[Iluvatar GPU] Optimize attention performance and fix moe load ckpt error (#3651)

This commit is contained in:
yzwu
2025-09-22 21:13:59 +08:00
committed by GitHub
parent 5532e8a323
commit 504461b6b5
17 changed files with 1344 additions and 363 deletions

View File

@@ -536,6 +536,8 @@ elif paddle.is_compiled_with_custom_device("iluvatar_gpu"):
"iluvatar_ops/moe_dispatch.cu",
"iluvatar_ops/moe_reduce.cu",
"iluvatar_ops/paged_attn.cu",
"iluvatar_ops/prefill_fused_attn.cu",
"iluvatar_ops/mixed_fused_attn.cu",
"iluvatar_ops/w8a16_group_gemm.cu",
"iluvatar_ops/runtime/iluvatar_context.cc",
],