bytedance / InfiniStoreLinks
KV cache store for distributed LLM inference
☆341Updated 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☆494Updated last month
- NVIDIA Inference Xfer Library (NIXL)☆663Updated this week
- Ultra and Unified CCL☆578Updated this week
- ☆304Updated last week
- Fast OS-level support for GPU checkpoint and restore☆238Updated 2 weeks ago
- Perplexity GPU Kernels☆482Updated 3 weeks ago
- GLake: optimizing GPU memory management and IO transmission.☆479Updated 6 months ago
- A prefill & decode disaggregated LLM serving framework with shared GPU memory and fine-grained compute isolation.☆111Updated 4 months ago
- A low-latency & high-throughput serving engine for LLMs☆425Updated 4 months ago
- Dynamic Memory Management for Serving LLMs without PagedAttention☆424Updated 4 months ago
- High performance Transformer implementation in C++.☆135Updated 8 months ago
- Genai-bench is a powerful benchmark tool designed for comprehensive token-level performance evaluation of large language model (LLM) serv…☆219Updated last week
- DeepSeek-V3/R1 inference performance simulator☆169Updated 6 months ago
- MSCCL++: A GPU-driven communication stack for scalable AI applications☆417Updated this week
- Materials for learning SGLang☆597Updated last week
- Disaggregated serving system for Large Language Models (LLMs).☆700Updated 6 months ago
- The driver for LMCache core to run in vLLM☆52Updated 8 months ago
- Stateful LLM Serving☆85Updated 7 months ago
- A lightweight design for computation-communication overlap.☆179Updated 3 weeks ago
- NVIDIA NVSHMEM is a parallel programming interface for NVIDIA GPUs based on OpenSHMEM. NVSHMEM can significantly reduce multi-process com…☆328Updated 3 weeks ago
- Train speculative decoding models effortlessly and port them smoothly to SGLang serving.☆417Updated last week
- ☆91Updated last week
- DeepXTrace is a lightweight tool for precisely diagnosing slow ranks in DeepEP-based environments.☆60Updated this week
- A fast communication-overlapping library for tensor/expert parallelism on GPUs.☆1,142Updated last month
- ☆60Updated 9 months ago
- PyTorch distributed training acceleration framework☆52Updated 2 months ago
- Fast and memory-efficient exact attention☆94Updated this week
- Offline optimization of your disaggregated Dynamo graph☆72Updated this week
- Serverless LLM Serving for Everyone.☆555Updated last month
- OME is a Kubernetes operator for enterprise-grade management and serving of Large Language Models (LLMs)☆287Updated this week