Artifact for "Apparate: Rethinking Early Exits to Tame Latency-Throughput Tensions in ML Serving" [SOSP '24]
☆25Nov 21, 2024Updated last year
Alternatives and similar repositories for apparate
Users that are interested in apparate are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- A Cluster-Wide Model Manager to Accelerate DNN Training via Automated Training Warmup☆36Jan 9, 2023Updated 3 years ago
- An Attention Superoptimizer☆22Jan 20, 2025Updated last year
- [ICML 2026] Less Is More: Training-Free Sparse Attention with Global Locality for Efficient Reasoning☆36Sep 12, 2025Updated last year
- [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention☆57Aug 6, 2025Updated last year
- Artifact for "Shockwave: Fair and Efficient Cluster Scheduling for Dynamic Adaptation in Machine Learning" [NSDI '23]☆47Nov 24, 2022Updated 3 years ago
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- Expressive, Easy to Build, and High-Performance Application Networks☆20Jul 1, 2025Updated last year
- ☆22Jun 1, 2026Updated 5 months ago
- ☆17May 10, 2024Updated 2 years ago
- Predict the performance of LLM inference services☆23Sep 18, 2025Updated last year
- A Distributed Analysis and Benchmarking Framework for Apache OpenWhisk Serverless Platform☆12Dec 11, 2018Updated 7 years ago
- ☆137Nov 11, 2024Updated last year
- ☆13Jan 23, 2021Updated 5 years ago
- PipeRAG: Fast Retrieval-Augmented Generation via Algorithm-System Co-design (KDD 2025)☆32Jun 14, 2024Updated 2 years ago
- ☆10Nov 12, 2020Updated 5 years ago
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- ☆13Nov 5, 2025Updated 11 months ago
- ☆174Oct 9, 2024Updated 2 years ago
- A Coq framework to support structural design and proof of hardware cache-coherence protocols☆16May 7, 2022Updated 4 years ago
- ☆13Jul 29, 2025Updated last year
- ☆13Oct 13, 2021Updated 5 years ago
- ☆49Jun 27, 2024Updated 2 years ago
- ☆13Jun 2, 2026Updated 5 months ago
- Simulator for the datacenter, including power, cooling, server and other components☆18Feb 12, 2025Updated last year
- Neural machine translation with Recurrent Deterministic Policy Gradient☆10Aug 18, 2016Updated 10 years ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Repository for the COLM 2025 paper SpecDec++: Boosting Speculative Decoding via Adaptive Candidate Lengths☆19Jul 10, 2025Updated last year
- ☆22Nov 20, 2020Updated 5 years ago
- ☆19Jun 3, 2023Updated 3 years ago
- ☆19Apr 15, 2025Updated last year
- ☆46Oct 11, 2025Updated last year
- ☆11Updated this week
- Surrogate-based Hyperparameter Tuning System☆30Jun 29, 2023Updated 3 years ago
- Code for reproducing experiments performed for Accoridon☆13Jun 11, 2021Updated 5 years ago
- ☆14Feb 1, 2021Updated 5 years ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Code associated with the paper **Fine-tuning Language Models over Slow Networks using Activation Compression with Guarantees**.☆29Apr 25, 2023Updated 3 years ago
- A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems☆292Jun 30, 2026Updated 4 months ago
- ☆34Jun 22, 2024Updated 2 years ago
- FlexFlow Serve: Low-Latency, High-Performance LLM Serving☆90Sep 15, 2025Updated last year
- A benchmark suite for evaluating FaaS scheduler.☆23Nov 5, 2022Updated 3 years ago
- CS61A Ants Project Web GUI☆11Nov 2, 2016Updated 10 years ago
- Mini-SGLang is a mini version of SGLang project ().☆13Sep 24, 2025Updated last year