-
-
-
PairGEMM Public
Optimized a high-performance CUDA kernel for pair-wise batched 4x4 matrix multiplication on NVIDIA T4 GPUs.
Cuda UpdatedApr 19, 2026 -
distributed-matmul Public
A progressively optimized implementation of Cannon's algorithm for distributed matrix multiplication using MPI.
C UpdatedApr 19, 2026 -
NAND-to-Computer Public
Built a fully functional 16-bit computer from the ground up — starting from a single NAND gate through to a working CPU, ALU, and memory hierarchy — using a hardware description language(simplified…
Hack UpdatedApr 19, 2026 -
Key-Value-Store Public
A lightweight, Redis-compatible in-memory key-value store built from scratch in Go. Integrated the RESP (Redis Serialization Protocol) for wire-level compatibility with standard Redis clients.
Go UpdatedApr 19, 2026 -
-
Meditrack Public
A microservice-based patient management system. Build using Java SpringBoot, gRpc, Kafka, Docker, LocalStack, AWS
Java UpdatedApr 12, 2026 -
-
{{ message }}