Pinned Loading

1. openml/openml-python openml/openml-python Public

   OpenML's Python API for a World of Data and More 💫

   Python 368 309

2. headrace headrace Public

   A single-GPU LLM inference engine: continuous batching, paged KV cache, radix prefix cache, chunked prefill, CPU-GPU overlap scheduling, CUDA Graph decode, a C++ scheduling core, and two-model spec…

   Python

3. fused-llm-kernels fused-llm-kernels Public

   FP32 SGEMM optimization ladder (naive to warp tiling) on Ada sm_89, plus fused Triton operators. Every speedup backed by Nsight Compute data.

   Cuda

4. silverhand silverhand Public

   An end-to-end solution leveraging SOTA AI frameworks to automate and refine application writing. Keywords: Autonomous Multi-agent Workflow; RAG pipeline; OpenAI Integration; Semantic Text Splitting…

   Python

5. distributed-kv-db distributed-kv-db Public

   Distributed system with MIT | Highly consistent and fault-tolerant distributed key-value store using the RAFT consensus algorithm

   C++

6. goliath-national goliath-national Public

   Istio Service Mesh | mTLS | Apache Kafka | Spring Cloud Stream | Kubernetes | K8s Service Discovery | Resilience4j | Actuator-OpenTelemetry-Tempo-Prometheus-Grafana | SpringBoot | H2

   Java