26 tagged jax, measured the same way as everything else here.
Browse within: machine-learning 23autoresearch 13knowledge-graph 13mfu 13nisq 11PyTorch 10open-quantum-systems 10quantum-algorithm 10
tensorcircuit/tensorcircuit-ng
Skill Claude CodeCodex
Autonomously reproduces quantum computing arXiv papers using TensorCircuit-NG. It creates standardized repository structures, generates meta.yaml, writes and runs JAX-accelerated code, and strictly enforces code quality (black/pylint) before saving final figures.
tensorcircuit/tensorcircuit-ng
Skill Claude CodeCodex
Tune tensor-network contraction path search and slicing for TensorCircuit-NG workloads, especially OMECO and cotengra hyperparameters, memory targets, total FLOPs/write, slice counts, and large-circuit amplitude or expectation contractions.
tensorcircuit/tensorcircuit-ng
Skill Claude CodeCodex
Analyzes and refactors TensorCircuit-NG code to achieve peak time and memory performance. It enforces advanced JAX vectorization, intelligent JIT staging, optimal tensor network contraction, and memory-efficient autodiff strategies.
vlasenkoalexey/tpu_performance_autoresearch_wiki
Skill Claude CodeCodex
Generate a comprehensive retrospective for a (model, lane) pair that maps the explored search space, identifies coverage gaps from the topic taxonomy (model-optimization-index.md) and Pallas kernel catalog, surfaces premature-exhaustion signals (single-axis-probe vs kernel-port imbalance, frontier-stuck duration), and…
vlasenkoalexey/tpu_performance_autoresearch_wiki
Skill Claude CodeCodex
Generate a structured optimization hypothesis for the autoresearch loop. Walks three layers — (1) the generic wiki/model-optimization-index.md for TPU envelope data + topic pointers + cross-model refuted-pattern principles, (2) the generic wiki/model-optimization-blueprint.md for ladder-keyed phase ordering +…
vlasenkoalexey/tpu_performance_autoresearch_wiki
Skill Claude CodeCodex
Start the autoresearch optimization loop for a specific model + lane. Resolves the hierarchical program.md (root → model → lane), asks the user for hardware (local TPU VM or GKE cluster of a specified TPU type + topology), discovers available clusters from .env/, checks occupancy with USERPREFIX-aware attribution…
Skill Claude CodeCodex
Drive Dense-Evolution's real quantum circuit simulator, VQE solver, molecular Hamiltonian builder, QM/MM force calculator, and MD trajectory engine directly through the denseevolutionmcp MCP server, instead of writing new simulation code or describing what a circuit should do in the abstract. Use this skill whenever…