TokenSpeed is a speed-of-light LLM inference engine.
☆1,589Jul 14, 2026Updated this week
Alternatives and similar repositories for tokenspeed
Users that are interested in tokenspeed are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Engine-agnostic LLM gateway in Rust. Full OpenAI & Anthropic API compatibility across vLLM, TRT-LLM, TokenSpeed, SGLang, OpenAI, Gemini &…☆391Updated this week
- A PyTorch native library for training speculative decoding models☆200Updated this week
- FlashInfer: Kernel Library for LLM Serving☆5,957Updated this week
- FlashKDA: high-performance Kimi Delta Attention kernels☆450May 26, 2026Updated last month
- mKernel: fast multi-node, multi-GPU fused kernels☆251Jun 21, 2026Updated 3 weeks ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- ☆670Updated this week
- A kernel library written in tilelang☆1,642Apr 23, 2026Updated 2 months ago
- SGLang Omni: High-Performance Multi-Stage Pipeline Framework for Omni Models☆627Updated this week
- ☆743Jun 2, 2026Updated last month
- high-performance linear attention kernel library built on TileLang☆590Updated this week
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆5,821Updated this week
- Pure Rust + CUDA LLM inference engine — no PyTorch, OpenAI-compatible, serves Qwen3 to Kimi-K2☆536Updated this week
- DFlash: Block Diffusion for Flash Speculative Decoding☆5,468May 10, 2026Updated 2 months ago
- Distributed Compiler based on Triton for Parallel Systems☆1,488Updated this week
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- NVIDIA Inference Xfer Library (NIXL)☆1,133Updated this week
- DeepSpec: a full-stack codebase for training and evaluating speculative decoding algorithms☆6,638Updated this week
- CODA: Rewriting Transformer Blocks as GEMM-Epilogue Programs☆227Updated this week
- SGLang is a high-performance serving framework for large language models and multimodal models.☆30,306Updated this week
- A Datacenter Scale Distributed Inference Serving Framework☆7,483Updated this week
- ☆303Jun 9, 2026Updated last month
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆6,636Updated this week
- An LLM post-training framework with vLLM for RL Scaling☆363Updated this week
- Perplexity GPU Kernels☆588Nov 7, 2025Updated 8 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Agent-friendly GPU profile-query CLI☆105Jun 22, 2026Updated 3 weeks ago
- ☆224Updated this week
- High-performance KV cache storage for LLM inference — GPU offloading, SSD caching, and cross-node sharing via RDMA. Works with vLLM and S…☆172Updated this week
- ☆44Updated this week
- Tile-Based Runtime for Ultra-Low-Latency LLM Inference☆1,546Updated this week
- A fast communication-overlapping library for tensor/expert parallelism on GPUs.☆1,341Aug 28, 2025Updated 10 months ago
- Accelerating MoE with IO and Tile-aware Optimizations☆730Jul 4, 2026Updated last week
- CUDA Templates and Python DSLs for High-Performance Linear Algebra☆10,076Updated this week
- Compact and Agent-Native MoE Training System☆253Updated this week
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- LMCache: Supercharge Your LLM with the Fastest KV Cache Layer☆10,547Updated this week
- My learning notes for ML SYS.☆6,710Updated this week
- Autoresearch for GPU kernels. Give it any PyTorch model, go to sleep, wake up to optimized Triton kernels.☆1,458Mar 19, 2026Updated 3 months ago
- ☆155May 24, 2026Updated last month
- Skills for writing tilelang and debugging with CUDA toolkits.☆130May 20, 2026Updated last month
- A throughput-oriented high-performance serving framework for LLMs☆967Mar 29, 2026Updated 3 months ago
- An Optimizer for Nvidia Compilers.☆107Jul 3, 2026Updated last week