ranggihwang / Pregated_MoELinks
☆51Updated 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)☆43Updated 8 months ago
- LLM Inference analyzer for different hardware platforms☆87Updated last month
- [HPCA'24] Smart-Infinity: Fast Large Language Model Training using Near-Storage Processing on a Real System☆47Updated last month
- ☆23Updated last year
- SpInfer: Leveraging Low-Level Sparsity for Efficient Large Language Model Inference on GPUs☆52Updated 5 months ago
- ☆150Updated last year
- Tender: Accelerating Large Language Models via Tensor Decompostion and Runtime Requantization (ISCA'24)☆20Updated last year
- InfiniGen: Efficient Generative Inference of Large Language Models with Dynamic KV Cache Management (OSDI'24)☆151Updated last year
- ☆73Updated 3 months ago
- A GPU-optimized system for efficient long-context LLMs decoding with low-bit KV cache.☆57Updated 3 weeks ago
- Explore Inter-layer Expert Affinity in MoE Model Inference☆13Updated last year
- ☆179Updated last year
- ☆68Updated last year
- LLMServingSim: A HW/SW Co-Simulation Infrastructure for LLM Inference Serving at Scale☆131Updated last month
- ☆54Updated last year
- MAGIS: Memory Optimization via Coordinated Graph Transformation and Scheduling for DNN (ASPLOS'24)☆53Updated last year
- Artifact for "Marconi: Prefix Caching for the Era of Hybrid LLMs" [MLSys '25 Outstanding Paper Award, Honorable Mention]☆20Updated 5 months ago
- ☆114Updated 9 months ago
- ☆14Updated last year
- Proteus: A High-Throughput Inference-Serving System with Accuracy Scaling☆13Updated last year
- LLM serving cluster simulator☆108Updated last year
- ☆51Updated last year
- ☆50Updated 2 months ago
- UPMEM LLM Framework allows profiling PyTorch layers and functions and simulate those layers/functions with a given hardware profile.☆34Updated 2 weeks ago
- A lightweight design for computation-communication overlap.☆157Updated last week
- [ICML 2024 Oral] Any-Precision LLM: Low-Cost Deployment of Multiple, Different-Sized LLMs☆113Updated last month
- ☆25Updated 8 months ago
- ☆68Updated last year
- Magicube is a high-performance library for quantized sparse matrix operations (SpMM and SDDMM) of deep learning on Tensor Cores.☆89Updated 2 years ago
- [ICML 2024] Serving LLMs on heterogeneous decentralized clusters.☆27Updated last year