infinigence / Semi-PDLinks
A prefill & decode disaggregated LLM serving framework with shared GPU memory and fine-grained compute isolation.
☆111Updated 4 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.☆177Updated 2 weeks ago
- NVSHMEM‑Tutorial: Build a DeepEP‑like GPU Buffer☆130Updated 2 weeks ago
- Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“☆62Updated last year
- High performance Transformer implementation in C++.☆134Updated 8 months ago
- ☆85Updated 6 months ago
- DeepSeek-V3/R1 inference performance simulator☆170Updated 6 months ago
- DLSlime: Flexible & Efficient Heterogeneous Transfer Toolkit☆66Updated this week
- ☆98Updated last year
- Stateful LLM Serving☆85Updated 6 months ago
- FlexFlow Serve: Low-Latency, High-Performance LLM Serving☆61Updated 2 weeks ago
- ☆298Updated last week
- ☆106Updated 4 months ago
- Paella: Low-latency Model Serving with Virtualized GPU Scheduling☆62Updated last year
- Summary of the Specs of Commonly Used GPUs for Training and Inference of LLM☆63Updated last month
- PyTorch distributed training acceleration framework☆53Updated last month
- Aims to implement dual-port and multi-qp solutions in deepEP ibrc transport☆63Updated 4 months ago
- DeepXTrace is a lightweight tool for precisely diagnosing slow ranks in DeepEP-based environments.☆54Updated last week
- ☆88Updated last week
- ☆72Updated last year
- ⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, Achieve Peak⚡️ Performance.☆118Updated 4 months ago
- Compare different hardware platforms via the Roofline Model for LLM inference tasks.☆115Updated last year
- [USENIX ATC '24] Accelerating the Training of Large Language Models using Efficient Activation Rematerialization and Optimal Hybrid Paral…☆65Updated last year
- ☆150Updated 8 months ago
- ☆123Updated 10 months ago
- ☆46Updated 9 months ago
- kvcached: Elastic KV cache for dynamic GPU sharing and efficient multi-LLM inference.☆94Updated this week
- Summary of some awesome work for optimizing LLM inference☆111Updated 4 months ago
- Automated Parallelization System and Infrastructure for Multiple Ecosystems☆80Updated 10 months ago
- gLLM: Global Balanced Pipeline Parallelism System for Distributed LLM Serving with Token Throttling☆41Updated this week
- AI Accelerator Benchmark focuses on evaluating AI Accelerators from a practical production perspective, including the ease of use and ver…☆266Updated last month