TokenSpeed is a speed-of-light LLM inference engine.
☆2,189Oct 2, 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 &…☆553Updated this week
- Tile-Based Runtime for Ultra-Low-Latency LLM Inference☆1,831Sep 24, 2026Updated last week
- FlashInfer: Kernel Library for LLM Serving☆6,532Updated this week
- A PyTorch native library for training speculative decoding models☆252Updated this week
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆6,703Updated this week
- 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.
- Accelerating MoE with IO and Tile-aware Optimizations☆776Aug 29, 2026Updated last month
- Distributed Compiler and Optimized Parallel Kernels☆1,555Sep 18, 2026Updated 2 weeks ago
- CUDA kernels for linear attention variants, written in CuTe DSL and CUTLASS C++.☆553Sep 20, 2026Updated last week
- Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.☆3,039Updated this week
- FlashKDA: high-performance Kimi Delta Attention kernels☆1,266Sep 1, 2026Updated last month
- High Performance LLM Inference Operator Library☆1,171Sep 7, 2026Updated 3 weeks ago
- A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.☆5,207May 17, 2026Updated 4 months ago
- mKernel: fast multi-node, multi-GPU fused kernels☆286Updated this week
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆8,242Updated this week
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- A Quirky Assortment of CuTe Kernels☆1,163Sep 17, 2026Updated 2 weeks ago
- A kernel library written in tilelang☆1,899Updated this week
- A Datacenter Scale Distributed Inference Serving Framework☆8,207Updated this week
- ☆881Sep 22, 2026Updated last week
- SGLang-Omni is a high-performance serving framework for audio models (TTS, ASR) and unified multimodal models.☆1,307Updated this week
- high-performance linear attention kernel library built on TileLang☆718Updated this week
- NVIDIA Inference Xfer Library (NIXL)☆1,283Updated this week
- Kernel Design Agents (KDA) is a agent-centric workflow to write high-performance CUDA Kernels.☆1,214Updated this week
- SGLang is a high-performance serving framework for large language models and multimodal models.☆36,718Updated 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.
- Perplexity GPU Kernels☆607Nov 7, 2025Updated 10 months ago
- A fast communication-overlapping library for tensor/expert parallelism on GPUs.☆1,368Aug 28, 2025Updated last year
- slime is an LLM post-training framework for RL Scaling.☆8,586Updated this week
- My learning notes for ML SYS.☆7,421Sep 20, 2026Updated last week
- RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.☆1,356Updated this week
- ☆389Jan 28, 2026Updated 8 months ago
- Train speculative decoding models effortlessly and port them smoothly to SGLang serving.☆1,197Updated this week
- Pure Rust + CUDA LLM inference engine — no PyTorch, OpenAI-compatible, serves Qwen3 to Kimi-K2☆715Updated this week
- DFlash: Block Diffusion for Flash Speculative Decoding☆6,131Aug 18, 2026Updated last month
- 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.
- Mirage Persistent Kernel: Compiling LLMs into a MegaKernel☆2,528Updated this week
- KV cache store for distributed LLM inference☆445Sep 16, 2026Updated 2 weeks ago
- Checkpoint-engine is a simple middleware to update model weights in LLM inference engines☆1,006Sep 15, 2026Updated 2 weeks ago
- LMCache: Supercharge Your LLM with the Fastest KV Cache Layer☆11,946Updated this week
- Tile primitives for speedy kernels☆3,736Sep 12, 2026Updated 2 weeks ago
- Nano vLLM☆15,689Apr 26, 2026Updated 5 months ago
- Kernels, of the mega variety :)☆839May 26, 2026Updated 4 months ago