e20813f441
### What this PR does / why we need it? this pr implement eagle spec decoding for model runner v2, please see RFC https://github.com/vllm-project/vllm-ascend/issues/5208 ### Does this PR introduce _any_ user-facing change? No ### How was this patch tested? vLLM version: v0.13.0 --------- Signed-off-by: Ronald1995 <ronaldautomobile@163.com>
19 lines
1.1 KiB
Python
19 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
|