SJTU-IPADS / PhoenixOSLinks
Fast OS-level support for GPU checkpoint and restore
☆267Updated 3 months ago
Alternatives and similar repositories for PhoenixOS
Users that are interested in PhoenixOS are comparing it to the libraries listed below
Sorting:
- ☆222Updated 2 weeks ago
- An interference-aware scheduler for fine-grained GPU sharing☆158Updated last month
- Artifacts for our NSDI'23 paper TGS☆95Updated last year
- Here are my personal paper reading notes (including cloud computing, resource management, systems, machine learning, deep learning, and o…☆146Updated this week
- REEF is a GPU-accelerated DNN inference serving system that enables instant kernel preemption and biased concurrent execution in GPU sche…☆105Updated 3 years ago
- A scheduling framework for multitasking over diverse XPUs, including GPUs, NPUs, ASICs, and FPGAs☆150Updated last week
- ☆70Updated 2 months ago
- High performance Transformer implementation in C++.☆148Updated 11 months ago
- A framework for generating realistic LLM serving workloads☆94Updated 3 months ago
- KV cache store for distributed LLM inference☆384Updated last month
- DeepSeek-V3/R1 inference performance simulator☆175Updated 9 months ago
- Stateful LLM Serving☆93Updated 10 months ago
- ☆20Updated 6 months ago
- ☆92Updated 9 months ago
- SpotServe: Serving Generative Large Language Models on Preemptible Instances☆134Updated last year
- ☆79Updated 3 years ago
- NCCL Profiling Kit☆150Updated last year
- Venus Collective Communication Library, supported by SII and Infrawaves.☆132Updated this week
- ☆337Updated last week
- Artifact of OSDI '24 paper, ”Llumnix: Dynamic Scheduling for Large Language Model Serving“☆64Updated last year
- ☆81Updated 2 months ago
- Efficient and easy multi-instance LLM serving☆520Updated 4 months ago
- A prefill & decode disaggregated LLM serving framework with shared GPU memory and fine-grained compute isolation.☆123Updated 2 weeks ago
- NEO is a LLM inference engine built to save the GPU memory crisis by CPU offloading☆77Updated 6 months ago
- Paella: Low-latency Model Serving with Virtualized GPU Scheduling☆66Updated last year
- example code for using DC QP for providing RDMA READ and WRITE operations to remote GPU memory☆152Updated last year
- Microsoft Collective Communication Library☆66Updated last year
- A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems☆228Updated 5 months ago
- Injecting Adrenaline into LLM Serving: Boosting Resource Utilization and Throughput via Attention Disaggregation☆39Updated 2 months ago
- A lightweight design for computation-communication overlap.☆207Updated 2 weeks ago