### What this PR does / why we need it? qwen3-next suppot triton chunk_gated_delta_rule ops ### co-owners @OsirisDuan - vLLM version: v0.11.2 Signed-off-by: shiyuan680 <917935075@qq.com>
15 lines
897 B
Python
15 lines
897 B
Python
import vllm.model_executor.layers.mamba.ops.causal_conv1d
|
|
|
|
from vllm_ascend.ops.triton.fla.chunk import chunk_gated_delta_rule
|
|
from vllm_ascend.ops.triton.fla.layernorm_guard import LayerNormFn
|
|
from vllm_ascend.ops.triton.fla.sigmoid_gating import \
|
|
fused_recurrent_gated_delta_rule_fwd_kernel
|
|
from vllm_ascend.ops.triton.mamba.casual_conv1d import (
|
|
causal_conv1d_fn, causal_conv1d_update_npu)
|
|
|
|
vllm.model_executor.layers.mamba.ops.causal_conv1d.causal_conv1d_update = causal_conv1d_update_npu
|
|
vllm.model_executor.layers.mamba.ops.causal_conv1d.causal_conv1d_fn = causal_conv1d_fn
|
|
vllm.model_executor.layers.fla.ops.fused_recurrent.fused_recurrent_gated_delta_rule_fwd_kernel = fused_recurrent_gated_delta_rule_fwd_kernel
|
|
vllm.model_executor.layers.fla.ops.layernorm_guard.LayerNormFn = LayerNormFn
|
|
vllm.model_executor.layers.fla.ops.chunk.chunk_gated_delta_rule = chunk_gated_delta_rule
|