This commit is contained in:
2026-02-10 23:08:39 +08:00
parent 1baa36026c
commit 6680585975
172 changed files with 52867 additions and 892 deletions

View File

@@ -0,0 +1,16 @@
import vllm.model_executor.layers.fla.ops.chunk
import vllm.model_executor.layers.fla.ops.fused_recurrent
import vllm.model_executor.layers.fla.ops.layernorm_guard
import vllm.model_executor.layers.mamba.ops.causal_conv1d
from vllm_npu.ops.casual_conv1d import (causal_conv1d_fn,
causal_conv1d_update_npu)
from vllm_npu.ops.fla import LayerNormFn, torch_chunk_gated_delta_rule
from vllm_npu.ops.sigmoid_gating import \
fused_recurrent_gated_delta_rule_fwd_kernel
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 = torch_chunk_gated_delta_rule