Add Qwen3.6 MoE inference support

This commit is contained in:
2026-07-13 20:24:41 +08:00
parent 588bfd9df3
commit a2de146fb6
27 changed files with 3153 additions and 149 deletions

View File

@@ -30,6 +30,7 @@ fn main() {
.file("../../csrc/attention/flash_attention.cu")
.file("../../csrc/attention/paged_attention.cu")
.file("../../csrc/attention/reshape_and_cache.cu")
.file("../../csrc/attention/deltanet.cu")
.file("../../csrc/moe/moe_kernels.cu")
.file("../../csrc/moe/moe_sparse.cu")
.file("../../csrc/quantization/dequant_fp8.cu")