Pinned Loading

1. velo-sentinel velo-sentinel Public

   Production-grade Java 25 Virtual Thread inference gateway bridging NVIDIA Triton → Dynamo with Earliest Deadline First (EDF) priority queuing, adaptive batching, and async shadow validation.

   Java 1

2. velo-core velo-core Public

   A production-grade, native Rust speculative inference engine for Apple Silicon with Metal GPU acceleration and paged attention.

   Rust 2

3. velo-infra-playground velo-infra-playground Public

   A Go-centric systems engineering lab simulating HPC batch scheduling (Slurm), bare-metal BMCs (Redfish), collective GPU topologies (NCCL), and custom Kubernetes scaling operators for local macOS de…

   Go 1

4. beat-opus-4.5-challenge beat-opus-4.5-challenge Public

   An optimized schedule for a simulated VLIW/SIMD CPU kernel executing a parallel tree traversal & custom hashing workload using Python. Achieves a 16.74x speedup (reducing CPU cycles from 18532 to 1…

   1

5. vllm vllm Public

   Forked from vllm-project/vllm

   A high-throughput and memory-efficient inference and serving engine for LLMs

   Python

6. scrub-pii scrub-pii Public

   Scrub personal identifiable information on unstructured json data with Go

   Go 1