infinigence / Semi-PDLinks
A prefill & decode disaggregated LLM serving framework with shared GPU memory and fine-grained compute isolation.
☆104Updated 3 months ago
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.☆155Updated last week
- ☆84Updated 4 months ago
- High performance Transformer implementation in C++.☆129Updated 7 months ago
- DeepSeek-V3/R1 inference performance simulator☆165Updated 4 months ago
- Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“☆62Updated last year
- Stateful LLM Serving☆81Updated 5 months ago
- ☆97Updated 11 months ago
- Compare different hardware platforms via the Roofline Model for LLM inference tasks.☆111Updated last year
- Paella: Low-latency Model Serving with Virtualized GPU Scheduling☆60Updated last year
- PyTorch distributed training acceleration framework☆51Updated last week
- Summary of the Specs of Commonly Used GPUs for Training and Inference of LLM☆62Updated last week
- ☆98Updated 3 months ago
- ☆150Updated 7 months ago
- ⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, Achieve Peak⚡️ Performance.☆100Updated 3 months ago
- AI Accelerator Benchmark focuses on evaluating AI Accelerators from a practical production perspective, including the ease of use and ver…☆257Updated this week
- ☆84Updated last week
- FlexFlow Serve: Low-Latency, High-Performance LLM Serving☆52Updated 3 weeks ago
- A standalone GEMM kernel for fp16 activation and quantized weight, extracted from FasterTransformer☆94Updated 2 weeks ago
- Aims to implement dual-port and multi-qp solutions in deepEP ibrc transport☆59Updated 3 months ago
- ☆68Updated last year
- ☆279Updated last week
- ☆113Updated 9 months ago
- ☆47Updated 8 months ago
- ☆92Updated 4 months ago
- Fast and memory-efficient exact attention☆87Updated last week
- gLLM: Global Balanced Pipeline Parallelism System for Distributed LLM Serving with Token Throttling☆37Updated last week
- nnScaler: Compiling DNN models for Parallel Training☆115Updated this week
- Tile-based language built for AI computation across all scales☆46Updated this week
- ☆39Updated last year
- ☆106Updated 7 months ago