ai-dynamo / nixl
NVIDIA Inference Xfer Library (NIXL)
☆191Updated this week
Alternatives and similar repositories for nixl:
Users that are interested in nixl are comparing it to the libraries listed below
- DeepSeek-V3/R1 inference performance simulator☆76Updated this week
- Efficient and easy multi-instance LLM serving☆348Updated this week
- NCCL Profiling Kit☆128Updated 8 months ago
- A low-latency & high-throughput serving engine for LLMs☆327Updated last month
- Dynamic Memory Management for Serving LLMs without PagedAttention☆326Updated this week
- MSCCL++: A GPU-driven communication stack for scalable AI applications☆315Updated this week
- High performance Transformer implementation in C++.☆111Updated 2 months ago
- ☆49Updated 2 weeks ago
- KV cache store for distributed LLM inference☆78Updated this week
- Microsoft Collective Communication Library☆60Updated 4 months ago
- Paella: Low-latency Model Serving with Virtualized GPU Scheduling☆58Updated 10 months ago
- NCCL Fast Socket is a transport layer plugin to improve NCCL collective communication performance on Google Cloud.☆116Updated last year
- ☆36Updated 3 months ago
- Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“☆60Updated 9 months ago
- Microsoft Collective Communication Library☆343Updated last year
- RDMA and SHARP plugins for nccl library☆184Updated this week
- Fast OS-level support for GPU checkpoint and restore☆169Updated 3 weeks ago
- Zero Bubble Pipeline Parallelism☆373Updated 3 weeks ago
- ☆57Updated 3 months ago
- A tool for bandwidth measurements on NVIDIA GPUs.☆392Updated last month
- CUDA checkpoint and restore utility☆315Updated 2 months ago
- Synthesizer for optimal collective communication algorithms☆106Updated 11 months ago
- Stateful LLM Serving☆50Updated 2 weeks ago
- [OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable☆150Updated 6 months ago
- SpotServe: Serving Generative Large Language Models on Preemptible Instances☆112Updated last year
- PyTorch distributed training acceleration framework☆46Updated last month
- NVIDIA Resiliency Extension is a python package for framework developers and users to implement fault-tolerant features. It improves the …☆109Updated this week
- Disaggregated serving system for Large Language Models (LLMs).☆507Updated 7 months ago
- ☆90Updated 4 months ago
- FlexFlow Serve: Low-Latency, High-Performance LLM Serving☆29Updated this week