TokenSpeed is a speed-of-light LLM inference engine.
☆1,952Aug 23, 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 &…☆471Updated this week
- Tile-Based Runtime for Ultra-Low-Latency LLM Inference☆1,728Aug 13, 2026Updated last week
- FlashInfer: Kernel Library for LLM Serving☆6,218Updated this week
- A PyTorch native library for training speculative decoding models☆229Updated this week
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆6,351Updated 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.
- Accelerating MoE with IO and Tile-aware Optimizations☆747Aug 17, 2026Updated last week
- Distributed Compiler and Optimized Parallel Kernels☆1,520Aug 12, 2026Updated last week
- Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.☆2,216Updated this week
- CUDA kernels for linear attention variants, written in CuTe DSL and CUTLASS C++.☆539Aug 14, 2026Updated last week
- High Performance LLM Inference Operator Library☆1,126Aug 6, 2026Updated 2 weeks ago
- FlashKDA: high-performance Kimi Delta Attention kernels☆1,227Jul 30, 2026Updated 3 weeks ago
- A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.☆4,816May 17, 2026Updated 3 months ago
- mKernel: fast multi-node, multi-GPU fused kernels☆268Updated this week
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆7,266Updated this week
- Simple, predictable pricing with DigitalOcean hosting • AdAlways know what you'll pay with monthly caps and flat pricing. Enterprise-grade infrastructure trusted by 600k+ customers.
- A Quirky Assortment of CuTe Kernels☆1,123Updated this week
- ☆754Updated this week
- A kernel library written in tilelang☆1,740Apr 23, 2026Updated 4 months ago
- A Datacenter Scale Distributed Inference Serving Framework☆7,835Updated this week
- ☆856Jun 2, 2026Updated 2 months ago
- high-performance linear attention kernel library built on TileLang☆645Aug 11, 2026Updated last week
- NVIDIA Inference Xfer Library (NIXL)☆1,211Updated this week
- SGLang-Omni empowers high-performance serving for TTS, ASR, speech and omni models.☆920Updated this week
- Perplexity GPU Kernels☆602Nov 7, 2025Updated 9 months ago
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- SGLang is a high-performance serving framework for large language models and multimodal models.☆32,291Updated 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.☆8,209Updated this week
- My learning notes for ML SYS.☆6,936Updated this week
- RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.☆1,313Updated this week
- ☆383Jan 28, 2026Updated 6 months ago
- Train speculative decoding models effortlessly and port them smoothly to SGLang serving.☆1,111Updated this week
- Pure Rust + CUDA LLM inference engine — no PyTorch, OpenAI-compatible, serves Qwen3 to Kimi-K2☆655Updated this week
- DFlash: Block Diffusion for Flash Speculative Decoding☆5,898Updated this week
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- KV cache store for distributed LLM inference☆430Nov 13, 2025Updated 9 months ago
- Checkpoint-engine is a simple middleware to update model weights in LLM inference engines☆1,001Aug 12, 2026Updated last week
- Mirage Persistent Kernel: Compiling LLMs into a MegaKernel☆2,446Aug 4, 2026Updated 2 weeks ago
- LMCache: Supercharge Your LLM with the Fastest KV Cache Layer☆11,322Updated this week
- Tile primitives for speedy kernels☆3,642Updated this week
- Nano vLLM☆15,100Apr 26, 2026Updated 3 months ago
- Kernels, of the mega variety :)☆812May 26, 2026Updated 2 months ago