lambda7xx / mlc-notes
☆11Updated 2 years ago
Related projects ⓘ
Alternatives and complementary repositories for mlc-notes
- ATC23 AE☆43Updated last year
- ☆24Updated 3 weeks ago
- Python package for rematerialization-aware gradient checkpointing☆23Updated last year
- Artifacts for our SIGCOMM'23 paper Ditto☆16Updated last year
- paper and its code for AI System☆215Updated 2 months ago
- ☆67Updated last month
- Cupcake: A Compression Scheduler for Scalable Communication-Efficient Distributed Training (MLSys '23)☆9Updated last year
- ☆15Updated 4 months ago
- Bamboo is a system for running large pipeline-parallel DNNs affordably, reliably, and efficiently using spot instances.☆47Updated last year
- ☆23Updated last year
- ☆46Updated 5 months ago
- Stateful LLM Serving☆38Updated 3 months ago
- ☆35Updated 3 months ago
- Official repository for the paper DynaPipe: Optimizing Multi-task Training through Dynamic Pipelines☆14Updated 11 months ago
- MagicPIG: LSH Sampling for Efficient LLM Generation☆59Updated 3 weeks ago
- Deferred Continuous Batching in Resource-Efficient Large Language Model Serving (EuroMLSys 2024)☆11Updated 5 months ago
- nnScaler: Compiling DNN models for Parallel Training☆75Updated 3 weeks ago
- Systems for GenAI☆68Updated last week
- Code for "Apparate: Rethinking Early Exits to Tame Latency-Throughput Tensions in ML Serving" [SOSP '24]☆16Updated last month
- A high-performance distributed deep learning system targeting large-scale and automated distributed training. If you have any interests, …☆104Updated 11 months ago
- LLM serving cluster simulator☆81Updated 6 months ago
- A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems☆133Updated last month
- PyTorch implementation of paper "Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline".☆74Updated last year
- ☆51Updated last month
- Vector search with bounded performance.☆33Updated 9 months ago
- ☆66Updated 3 years ago
- AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving (OSDI 23)☆78Updated last year
- EuroSys '24: "Trinity: A Fast Compressed Multi-attribute Data Store"☆16Updated 6 months ago
- An experimental parallel training platform☆52Updated 7 months ago
- Code for "Shockwave: Fair and Efficient Cluster Scheduling for Dynamic Adaptation in Machine Learning" [NSDI '23]☆38Updated last year