uccl-project / ucclLinks
Ultra and Unified CCL
☆390Updated 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☆385Updated this week
- Microsoft Collective Communication Library☆351Updated last year
- NCCL Profiling Kit☆139Updated last year
- NVIDIA Inference Xfer Library (NIXL)☆459Updated this week
- DeepSeek-V3/R1 inference performance simulator☆154Updated 3 months ago
- Perplexity GPU Kernels☆395Updated last month
- High performance Transformer implementation in C++.☆125Updated 5 months ago
- A lightweight design for computation-communication overlap.☆146Updated 3 weeks ago
- Efficient and easy multi-instance LLM serving☆448Updated this week
- Dynamic Memory Management for Serving LLMs without PagedAttention☆401Updated last month
- nnScaler: Compiling DNN models for Parallel Training☆113Updated last week
- An interference-aware scheduler for fine-grained GPU sharing☆141Updated 5 months ago
- ☆79Updated 3 months ago
- ☆94Updated 6 months ago
- Fast OS-level support for GPU checkpoint and restore☆212Updated 3 weeks ago
- KV cache store for distributed LLM inference☆288Updated last month
- Paella: Low-latency Model Serving with Virtualized GPU Scheduling☆59Updated last year
- Synthesizer for optimal collective communication algorithms☆108Updated last year
- Here are my personal paper reading notes (including cloud computing, resource management, systems, machine learning, deep learning, and o…☆114Updated 2 weeks ago
- A low-latency & high-throughput serving engine for LLMs☆388Updated last month
- Since the emergence of chatGPT in 2022, the acceleration of Large Language Model has become increasingly important. Here is a list of pap…☆256Updated 4 months ago
- Thunder Research Group's Collective Communication Library☆38Updated last week
- A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems☆181Updated 9 months ago
- FlexFlow Serve: Low-Latency, High-Performance LLM Serving☆48Updated 2 months ago
- Microsoft Collective Communication Library☆64Updated 7 months ago
- A prefill & decode disaggregated LLM serving framework with shared GPU memory and fine-grained compute isolation.☆95Updated last month
- NCCL Fast Socket is a transport layer plugin to improve NCCL collective communication performance on Google Cloud.☆117Updated last year
- ☆123Updated 2 months ago
- Stateful LLM Serving☆76Updated 4 months ago
- ☆79Updated 2 years ago