infinigence / Semi-PDLinks
A prefill & decode disaggregated LLM serving framework with shared GPU memory and fine-grained compute isolation.
☆93Updated last month
Alternatives and similar repositories for Semi-PD
Users that are interested in Semi-PD are comparing it to the libraries listed below
Sorting:
- A lightweight design for computation-communication overlap.☆146Updated 3 weeks ago
- DeepSeek-V3/R1 inference performance simulator☆154Updated 3 months ago
- High performance Transformer implementation in C++.☆125Updated 5 months ago
- AI Accelerator Benchmark focuses on evaluating AI Accelerators from a practical production perspective, including the ease of use and ver…☆249Updated 2 weeks ago
- Summary of the Specs of Commonly Used GPUs for Training and Inference of LLM☆50Updated 3 months ago
- Paella: Low-latency Model Serving with Virtualized GPU Scheduling☆59Updated last year
- Compare different hardware platforms via the Roofline Model for LLM inference tasks.☆107Updated last year
- Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“☆61Updated last year
- ☆79Updated 3 months ago
- Stateful LLM Serving☆73Updated 4 months ago
- PyTorch distributed training acceleration framework☆51Updated 5 months ago
- Automated Parallelization System and Infrastructure for Multiple Ecosystems☆79Updated 7 months ago
- ☆96Updated 10 months ago
- ☆37Updated 7 months ago
- ☆82Updated last month
- ☆149Updated 6 months ago
- ☆78Updated this week
- ⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, Achieve Peak⚡️ Performance.☆86Updated 2 months ago
- nnScaler: Compiling DNN models for Parallel Training☆113Updated this week
- FlexFlow Serve: Low-Latency, High-Performance LLM Serving☆48Updated 2 months ago
- ☆87Updated 3 months ago
- Fast and memory-efficient exact attention☆80Updated this week
- ☆64Updated last year
- Dynamic Memory Management for Serving LLMs without PagedAttention☆401Updated last month
- A low-latency & high-throughput serving engine for LLMs☆388Updated last month
- We invite you to visit and follow our new repository at https://github.com/microsoft/TileFusion. TiledCUDA is a highly efficient kernel …☆183Updated 5 months ago
- Efficient and easy multi-instance LLM serving☆445Updated this week
- ☆106Updated 8 months ago
- KV cache store for distributed LLM inference☆288Updated last month
- ☆94Updated 6 months ago