mkdir triton package and move triton files (#4420)
### What this PR does / why we need it?
mkdir triton package and move triton files
- vLLM version: v0.11.0
- vLLM main:
2918c1b49c
Signed-off-by: shiyuan680 <917935075@qq.com>
This commit is contained in:
0
vllm_ascend/ops/triton/__init__.py
Normal file
0
vllm_ascend/ops/triton/__init__.py
Normal file
0
vllm_ascend/ops/triton/fla/__init__.py
Normal file
0
vllm_ascend/ops/triton/fla/__init__.py
Normal file
0
vllm_ascend/ops/triton/mamba/__init__.py
Normal file
0
vllm_ascend/ops/triton/mamba/__init__.py
Normal file
@@ -3,11 +3,12 @@ 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_ascend.ops.casual_conv1d import (causal_conv1d_fn,
|
||||
causal_conv1d_update_npu)
|
||||
from vllm_ascend.ops.fla import LayerNormFn, torch_chunk_gated_delta_rule
|
||||
from vllm_ascend.ops.sigmoid_gating import \
|
||||
from vllm_ascend.ops.triton.fla.fla import (LayerNormFn,
|
||||
torch_chunk_gated_delta_rule)
|
||||
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
|
||||
|
||||
Reference in New Issue
Block a user