 21, 2024Updated last year
- MAGIS: Memory Optimization via Coordinated Graph Transformation and Scheduling for DNN (ASPLOS'24)☆57May 29, 2024Updated last year
- a simple API to use CUPTI☆10Aug 19, 2025Updated 7 months ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click and start building anything your business needs.
- Tacker: Tensor-CUDA Core Kernel Fusion for Improving the GPU Utilization while Ensuring QoS☆34Feb 10, 2025Updated last year
- libsmctrl论文的复现，添加了python端接口，可以在python端灵活调用接口来分配计算资源☆12May 21, 2024Updated last year
- A collection of specialized agent skills for AI infrastructure development, enabling Claude Code to write, optimize, and debug high-perfo…☆96Feb 2, 2026Updated last month
- ☆12Jun 29, 2024Updated last year
- ☆15Jun 26, 2024Updated last year
- ☆234Nov 19, 2025Updated 4 months ago
- A lightweight design for computation-communication overlap.☆225Jan 20, 2026Updated 2 months ago
- ☆145Dec 19, 2025Updated 3 months ago
- Utility scripts for PyTorch (e.g. Make Perfetto show some disappearing kernels, Memory profiler that understands more low-level allocatio…☆94Sep 11, 2025Updated 6 months ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click and start building anything your business needs.
- fft impl for ff::Field☆17May 9, 2024Updated last year
- Compiler for Dynamic Neural Networks☆45Nov 13, 2023Updated 2 years ago
- Medusa: Accelerating Serverless LLM Inference with Materialization [ASPLOS'25]☆42May 13, 2025Updated 10 months ago
- ☆131Nov 11, 2024Updated last year
- STREAMer: Benchmarking remote volatile and non-volatile memory bandwidth☆17Aug 21, 2023Updated 2 years ago
- DeeperGEMM: crazy optimized version☆75May 5, 2025Updated 10 months ago
- Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“☆63Jun 5, 2024Updated last year
- (WIP) Parallel inference for black-forest-labs' FLUX model.☆19Nov 18, 2024Updated last year
- ☆43Oct 15, 2025Updated 5 months ago
- DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- ☆38Aug 7, 2025Updated 7 months ago
- ☆52May 19, 2025Updated 10 months ago
- tutorials about polyhedral compilation.☆61Feb 9, 2026Updated last month
- Boosting GPU utilization for LLM serving via dynamic spatial-temporal prefill & decode orchestration☆39Jan 8, 2026Updated 2 months ago
- Tilus is a tile-level kernel programming language with explicit control over shared memory and registers.☆456Mar 17, 2026Updated last week
- A Easy-to-understand TensorOp Matmul Tutorial☆422Mar 5, 2026Updated 3 weeks ago
- ☆16Feb 13, 2026Updated last month
- ☆13Apr 27, 2022Updated 3 years ago
- A low-latency & high-throughput serving engine for LLMs☆486Jan 8, 2026Updated 2 months ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- Source code of "FlowWalker: A Memory-efficient and High-performance GPU-based Dynamic Graph Random Walk Framework"☆11Oct 23, 2024Updated last year
- Efficient GPU communication over multiple NICs.☆26Nov 20, 2025Updated 4 months ago
- GLake: optimizing GPU memory management and IO transmission.☆498Mar 24, 2025Updated last year
- An auxiliary project analysis of the characteristics of KV in DiT Attention.☆34Nov 29, 2024Updated last year
- An ultra-fast, distributed Safetensors loader☆31Updated this week
- Distributed MoE in a Single Kernel [NeurIPS '25]☆210Mar 19, 2026Updated last week
- A throughput-oriented high-performance serving framework for LLMs☆950Oct 29, 2025Updated 4 months ago