ciflow/xpu/185531: Add oneDNN LSTM primitive support for XPU inference
🔒
https://github.com
«Use dnnl::lstm_forward primitive on XPU for LSTM inference, providing
significant speedup over the per-timestep fused cell approach by
eliminating kernel launch overhead entirely.
Key changes:
New aten/src/ATen/native/m...»
Automatische Weiterleitung...
1.5s