Expand description
wgpu-backed host engines and runtime glue. Layer 3 complete compute engines.
Each engine is a self-contained GPU compute pipeline: structured input in, compute passes on a real GPU backend, typed output back.
Modules§
- bfs_
queue_ slots_ for_ device - Adapter-limit helper for BFS queue sizing.
- dataflow
- Generic graph dataflow engines. Generic GPU graph dataflow engines.
- decode
- Recursive decode pipeline (base64, hex, url, unicode) with region management.
- decompress
- Block decompression pipeline (deflate, LZ4, zstd) over IR compositions. Bulk GPU decompression pipeline using the vyre runtime.
- dfa
- DFA pattern matching engine. Host-side DFA workflow dispatcher.