bytedance / InfiniStoreLinks
KV cache store for distributed LLM inference
☆351Updated last month
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☆504Updated 2 months ago
- NVIDIA Inference Xfer Library (NIXL)☆688Updated this week
- Virtualized Elastic KV Cache for Dynamic GPU Sharing and Beyond☆469Updated this week
- ☆309Updated last month
- GLake: optimizing GPU memory management and IO transmission.☆486Updated 7 months ago
- Fast OS-level support for GPU checkpoint and restore☆252Updated last month
- Perplexity GPU Kernels☆513Updated this week
- A prefill & decode disaggregated LLM serving framework with shared GPU memory and fine-grained compute isolation.☆114Updated 5 months ago
- High performance Transformer implementation in C++.☆139Updated 9 months ago
- Dynamic Memory Management for Serving LLMs without PagedAttention☆432Updated 5 months ago
- Offline optimization of your disaggregated Dynamo graph☆88Updated this week
- Materials for learning SGLang☆626Updated last week
- DeepSeek-V3/R1 inference performance simulator☆170Updated 7 months ago
- A low-latency & high-throughput serving engine for LLMs☆431Updated 2 weeks ago
- Stateful LLM Serving☆87Updated 7 months ago
- Genai-bench is a powerful benchmark tool designed for comprehensive token-level performance evaluation of large language model (LLM) serv…☆225Updated last week
- ☆65Updated 9 months ago
- The driver for LMCache core to run in vLLM☆55Updated 8 months ago
- MSCCL++: A GPU-driven communication stack for scalable AI applications☆427Updated this week
- Disaggregated serving system for Large Language Models (LLMs).☆713Updated 6 months ago
- Train speculative decoding models effortlessly and port them smoothly to SGLang serving.☆451Updated this week
- OME is a Kubernetes operator for enterprise-grade management and serving of Large Language Models (LLMs)☆301Updated this week
- A lightweight design for computation-communication overlap.☆182Updated 3 weeks ago
- Fast and memory-efficient exact attention☆96Updated 2 weeks ago
- PyTorch distributed training acceleration framework☆53Updated 2 months ago
- ☆91Updated last week
- ☆90Updated 7 months ago
- DeepXTrace is a lightweight tool for precisely diagnosing slow ranks in DeepEP-based environments.☆65Updated last week
- Venus Collective Communication Library, supported by SII and Infrawaves.☆107Updated last week
- A fast communication-overlapping library for tensor/expert parallelism on GPUs.☆1,161Updated 2 months ago