ranggihwang / Pregated_MoELinks
☆58Updated last year
Alternatives and similar repositories for Pregated_MoE
Users that are interested in Pregated_MoE are comparing it to the libraries listed below
Sorting:
- ArkVale: Efficient Generative LLM Inference with Recallable Key-Value Eviction (NIPS'24)☆50Updated last year
- [HPCA 2026] A GPU-optimized system for efficient long-context LLMs decoding with low-bit KV cache.☆76Updated 3 weeks ago
- [HPCA'24] Smart-Infinity: Fast Large Language Model Training using Near-Storage Processing on a Real System☆50Updated 5 months ago
- Tender: Accelerating Large Language Models via Tensor Decompostion and Runtime Requantization (ISCA'24)☆24Updated last year
- InfiniGen: Efficient Generative Inference of Large Language Models with Dynamic KV Cache Management (OSDI'24)☆170Updated last year
- LLM Inference analyzer for different hardware platforms☆99Updated last month
- SpInfer: Leveraging Low-Level Sparsity for Efficient Large Language Model Inference on GPUs☆59Updated 9 months ago
- Code release for AdapMoE accepted by ICCAD 2024☆35Updated 8 months ago
- ☆217Updated 2 months ago
- ☆81Updated 7 months ago
- ☆83Updated last year
- ☆26Updated last year
- ☆130Updated last year
- Keyformer proposes KV Cache reduction through key tokens identification and without the need for fine-tuning☆59Updated last year
- [NeurIPS 2025] ClusterFusion: Expanding Operator Fusion Scope for LLM Inference via Cluster-Level Collective Primitive☆62Updated last month
- LLMServingSim: A HW/SW Co-Simulation Infrastructure for LLM Inference Serving at Scale☆170Updated 5 months ago
- ☆164Updated last year
- LLM serving cluster simulator☆132Updated last year
- Accelerating Large-Scale Reasoning Model Inference with Sparse Self-Speculative Decoding☆74Updated last month
- [PACT'24] GraNNDis. A fast and unified distributed graph neural network (GNN) training framework for both full-batch (full-graph) and min…☆10Updated last year
- MAGIS: Memory Optimization via Coordinated Graph Transformation and Scheduling for DNN (ASPLOS'24)☆56Updated last year
- [ICML 2024 Oral] Any-Precision LLM: Low-Cost Deployment of Multiple, Different-Sized LLMs☆123Updated 6 months ago
- PIM-DL: Expanding the Applicability of Commodity DRAM-PIMs for Deep Learning via Algorithm-System Co-Optimization☆34Updated last year
- ☆81Updated 2 months ago
- ☆15Updated last year
- Explore Inter-layer Expert Affinity in MoE Model Inference☆16Updated last year
- ☆21Updated 3 weeks ago
- Magicube is a high-performance library for quantized sparse matrix operations (SpMM and SDDMM) of deep learning on Tensor Cores.☆91Updated 3 years ago
- ☆35Updated 3 months ago
- [DAC'25] Official implement of "HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inference"☆96Updated last month