Pinned Loading
-
dnsts-cascade
dnsts-cascade Public4-tier asynchronous LLM cascade system achieving 120 tokens/sec on constrained hardware using llama.cpp, speculative decoding, and GPU+CPU parallel inference
Python
-
Quantum-Experiment
Quantum-Experiment PublicProduction-ready quantum computing platform: Local simulation (30 qubits), analytical mode (6000+ qubits), cloud integration (IBM Quantum, AWS Braket, Google Quantum)
Python
Something went wrong, please refresh the page to try again.
If the problem persists, check the GitHub status page or contact support.
If the problem persists, check the GitHub status page or contact support.