[Feature][Kernel]FusedMoE LoRA (#21229)

Signed-off-by: wuchen <cntryroa@gmail.com>
Signed-off-by: banjuede <lmklhc@163.com>
Signed-off-by: Chen Wu <cntryroa@gmail.com>
Signed-off-by: Danielle Robinson <dmmaddix@amazon.com>
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
Signed-off-by: bk-201 <joy25810@foxmail.com>
Co-authored-by: wuchen <wuchen@zetyun.com>
Co-authored-by: Nathan Van Gheem <vangheem@gmail.com>
Co-authored-by: banjuede <lmklhc@163.com>
Co-authored-by: Danielle Robinson <dmmaddix@amazon.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
Co-authored-by: bk-201 <joy25810@foxmail.com>
This commit is contained in:
Chen Wu
2025-10-21 03:01:37 +00:00
committed by GitHub
co-authored by wuchen Nathan Van Gheem banjuede Danielle Robinson Jee Jee Li bk-201
parent 3ada34f9cb
commit 5f6cbf60d6
28 changed files with 2084 additions and 55 deletions
+22
View File
@@ -1795,6 +1795,28 @@ def batched_moe_align_block_size(
)
def moe_lora_align_block_size(
topk_ids: torch.Tensor,
token_lora_mapping: torch.Tensor,
num_experts: int,
block_size: int,
max_loras: int,
sorted_token_ids: torch.Tensor,
experts_ids: torch.Tensor,
num_tokens_post_pad: torch.Tensor,
) -> None:
torch.ops._moe_C.moe_lora_align_block_size(
topk_ids,
token_lora_mapping,
num_experts,
block_size,
max_loras,
sorted_token_ids,
experts_ids,
num_tokens_post_pad,
)
def moe_wna16_gemm(
input: torch.Tensor,
output: torch.Tensor,