eunomia-bpf / eGPULinks
Extending eBPF Programmability and Observability to GPUs (merged into https://github.com/eunomia-bpf/bpftime)
☆290Updated 2 months ago
Alternatives and similar repositories for eGPU
Users that are interested in eGPU are comparing it to the libraries listed below
Sorting:
- CXL remote offloading data movement aware compiler☆72Updated last month
- CXLMemSim: A pure software simulated CXL.mem for performance characterization☆599Updated last week
- UCCL is an efficient communication library for GPUs, covering collectives, P2P (e.g., KV cache transfer, RL weight transfer), and EP (e.g…☆1,208Updated this week
- Heterogeneous Containerization of Agents☆109Updated 6 months ago
- PTX on XPUs☆123Updated 2 weeks ago
- Expert Kit is an efficient foundation of Expert Parallelism (EP) for MoE model Inference on heterogenous hardware☆61Updated last week
- YiRage (Yield Revolutionary AGile Engine) - Multi-Backend LLM Inference Optimization. Extends Mirage with comprehensive support for CUDA,…☆36Updated last week
- [Neurips 2025] R-KV: Redundancy-aware KV Cache Compression for Reasoning Models☆1,174Updated 3 months ago
- Hybrid-tier key-value storage engine built on object storage & local SSDs. Engineered for batch-write efficiency and read optimization wi…☆265Updated this week
- Some Hardware Architectures for GEMM☆288Updated 8 months ago
- Official implementation of "REASONING COMPILER: LLM-Guided Optimizations for Efficient Model Serving" (NeurIPS 2025)☆99Updated 2 months ago
- An acceleration library that supports arbitrary bit-width combinatorial quantization operations☆240Updated last year
- A Tiny structure of pytorch for learning;☆61Updated last year
- [NeurIPS'25] KVCOMM: Online Cross-context KV-cache Communication for Efficient LLM-based Multi-agent Systems☆127Updated 3 months ago
- A toolkit enhances PyTorch with specialized functions for low-bit quantized neural networks.☆196Updated last year
- 2025华为软件精英挑战赛 总决赛最佳大模型应用奖☆38Updated 9 months ago
- Unified KV Cache Compression Methods for Auto-Regressive Models☆1,306Updated last year
- ☆140Updated 6 months ago
- YiTu is an easy-to-use runtime to fully exploit the hybrid parallelism of different hardwares (e.g., GPU) to efficiently support the exec…☆254Updated last month
- JittorGeometric is a Jittor-based graph machine learning library.☆603Updated 5 months ago
- Code Efficiency Benchmark☆86Updated 9 months ago
- ☆204Updated 4 months ago
- Mega Scale Multimodal DataPipeline for SOTA models☆105Updated this week
- ☆260Updated this week
- ☆24Updated last year
- Fastest bloom filter in C++/Go/Rust/Java/C#☆109Updated last month
- ☆280Updated last month
- ☆102Updated 5 years ago
- Mixed precision inference by Tensorrt-LLM☆81Updated last year
- TVM Documentation in Chinese Simplified / TVM 中文文档☆3,239Updated 2 months ago