A framework for generating realistic LLM serving workloads
☆106Oct 9, 2025Updated 5 months ago
Alternatives and similar repositories for ServeGen
Users that are interested in ServeGen are comparing it to the libraries listed below
Sorting:
- Research prototype of PRISM — a cost-efficient multi-LLM serving system with flexible time- and space-based GPU sharing.☆58Updated this week
- Asynchronous pipeline parallel optimization☆19Feb 2, 2026Updated last month
- High-performance KV cache storage for LLM inference — GPU offloading, SSD caching, and cross-node sharing via RDMA. Works with vLLM and S…☆27Updated this week
- TraceWeaver is a research prototype for transparently tracing requests through a microservice without application instrumentation.☆23Sep 2, 2024Updated last year
- Deferred Continuous Batching in Resource-Efficient Large Language Model Serving (EuroMLSys 2024)☆19May 28, 2024Updated last year
- A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems☆243Updated this week
- Adaptive Message Quantization and Parallelization for Distributed Full-graph GNN Training☆24Mar 1, 2024Updated 2 years ago
- A parallelism VAE avoids OOM for high resolution image generation☆89Mar 12, 2026Updated last week
- ☆176Mar 12, 2024Updated 2 years ago
- ☆14Jun 17, 2024Updated last year
- Easy, Fast, and Scalable Multimodal AI☆118Mar 10, 2026Updated last week
- Sample Codes using NVSHMEM on Multi-GPU☆30Jan 22, 2023Updated 3 years ago
- ☆64Jun 25, 2024Updated last year
- Магрепорт - свободно-рапространяемая система корпоративной отчётности и BI☆11Apr 9, 2025Updated 11 months ago
- SpotServe: Serving Generative Large Language Models on Preemptible Instances☆134Feb 22, 2024Updated 2 years ago
- NVSHMEM‑Tutorial: Build a DeepEP‑like GPU Buffer☆170Feb 11, 2026Updated last month
- An auxiliary project analysis of the characteristics of KV in DiT Attention.☆33Nov 29, 2024Updated last year
- ACM SoCC 2019, "Coupling Decentralized Key-Value Stores with Erasure Coding"☆15May 22, 2021Updated 4 years ago
- Releasing the spot availability traces used in "Can't Be Late" paper.☆25Mar 31, 2024Updated last year
- Efficient Long-context Language Model Training by Core Attention Disaggregation☆96Mar 5, 2026Updated 2 weeks ago
- A low-latency & high-throughput serving engine for LLMs☆484Jan 8, 2026Updated 2 months ago
- ☆20Jun 9, 2025Updated 9 months ago
- Source code for OSDI 2023 paper titled "Cilantro - Performance-Aware Resource Allocation for General Objectives via Online Feedback"☆40Jul 6, 2023Updated 2 years ago
- ☆28Feb 15, 2025Updated last year
- ☆16Apr 22, 2025Updated 11 months ago
- Official repository for the paper DynaPipe: Optimizing Multi-task Training through Dynamic Pipelines☆19Dec 8, 2023Updated 2 years ago
- Predict the performance of LLM inference services☆23Sep 18, 2025Updated 6 months ago
- Implementation from scratch in C of the Multi-head latent attention used in the Deepseek-v3 technical paper.☆18Jan 15, 2025Updated last year
- Implement some method of LLM KV Cache Sparsity☆41Jun 6, 2024Updated last year
- Using Monte Carlo method to find a minimal cut set (MCS) for a fault tree.☆15Apr 3, 2017Updated 8 years ago
- a size profiler for cuda binary☆71Jan 15, 2026Updated 2 months ago
- Query-Adaptive Vector Search☆69Updated this week
- ☆27Aug 31, 2023Updated 2 years ago
- A caching framework for microservice applications☆24Apr 22, 2024Updated last year
- ☆13Oct 13, 2021Updated 4 years ago
- Disaggregated serving system for Large Language Models (LLMs).☆785Apr 6, 2025Updated 11 months ago
- Serverless LLM Serving for Everyone.☆664Mar 6, 2026Updated 2 weeks ago
- ☆96Jan 22, 2026Updated 2 months ago
- Efficient and easy multi-instance LLM serving☆532Mar 12, 2026Updated last week