infinigence / Semi-PDLinks
A prefill & decode disaggregated LLM serving framework with shared GPU memory and fine-grained compute isolation.
☆103Updated 2 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.☆154Updated last month
- High performance Transformer implementation in C++.☆128Updated 6 months ago
- DeepSeek-V3/R1 inference performance simulator☆156Updated 4 months ago
- ☆81Updated 4 months ago
- Paella: Low-latency Model Serving with Virtualized GPU Scheduling☆60Updated last year
- Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“☆62Updated last year
- ⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, Achieve Peak⚡️ Performance.☆91Updated 2 months ago
- Stateful LLM Serving☆77Updated 4 months ago
- Compare different hardware platforms via the Roofline Model for LLM inference tasks.☆110Updated last year
- AI Accelerator Benchmark focuses on evaluating AI Accelerators from a practical production perspective, including the ease of use and ver…☆254Updated last month
- PyTorch distributed training acceleration framework☆51Updated 5 months ago
- ☆89Updated 2 months ago
- ☆149Updated 6 months ago
- ☆80Updated last week
- ☆65Updated last year
- Summary of some awesome work for optimizing LLM inference☆88Updated last month
- ☆96Updated 10 months ago
- ☆24Updated last week
- Aims to implement dual-port and multi-qp solutions in deepEP ibrc transport☆57Updated 2 months ago
- Summary of the Specs of Commonly Used GPUs for Training and Inference of LLM☆53Updated 4 months ago
- ☆109Updated 8 months ago
- ☆37Updated 7 months ago
- A standalone GEMM kernel for fp16 activation and quantized weight, extracted from FasterTransformer☆93Updated 2 weeks ago
- We invite you to visit and follow our new repository at https://github.com/microsoft/TileFusion. TiledCUDA is a highly efficient kernel …☆183Updated 6 months ago
- DeeperGEMM: crazy optimized version☆70Updated 2 months ago
- Efficient and easy multi-instance LLM serving☆454Updated this week
- gLLM: Global Balanced Pipeline Parallelism System for Distributed LLM Serving with Token Throttling☆36Updated this week
- FlexFlow Serve: Low-Latency, High-Performance LLM Serving☆48Updated last week
- ☆101Updated 7 months ago
- nnScaler: Compiling DNN models for Parallel Training☆114Updated this week