ModelEngine-Group · ygwpz · Sep 5, 2025 · Sep 5, 2025
@@ -1,5 +1,5 @@
 name: 📚 Documentation
-description: Report an issue related to unifiedcache official website
+description: Report an issue related to ucm official website
 title: "[Doc]: "
 labels: ["documentation"]
 

@@ -1,5 +1,5 @@
 name: 📚 User Story
-description: Apply for an user story to be displayed on unifiedcache official website
+description: Apply for an user story to be displayed on ucm official website
 title: "[User Story]: "
 labels: ["user-story"]
 
@@ -23,7 +23,7 @@ body:
       Tell us how what kind of challenge you faced in this user story.
 - type: textarea
   attributes:
-    label: Solving challenges with unifiedcache and benefits
+    label: Solving challenges with ucm and benefits
     description: >
       Tell us how unifiedcache helped you overcome the challenges, including details like how you use it, what version you used, hardware info, etc. And what kind of benefit do you get from using unifiedcache
 - type: textarea

@@ -30,7 +30,7 @@ body:
     required: true
 - type: textarea
   attributes:
-    label: How you are installing unifiedcache, also vllm and vllm-ascend.
+    label: How you are installing ucm, also vllm and vllm-ascend.
     description: |
       Paste the full command you are trying to execute.
     value: |

@@ -1,5 +1,5 @@
 name: 💻 Usage
-description: Raise an issue here if you don't know how to use unifiedcache.
+description: Raise an issue here if you don't know how to use ucm.
 title: "[Usage]: "
 labels: ["usage"]
 
@@ -30,7 +30,7 @@ body:
     required: true
 - type: textarea
   attributes:
-    label: How would you like to use unifiedcache.
+    label: How would you like to use ucm.
     description: |
       A detailed description of how you want to use unifiedcache.
     value: |

@@ -1,5 +1,5 @@
 name: 🚀 Feature request
-description: Submit a proposal/request for a new unifiedcache feature
+description: Submit a proposal/request for a new ucm feature
 title: "[Feature]: "
 labels: ["feature request"]
 

@@ -1,5 +1,5 @@
-name: 🤗 Support request for new model supported from huggingface/modelscope/modelers on unifiedcache
-description: Submit a proposal/request for a new model from huggingface/modelscope/modelers on unifiedcache
+name: 🤗 Support request for new model supported from huggingface/modelscope/modelers on ucm
+description: Submit a proposal/request for a new model from huggingface/modelscope/modelers on ucm
 title: "[New Model]: "
 labels: ["new model"]
 
@@ -19,7 +19,7 @@ body:
     required: true
 - type: textarea
   attributes:
-    label: The closest model unifiedcache already supports.
+    label: The closest model ucm already supports.
     description: >
       Here is the list of models already supported by unifiedcache in our official website . Which model is the most similar to the model you want to add support for?
 - type: textarea

@@ -1,5 +1,5 @@
-name: ⚡ Discussion on the performance of unifiedcache
-description: Submit a proposal/discussion about the performance of unifiedcache
+name: ⚡ Discussion on the performance of ucm
+description: Submit a proposal/discussion about the performance of ucm
 title: "[Performance]: "
 labels: ["performance"]
 

@@ -10,7 +10,7 @@ body:
       #### Before submitting an issue, please make sure the issue hasn't been already addressed by searching through [the existing and past issues](https://github.com/ModelEngine-Group/unified-cache-management/issues?q=is%3Aissue%20sort%3Acreated-desc).
 - type: textarea
   attributes:
-    label: Anything you want to discuss about unifiedcache.
+    label: Anything you want to discuss about ucm.
     description: >
       Anything you want to discuss about unifiedcache.
   validations:

@@ -41,7 +41,7 @@ jobs:
     - name: Configure CMake
       # Configure CMake in a 'build' subdirectory. `CMAKE_BUILD_TYPE` is only required if you are using a single-configuration generator such as make.
       # See https://cmake.org/cmake/help/latest/variable/CMAKE_BUILD_TYPE.html?highlight=cmake_build_type
-      working-directory: ${{github.workspace}}/unifiedcache/csrc/ucmnfsstore
+      working-directory: ${{github.workspace}}/ucm/csrc/ucmnfsstore
       run: cmake -B ${{github.workspace}}/build -DCMAKE_BUILD_TYPE=${{env.BUILD_TYPE}} -DBUILD_TESTS=ON -DCOVERAGE_ENABLED=ON -DDOWNLOAD_DEPENDENCE=ON -DRUNTIME_ENVIRONMENT=simu
 
     - name: Build

@@ -4,7 +4,7 @@ repos:
     hooks:
       - id: codespell
         args: [
-          '--skip', 'unifiedcache/csrc/**,./unifiedcache.egg-info/**,.github/**',
+          '--skip', 'ucm/csrc/**,./ucm.egg-info/**,.github/**',
           '-L', 'CANN,cann,NNAL,nnal,ASCEND,ascend,EnQue,CopyIn'
         ]
   - repo: https://github.com/psf/black

@@ -15,7 +15,7 @@ RUN export PLATFORM="cuda" && \
 
 # Apply patch for vLLM
 RUN cd $(pip show vllm | grep Location | awk '{print $2}') \
-    && git apply /vllm-workspace/unified-cache-management/unifiedcache/patch/0.9.2/vllm-adapt.patch \
-    && git apply /vllm-workspace/unified-cache-management/unifiedcache/patch/0.9.2/vllm-adapt-sparse.patch
+    && git apply /vllm-workspace/unified-cache-management/ucm/patch/0.9.2/vllm-adapt.patch \
+    && git apply /vllm-workspace/unified-cache-management/ucm/patch/0.9.2/vllm-adapt-sparse.patch
 
 ENTRYPOINT ["/bin/bash"]
@@ -16,12 +16,12 @@ RUN export PLATFORM="ascend" && \
 
 # Apply patch for vLLM
 RUN cd /vllm-workspace/vllm \
-    && git apply /vllm-workspace/unified-cache-management/unifiedcache/patch/0.9.2/vllm-adapt.patch \
-    && git apply /vllm-workspace/unified-cache-management/unifiedcache/patch/0.9.2/vllm-adapt-sparse.patch
+    && git apply /vllm-workspace/unified-cache-management/ucm/patch/0.9.2/vllm-adapt.patch \
+    && git apply /vllm-workspace/unified-cache-management/ucm/patch/0.9.2/vllm-adapt-sparse.patch
 
 # Apply patch for vLLM-Ascend
 RUN cd /vllm-workspace/vllm-ascend \
-    && git apply /vllm-workspace/unified-cache-management/unifiedcache/patch/0.9.2/vllm-ascend-adapt.patch \
-    && git apply /vllm-workspace/unified-cache-management/unifiedcache/patch/0.9.2/vllm-ascend-adapt-sparse.patch
+    && git apply /vllm-workspace/unified-cache-management/ucm/patch/0.9.2/vllm-ascend-adapt.patch \
+    && git apply /vllm-workspace/unified-cache-management/ucm/patch/0.9.2/vllm-ascend-adapt-sparse.patch
 
 CMD ["/bin/bash"]
@@ -34,7 +34,7 @@ docker run \
 Refer to [Set up using docker](https://docs.vllm.ai/en/latest/getting_started/installation/gpu.html#set-up-using-docker) for more information to run your own vLLM container. After installation, please apply patch to ensure uc_connector can be used:
 ```bash
 cd /vllm-workspace/vllm
-git apply /vllm-workspace/unified-cache-management/unifiedcache/patch/0.9.2/vllm-adapt.patch
+git apply /vllm-workspace/unified-cache-management/ucm/patch/0.9.2/vllm-adapt.patch
 ``` 
 Refer to this [issue](https://github.com/vllm-project/vllm/issues/21702) to see details of this patch's changes.
 

@@ -42,9 +42,9 @@ docker run --rm \
 Codes of vLLM and vLLM Ascend are placed in /vllm-workspace, you can refer to [vLLM-Ascend Installation](https://vllm-ascend.readthedocs.io/en/latest/installation.html) for more information. After installation, please apply patches to ensure uc_connector can be used:
 ```bash
 cd /vllm-workspace/vllm
-git apply /vllm-workspace/unified-cache-management/unifiedcache/patch/0.9.2/vllm-adapt.patch
+git apply /vllm-workspace/unified-cache-management/ucm/patch/0.9.2/vllm-adapt.patch
 cd /vllm-workspace/vllm-ascend
-git apply /vllm-workspace/unified-cache-management/unifiedcache/patch/0.9.2/vllm-ascend-adapt.patch
+git apply /vllm-workspace/unified-cache-management/ucm/patch/0.9.2/vllm-ascend-adapt.patch
 ```
 Refer to these issues [vllm-issue](https://github.com/vllm-project/vllm/issues/21702) and [vllm-ascend-issue](https://github.com/vllm-project/vllm-ascend/issues/2057) to see details of patches' changes.
 

@@ -26,7 +26,7 @@ CUDA_VISIBLE_DEVICES=0 vllm serve /home/models/Qwen2.5-7B-Instruct \
 --kv-transfer-config \
 '{
     "kv_connector": "UnifiedCacheConnectorV1",
-    "kv_connector_module_path": "unifiedcache.integration.vllm.uc_connector",
+    "kv_connector_module_path": "ucm.integration.vllm.uc_connector",
     "kv_role": "kv_producer",
     "kv_connector_extra_config": {
         "ucm_connector_name": "UcmNfsStore",
@@ -54,7 +54,7 @@ CUDA_VISIBLE_DEVICES=1 vllm serve /home/models/Qwen2.5-7B-Instruct \
 --kv-transfer-config \
 '{
     "kv_connector": "UnifiedCacheConnectorV1",
-    "kv_connector_module_path": "unifiedcache.integration.vllm.uc_connector",
+    "kv_connector_module_path": "ucm.integration.vllm.uc_connector",
     "kv_role": "kv_consumer",
     "kv_connector_extra_config": {
         "ucm_connector_name": "UcmNfsStore",

@@ -25,7 +25,7 @@ CUDA_VISIBLE_DEVICES=0 vllm serve /home/models/Qwen2.5-7B-Instruct \
 --kv-transfer-config \
 '{
     "kv_connector": "UnifiedCacheConnectorV1",
-    "kv_connector_module_path": "unifiedcache.integration.vllm.uc_connector",
+    "kv_connector_module_path": "ucm.integration.vllm.uc_connector",
     "kv_role": "kv_producer",
     "kv_connector_extra_config": {
         "ucm_connector_name": "UcmNfsStore",
@@ -52,7 +52,7 @@ CUDA_VISIBLE_DEVICES=1 vllm serve /home/models/Qwen2.5-7B-Instruct \
 --kv-transfer-config \
 '{
     "kv_connector": "UnifiedCacheConnectorV1",
-    "kv_connector_module_path": "unifiedcache.integration.vllm.uc_connector",
+    "kv_connector_module_path": "ucm.integration.vllm.uc_connector",
     "kv_role": "kv_producer",
     "kv_connector_extra_config": {
         "ucm_connector_name": "UcmNfsStore",
@@ -80,7 +80,7 @@ CUDA_VISIBLE_DEVICES=2 vllm serve /home/models/Qwen2.5-7B-Instruct \
 --kv-transfer-config \
 '{
     "kv_connector": "UnifiedCacheConnectorV1",
-    "kv_connector_module_path": "unifiedcache.integration.vllm.uc_connector",
+    "kv_connector_module_path": "ucm.integration.vllm.uc_connector",
     "kv_role": "kv_consumer",
     "kv_connector_extra_config": {
         "ucm_connector_name": "UcmNfsStore",
@@ -106,7 +106,7 @@ CUDA_VISIBLE_DEVICES=3 vllm serve /home/models/Qwen2.5-7B-Instruct \
 --kv-transfer-config \
 '{
     "kv_connector": "UnifiedCacheConnectorV1",
-    "kv_connector_module_path": "unifiedcache.integration.vllm.uc_connector",
+    "kv_connector_module_path": "ucm.integration.vllm.uc_connector",
     "kv_role": "kv_consumer",
     "kv_connector_extra_config": {
         "ucm_connector_name": "UcmNfsStore",

@@ -82,7 +82,7 @@ vllm serve /home/models/Qwen2.5-14B-Instruct \
 --kv-transfer-config \
 '{
     "kv_connector": "UnifiedCacheConnectorV1",
-    "kv_connector_module_path": "unifiedcache.integration.vllm.uc_connector",
+    "kv_connector_module_path": "ucm.integration.vllm.uc_connector",
     "kv_role": "kv_both",
     "kv_connector_extra_config": {
         "ucm_connector_name": "UcmDram",

@@ -140,7 +140,7 @@ vllm serve /home/models/Qwen2.5-14B-Instruct \
 --kv-transfer-config \
 '{
     "kv_connector": "UnifiedCacheConnectorV1",
-    "kv_connector_module_path": "unifiedcache.integration.vllm.uc_connector",
+    "kv_connector_module_path": "ucm.integration.vllm.uc_connector",
     "kv_role": "kv_both",
     "kv_connector_extra_config": {
         "ucm_connector_name": "UcmMooncakeStore", 

@@ -75,7 +75,7 @@ vllm serve /home/models/Qwen2.5-14B-Instruct \
 --kv-transfer-config \
 '{
     "kv_connector": "UnifiedCacheConnectorV1",
-    "kv_connector_module_path": "unifiedcache.integration.vllm.uc_connector",
+    "kv_connector_module_path": "ucm.integration.vllm.uc_connector",
     "kv_role": "kv_both",
     "kv_connector_extra_config": {
         "ucm_connector_name": "UcmNfsStore",

@@ -67,7 +67,7 @@ vllm serve /home/models/Qwen2.5-14B-Instruct \
 --kv-transfer-config \
 '{
     "kv_connector": "UnifiedCacheConnectorV1",
-    "kv_connector_module_path": "unifiedcache.integration.vllm.uc_connector",
+    "kv_connector_module_path": "ucm.integration.vllm.uc_connector",
     "kv_role": "kv_both",
     "kv_connector_extra_config": {
         "ucm_connector_name": "UcmNfsStore",

@@ -8,7 +8,7 @@
 from vllm.config import KVTransferConfig
 from vllm.engine.arg_utils import EngineArgs
 
-from unifiedcache.logger import init_logger
+from ucm.logger import init_logger
 
 logger = init_logger(__name__)
 
@@ -65,7 +65,7 @@ def print_output(
 
 
 def main():
-    module_path = "unifiedcache.integration.vllm.uc_connector"
+    module_path = "ucm.integration.vllm.uc_connector"
     name = "UnifiedCacheConnectorV1"
     model = os.getenv("MODEL_PATH", "/home/models/Qwen2.5-14B-Instruct")
 

@@ -31,8 +31,8 @@
 from setuptools.command.develop import develop
 
 ROOT_DIR = os.path.abspath(os.path.dirname(__file__))
-SRC_DIR = os.path.join(ROOT_DIR, "unifiedcache", "csrc", "ucmnfsstore")
-INSTALL_DIR = os.path.join(ROOT_DIR, "unifiedcache", "ucm_connector")
+SRC_DIR = os.path.join(ROOT_DIR, "ucm", "csrc", "ucmnfsstore")
+INSTALL_DIR = os.path.join(ROOT_DIR, "ucm", "store")
 PLATFORM = os.getenv("PLATFORM")
 
 
@@ -104,9 +104,7 @@ def build_cmake(self, ext: CMakeExtension):
 
         src_path = os.path.join(so_search_dir, so_file)
         dev_path = os.path.join(INSTALL_DIR, so_file)
-        dst_path = os.path.join(
-            self.build_lib, "unifiedcache", "ucm_connector", so_file
-        )
+        dst_path = os.path.join(self.build_lib, "ucm", "store", so_file)
         os.makedirs(os.path.dirname(dst_path), exist_ok=True)
         shutil.copy(src_path, dst_path)
         print(f"[INFO] Copied {src_path} → {dst_path}")
@@ -116,7 +114,7 @@ def build_cmake(self, ext: CMakeExtension):
 
 
 setup(
-    name="unifiedcache",
+    name="ucm",
     version="0.0.2",
     description="Unified Cache Management",
     author="Unified Cache Team",

@@ -3,9 +3,9 @@
 
 import torch
 
-from unifiedcache.logger import init_logger
-from unifiedcache.ucm_connector.base import Task
-from unifiedcache.ucm_connector.ucm_mooncake import UcmMooncakeStore
+from ucm.logger import init_logger
+from ucm.store.base import Task
+from ucm.store.ucm_mooncake import UcmMooncakeStore
 
 logger = init_logger(__name__)
 

@@ -33,14 +33,14 @@
 from vllm.sampling_params import SamplingParams
 from vllm.v1.request import Request
 
-from unifiedcache.integration.vllm.uc_connector import (
+from ucm.integration.vllm.uc_connector import (
     LoadPara,
     ReqMeta,
     SavePara,
     UCConnectorV1Metadata,
     UnifiedCacheConnectorV1,
 )
-from unifiedcache.ucm_connector.base import Task, UcmKVStoreBase
+from ucm.store.base import Task, UcmKVStoreBase
 
 
 def make_request(

@@ -86,7 +86,7 @@ def patch_cuda_for_cpu():
 
 
 patch_cuda_for_cpu()
-from unifiedcache.ucm_connector.ucm_dram import DramTask, UcmDram  # isort: skip
+from ucm.store.ucm_dram import DramTask, UcmDram  # isort: skip
 
 
 def make_request(