HugoZHL / PQCache
☆13Updated 3 months ago
Related projects ⓘ
Alternatives and complementary repositories for PQCache
- InfiniGen: Efficient Generative Inference of Large Language Models with Dynamic KV Cache Management (OSDI'24)☆76Updated 4 months ago
- ☆55Updated 2 years ago
- ☆43Updated last month
- A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems☆126Updated 3 weeks ago
- ☆15Updated 4 months ago
- Compiler for Dynamic Neural Networks☆43Updated 11 months ago
- ArkVale: Efficient Generative LLM Inference with Recallable Key-Value Eviction (NIPS'24)☆16Updated 2 weeks ago
- ☆14Updated 5 months ago
- ☆82Updated 5 months ago
- MAGIS: Memory Optimization via Coordinated Graph Transformation and Scheduling for DNN (ASPLOS'24)☆43Updated 5 months ago
- This repository is established to store personal notes and annotated papers during daily research.☆86Updated this week
- Efficient Interactive LLM Serving with Proxy Model-based Sequence Length Prediction | A tiny model can tell you the verbosity of an LLM (…☆19Updated 5 months ago
- Puzzles for learning Triton, play it with minimal environment configuration!☆61Updated this week
- ☆20Updated last week
- MagicPIG: LSH Sampling for Efficient LLM Generation☆45Updated 2 weeks ago
- Adaptive Message Quantization and Parallelization for Distributed Full-graph GNN Training☆20Updated 8 months ago
- Stateful LLM Serving☆37Updated 3 months ago
- REEF is a GPU-accelerated DNN inference serving system that enables instant kernel preemption and biased concurrent execution in GPU sche…☆85Updated last year
- Artifacts for our ASPLOS'23 paper ElasticFlow☆52Updated 6 months ago
- High performance Transformer implementation in C++.☆80Updated last month
- ☆12Updated 6 months ago
- Awesome-LLM-KV-Cache: A curated list of 📙Awesome LLM KV Cache Papers with Codes.☆96Updated this week
- ☆42Updated 7 months ago
- AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving (OSDI 23)☆79Updated last year
- ☆27Updated 3 months ago
- Official repository for the paper DynaPipe: Optimizing Multi-task Training through Dynamic Pipelines☆14Updated 11 months ago
- DISB is a new DNN inference serving benchmark with diverse workloads and models, as well as real-world traces.☆54Updated 2 months ago
- Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“☆56Updated 5 months ago
- ☆34Updated 2 months ago
- ☆23Updated last year