bytedance / InfiniStoreLinks
KV cache store for distributed LLM inference
☆361Updated last week
Alternatives and similar repositories for InfiniStore
Users that are interested in InfiniStore are comparing it to the libraries listed below
Sorting:
- Efficient and easy multi-instance LLM serving☆510Updated 2 months ago
- NVIDIA Inference Xfer Library (NIXL)☆721Updated this week
- Virtualized Elastic KV Cache for Dynamic GPU Sharing and Beyond☆661Updated 2 weeks ago
- ☆316Updated last week
- Perplexity GPU Kernels☆529Updated 2 weeks ago
- Fast OS-level support for GPU checkpoint and restore☆257Updated last month
- GLake: optimizing GPU memory management and IO transmission.☆489Updated 7 months ago
- MSCCL++: A GPU-driven communication stack for scalable AI applications☆437Updated this week
- A prefill & decode disaggregated LLM serving framework with shared GPU memory and fine-grained compute isolation.☆115Updated 6 months ago
- Dynamic Memory Management for Serving LLMs without PagedAttention☆436Updated 5 months ago
- High performance Transformer implementation in C++.☆142Updated 10 months ago
- torchcomms: a modern PyTorch communications API☆291Updated this week
- The driver for LMCache core to run in vLLM☆58Updated 9 months ago
- Genai-bench is a powerful benchmark tool designed for comprehensive token-level performance evaluation of large language model (LLM) serv…☆230Updated last week
- A low-latency & high-throughput serving engine for LLMs☆445Updated last month
- Offline optimization of your disaggregated Dynamo graph☆106Updated this week
- Materials for learning SGLang☆650Updated this week
- Disaggregated serving system for Large Language Models (LLMs).☆729Updated 7 months ago
- OME is a Kubernetes operator for enterprise-grade management and serving of Large Language Models (LLMs)☆312Updated last week
- DeepSeek-V3/R1 inference performance simulator☆168Updated 7 months ago
- DeepXTrace is a lightweight tool for precisely diagnosing slow ranks in DeepEP-based environments.☆67Updated 2 weeks ago
- Stateful LLM Serving☆88Updated 8 months ago
- Fast and memory-efficient exact attention☆99Updated this week
- ☆71Updated 10 months ago
- NVIDIA NVSHMEM is a parallel programming interface for NVIDIA GPUs based on OpenSHMEM. NVSHMEM can significantly reduce multi-process com…☆385Updated last week
- Perplexity open source garden for inference technology☆232Updated this week
- Train speculative decoding models effortlessly and port them smoothly to SGLang serving.☆483Updated this week
- A lightweight design for computation-communication overlap.☆187Updated last month
- Allow torch tensor memory to be released and resumed later☆167Updated last week
- PyTorch distributed training acceleration framework☆53Updated 3 months ago