MachineLearningSystem / 25ASPLOS-MedusaLinks
Medusa: Accelerating Serverless LLM Inference with Materialization [ASPLOS'25]
☆12Updated last year
Alternatives and similar repositories for 25ASPLOS-Medusa
Users that are interested in 25ASPLOS-Medusa are comparing it to the libraries listed below
Sorting:
- Open-source implementation for "Helix: Serving Large Language Models over Heterogeneous GPUs and Network via Max-Flow"☆77Updated 3 months ago
- Artifacts for our ASPLOS'23 paper ElasticFlow☆55Updated last year
- Here are my personal paper reading notes (including machine learning systems, AI infrastructure, and other interesting stuffs).☆155Updated last week
- Compiler for Dynamic Neural Networks☆45Updated 2 years ago
- Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“☆64Updated last year
- ☆78Updated 2 weeks ago
- An interference-aware scheduler for fine-grained GPU sharing☆159Updated 2 months ago
- REEF is a GPU-accelerated DNN inference serving system that enables instant kernel preemption and biased concurrent execution in GPU sche…☆104Updated 3 years ago
- A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems☆236Updated 2 weeks ago
- This repository is established to store personal notes and annotated papers during daily research.☆179Updated 2 weeks ago
- Proteus: A High-Throughput Inference-Serving System with Accuracy Scaling☆12Updated last year
- ☆44Updated last year
- LLM serving cluster simulator☆135Updated last year
- ☆79Updated 3 years ago
- AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving (OSDI 23)☆93Updated 2 years ago
- ☆24Updated last year
- Medusa: Accelerating Serverless LLM Inference with Materialization [ASPLOS'25]☆41Updated 8 months ago
- ☆38Updated 7 months ago
- ☆29Updated last year
- Tacker: Tensor-CUDA Core Kernel Fusion for Improving the GPU Utilization while Ensuring QoS☆34Updated 11 months ago
- ☆84Updated 3 months ago
- ☆65Updated 7 months ago
- ☆131Updated last year
- ☆15Updated last year
- ☆23Updated 2 years ago
- PerFlow-AI is a programmable performance analysis, modeling, prediction tool for AI system.☆28Updated last week
- A framework for generating realistic LLM serving workloads☆99Updated 3 months ago
- [NeurIPS 2025] ClusterFusion: Expanding Operator Fusion Scope for LLM Inference via Cluster-Level Collective Primitive☆66Updated last month
- Bamboo is a system for running large pipeline-parallel DNNs affordably, reliably, and efficiently using spot instances.☆55Updated 3 years ago
- NEO is a LLM inference engine built to save the GPU memory crisis by CPU offloading☆81Updated 7 months ago