Engine-Agnostic Model Hot-Swapping for Cost-Effective LLM Inference
☆15Nov 13, 2025Updated 11 months ago
Alternatives and similar repositories for SwapServeLLM
Users that are interested in SwapServeLLM are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Deduplication over dis-aggregated memory for Serverless Computing☆14Mar 21, 2022Updated 4 years ago
- This is the code repository for our work on resourcing-on-demand GPU provisioning for serverless deep learning serving.☆17Apr 17, 2026Updated 6 months ago
- code repo for GCR [FAST'26]☆17Mar 3, 2026Updated 7 months ago
- ☆19May 28, 2024Updated 2 years ago
- ☆21May 11, 2026Updated 5 months ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- Simplifying FPGA management in Docker☆13Mar 20, 2024Updated 2 years ago
- Medusa: Accelerating Serverless LLM Inference with Materialization [ASPLOS'25]☆49May 13, 2025Updated last year
- Foundry materializes CUDA graphs along with its execution context to disk to support fast cold start of serving engines.☆66Updated this week
- ☆12Jun 1, 2023Updated 3 years ago
- A framework for few-shot evaluation of autoregressive language models.☆13Jul 14, 2025Updated last year
- ☆12May 30, 2023Updated 3 years ago
- Artifacts for SWARM: Replicating Shared Disaggregated-Memory Data in No Time☆10Sep 25, 2024Updated 2 years ago
- ☆12Dec 8, 2022Updated 3 years ago
- Fast OS-level support for GPU checkpoint and restore☆298Sep 28, 2025Updated last year
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Simple example for learning and serving 'MNIST' in kubernetes cluster☆10Mar 27, 2019Updated 7 years ago
- Snapshot gets GPU pods ready in seconds instead of minutes — by restoring a fully initialized GPU worker instead of starting one from scr…☆72Updated this week
- Deploy the SC2 system on Kubernetes.☆12May 7, 2025Updated last year
- Performance analysis for distributed inference systems☆14Oct 17, 2026Updated last week
- BATCH: Adaptive Batching for Efficient MachineLearning Serving on Serverless Platforms☆10Aug 7, 2021Updated 5 years ago
- ARIES is an open-source experimentation framework for agent serving systems research.☆37Updated this week
- ☆42Nov 5, 2023Updated 2 years ago
- Source Code for Partial Interference☆10Dec 17, 2022Updated 3 years ago
- A fault-tolerant RDMA-based disaggregated key-value store with 1-RTT UPDATEs and GETs thanks to the SWARM replication protocol☆14Sep 25, 2024Updated 2 years ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- ☆13Apr 7, 2025Updated last year
- This is the open source release of an Azure PAAS project to accelerate the deployment of the hybris e-commerce software suite on Azure.☆22Jun 14, 2023Updated 3 years ago
- Fast inference engine for DACVAE, a neural audio codec that compresses and reconstructs audio using a convolutional encoder-decoder with …☆21Mar 17, 2026Updated 7 months ago
- ☆12Mar 22, 2022Updated 4 years ago
- High performance human detector☆25Oct 9, 2024Updated 2 years ago
- Medusa: Accelerating Serverless LLM Inference with Materialization [ASPLOS'25]☆12Nov 8, 2024Updated last year
- A collection of software alternatives written in Rust☆29Apr 14, 2023Updated 3 years ago
- Step-by-step GEMM optimization, one hardware feature at a time. High performance CuTeDSL kernels for H100, B200 and RTX 50s GPUs. This re…☆21May 14, 2026Updated 5 months ago
- "JABAS: Joint Adaptive Batching and Automatic Scaling for DNN Training on Heterogeneous GPUs" (EuroSys '25)☆16Apr 7, 2025Updated last year
- 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.
- Boosting GPU utilization for LLM serving via dynamic spatial-temporal prefill & decode orchestration☆54Sep 23, 2026Updated last month
- Evaluation Suite for NVMe devices☆14Nov 14, 2024Updated last year
- Proximal Policy Optimization(PPO) with Keras Implementation☆17Aug 8, 2020Updated 6 years ago
- A new memory mapping interface for efficient direct user-space access to byte-addressable storage, published in MICRO2022.☆15Sep 29, 2022Updated 4 years ago
- Official implementation of ICLR 2026 paper "LUMINA: Detecting Hallucinations in RAG System with Context–Knowledge Signals"☆19Jan 31, 2026Updated 8 months ago
- Install Pocketbase on Dokku a Heroku Alternative☆24Jun 5, 2025Updated last year
- Meta repository for the USENIX ATC'25 Publication "Accelerating Nested Virtualization with HyperTurtle"☆17Mar 22, 2026Updated 7 months ago