diff --git a/docs/source/feature/dynamicemb.md b/docs/source/feature/dynamicemb.md
index 05278721..61f5fd63 100644
--- a/docs/source/feature/dynamicemb.md
+++ b/docs/source/feature/dynamicemb.md
@@ -4,9 +4,11 @@ DynamicEmbedding 是特征零Hash冲突Id化的一种方式，它相比设置`ha
 
 注：目前使用DynamicEmbedding还处于实验阶段，配置和接口都可能调整，暂只支持训练和评估，暂不包含在官方提供的镜像环境中，使用前需要额外安装如下whl包
 
+注：同一个 FeatureGroup 中若存在多个配置了 DynamicEmbedding 的特征，底层 dynamicemb 会自动将这些表融合到同一份存储里（table fusion），共享 cache/admission counter，降低显存占用并减少内存碎片，无需额外配置。
+
 ```bash
 # DEVICE 可选: cu126/cu129 (支持 Python 3.10/3.11/3.12)
-pip install dynamicemb-0.0.1+20260331.bea6b4b.${DEVICE} -f https://tzrec.oss-cn-beijing.aliyuncs.com/third_party/dynamicemb/${DEVICE}/repo.html
+pip install dynamicemb-0.0.1+20260407.97b80bf.${DEVICE} -f https://tzrec.oss-cn-beijing.aliyuncs.com/third_party/dynamicemb/${DEVICE}/repo.html
 ```
 
 以id_feature的配置为例，DynamicEmbedding 只需在id_feature新增一个dynamicemb的配置字段
@@ -34,11 +36,14 @@ feature_configs {
 
 - **max_capacity**: 最大的id数，Id数超过后会根据Id的驱逐策略进行淘汰
 
-- **score_strategy**: Id驱逐策略，默认为 STEP，目前支持 TIMESTAMP | STEP | LFU
+- **score_strategy**: Id驱逐策略，默认为 STEP，目前支持 TIMESTAMP | STEP | LFU | NO_EVICTION
 
   - TIMESTAMP: 每个Id根据最近更新的时间戳，驱逐时间戳最小的Id
   - STEP: 每个Id根据最近更新的迭代步数，驱逐步数最早的Id
   - LFU: 每个Id根据出现的频次，驱逐频次小的Id
+  - NO_EVICTION: 不驱逐，表容量到达 `max_capacity` 后不再接收新Id，适合配合 `init_capacity_per_rank` 做可扩容的表
+
+- **bucket_capacity**: （可选）dynamicemb 哈希表 bucket 大小，默认为 128，增大可提升表的装填率但会增加每次查表的探测代价
 
 - **initializer_args**: 参数初始化设置，默认是 UNIFORM
 
diff --git a/requirements/extra.txt b/requirements/extra.txt
index 4a50b4c8..76086107 100644
--- a/requirements/extra.txt
+++ b/requirements/extra.txt
@@ -1,4 +1,4 @@
-dynamicemb @ https://tzrec.oss-accelerate.aliyuncs.com/third_party/dynamicemb/cu129/dynamicemb-0.0.1%2B20260331.bea6b4b.cu129-cp310-cp310-linux_x86_64.whl ; python_version=="3.10"
-dynamicemb @ https://tzrec.oss-accelerate.aliyuncs.com/third_party/dynamicemb/cu129/dynamicemb-0.0.1%2B20260331.bea6b4b.cu129-cp311-cp311-linux_x86_64.whl ; python_version=="3.11"
-dynamicemb @ https://tzrec.oss-accelerate.aliyuncs.com/third_party/dynamicemb/cu129/dynamicemb-0.0.1%2B20260331.bea6b4b.cu129-cp312-cp312-linux_x86_64.whl ; python_version=="3.12"
+dynamicemb @ https://tzrec.oss-accelerate.aliyuncs.com/third_party/dynamicemb/cu129/dynamicemb-0.0.1%2B20260407.97b80bf.cu129-cp310-cp310-linux_x86_64.whl ; python_version=="3.10"
+dynamicemb @ https://tzrec.oss-accelerate.aliyuncs.com/third_party/dynamicemb/cu129/dynamicemb-0.0.1%2B20260407.97b80bf.cu129-cp311-cp311-linux_x86_64.whl ; python_version=="3.11"
+dynamicemb @ https://tzrec.oss-accelerate.aliyuncs.com/third_party/dynamicemb/cu129/dynamicemb-0.0.1%2B20260407.97b80bf.cu129-cp312-cp312-linux_x86_64.whl ; python_version=="3.12"
 torch_fx_tool @ https://tzrec.oss-accelerate.aliyuncs.com/third_party/rtp/torch_fx_tool-0.0.1%2B20251201.8c109c4-py3-none-any.whl
diff --git a/tzrec/protos/feature.proto b/tzrec/protos/feature.proto
index c5bd99d8..29897b0d 100644
--- a/tzrec/protos/feature.proto
+++ b/tzrec/protos/feature.proto
@@ -94,7 +94,7 @@ message DynamicEmbedding {
     // the initializer args for evaluation mode. default is
     // default is constant initialization with value 0.0.
     optional DynamicEmbInitializerArgs eval_initializer_args = 2;
-    // strategy to set the score for each indices in forward and backward per table. TIMESTAMP | STEP | CUSTOMIZED | LFU
+    // strategy to set the score for each indices in forward and backward per table. TIMESTAMP | STEP | CUSTOMIZED | LFU | NO_EVICTION
     optional string score_strategy = 4 [default = "STEP"];
     // max number of embedding rows
     required uint64 max_capacity = 5;
@@ -104,6 +104,10 @@ message DynamicEmbedding {
     optional uint64 init_capacity_per_rank = 7;
     // init table path
     optional string init_table = 8;
+    // hash-table bucket capacity. default 128 (matches dynamicemb
+    // DEFAULT_BUCKET_CAPACITY). larger buckets trade probe cost for
+    // higher load factor.
+    optional uint64 bucket_capacity = 9;
     oneof admission_strategy {
         DynamicEmbFrequencyAdmissionStrategy frequency_admission_strategy = 100;
     }
diff --git a/tzrec/utils/dynamicemb_util.py b/tzrec/utils/dynamicemb_util.py
index 621a5dae..9d437f92 100644
--- a/tzrec/utils/dynamicemb_util.py
+++ b/tzrec/utils/dynamicemb_util.py
@@ -20,7 +20,6 @@
 from torchrec.distributed.embedding_types import (
     EmbeddingComputeKernel,
     GroupedEmbeddingConfig,
-    ShardedEmbeddingTable,
 )
 from torchrec.distributed.planner import (
     constants,
@@ -47,7 +46,7 @@
     ShardingType,
     ShardMetadata,
 )
-from torchrec.modules.embedding_configs import BaseEmbeddingConfig, DataType
+from torchrec.modules.embedding_configs import BaseEmbeddingConfig
 
 from tzrec.protos import feature_pb2
 
@@ -61,7 +60,6 @@
         FrequencyAdmissionStrategy,
         KVCounter,
         align_to_table_size,
-        batched_dynamicemb_compute_kernel,
     )
     from dynamicemb.batched_dynamicemb_compute_kernel import (
         BatchedDynamicEmbedding,
@@ -191,6 +189,10 @@ def build_dynamicemb_constraints(
         else:
             raise ValueError(f"Unknown AdmissionStrategy: {admission_strategy_type}")
 
+    demb_opt_kwargs = {}
+    if dynamicemb_cfg.HasField("bucket_capacity"):
+        demb_opt_kwargs["bucket_capacity"] = dynamicemb_cfg.bucket_capacity
+
     dynamicemb_options = dynamicemb.DynamicEmbTableOptions(
         max_capacity=dynamicemb_cfg.max_capacity,
         init_capacity=init_capacity,
@@ -207,6 +209,7 @@ def build_dynamicemb_constraints(
         score_strategy=score_strategy,
         admit_strategy=admit_strategy,
         admission_counter=admission_counter,
+        **demb_opt_kwargs,
     )
 
     constraints_kwargs = {}
@@ -352,18 +355,18 @@ def _to_sharding_plan(
                         bucket_capacity=dynamicemb_options.bucket_capacity,
                     )
                 )
-
-                # align to DEMB_TABLE_ALIGN_SIZE
-                num_aligned_embedding_per_rank = align_to_table_size(shards[0].size[0])
-                num_embeddings_per_shard = shards[0].size[0]
-                if num_aligned_embedding_per_rank < dynamicemb_options.bucket_capacity:
-                    num_aligned_embedding_per_rank = align_to_table_size(
-                        dynamicemb_options.bucket_capacity
-                    )
-                if num_embeddings_per_shard != num_aligned_embedding_per_rank:
-                    dynamicemb_options.num_aligned_embedding_per_rank = (
-                        num_aligned_embedding_per_rank
-                    )
+                # Fill in per-shard fields that used to be populated by
+                # dynamicemb's internal ``_get_dynamicemb_options_per_table``.
+                # After the fused-storage refactor (NVIDIA recsys-examples
+                # PR #343) that upstream function became a pass-through
+                # validator, so the caller must set ``dim``, ``max_capacity``
+                # (per-shard row count) and ``embedding_dtype`` directly.
+                dynamicemb_options.dim = shards[0].size[1]
+                dynamicemb_options.max_capacity = shards[0].size[0]
+                if dynamicemb_options.embedding_dtype is None:
+                    dynamicemb_options.embedding_dtype = tensor.dtype
+                if dynamicemb_options.index_type is None:
+                    dynamicemb_options.index_type = torch.int64
 
                 module_plan[sharding_option.name] = DynamicEmbParameterSharding(
                     sharding_spec=sharding_spec,
@@ -614,42 +617,6 @@ def dynamicemb_calculate_shard_storages(
             for hbm_size, ddr_size in zip(hbm_sizes, ddr_sizes)
         ]
 
-    _dynamicemb_get_dynamicemb_options_per_table = (
-        batched_dynamicemb_compute_kernel._get_dynamicemb_options_per_table
-    )
-
-    def _get_dynamicemb_options_per_table(
-        local_row: int,
-        local_col: int,
-        data_type: DataType,
-        optimizer: dynamicemb.EmbOptimType,
-        table: ShardedEmbeddingTable,
-    ) -> dynamicemb.DynamicEmbTableOptions:
-        # pyre-ignore [16]
-        dynamicemb_options = table.fused_params["dynamicemb_options"]
-        bak_local_hbm_for_values = None
-        if dynamicemb_options.num_aligned_embedding_per_rank is not None:
-            bak_local_hbm_for_values = dynamicemb_options.local_hbm_for_values
-
-        dynamicemb_options = _dynamicemb_get_dynamicemb_options_per_table(
-            local_row=local_row,
-            local_col=local_col,
-            data_type=data_type,
-            optimizer=optimizer,
-            table=table,
-        )
-
-        # do not improve the HBM budget, already aligned in planner.
-        if bak_local_hbm_for_values is not None:
-            dynamicemb_options.local_hbm_for_values = bak_local_hbm_for_values
-
-        return dynamicemb_options
-
-    # pyre-ignore [9]
-    batched_dynamicemb_compute_kernel._get_dynamicemb_options_per_table = (
-        _get_dynamicemb_options_per_table
-    )
-
     # Monkey-patch for torchrec 1.5.0 compatibility
     # The base class now passes 'env' parameter to _create_embedding_kernel
     def _grouped_embeddings_lookup_create_embedding_kernel(
diff --git a/tzrec/version.py b/tzrec/version.py
index e9552152..e32c82ac 100644
--- a/tzrec/version.py
+++ b/tzrec/version.py
@@ -9,4 +9,4 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-__version__ = "1.1.6"
+__version__ = "1.1.7"