WukLab / InferCeptLinks
☆32Updated last year
Alternatives and similar repositories for InferCept
Users that are interested in InferCept are comparing it to the libraries listed below
Sorting:
- [NeurIPS 2024] Efficient LLM Scheduling by Learning to Rank☆66Updated last year
- ☆79Updated 2 months ago
- [OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable☆203Updated last year
- Stateful LLM Serving☆90Updated 9 months ago
- A framework for generating realistic LLM serving workloads☆93Updated 2 months ago
- ☆70Updated 3 months ago
- A resilient distributed training framework☆96Updated last year
- ☆156Updated 5 months ago
- Artifact for "Apparate: Rethinking Early Exits to Tame Latency-Throughput Tensions in ML Serving" [SOSP '24]☆25Updated last year
- Paper-reading notes for Berkeley OS prelim exam.☆14Updated last year
- PyTorch implementation of paper "Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline".☆93Updated 2 years ago
- [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention☆49Updated 4 months ago
- ☆20Updated last year
- ☆126Updated last year
- Official repository for the paper DynaPipe: Optimizing Multi-task Training through Dynamic Pipelines☆20Updated 2 years ago
- Scalable long-context LLM decoding that leverages sparsity—by treating the KV cache as a vector storage system.☆106Updated 3 months ago
- ☆42Updated last year
- ☆25Updated 2 years ago
- SpotServe: Serving Generative Large Language Models on Preemptible Instances☆133Updated last year
- ☆47Updated 7 months ago
- Official Repo for "SplitQuant / LLM-PQ: Resource-Efficient LLM Offline Serving on Heterogeneous GPUs via Phase-Aware Model Partition and …☆35Updated 3 months ago
- APEX+ is an LLM Serving Simulator☆41Updated 6 months ago
- Systems for GenAI☆148Updated 8 months ago
- [ICML 2024] Serving LLMs on heterogeneous decentralized clusters.☆33Updated last year
- Accelerating Large-Scale Reasoning Model Inference with Sparse Self-Speculative Decoding☆62Updated 3 weeks ago
- NEO is a LLM inference engine built to save the GPU memory crisis by CPU offloading☆73Updated 6 months ago
- ArkVale: Efficient Generative LLM Inference with Recallable Key-Value Eviction (NIPS'24)☆49Updated last year
- Dynamic resources changes for multi-dimensional parallelism training☆30Updated 4 months ago
- Surrogate-based Hyperparameter Tuning System☆27Updated 2 years ago
- Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“☆64Updated last year