Tile-Based Runtime for Ultra-Low-Latency LLM Inference
☆1,579Jul 14, 2026Updated last week
Alternatives and similar repositories for TileRT
Users that are interested in TileRT are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- High-performance LLM operator library built on TileLang.☆161Updated this week
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆6,681Updated this week
- Tile-based language built for AI computation across all scales☆174Jun 16, 2026Updated last month
- Distributed Compiler based on Triton for Parallel Systems☆1,495Updated this week
- FlashInfer: Kernel Library for LLM Serving☆5,994Updated this week
- 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.
- TokenSpeed is a speed-of-light LLM inference engine.☆1,643Updated this week
- Accelerating MoE with IO and Tile-aware Optimizations☆732Jul 4, 2026Updated 2 weeks ago
- Mirage Persistent Kernel: Compiling LLMs into a MegaKernel☆2,378Updated this week
- High Performance LLM Inference Operator Library☆1,052Updated this week
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆5,941Updated this week
- A fast communication-overlapping library for tensor/expert parallelism on GPUs.☆1,344Aug 28, 2025Updated 10 months ago
- A kernel library written in tilelang☆1,646Apr 23, 2026Updated 2 months ago
- Open ABI and FFI for Machine Learning Systems☆435Updated this week
- ☆692Jul 14, 2026Updated last 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.
- Perplexity GPU Kernels☆591Nov 7, 2025Updated 8 months ago
- A Quirky Assortment of CuTe Kernels☆1,064Updated this week
- ☆232Updated this week
- Train speculative decoding models effortlessly and port them smoothly to SGLang serving.☆1,000Updated this week
- Skills for writing tilelang and debugging with CUDA toolkits.☆131May 20, 2026Updated 2 months ago
- FlashKDA: high-performance Kimi Delta Attention kernels☆464May 26, 2026Updated last month
- ☆310Jun 9, 2026Updated last month
- cuTile is a programming model for writing parallel kernels for NVIDIA GPUs☆2,121Updated this week
- A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.☆4,616May 17, 2026Updated 2 months ago
- 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.
- Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.☆1,761Updated this week
- CUDA kernels for linear attention variants, written in CuTe DSL and CUTLASS C++.☆534Updated this week
- DeepGEMM: clean and efficient BLAS kernel library on GPU☆7,541Updated this week
- ☆760Jun 2, 2026Updated last month
- Tile primitives for speedy kernels☆3,555Jul 13, 2026Updated last week
- ☆32Jul 2, 2025Updated last year
- Learning TileLang with 10 puzzles!☆342May 28, 2026Updated last month
- ☆54Updated this week
- NVIDIA Inference Xfer Library (NIXL)☆1,139Updated 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.
- My learning notes for ML SYS.☆6,759Updated this week
- NVSHMEM‑Tutorial: Build a DeepEP‑like GPU Buffer☆195Feb 11, 2026Updated 5 months ago
- Compact and Agent-Native MoE Training System☆295Updated this week
- mKernel: fast multi-node, multi-GPU fused kernels☆252Jun 21, 2026Updated last month
- Tilus is a tile-level kernel programming language with explicit control over shared memory and registers.☆489Jul 5, 2026Updated 2 weeks ago
- high-performance linear attention kernel library built on TileLang☆600Updated this week
- RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.☆1,282Updated this week