[releases/v0.18.0][Doc][Misc] Modifying Configuration Parameters (#8618)

### What this PR does / why we need it?
This PR renames the environment variable VLLM_NIXL_ABORT_REQUEST_TIMEOUT
to VLLM_MOONCAKE_ABORT_REQUEST_TIMEOUT to align with the Mooncake
connector naming convention. It also updates the documentation and test
configurations to reflect this change and adjusts the suggested timeout
value in the documentation to 480 seconds for consistency.

### Does this PR introduce _any_ user-facing change?
Yes. The environment variable for configuring the abort request timeout
has been renamed. Users should update their environment settings from
VLLM_NIXL_ABORT_REQUEST_TIMEOUT to VLLM_MOONCAKE_ABORT_REQUEST_TIMEOUT.

### How was this patch tested?
The changes were verified by updating the corresponding test
configuration files and ensuring consistency across the documentation.

---------

Signed-off-by: herizhen <1270637059@qq.com>
Signed-off-by: herizhen <59841270+herizhen@users.noreply.github.com>

docs/source/locale/zh_CN/LC_MESSAGES/developer_guide/Design_Documents/eplb_swift_balancer.po

@@ -434,6 +434,10 @@ msgstr ""
 msgid "Consistency"
 msgstr "一致性"
 
+#: ../../source/developer_guide/Design_Documents/eplb_swift_balancer.md:236
+msgid "Expert Map"
+msgstr "专家映射"
+
 #: ../../source/developer_guide/Design_Documents/eplb_swift_balancer.md:237
 msgid ""
 "The expert map must be globally unique during initialization and update. "

docs/source/tutorials/models/DeepSeek-V3.2.md

@@ -526,7 +526,8 @@ Before you start, please
         export ASCEND_TRANSPORT_PRINT=1
         export ACL_OP_INIT_MODE=1
         export ASCEND_A3_ENABLE=1
-        export VLLM_NIXL_ABORT_REQUEST_TIMEOUT=300000
+        # Timeout (in seconds) for automatically releasing the prefiller’s KV cache for a particular request.
+        export VLLM_MOONCAKE_ABORT_REQUEST_TIMEOUT=480
 
         export ASCEND_RT_VISIBLE_DEVICES=$1
 
@@ -600,7 +601,8 @@ Before you start, please
         export ASCEND_TRANSPORT_PRINT=1
         export ACL_OP_INIT_MODE=1
         export ASCEND_A3_ENABLE=1
-        export VLLM_NIXL_ABORT_REQUEST_TIMEOUT=300000
+        # Timeout (in seconds) for automatically releasing the prefiller’s KV cache for a particular request.
+        export VLLM_MOONCAKE_ABORT_REQUEST_TIMEOUT=480
 
         export ASCEND_RT_VISIBLE_DEVICES=$1
 
@@ -676,7 +678,8 @@ Before you start, please
         export ASCEND_TRANSPORT_PRINT=1
         export ACL_OP_INIT_MODE=1
         export ASCEND_A3_ENABLE=1
-        export VLLM_NIXL_ABORT_REQUEST_TIMEOUT=300000
+        # Timeout (in seconds) for automatically releasing the prefiller’s KV cache for a particular request.
+        export VLLM_MOONCAKE_ABORT_REQUEST_TIMEOUT=480
 
         export TASK_QUEUE_ENABLE=1
 
@@ -752,7 +755,8 @@ Before you start, please
         export ASCEND_TRANSPORT_PRINT=1
         export ACL_OP_INIT_MODE=1
         export ASCEND_A3_ENABLE=1
-        export VLLM_NIXL_ABORT_REQUEST_TIMEOUT=300000
+        # Timeout (in seconds) for automatically releasing the prefiller’s KV cache for a particular request.
+        export VLLM_MOONCAKE_ABORT_REQUEST_TIMEOUT=480
 
         export TASK_QUEUE_ENABLE=1
 

docs/source/tutorials/models/GLM4.x.md

@@ -530,6 +530,8 @@ Before you start, please
         export ASCEND_TRANSPORT_PRINT=1
         export ACL_OP_INIT_MODE=1
         export ASCEND_A3_ENABLE=1
+        # Timeout (in seconds) for automatically releasing the prefiller’s KV cache for a particular request.
+        export VLLM_MOONCAKE_ABORT_REQUEST_TIMEOUT=480
         export TASK_QUEUE_ENABLE=1
         export LD_LIBRARY_PATH=/usr/local/Ascend/ascend-toolkit/latest/python/site-packages/mooncake:$LD_LIBRARY_PATH
         export VLLM_ASCEND_ENABLE_TOPK_OPTIMIZE=1
@@ -598,6 +600,8 @@ Before you start, please
         export ASCEND_TRANSPORT_PRINT=1
         export ACL_OP_INIT_MODE=1
         export ASCEND_A3_ENABLE=1
+        # Timeout (in seconds) for automatically releasing the prefiller’s KV cache for a particular request.
+        export VLLM_MOONCAKE_ABORT_REQUEST_TIMEOUT=480
         export TASK_QUEUE_ENABLE=1
         export LD_LIBRARY_PATH=/usr/local/Ascend/ascend-toolkit/latest/python/site-packages/mooncake:$LD_LIBRARY_PATH
         export VLLM_ASCEND_ENABLE_TOPK_OPTIMIZE=1

docs/source/tutorials/models/GLM5.md

@@ -766,7 +766,8 @@ Before you start, please
         export ASCEND_TRANSPORT_PRINT=1
         export ACL_OP_INIT_MODE=1
         export ASCEND_A3_ENABLE=1
-        export VLLM_NIXL_ABORT_REQUEST_TIMEOUT=300000
+        # Timeout (in seconds) for automatically releasing the prefiller’s KV cache for a particular request.
+        export VLLM_MOONCAKE_ABORT_REQUEST_TIMEOUT=480
 
         export ASCEND_RT_VISIBLE_DEVICES=$1
         export VLLM_ASCEND_ENABLE_FLASHCOMM1=1
@@ -844,7 +845,8 @@ Before you start, please
         export ASCEND_TRANSPORT_PRINT=1
         export ACL_OP_INIT_MODE=1
         export ASCEND_A3_ENABLE=1
-        export VLLM_NIXL_ABORT_REQUEST_TIMEOUT=300000
+        # Timeout (in seconds) for automatically releasing the prefiller’s KV cache for a particular request.
+        export VLLM_MOONCAKE_ABORT_REQUEST_TIMEOUT=480
 
         export ASCEND_RT_VISIBLE_DEVICES=$1
         export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True
@@ -926,7 +928,8 @@ Before you start, please
         export ASCEND_TRANSPORT_PRINT=1
         export ACL_OP_INIT_MODE=1
         export ASCEND_A3_ENABLE=1
-        export VLLM_NIXL_ABORT_REQUEST_TIMEOUT=300000
+        # Timeout (in seconds) for automatically releasing the prefiller’s KV cache for a particular request.
+        export VLLM_MOONCAKE_ABORT_REQUEST_TIMEOUT=480
     
         export TASK_QUEUE_ENABLE=1
     
@@ -1007,7 +1010,8 @@ Before you start, please
          export ASCEND_TRANSPORT_PRINT=1
          export ACL_OP_INIT_MODE=1
          export ASCEND_A3_ENABLE=1
-         export VLLM_NIXL_ABORT_REQUEST_TIMEOUT=300000
+         # Timeout (in seconds) for automatically releasing the prefiller’s KV cache for a particular request.
+         export VLLM_MOONCAKE_ABORT_REQUEST_TIMEOUT=480
             
          export TASK_QUEUE_ENABLE=1
             
@@ -1088,7 +1092,8 @@ Before you start, please
          export ASCEND_TRANSPORT_PRINT=1
          export ACL_OP_INIT_MODE=1
          export ASCEND_A3_ENABLE=1
-         export VLLM_NIXL_ABORT_REQUEST_TIMEOUT=300000
+         # Timeout (in seconds) for automatically releasing the prefiller’s KV cache for a particular request.
+         export VLLM_MOONCAKE_ABORT_REQUEST_TIMEOUT=480
             
          export TASK_QUEUE_ENABLE=1
             
@@ -1169,7 +1174,8 @@ Before you start, please
          export ASCEND_TRANSPORT_PRINT=1
          export ACL_OP_INIT_MODE=1
          export ASCEND_A3_ENABLE=1
-         export VLLM_NIXL_ABORT_REQUEST_TIMEOUT=300000
+         # Timeout (in seconds) for automatically releasing the prefiller’s KV cache for a particular request.
+         export VLLM_MOONCAKE_ABORT_REQUEST_TIMEOUT=480
             
          export TASK_QUEUE_ENABLE=1
             

docs/source/tutorials/models/Qwen3.5-397B-A17B.md

@@ -288,7 +288,8 @@ To run the vllm-ascend `Prefill-Decode Disaggregation` service, you need to depl
        # jemalloc is for better performance, if `libjemalloc.so` is installed on your machine, you can turn it on.
        # export LD_PRELOAD=/usr/lib/aarch64-linux-gnu/libjemalloc.so.2:$LD_PRELOAD
        export VLLM_ENGINE_READY_TIMEOUT_S=30000
-       export VLLM_NIXL_ABORT_REQUEST_TIMEOUT=30000
+       # Timeout (in seconds) for automatically releasing the prefiller’s KV cache for a particular request.
+       export VLLM_MOONCAKE_ABORT_REQUEST_TIMEOUT=480
        export IP_ADDRESS=$local_ip
        export NETWORK_CARD_NAME=$nic_name
        export HCCL_IF_IP=$IP_ADDRESS
@@ -362,7 +363,8 @@ To run the vllm-ascend `Prefill-Decode Disaggregation` service, you need to depl
        node0_ip="xxxx"
 
        export VLLM_ENGINE_READY_TIMEOUT_S=30000
-       export VLLM_NIXL_ABORT_REQUEST_TIMEOUT=30000
+       # Timeout (in seconds) for automatically releasing the prefiller’s KV cache for a particular request.
+       export VLLM_MOONCAKE_ABORT_REQUEST_TIMEOUT=480
        export MASTER_IP_ADDRESS=$node0_ip
        export IP_ADDRESS=$local_ip
 
@@ -442,7 +444,8 @@ To run the vllm-ascend `Prefill-Decode Disaggregation` service, you need to depl
        node0_ip="xxxx"
 
        export VLLM_ENGINE_READY_TIMEOUT_S=30000
-       export VLLM_NIXL_ABORT_REQUEST_TIMEOUT=30000
+       # Timeout (in seconds) for automatically releasing the prefiller’s KV cache for a particular request.
+       export VLLM_MOONCAKE_ABORT_REQUEST_TIMEOUT=480
        export MASTER_IP_ADDRESS=$node0_ip
        export IP_ADDRESS=$local_ip
 

tests/e2e/nightly/multi_node/config/DeepSeek-R1-W8A8-longseq.yaml

@@ -13,7 +13,7 @@ env_common:
   HCCL_DETERMINISTIC: True
   TASK_QUEUE_ENABLE: 1
   HCCL_OP_RETRY_ENABLE: "L0:0, L1:0"
-  VLLM_NIXL_ABORT_REQUEST_TIMEOUT: 300000
+  VLLM_MOONCAKE_ABORT_REQUEST_TIMEOUT: 480
 
 disaggregated_prefill:
   enabled: true

tests/e2e/nightly/multi_node/config/DeepSeek-V3_2-W8A8-EP-aime2025.yaml

@@ -15,7 +15,7 @@ env_common:
   ASCEND_TRANSPORT_PRINT: 1
   ACL_OP_INIT_MODE: 1
   ASCEND_A3_ENABLE: 1
-  VLLM_NIXL_ABORT_REQUEST_TIMEOUT: 300000
+  VLLM_MOONCAKE_ABORT_REQUEST_TIMEOUT: 480
   VLLM_ENGINE_READY_TIMEOUT_S: 1800
   HCCL_CONNECT_TIMEOUT: 1200
   HCCL_INTRA_PCIE_ENABLE: 1

tests/e2e/nightly/multi_node/config/DeepSeek-V3_2-W8A8-EP.yaml

@@ -15,7 +15,7 @@ env_common:
   ASCEND_TRANSPORT_PRINT: 1
   ACL_OP_INIT_MODE: 1
   ASCEND_A3_ENABLE: 1
-  VLLM_NIXL_ABORT_REQUEST_TIMEOUT: 300000
+  VLLM_MOONCAKE_ABORT_REQUEST_TIMEOUT: 480
   VLLM_ENGINE_READY_TIMEOUT_S: 1800
   HCCL_CONNECT_TIMEOUT: 1200
   HCCL_INTRA_PCIE_ENABLE: 1

vllm_ascend/distributed/kv_transfer/kv_p2p/mooncake_connector.py

@@ -173,7 +173,7 @@ class KVCacheTaskTracker:
         while self.delayed_free_requests:
             request_id = next(iter(self.delayed_free_requests))
             delay_start_time = self.delayed_free_requests[request_id]
-            if current_time - delay_start_time > envs.VLLM_NIXL_ABORT_REQUEST_TIMEOUT:
+            if current_time - delay_start_time > envs.VLLM_MOONCAKE_ABORT_REQUEST_TIMEOUT:
                 self.delayed_free_requests.popitem(last=False)
                 self.reqs_to_process.discard(request_id)
                 expired_requests.add(request_id)