TokenSpeed is a speed-of-light LLM inference engine.
☆2,754Oct 22, 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 &…☆661Updated this week
- Tile-Based Runtime for Ultra-Low-Latency LLM Inference☆1,874Sep 24, 2026Updated 3 weeks ago
- FlashInfer: Kernel Library for LLM Serving☆6,744Updated this week
- Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.☆3,182Updated this week
- A PyTorch native library for training speculative decoding models☆266Updated this week
- 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.
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆6,865Updated this week
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆8,725Updated this week
- FlashKDA: high-performance Kimi Delta Attention kernels☆1,286Sep 1, 2026Updated last month
- Kernel Design Agents (KDA) is a agent-centric workflow to write high-performance CUDA Kernels.☆1,431Updated this week
- mKernel: fast multi-node, multi-GPU fused kernels☆296Updated this week
- A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.☆5,386May 17, 2026Updated 5 months ago
- ☆1,040Updated this week
- Accelerating MoE with IO and Tile-aware Optimizations☆781Aug 29, 2026Updated last month
- A Datacenter Scale Distributed Inference Serving Framework☆8,362Updated this week
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- Distributed Compiler and Optimized Parallel Kernels☆1,569Sep 18, 2026Updated last month
- High Performance LLM Inference Operator Library☆1,184Sep 7, 2026Updated last month
- MoonEP: A Perfectly Balanced Expert Parallelism Library via Dynamic Redundant Experts☆1,189Oct 12, 2026Updated last week
- CUDA kernels for linear attention variants, written in CuTe DSL and CUTLASS C++.☆557Updated this week
- SGLang is a high-performance serving framework for large language models and multimodal models.☆37,616Updated this week
- high-performance linear attention kernel library built on TileLang☆735Oct 14, 2026Updated last week
- A kernel library written in tilelang☆2,000Oct 14, 2026Updated last week
- LMCache: Supercharge Your LLM with the Fastest KV Cache Layer☆12,129Updated this week
- A Quirky Assortment of CuTe Kernels☆1,176Oct 15, 2026Updated last week
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- slime is an LLM training framework for RL Scaling.☆8,718Updated this week
- DFlash: Block Diffusion for Flash Speculative Decoding☆6,190Aug 18, 2026Updated 2 months ago
- NVIDIA Inference Xfer Library (NIXL)☆1,325Updated this week
- Train speculative decoding models effortlessly and port them smoothly to SGLang serving.☆1,233Updated this week
- DeepGEMM: clean and efficient BLAS kernel library on GPU☆9,074Updated this week
- High Performance Serving Runtime For Interactive Super Intelligence System☆1,593Updated this week
- Nano vLLM☆16,016Apr 26, 2026Updated 5 months ago
- Pure Rust + CUDA LLM inference engine — no PyTorch, OpenAI-compatible, serves Qwen3 to Kimi-K2☆724Updated this week
- A fast communication-overlapping library for tensor/expert parallelism on GPUs.☆1,375Aug 28, 2025Updated last year
- 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.
- RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.☆1,366Updated this week
- Tile primitives for speedy kernels☆3,763Sep 12, 2026Updated last month
- My learning notes for ML SYS.☆7,587Updated this week
- DeepSpec: a full-stack codebase for training and evaluating speculative decoding algorithms☆7,243Jul 9, 2026Updated 3 months ago
- ☆116Aug 5, 2026Updated 2 months ago
- Mirage Persistent Kernel: Compiling LLMs into a MegaKernel☆2,569Updated this week
- 🚀 Efficient implementations for emerging model architectures☆5,965Updated this week