repoGitHubTrust 82 · PrimaryPublished 2d agoLive · yesterday

palle-k/DL4S

Accelerated tensor operations and dynamic neural networks based on reverse mode automatic differentiation for every device that can run Swift - from watchOS to Linux

Lineage graph

Paper → model → repo connections mined from source citations (Tier-1 exact match).

Why these links exist

Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.

PossiblePossibly related (embedding) · 47%[Paper] Automated Tensor Scheduling for Hybrid CPU-GPU LLM Inference on Consumer Devices →
PossiblePossibly related (embedding) · 46%A Thread-Register Decoupled GPU Execution Model for Efficient Tensor Computation →

Covers

news[Paper] Automated Tensor Scheduling for Hybrid CPU-GPU LLM Inference on Consumer Devices newsA Thread-Register Decoupled GPU Execution Model for Efficient Tensor Computation

Related across the graph

news[Paper] Automated Tensor Scheduling for Hybrid CPU-GPU LLM Inference on Consumer Devices newsA Thread-Register Decoupled GPU Execution Model for Efficient Tensor Computation

Topics