TokenSpeed is a speed-of-light LLM inference engine.
☆1,795Aug 3, 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 &…☆439Updated this week
- Tile-Based Runtime for Ultra-Low-Latency LLM Inference☆1,617Jul 14, 2026Updated 2 weeks ago
- FlashInfer: Kernel Library for LLM Serving☆6,090Updated this week
- A PyTorch native library for training speculative decoding models☆218Updated this week
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆6,135Updated 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.
- Accelerating MoE with IO and Tile-aware Optimizations☆736Jul 4, 2026Updated last month
- Distributed Compiler based on Triton for Parallel Systems☆1,507Jul 20, 2026Updated 2 weeks ago
- Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.☆1,856Updated this week
- CUDA kernels for linear attention variants, written in CuTe DSL and CUTLASS C++.☆535Updated this week
- FlashKDA: high-performance Kimi Delta Attention kernels☆1,147Updated this week
- High Performance LLM Inference Operator Library☆1,080Updated this week
- A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.☆4,668May 17, 2026Updated 2 months ago
- mKernel: fast multi-node, multi-GPU fused kernels☆260Updated this week
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆7,112Updated this week
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- A Quirky Assortment of CuTe Kernels☆1,084Updated this week
- ☆715Updated this week
- A kernel library written in tilelang☆1,696Apr 23, 2026Updated 3 months ago
- A Datacenter Scale Distributed Inference Serving Framework☆7,667Updated this week
- ☆790Jun 2, 2026Updated 2 months ago
- high-performance linear attention kernel library built on TileLang☆625Updated this week
- SGLang Omni: High-Performance Multi-Stage Pipeline Framework for Omni Models☆735Updated this week
- NVIDIA Inference Xfer Library (NIXL)☆1,166Updated this week
- Perplexity GPU Kernels☆597Nov 7, 2025Updated 8 months ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- SGLang is a high-performance serving framework for large language models and multimodal models.☆31,163Updated this week
- A fast communication-overlapping library for tensor/expert parallelism on GPUs.☆1,352Aug 28, 2025Updated 11 months ago
- slime is an LLM post-training framework for RL Scaling.☆7,742Updated this week
- My learning notes for ML SYS.☆6,810Updated this week
- RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.☆1,295Updated this week
- ☆381Jan 28, 2026Updated 6 months ago
- Train speculative decoding models effortlessly and port them smoothly to SGLang serving.☆1,038Updated this week
- Pure Rust + CUDA LLM inference engine — no PyTorch, OpenAI-compatible, serves Qwen3 to Kimi-K2☆622Updated this week
- DFlash: Block Diffusion for Flash Speculative Decoding☆5,562May 10, 2026Updated 2 months ago
- Open source password manager - Proton Pass • AdSecurely store, share, and autofill your credentials with Proton Pass, the end-to-end encrypted password manager trusted by millions.
- KV cache store for distributed LLM inference☆424Nov 13, 2025Updated 8 months ago
- Checkpoint-engine is a simple middleware to update model weights in LLM inference engines☆991Updated this week
- Mirage Persistent Kernel: Compiling LLMs into a MegaKernel☆2,404Jul 28, 2026Updated last week
- LMCache: Supercharge Your LLM with the Fastest KV Cache Layer☆11,000Updated this week
- Tile primitives for speedy kernels☆3,588Jul 13, 2026Updated 3 weeks ago
- Nano vLLM☆14,790Apr 26, 2026Updated 3 months ago
- Kernels, of the mega variety :)☆790May 26, 2026Updated 2 months ago