AISys-01 / vllm-CachedAttentionLinks
The code based on vLLM for the paper “ Cost-Efficient Large Language Model Serving for Multi-turn Conversations with CachedAttention”.
☆11Updated last year
Alternatives and similar repositories for vllm-CachedAttention
Users that are interested in vllm-CachedAttention are comparing it to the libraries listed below
Sorting:
- ☆40Updated 2 years ago
- WaferLLM: Large Language Model Inference at Wafer Scale☆77Updated last month
- MAGIS: Memory Optimization via Coordinated Graph Transformation and Scheduling for DNN (ASPLOS'24)☆55Updated last year
- Large Language Model (LLM) Serving Paper and Resource List☆24Updated 6 months ago
- ☆58Updated 5 months ago
- Github repository of HPCA 2025 paper "UniNDP: A Unified Compilation and Simulation Tool for Near DRAM Processing Architectures"☆15Updated last week
- LLM serving cluster simulator☆126Updated last year
- REEF is a GPU-accelerated DNN inference serving system that enables instant kernel preemption and biased concurrent execution in GPU sche…☆102Updated 2 years ago
- ☆141Updated this week
- ☆25Updated 3 years ago
- [HPCA'24] Smart-Infinity: Fast Large Language Model Training using Near-Storage Processing on a Real System☆49Updated 4 months ago
- ☆32Updated 5 years ago
- ☆34Updated last year
- Open-source implementation for "Helix: Serving Large Language Models over Heterogeneous GPUs and Network via Max-Flow"☆74Updated 2 months ago
- The Artifact of NeoMem: Hardware/Software Co-Design for CXL-Native Memory Tiering☆59Updated last year
- InfiniGen: Efficient Generative Inference of Large Language Models with Dynamic KV Cache Management (OSDI'24)☆167Updated last year
- Artifact for paper "PIM is All You Need: A CXL-Enabled GPU-Free System for LLM Inference", ASPLOS 2025☆112Updated 7 months ago
- A scheduling framework for multitasking over diverse XPUs, including GPUs, NPUs, ASICs, and FPGAs☆140Updated last week
- ☆63Updated last month
- This serves as a repository for reproducibility of the SC21 paper "In-Depth Analyses of Unified Virtual Memory System for GPU Accelerated…☆36Updated 2 years ago
- ☆27Updated last year
- CXL-DMSim: A Full-System CXL Disaggregated Memory Simulator With Comprehensive Silicon Validation☆113Updated last month
- This is an read-only mirror of the gem5 simulator. The upstream repository is stored in https://gem5.googlesource.com, code reviews shoul…☆36Updated last year
- ☆212Updated last month
- A GPU-accelerated DNN inference serving system that supports instant kernel preemption and biased concurrent execution in GPU scheduling.☆44Updated 3 years ago
- PIM-DL: Expanding the Applicability of Commodity DRAM-PIMs for Deep Learning via Algorithm-System Co-Optimization☆34Updated last year
- ☆36Updated last year
- ☆23Updated 2 years ago
- NeuPIMs: NPU-PIM Heterogeneous Acceleration for Batched LLM Inferencing☆104Updated last year
- LLMServingSim: A HW/SW Co-Simulation Infrastructure for LLM Inference Serving at Scale☆162Updated 4 months ago