Add Qwen3.6 MoE inference support
This commit is contained in:
@@ -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")
|
||||
|
||||
Reference in New Issue
Block a user