TokenSpeed is a speed-of-light LLM inference engine.
☆2,918Nov 11, 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:
- FlashInfer: Kernel Library for LLM Serving☆6,897Updated this week
- Tile-Based Runtime for Ultra-Low-Latency LLM Inference☆1,893Sep 24, 2026Updated last month
- Engine-agnostic LLM gateway in Rust. Full OpenAI & Anthropic API compatibility across vLLM, TRT-LLM, TokenSpeed, SGLang, OpenAI, Gemini &…☆712Updated this week
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆7,024Updated this week
- 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
- 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.
- A PyTorch native library for training speculative decoding models☆267Updated this week
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆8,949Updated this week
- A Datacenter Scale Distributed Inference Serving Framework☆8,470Updated this week
- Kernel Design Agents (KDA) is a agent-centric workflow to write high-performance CUDA Kernels.☆1,568Oct 19, 2026Updated 3 weeks ago
- SGLang is a high-performance serving framework for large language models and multimodal models.☆38,744Updated this week
- A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.☆5,561May 17, 2026Updated 5 months ago
- High Performance LLM Inference Operator Library☆1,191Updated this week
- ☆1,162Updated this week
- Distributed Compiler and Optimized Parallel Kernels☆1,578Sep 18, 2026Updated last month
- 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.
- FlashKDA: high-performance Kimi Delta Attention kernels☆1,297Oct 26, 2026Updated 2 weeks ago
- CUDA kernels for linear attention variants, written in CuTe DSL and CUTLASS C++.☆560Updated this week
- LMCache: Supercharge Your LLM with the Fastest KV Cache Layer☆12,340Updated this week
- Accelerating MoE with IO and Tile-aware Optimizations☆791Aug 29, 2026Updated 2 months ago
- NVIDIA Inference Xfer Library (NIXL)☆1,363Updated this week
- A Quirky Assortment of CuTe Kernels☆1,193Oct 30, 2026Updated last week
- mKernel: fast multi-node, multi-GPU fused kernels☆309Oct 17, 2026Updated 3 weeks ago
- Train speculative decoding models effortlessly and port them smoothly to SGLang serving.☆1,280Updated this week
- A kernel library written in tilelang☆2,039Oct 14, 2026Updated 3 weeks ago
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- MoonEP: A Perfectly Balanced Expert Parallelism Library via Dynamic Redundant Experts☆1,210Oct 12, 2026Updated last month
- high-performance linear attention kernel library built on TileLang☆753Oct 30, 2026Updated last week
- slime is an LLM training framework for RL Scaling.☆8,814Nov 5, 2026Updated last week
- DFlash: Block Diffusion for Flash Speculative Decoding☆6,224Aug 18, 2026Updated 2 months ago
- DeepGEMM: clean and efficient BLAS kernel library on GPU☆9,186Oct 20, 2026Updated 3 weeks ago
- Tile primitives for speedy kernels☆3,795Sep 12, 2026Updated 2 months ago
- Pure Rust + CUDA LLM inference engine — no PyTorch, OpenAI-compatible, serves Qwen3 to Kimi-K2☆739Updated this week
- Nano vLLM☆16,388Apr 26, 2026Updated 6 months ago
- My learning notes for ML SYS.☆7,665Oct 21, 2026Updated 3 weeks ago
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- Mirage Persistent Kernel: Compiling LLMs into a MegaKernel☆2,609Updated this week
- DeepSpec: a full-stack codebase for training and evaluating speculative decoding algorithms☆7,306Jul 9, 2026Updated 4 months ago
- High Performance Serving Runtime For Interactive Super Intelligence System☆1,756Updated this week
- TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizat…☆15,062Updated this week
- RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.☆1,394Updated this week
- A fast communication-overlapping library for tensor/expert parallelism on GPUs.☆1,377Aug 28, 2025Updated last year
- 🚀 Efficient implementations for emerging model architectures☆6,040Updated this week
Are these results useful?