Engine-agnostic LLM gateway in Rust. Full OpenAI & Anthropic API compatibility across vLLM, TRT-LLM, TokenSpeed, SGLang, OpenAI, Gemini & more. Industry-first gRPC pipeline, KV cache-aware routing, chat history, tokenization caching, Responses API, embeddings, WASM plugins, MCP, and multi-tenant auth.
☆712Nov 11, 2026Updated this week
Alternatives and similar repositories for smg
Users that are interested in smg are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- TokenSpeed is a speed-of-light LLM inference engine.☆2,918Updated this week
- Open Model Engine (OME) — Kubernetes operator for LLM serving, GPU scheduling, and model lifecycle management. Works with SGLang, vLLM, T…☆524Updated this week
- A PyTorch native library for training speculative decoding models☆267Updated this week
- Genai-bench is a powerful benchmark tool designed for comprehensive token-level performance evaluation of large language model (LLM) serv…☆335Oct 14, 2026Updated 3 weeks ago
- A high-performance and light-weight router for vLLM large scale deployment☆511Updated this week
- End-to-end encrypted cloud storage - Proton Drive • AdSpecial offer: 40% Off Yearly / 80% Off First Month. Protect your most important files, photos, and documents from prying eyes.
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆7,024Updated this week
- A Datacenter Scale Distributed Inference Serving Framework☆8,470Updated this week
- High-performance Rust benchmark client for vLLM serving endpoints.☆53Aug 3, 2026Updated 3 months ago
- High-performance KV cache storage for LLM inference — GPU offloading, SSD caching, and cross-node sharing via RDMA. Works with vLLM and S…☆221Updated this week
- FlashInfer: Kernel Library for LLM Serving☆6,897Updated this week
- NVIDIA Inference Xfer Library (NIXL)☆1,363Updated this week
- Model Express is a Rust-based component meant to be placed next to existing model inference systems to speed up their startup times and i…☆203Updated this week
- A workload for deploying LLM inference services on Kubernetes☆314Updated this week
- Train speculative decoding models effortlessly and port them smoothly to SGLang serving.☆1,280Updated this week
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.☆3,292Updated this week
- Early-stage Rust drop-in alternative frontend for vLLM☆73May 22, 2026Updated 5 months ago
- ☆29Updated this week
- State of the art inference performance with modern accelerators on Kubernetes☆5,227Updated this week
- SGLang is a high-performance serving framework for large language models and multimodal models.☆38,744Updated this week
- Offline optimization of your disaggregated Dynamo graph☆467Oct 29, 2026Updated 2 weeks ago
- Speed-of-Light SW efficiency by using ultra low-latency primitives for comms collectives☆13Apr 8, 2026Updated 7 months ago
- KV cache store for distributed LLM inference☆452Sep 16, 2026Updated last month
- Open Source AI Accelerator Research Platform Standard / 开源推理研究平台☆2,025Updated this week
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- Evaluate and Enhance Your LLM Deployments for Real-World Inference Needs☆1,771Updated this week
- LMCache: Supercharge Your LLM with the Fastest KV Cache Layer☆12,340Updated this week
- An LLM post-training framework with vLLM for RL Scaling☆503Updated this week
- Tile-Based Runtime for Ultra-Low-Latency LLM Inference☆1,893Sep 24, 2026Updated last month
- AIPerf is a comprehensive benchmarking tool that measures the performance of generative AI models served by your preferred inference solu…☆868Updated this week
- Humming is a high-performance, lightweight, and highly flexible JIT (Just-In-Time) compiled GEMM kernel library specifically designed for…☆356Updated this week
- A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.☆5,561May 17, 2026Updated 5 months ago
- Cost-efficient and pluggable Infrastructure components for GenAI inference☆5,186Updated this week
- ☆1,162Updated this week
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Checkpoint-engine is a simple middleware to update model weights in LLM inference engines☆1,023Oct 22, 2026Updated 3 weeks ago
- ☆384Updated this week
- slime is an LLM training framework for RL Scaling.☆8,814Nov 5, 2026Updated last week
- A fast communication-overlapping library for tensor/expert parallelism on GPUs.☆1,377Aug 28, 2025Updated last year
- High Performance Serving Runtime For Interactive Super Intelligence System☆1,756Updated this week
- Efficient and easy multi-instance LLM serving☆562Mar 12, 2026Updated 8 months ago
- My learning notes for ML SYS.☆7,665Oct 21, 2026Updated 3 weeks ago
Are these results useful?