microsoft / apex_plusLinks
APEX+ is an LLM Serving Simulator
☆35Updated 3 months ago
Alternatives and similar repositories for apex_plus
Users that are interested in apex_plus are comparing it to the libraries listed below
Sorting:
- gLLM: Global Balanced Pipeline Parallelism System for Distributed LLM Serving with Token Throttling☆41Updated last week
- Stateful LLM Serving☆85Updated 7 months ago
- ☆123Updated 11 months ago
- ☆72Updated last year
- NEO is a LLM inference engine built to save the GPU memory crisis by CPU offloading☆64Updated 3 months ago
- [NeurIPS 2024] Efficient LLM Scheduling by Learning to Rank☆59Updated 11 months ago
- LLM serving cluster simulator☆115Updated last year
- ArkVale: Efficient Generative LLM Inference with Recallable Key-Value Eviction (NIPS'24)☆43Updated 9 months ago
- SpotServe: Serving Generative Large Language Models on Preemptible Instances☆129Updated last year
- Virtualized Elastic KV Cache for Dynamic GPU Sharing and Beyond☆99Updated last week
- Open-source implementation for "Helix: Serving Large Language Models over Heterogeneous GPUs and Network via Max-Flow"☆67Updated 10 months ago
- Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“☆62Updated last year
- Compiler for Dynamic Neural Networks☆46Updated last year
- [NeurIPS 2025] ClusterFusion: Expanding Operator Fusion Scope for LLM Inference via Cluster-Level Collective Primitive☆41Updated 2 weeks ago
- Research prototype of PRISM — a cost-efficient multi-LLM serving system with flexible time- and space-based GPU sharing.☆28Updated last month
- Supplemental materials for The ASPLOS 2025 / EuroSys 2025 Contest on Intra-Operator Parallelism for Distributed Deep Learning☆23Updated 5 months ago
- Official repository for the paper DynaPipe: Optimizing Multi-task Training through Dynamic Pipelines☆20Updated last year
- ☆18Updated 4 months ago
- ☆139Updated 2 months ago
- PerFlow-AI is a programmable performance analysis, modeling, prediction tool for AI system.☆24Updated last week
- Scalable long-context LLM decoding that leverages sparsity—by treating the KV cache as a vector storage system.☆85Updated 3 weeks ago
- ☆57Updated 3 weeks ago
- ☆49Updated 3 weeks ago
- Medusa: Accelerating Serverless LLM Inference with Materialization [ASPLOS'25]☆11Updated 11 months ago
- Artifact for "Apparate: Rethinking Early Exits to Tame Latency-Throughput Tensions in ML Serving" [SOSP '24]☆25Updated 10 months ago
- DLSlime: Flexible & Efficient Heterogeneous Transfer Toolkit☆67Updated this week
- ☆56Updated last year
- [ICML 2024] Serving LLMs on heterogeneous decentralized clusters.☆30Updated last year
- ☆132Updated last year
- Proteus: A High-Throughput Inference-Serving System with Accuracy Scaling☆13Updated last year