taco-project / FlexKVLinks
☆165Updated this week
Alternatives and similar repositories for FlexKV
Users that are interested in FlexKV are comparing it to the libraries listed below
Sorting:
- KV cache store for distributed LLM inference☆390Updated 2 months ago
- Efficient and easy multi-instance LLM serving☆524Updated 5 months ago
- NVIDIA Inference Xfer Library (NIXL)☆876Updated this week
- GLake: optimizing GPU memory management and IO transmission.☆497Updated 10 months ago
- Virtualized Elastic KV Cache for Dynamic GPU Sharing and Beyond☆773Updated this week
- ☆342Updated 2 weeks ago
- Open Model Engine (OME) — Kubernetes operator for LLM serving, GPU scheduling, and model lifecycle management. Works with SGLang, vLLM, T…☆365Updated last week
- Dynamic Memory Management for Serving LLMs without PagedAttention☆458Updated 8 months ago
- Fast OS-level support for GPU checkpoint and restore☆271Updated 4 months ago
- Disaggregated serving system for Large Language Models (LLMs).☆771Updated 10 months ago
- DeepSeek-V3/R1 inference performance simulator☆176Updated 10 months ago
- A low-latency & high-throughput serving engine for LLMs☆470Updated last month
- Research prototype of PRISM — a cost-efficient multi-LLM serving system with flexible time- and space-based GPU sharing.☆57Updated 5 months ago
- Offline optimization of your disaggregated Dynamo graph☆184Updated this week
- NVIDIA NCCL Tests for Distributed Training☆134Updated 2 weeks ago
- The driver for LMCache core to run in vLLM☆60Updated last year
- High performance Transformer implementation in C++.☆151Updated last year
- Genai-bench is a powerful benchmark tool designed for comprehensive token-level performance evaluation of large language model (LLM) serv…☆263Updated last week
- TePDist (TEnsor Program DISTributed) is an HLO-level automatic distributed system for DL models.☆99Updated 2 years ago
- AI Accelerator Benchmark focuses on evaluating AI Accelerators from a practical production perspective, including the ease of use and ver…☆298Updated 3 weeks ago
- MSCCL++: A GPU-driven communication stack for scalable AI applications☆462Updated this week
- Materials for learning SGLang☆738Updated last month
- DeepXTrace is a lightweight tool for precisely diagnosing slow ranks in DeepEP-based environments.☆92Updated 3 weeks ago
- torchcomms: a modern PyTorch communications API☆330Updated this week
- A high-performance and light-weight router for vLLM large scale deployment☆112Updated this week
- Fast and memory-efficient exact attention☆114Updated this week
- Byted PyTorch Distributed for Hyperscale Training of LLMs and RLs☆926Updated 2 months ago
- Stateful LLM Serving☆95Updated 11 months ago
- Persist and reuse KV Cache to speedup your LLM.☆250Updated this week
- A high-performance RL training-inference weight synchronization framework, designed to enable second-level parameter updates from trainin…☆131Updated last month