transformers.js
6c4fab64 - Introduce wasm/webgpu inference chain to prevent "Session already started" errors (#1293)

Commit
222 days ago
Introduce wasm/webgpu inference chain to prevent "Session already started" errors (#1293) * Add PKV generation unit test with onnxruntime-genai GQA model * Introduce wasm/webgpu inference chain to prevent "Session already started" errors
Author
Parents
Loading