microsoft / tokenweaveLinks
Efficient Compute-Communication Overlap for Distributed LLM Inference
☆26Updated last month
Alternatives and similar repositories for tokenweave
Users that are interested in tokenweave are comparing it to the libraries listed below
Sorting:
- DISB is a new DNN inference serving benchmark with diverse workloads and models, as well as real-world traces.☆53Updated 11 months ago
- Artifact for "Apparate: Rethinking Early Exits to Tame Latency-Throughput Tensions in ML Serving" [SOSP '24]☆25Updated 8 months ago
- ☆25Updated last year
- Tacker: Tensor-CUDA Core Kernel Fusion for Improving the GPU Utilization while Ensuring QoS☆31Updated 5 months ago
- ☆38Updated 3 months ago
- gLLM: Global Balanced Pipeline Parallelism System for Distributed LLM Serving with Token Throttling☆37Updated last week
- SOTA Learning-augmented Systems☆36Updated 3 years ago
- Stateful LLM Serving☆79Updated 4 months ago
- Official resporitory for "IPDPS' 24 QSync: Quantization-Minimized Synchronous Distributed Training Across Hybrid Devices".☆20Updated last year
- A GPU-accelerated DNN inference serving system that supports instant kernel preemption and biased concurrent execution in GPU scheduling.☆42Updated 3 years ago
- [ACM EuroSys 2023] Fast and Efficient Model Serving Using Multi-GPUs with Direct-Host-Access☆57Updated this week
- ☆44Updated 7 months ago
- Vector search with bounded performance.☆36Updated last year
- Microsoft Collective Communication Library☆65Updated 8 months ago
- Thunder Research Group's Collective Communication Library☆39Updated last month
- FractalTensor is a programming framework that introduces a novel approach to organizing data in deep neural networks (DNNs) as a list of …☆28Updated 7 months ago
- ☆67Updated last year
- SHADE: Enable Fundamental Cacheability for Distributed Deep Learning Training☆35Updated 2 years ago
- ☆13Updated last year
- High performance RDMA-based distributed feature collection component for training GNN model on EXTREMELY large graph☆54Updated 3 years ago
- ☆51Updated 2 months ago
- ☆83Updated 4 months ago
- REEF is a GPU-accelerated DNN inference serving system that enables instant kernel preemption and biased concurrent execution in GPU sche…☆98Updated 2 years ago
- kvcached: Elastic KV cache for dynamic GPU sharing and efficient multi-LLM inference.☆35Updated last week
- NEO is a LLM inference engine built to save the GPU memory crisis by CPU offloading☆49Updated last month
- Paella: Low-latency Model Serving with Virtualized GPU Scheduling☆60Updated last year
- An Attention Superoptimizer☆22Updated 6 months ago
- SpotServe: Serving Generative Large Language Models on Preemptible Instances☆126Updated last year
- PerFlow-AI is a programmable performance analysis, modeling, prediction tool for AI system.☆21Updated 3 months ago
- Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“☆62Updated last year