tile-ai / TileRTLinks
Tile-Based Runtime for Ultra-Low-Latency LLM Inference
☆516Updated 2 weeks ago
Alternatives and similar repositories for TileRT
Users that are interested in TileRT are comparing it to the libraries listed below
Sorting:
- An early research stage expert-parallel load balancer for MoE models based on linear programming.☆484Updated last month
- Perplexity GPU Kernels☆548Updated 2 months ago
- A lightweight design for computation-communication overlap.☆207Updated 2 weeks ago
- Tile-based language built for AI computation across all scales☆115Updated 2 weeks ago
- Open ABI and FFI for Machine Learning Systems☆274Updated this week
- ☆337Updated this week
- NVSHMEM‑Tutorial: Build a DeepEP‑like GPU Buffer☆151Updated 3 months ago
- Train speculative decoding models effortlessly and port them smoothly to SGLang serving.☆615Updated this week
- Accelerating MoE with IO and Tile-aware Optimizations☆522Updated this week
- ☆96Updated 9 months ago
- Dynamic Memory Management for Serving LLMs without PagedAttention☆454Updated 7 months ago
- Allow torch tensor memory to be released and resumed later☆196Updated last month
- Autonomous GPU Kernel Generation via Deep Agents☆202Updated this week
- [NeurIPS 2025] ClusterFusion: Expanding Operator Fusion Scope for LLM Inference via Cluster-Level Collective Primitive☆60Updated 3 weeks ago
- NVIDIA NVSHMEM is a parallel programming interface for NVIDIA GPUs based on OpenSHMEM. NVSHMEM can significantly reduce multi-process com…☆433Updated last week
- NVIDIA cuTile learn☆144Updated 3 weeks ago
- ☆153Updated 10 months ago
- DeepSeek-V3/R1 inference performance simulator☆175Updated 9 months ago
- Ascend TileLang adapter☆177Updated this week
- A prefill & decode disaggregated LLM serving framework with shared GPU memory and fine-grained compute isolation.☆123Updated 2 weeks ago
- ArcticInference: vLLM plugin for high-throughput, low-latency inference☆363Updated last week
- DLSlime: Flexible & Efficient Heterogeneous Transfer Toolkit☆91Updated this week
- ☆104Updated last year
- High performance Transformer implementation in C++.☆148Updated 11 months ago
- A tiny yet powerful LLM inference system tailored for researching purpose. vLLM-equivalent performance with only 2k lines of code (2% of …☆303Updated 6 months ago
- Github mirror of trition-lang/triton repo.☆113Updated last week
- [DAC'25] Official implement of "HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inference"☆95Updated 3 weeks ago
- ☆81Updated 2 months ago
- ☆92Updated 9 months ago
- Genai-bench is a powerful benchmark tool designed for comprehensive token-level performance evaluation of large language model (LLM) serv…☆250Updated 3 weeks ago