eunomia-bpf / eGPULinks
Extending eBPF Programmability and Observability to GPUs (merged into https://github.com/eunomia-bpf/bpftime)
☆288Updated 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☆71Updated 3 weeks ago
- CXLMemSim: A pure software simulated CXL.mem for performance characterization☆504Updated this week
- Heterogeneous Containerization of Large Language Model Apps☆109Updated 6 months ago
- UCCL is an efficient communication library for GPUs, covering collectives, P2P (e.g., KV cache transfer, RL weight transfer), and EP (e.g…☆1,188Updated this week
- Expert Kit is an efficient foundation of Expert Parallelism (EP) for MoE model Inference on heterogenous hardware☆61Updated this week
- PTX on XPUs☆119Updated last week
- [Neurips 2025] R-KV: Redundancy-aware KV Cache Compression for Reasoning Models☆1,170Updated 3 months ago
- Hybrid-tier key-value storage engine built on object storage & local SSDs. Engineered for batch-write efficiency and read optimization wi…☆200Updated last week
- YiRage (Yield Revolutionary AGile Engine) - Multi-Backend LLM Inference Optimization. Extends Mirage with comprehensive support for CUDA,…☆37Updated last week
- An acceleration library that supports arbitrary bit-width combinatorial quantization operations☆240Updated last year
- Some Hardware Architectures for GEMM☆286Updated 8 months ago
- Official implementation of "REASONING COMPILER: LLM-Guided Optimizations for Efficient Model Serving" (NeurIPS 2025)☆98Updated last month
- [NeurIPS'25] KVCOMM: Online Cross-context KV-cache Communication for Efficient LLM-based Multi-agent Systems☆125Updated 2 months ago
- ☆204Updated 4 months ago
- A Tiny structure of pytorch for learning;☆60Updated last year
- Unified KV Cache Compression Methods for Auto-Regressive Models☆1,298Updated last year
- DrCCTProf is a fine-grained call path profiling framework for binaries running on ARM and X86 architectures.☆123Updated 2 years ago
- TVM Documentation in Chinese Simplified / TVM 中文文档☆3,110Updated 2 months ago
- JittorGeometric is a Jittor-based graph machine learning library.☆585Updated 5 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 3 weeks ago
- A toolkit enhances PyTorch with specialized functions for low-bit quantized neural networks.☆196Updated last year
- Fastest bloom filter in C++/Go/Rust/Java/C#☆109Updated last month
- ☆265Updated 3 weeks ago
- 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
- Code Efficiency Benchmark☆86Updated 8 months ago
- The Next-Gen Database for AI—an infrastructure designed for data and AI. As the MySQL of the AI era.☆160Updated this week
- A highly optimized LLM inference acceleration engine for Llama and its variants.☆905Updated 6 months ago
- ☆24Updated last year
- ☆803Updated 3 weeks ago
- ☆102Updated 5 years ago