DeepLink-org / DLSlimeLinks
DLSlime: Flexible & Efficient Heterogeneous Transfer Toolkit
☆66Updated this week
Alternatives and similar repositories for DLSlime
Users that are interested in DLSlime are comparing it to the libraries listed below
Sorting:
- NVSHMEM‑Tutorial: Build a DeepEP‑like GPU Buffer☆130Updated 2 weeks ago
- ☆64Updated 5 months ago
- A lightweight design for computation-communication overlap.☆177Updated 2 weeks ago
- DeeperGEMM: crazy optimized version☆71Updated 4 months ago
- Tile-based language built for AI computation across all scales☆61Updated this week
- gLLM: Global Balanced Pipeline Parallelism System for Distributed LLM Serving with Token Throttling☆41Updated this week
- ☆85Updated 6 months ago
- A GPU-optimized system for efficient long-context LLMs decoding with low-bit KV cache.☆60Updated last month
- Triton adapter for Ascend. Mirror of https://gitee.com/ascend/triton-ascend☆75Updated last week
- [DAC'25] Official implement of "HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inference"☆72Updated 3 months ago
- Implement Flash Attention using Cute.☆95Updated 9 months ago
- ☆39Updated last month
- ☆50Updated 4 months ago
- An experimental communicating attention kernel based on DeepEP.☆34Updated 2 months ago
- ⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, Achieve Peak⚡️ Performance.☆118Updated 4 months ago
- A prefill & decode disaggregated LLM serving framework with shared GPU memory and fine-grained compute isolation.☆111Updated 4 months ago
- Aims to implement dual-port and multi-qp solutions in deepEP ibrc transport☆63Updated 4 months ago
- Efficient Compute-Communication Overlap for Distributed LLM Inference☆58Updated this week
- ☆98Updated last year
- ☆39Updated last year
- ☆72Updated last year
- ☆57Updated 4 months ago
- Debug print operator for cudagraph debugging☆13Updated last year
- ☆106Updated 4 months ago
- TiledLower is a Dataflow Analysis and Codegen Framework written in Rust.☆14Updated 10 months ago
- kvcached: Elastic KV cache for dynamic GPU sharing and efficient multi-LLM inference.☆94Updated this week
- ☆30Updated 3 months ago
- TileFusion is an experimental C++ macro kernel template library that elevates the abstraction level in CUDA C for tile processing.☆97Updated 3 months ago
- SpInfer: Leveraging Low-Level Sparsity for Efficient Large Language Model Inference on GPUs☆58Updated 6 months ago
- Artifact for "Marconi: Prefix Caching for the Era of Hybrid LLMs" [MLSys '25 Outstanding Paper Award, Honorable Mention]☆37Updated 6 months ago