mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-14 06:27:45 +08:00
A redundant D2D copy is observed when enabling torch.compile for the Llama model due to the swiglu triton kernel, which brings perf overhead. Use a custom op to wrap the swiglu op to avoid this overhead. Signed-off-by: Yukun He <23156053+hyukn@users.noreply.github.com> |
||
|---|---|---|
| .. | ||
| fused_moe | ||
| mamba | ||
| __init__.py | ||
| attention.py | ||
| decoder_layer.py | ||
| embedding.py | ||
| gated_mlp.py | ||
| layer_norm.py | ||
| linear.py | ||
| logits_processor.py | ||
| mlp.py | ||
| multi_stream_utils.py | ||
| rms_norm.py | ||
| rotary_embedding.py | ||
| swiglu.py | ||
| triton_linear.py | ||