FlexFlow Serve: Low-Latency, High-Performance LLM Serving
☆75Sep 15, 2025Updated 6 months ago
Alternatives and similar repositories for flexflow-serve
Users that are interested in flexflow-serve are comparing it to the libraries listed below
Sorting:
- ☆13Jan 7, 2025Updated last year
- Development repository for integrating FlexFlow (A distributed deep learning framework that supports flexible parallelization strategies)…☆29Oct 12, 2021Updated 4 years ago
- Automatically Discovering Fast Parallelization Strategies for Distributed Deep Neural Network Training☆1,864Mar 12, 2026Updated last week
- Vortex: A Flexible and Efficient Sparse Attention Framework☆49Jan 21, 2026Updated 2 months ago
- PoC for "SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning" [NeurIPS '25]☆67Oct 2, 2025Updated 5 months ago
- Prefix-Aware Attention for LLM Decoding☆31Jan 23, 2026Updated last month
- A throughput-oriented high-performance serving framework for LLMs☆949Oct 29, 2025Updated 4 months ago
- An Attention Superoptimizer☆22Jan 20, 2025Updated last year
- Dynamic Memory Management for Serving LLMs without PagedAttention☆466May 30, 2025Updated 9 months ago
- scalable and robust tree-based speculative decoding algorithm☆372Jan 28, 2025Updated last year
- Compression for Foundation Models☆35Jul 21, 2025Updated 7 months ago
- [SIGMOD 2025] PQCache: Product Quantization-based KVCache for Long Context LLM Inference☆83Dec 7, 2025Updated 3 months ago
- High performance Transformer implementation in C++.☆153Jan 18, 2025Updated last year
- [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention☆53Aug 6, 2025Updated 7 months ago
- Performance of the C++ interface of flash attention and flash attention v2 in large language model (LLM) inference scenarios.☆43Feb 27, 2025Updated last year
- A tiny yet powerful LLM inference system tailored for researching purpose. vLLM-equivalent performance with only 2k lines of code (2% of …☆320Jun 10, 2025Updated 9 months ago
- SpotServe: Serving Generative Large Language Models on Preemptible Instances☆134Feb 22, 2024Updated 2 years ago
- ☆131Nov 11, 2024Updated last year
- Artifact for "Marconi: Prefix Caching for the Era of Hybrid LLMs" [MLSys '25 Outstanding Paper Award, Honorable Mention]☆57Mar 5, 2025Updated last year
- ☆169Jul 15, 2025Updated 8 months ago
- [COLM 2024] SKVQ: Sliding-window Key and Value Cache Quantization for Large Language Models☆24Oct 5, 2024Updated last year
- Multiple GEMM operators are constructed with cutlass to support LLM inference.☆19Aug 3, 2025Updated 7 months ago
- ☆12Sep 16, 2025Updated 6 months ago
- Efficient and easy multi-instance LLM serving☆532Mar 12, 2026Updated last week
- Mirage Persistent Kernel: Compiling LLMs into a MegaKernel☆2,159Updated this week
- ☆12Oct 16, 2022Updated 3 years ago
- AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving (OSDI 23)☆94Jul 14, 2023Updated 2 years ago
- LLM Inference on consumer devices☆130Mar 17, 2025Updated last year
- ☆15Apr 29, 2025Updated 10 months ago
- Stateful LLM Serving☆97Mar 11, 2025Updated last year
- ☆12Dec 1, 2023Updated 2 years ago
- ☆19Jun 17, 2022Updated 3 years ago
- ☆97Mar 26, 2025Updated 11 months ago
- Decoding Attention is specially optimized for MHA, MQA, GQA and MLA using CUDA core for the decoding stage of LLM inference.☆45Jun 11, 2025Updated 9 months ago
- ☆17May 10, 2024Updated last year
- ☆20Jun 9, 2025Updated 9 months ago
- ☆46Mar 15, 2025Updated last year
- Standalone Flash Attention v2 kernel without libtorch dependency☆112Sep 10, 2024Updated last year
- TLLM_QMM strips the implementation of quantized kernels of Nvidia's TensorRT-LLM, removing NVInfer dependency and exposes ease of use Pyt…☆16Jul 5, 2024Updated last year