19b5d44ea8
### What this PR does / why we need it?
**Scope of Changes**:
| File Path |
| :--- |
|`vllm_ascend/ops/layer_shard_linear.py`|
|`vllm_ascend/ops/linear.py`|
|`vllm_ascend/ops/linear_op.py`|
|`vllm_ascend/worker/worker.py`|
| ` vllm_ascend/patch/worker/patch_bert.py` |
| ` vllm_ascend/patch/worker/patch_deepseek.py` |
| ` vllm_ascend/patch/worker/patch_distributed.py` |
| ` vllm_ascend/patch/worker/patch_module.py` |
| ` vllm_ascend/patch/worker/patch_multimodal_merge.py` |
| ` vllm_ascend/patch/worker/patch_qwen3_next.py` |
| ` vllm_ascend/patch/worker/patch_qwen3_next_mtp.py` |
| ` vllm_ascend/patch/worker/patch_rejection_sampler.py` |
| ` vllm_ascend/patch/worker/patch_rope.py` |
| ` vllm_ascend/patch/worker/patch_triton.py` |
| ` vllm_ascend/patch/worker/patch_unquantized_gemm.py` |
| ` vllm_ascend/patch/worker/patch_v2_egale.py` |
|` vllm_ascend/worker/npu_input_batch.py`|
|` vllm_ascend/worker/v2/aclgraph_utils.py`|
|` vllm_ascend/worker/v2/attn_utils.py`|
|` vllm_ascend/worker/v2/model_runner.py`|
|` vllm_ascend/worker/v2/sample/gumbel.py`|
|` vllm_ascend/worker/v2/sample/penalties.py`|
|` vllm_ascend/worker/v2/sample/sampler.py`|
|` vllm_ascend/worker/v2/spec_decode/__init__.py`|
|` vllm_ascend/worker/v2/spec_decode/eagle.py`|
|` vllm_ascend/worker/v2/states.py`|
### Does this PR introduce _any_ user-facing change?
### How was this patch tested?
- vLLM version: v0.14.0
- vLLM main:
d68209402d
Signed-off-by: MrZ20 <2609716663@qq.com>
Signed-off-by: SILONG ZENG <2609716663@qq.com>
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
Co-authored-by: wangxiyuan <wangxiyuan1007@gmail.com>
18 lines
1.1 KiB
Python
18 lines
1.1 KiB
Python
import vllm.model_executor.layers.mamba.ops.causal_conv1d
|
|
import vllm.v1.worker.gpu.sample.gumbel
|
|
|
|
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.causal_conv1d import causal_conv1d_fn, causal_conv1d_update_npu
|
|
from vllm_ascend.worker.v2.sample.gumbel import gumbel_sample as ascend_gumbel_sample
|
|
|
|
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_gated_delta_rule = chunk_gated_delta_rule
|
|
vllm.v1.worker.gpu.sample.gumbel.gumbel_sample = ascend_gumbel_sample
|