vllm-project / routerLinks
A high-performance and light-weight router for vLLM large scale deployment
☆65Updated this week
Alternatives and similar repositories for router
Users that are interested in router are comparing it to the libraries listed below
Sorting:
- Genai-bench is a powerful benchmark tool designed for comprehensive token-level performance evaluation of large language model (LLM) serv…☆250Updated 3 weeks ago
- Allow torch tensor memory to be released and resumed later☆195Updated 3 weeks ago
- Train speculative decoding models effortlessly and port them smoothly to SGLang serving.☆577Updated this week
- ☆336Updated last week
- Efficient and easy multi-instance LLM serving☆519Updated 3 months ago
- Dynamic Memory Management for Serving LLMs without PagedAttention☆453Updated 7 months ago
- A low-latency & high-throughput serving engine for LLMs☆459Updated 2 months ago
- Offline optimization of your disaggregated Dynamo graph☆136Updated last week
- Fast and memory-efficient exact attention☆106Updated 2 weeks ago
- ArcticInference: vLLM plugin for high-throughput, low-latency inference☆357Updated this week
- A lightweight design for computation-communication overlap.☆206Updated last week
- Virtualized Elastic KV Cache for Dynamic GPU Sharing and Beyond☆730Updated last month
- Materials for learning SGLang☆703Updated 2 weeks ago
- Zero Bubble Pipeline Parallelism☆443Updated 7 months ago
- torchcomms: a modern PyTorch communications API☆314Updated this week
- Perplexity GPU Kernels☆547Updated last month
- NVIDIA Inference Xfer Library (NIXL)☆783Updated this week
- A prefill & decode disaggregated LLM serving framework with shared GPU memory and fine-grained compute isolation.☆121Updated last week
- PyTorch distributed training acceleration framework☆54Updated 4 months ago
- DeepXTrace is a lightweight tool for precisely diagnosing slow ranks in DeepEP-based environments.☆80Updated last week
- LLM training technologies developed by kwai☆67Updated last month
- Open Model Engine (OME) — Kubernetes operator for LLM serving, GPU scheduling, and model lifecycle management. Works with SGLang, vLLM, T…☆351Updated this week
- ☆127Updated last year
- Compare different hardware platforms via the Roofline Model for LLM inference tasks.☆119Updated last year
- KV cache store for distributed LLM inference☆378Updated last month
- Stateful LLM Serving☆91Updated 9 months ago
- ByteCheckpoint: An Unified Checkpointing Library for LFMs☆256Updated 3 weeks ago
- Accelerating MoE with IO and Tile-aware Optimizations☆469Updated last week
- Pipeline Parallelism Emulation and Visualization☆74Updated 6 months ago
- DLSlime: Flexible & Efficient Heterogeneous Transfer Toolkit☆87Updated last week