[Model Refactoring] Move deepseek_v4_ops to models/deepseek_v4 [3/N] (#43073)

Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
This commit is contained in:
Woosuk Kwon
2026-05-19 00:52:54 -07:00
committed by GitHub
parent 301d986473
commit b14be81c1f
20 changed files with 34 additions and 29 deletions
+2 -2
View File
@@ -17,11 +17,11 @@ import pytest
import torch
from vllm import _custom_ops as ops
from vllm.v1.attention.ops.deepseek_v4_ops import (
from vllm.models.deepseek_v4.common.ops import (
dequantize_and_gather_k_cache,
quantize_and_insert_k_cache,
)
from vllm.v1.attention.ops.deepseek_v4_ops.fused_compress_quant_cache import (
from vllm.models.deepseek_v4.common.ops.fused_compress_quant_cache import (
_fused_kv_compress_norm_rope_insert_indexer_attn,
_fused_kv_compress_norm_rope_insert_indexer_mxfp4_attn,
)