uccl-project / ucclLinks
Ultra and Unified CCL
☆459Updated this week
Alternatives and similar repositories for uccl
Users that are interested in uccl are comparing it to the libraries listed below
Sorting:
- MSCCL++: A GPU-driven communication stack for scalable AI applications☆394Updated this week
- NCCL Profiling Kit☆140Updated last year
- Microsoft Collective Communication Library☆353Updated last year
- NVIDIA Inference Xfer Library (NIXL)☆502Updated this week
- DeepSeek-V3/R1 inference performance simulator☆158Updated 4 months ago
- Perplexity GPU Kernels☆418Updated 2 weeks ago
- An interference-aware scheduler for fine-grained GPU sharing☆142Updated 6 months ago
- Efficient and easy multi-instance LLM serving☆454Updated this week
- Dynamic Memory Management for Serving LLMs without PagedAttention☆405Updated 2 months ago
- A lightweight design for computation-communication overlap.☆155Updated last month
- ☆83Updated 4 months ago
- A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems☆190Updated last week
- High performance Transformer implementation in C++.☆129Updated 6 months ago
- nnScaler: Compiling DNN models for Parallel Training☆114Updated this week
- A low-latency & high-throughput serving engine for LLMs☆400Updated 2 months ago
- Fast OS-level support for GPU checkpoint and restore☆225Updated last week
- Synthesizer for optimal collective communication algorithms☆111Updated last year
- Thunder Research Group's Collective Communication Library☆39Updated 3 weeks ago
- Paella: Low-latency Model Serving with Virtualized GPU Scheduling☆60Updated last year
- Here are my personal paper reading notes (including cloud computing, resource management, systems, machine learning, deep learning, and o…☆115Updated this week
- ☆102Updated 7 months ago
- Curated collection of papers in machine learning systems☆388Updated last month
- ☆209Updated this week
- This repository is established to store personal notes and annotated papers during daily research.☆138Updated last week
- Disaggregated serving system for Large Language Models (LLMs).☆654Updated 4 months ago
- A prefill & decode disaggregated LLM serving framework with shared GPU memory and fine-grained compute isolation.☆103Updated 2 months ago
- Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“☆62Updated last year
- AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving (OSDI 23)☆83Updated 2 years ago
- KV cache store for distributed LLM inference☆303Updated 2 months ago
- NCCL Fast Socket is a transport layer plugin to improve NCCL collective communication performance on Google Cloud.☆119Updated last year