Revert the transport backend to UCX

Signed-off-by: Shixiaowei02 <[email protected]>

Author: Shixiaowei02

cpp/tensorrt_llm/batch_manager/cacheTransceiver.cpp

@@ -89,7 +89,7 @@ std::unique_ptr<BaseCacheTransceiver> CacheTransceiverFactory::createCacheTransc
         }
         else
         {
-            backendType = executor::CacheTransceiverConfig::BackendType::NIXL;
+            backendType = executor::CacheTransceiverConfig::BackendType::UCX;
         }
     }
     cacheTransceiverConfig.value().setBackendType(backendType);

docs/source/features/disagg-serving.md

@@ -118,7 +118,7 @@ cache_transceiver_config:
   max_tokens_in_buffer: <int>
 ```
 
-`backend` specifies the communication backend for transferring the kvCache, valid options include `DEFAULT`,`UCX`, `NIXL`, and `MPI`, the default backend is NIXL.
+`backend` specifies the communication backend for transferring the kvCache, valid options include `DEFAULT`,`UCX`, `NIXL`, and `MPI`, the default backend is UCX.
 
 `max_tokens_in_buffer` defines the buffer size for kvCache transfers, it is recommended to set this value greater than or equal to the maximum ISL (Input Sequence Length) of all requests for optimal performance.
 

examples/disaggregated/README.md

@@ -12,7 +12,7 @@ The `trtllm-serve` command supports the `extra-llm-config.yaml` parameter. In th
 
 ```yaml
 cache_transceiver_config:
-  # KV cache transmission backend. Valid options include `DEFAULT` (i.e., NIXL), `UCX`, `NIXL`.
+  # KV cache transmission backend. Valid options include `DEFAULT` (i.e., UCX), `UCX`, `NIXL`.
   backend: <str>
   # KV cache buffer size. Set it ≥ the maximum ISL (Input Sequence Length) for best performance.
   max_tokens_in_buffer: <int>

tensorrt_llm/_torch/pyexecutor/kv_cache_transceiver.py

@@ -39,9 +39,9 @@ def create_kv_cache_transceiver(
     if cache_transceiver_config.backend == "DEFAULT":
         # When cache_transceiver_config.backend is not set, fallback to env_vars settings
         # NIXL is the default backend
-        cache_transceiver_config.backend = "NIXL"
+        cache_transceiver_config.backend = "UCX"
         # Ordered by priority
-        env_vars = [("TRTLLM_USE_UCX_KVCACHE", "UCX"),
+        env_vars = [("TRTLLM_USE_NIXL_KVCACHE", "NIXL"),
                     ("TRTLLM_USE_MPI_KVCACHE", "MPI")]
         for env_var, be_type in env_vars:
             if getenv(env_var) == "1":