PKU-SEC-Lab / HybriMoELinks
[DAC'25] Official implement of "HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inference"
☆81Updated 4 months ago
Alternatives and similar repositories for HybriMoE
Users that are interested in HybriMoE are comparing it to the libraries listed below
Sorting:
- A GPU-optimized system for efficient long-context LLMs decoding with low-bit KV cache.☆60Updated last week
- DLSlime: Flexible & Efficient Heterogeneous Transfer Toolkit☆70Updated last week
- ☆82Updated 9 months ago
- SpInfer: Leveraging Low-Level Sparsity for Efficient Large Language Model Inference on GPUs☆59Updated 7 months ago
- A lightweight design for computation-communication overlap.☆181Updated 2 weeks ago
- ☆65Updated 6 months ago
- Tile-based language built for AI computation across all scales☆67Updated 3 weeks ago
- NVSHMEM‑Tutorial: Build a DeepEP‑like GPU Buffer☆139Updated last month
- Implement Flash Attention using Cute.☆96Updated 10 months ago
- ☆58Updated last year
- ☆74Updated last week
- DeeperGEMM: crazy optimized version☆72Updated 5 months ago
- ☆100Updated last year
- ☆148Updated 7 months ago
- A prefill & decode disaggregated LLM serving framework with shared GPU memory and fine-grained compute isolation.☆113Updated 5 months ago
- ☆78Updated 6 months ago
- 16-fold memory access reduction with nearly no loss☆105Updated 7 months ago
- ☆120Updated 2 months ago
- Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity☆221Updated 2 years ago
- ⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, Achieve Peak⚡️ Performance.☆124Updated 5 months ago
- PyTorch library for cost-effective, fast and easy serving of MoE models.☆252Updated last week
- ☆153Updated last year
- 🤖FFPA: Extend FlashAttention-2 with Split-D, ~O(1) SRAM complexity for large headdim, 1.8x~3x↑🎉 vs SDPA EA.☆226Updated 2 months ago
- ☆50Updated 5 months ago
- ☆107Updated 5 months ago
- Compare different hardware platforms via the Roofline Model for LLM inference tasks.☆116Updated last year
- Triton adapter for Ascend. Mirror of https://gitee.com/ascend/triton-ascend☆79Updated last month
- Repo for SpecEE: Accelerating Large Language Model Inference with Speculative Early Exiting (ISCA25)☆64Updated 6 months ago
- Decoding Attention is specially optimized for MHA, MQA, GQA and MLA using CUDA core for the decoding stage of LLM inference.☆45Updated 4 months ago
- [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention☆48Updated 2 months ago